Speech emotion recognition(SER)uses acoustic analysis to find features for emotion recognition and examines variations in voice that are caused by emotions.The number of features acquired with acoustic analysis is ext...Speech emotion recognition(SER)uses acoustic analysis to find features for emotion recognition and examines variations in voice that are caused by emotions.The number of features acquired with acoustic analysis is extremely high,so we introduce a hybrid filter-wrapper feature selection algorithm based on an improved equilibrium optimizer for constructing an emotion recognition system.The proposed algorithm implements multi-objective emotion recognition with the minimum number of selected features and maximum accuracy.First,we use the information gain and Fisher Score to sort the features extracted from signals.Then,we employ a multi-objective ranking method to evaluate these features and assign different importance to them.Features with high rankings have a large probability of being selected.Finally,we propose a repair strategy to address the problem of duplicate solutions in multi-objective feature selection,which can improve the diversity of solutions and avoid falling into local traps.Using random forest and K-nearest neighbor classifiers,four English speech emotion datasets are employed to test the proposed algorithm(MBEO)as well as other multi-objective emotion identification techniques.The results illustrate that it performs well in inverted generational distance,hypervolume,Pareto solutions,and execution time,and MBEO is appropriate for high-dimensional English SER.展开更多
Machine Learning(ML)algorithms play a pivotal role in Speech Emotion Recognition(SER),although they encounter a formidable obstacle in accurately discerning a speaker’s emotional state.The examination of the emotiona...Machine Learning(ML)algorithms play a pivotal role in Speech Emotion Recognition(SER),although they encounter a formidable obstacle in accurately discerning a speaker’s emotional state.The examination of the emotional states of speakers holds significant importance in a range of real-time applications,including but not limited to virtual reality,human-robot interaction,emergency centers,and human behavior assessment.Accurately identifying emotions in the SER process relies on extracting relevant information from audio inputs.Previous studies on SER have predominantly utilized short-time characteristics such as Mel Frequency Cepstral Coefficients(MFCCs)due to their ability to capture the periodic nature of audio signals effectively.Although these traits may improve their ability to perceive and interpret emotional depictions appropriately,MFCCS has some limitations.So this study aims to tackle the aforementioned issue by systematically picking multiple audio cues,enhancing the classifier model’s efficacy in accurately discerning human emotions.The utilized dataset is taken from the EMO-DB database,preprocessing input speech is done using a 2D Convolution Neural Network(CNN)involves applying convolutional operations to spectrograms as they afford a visual representation of the way the audio signal frequency content changes over time.The next step is the spectrogram data normalization which is crucial for Neural Network(NN)training as it aids in faster convergence.Then the five auditory features MFCCs,Chroma,Mel-Spectrogram,Contrast,and Tonnetz are extracted from the spectrogram sequentially.The attitude of feature selection is to retain only dominant features by excluding the irrelevant ones.In this paper,the Sequential Forward Selection(SFS)and Sequential Backward Selection(SBS)techniques were employed for multiple audio cues features selection.Finally,the feature sets composed from the hybrid feature extraction methods are fed into the deep Bidirectional Long Short Term Memory(Bi-LSTM)network to discern emotions.Since the deep Bi-LSTM can hierarchically learn complex features and increases model capacity by achieving more robust temporal modeling,it is more effective than a shallow Bi-LSTM in capturing the intricate tones of emotional content existent in speech signals.The effectiveness and resilience of the proposed SER model were evaluated by experiments,comparing it to state-of-the-art SER techniques.The results indicated that the model achieved accuracy rates of 90.92%,93%,and 92%over the Ryerson Audio-Visual Database of Emotional Speech and Song(RAVDESS),Berlin Database of Emotional Speech(EMO-DB),and The Interactive Emotional Dyadic Motion Capture(IEMOCAP)datasets,respectively.These findings signify a prominent enhancement in the ability to emotional depictions identification in speech,showcasing the potential of the proposed model in advancing the SER field.展开更多
The performance of a speech emotion recognition(SER)system is heavily influenced by the efficacy of its feature extraction techniques.The study was designed to advance the field of SER by optimizing feature extraction...The performance of a speech emotion recognition(SER)system is heavily influenced by the efficacy of its feature extraction techniques.The study was designed to advance the field of SER by optimizing feature extraction tech-niques,specifically through the incorporation of high-resolution Mel-spectrograms and the expedited calculation of Mel Frequency Cepstral Coefficients(MFCC).This initiative aimed to refine the system’s accuracy by identifying and mitigating the shortcomings commonly found in current approaches.Ultimately,the primary objective was to elevate both the intricacy and effectiveness of our SER model,with a focus on augmenting its proficiency in the accurate identification of emotions in spoken language.The research employed a dual-strategy approach for feature extraction.Firstly,a rapid computation technique for MFCC was implemented and integrated with a Bi-LSTM layer to optimize the encoding of MFCC features.Secondly,a pretrained ResNet model was utilized in conjunction with feature Stats pooling and dense layers for the effective encoding of Mel-spectrogram attributes.These two sets of features underwent separate processing before being combined in a Convolutional Neural Network(CNN)outfitted with a dense layer,with the aim of enhancing their representational richness.The model was rigorously evaluated using two prominent databases:CMU-MOSEI and RAVDESS.Notable findings include an accuracy rate of 93.2%on the CMU-MOSEI database and 95.3%on the RAVDESS database.Such exceptional performance underscores the efficacy of this innovative approach,which not only meets but also exceeds the accuracy benchmarks established by traditional models in the field of speech emotion recognition.展开更多
The hidden danger of the automatic speaker verification(ASV)system is various spoofed speeches.These threats can be classified into two categories,namely logical access(LA)and physical access(PA).To improve identifica...The hidden danger of the automatic speaker verification(ASV)system is various spoofed speeches.These threats can be classified into two categories,namely logical access(LA)and physical access(PA).To improve identification capability of spoofed speech detection,this paper considers the research on features.Firstly,following the idea of modifying the constant-Q-based features,this work considered adding variance or mean to the constant-Q-based cepstral domain to obtain good performance.Secondly,linear frequency cepstral coefficients(LFCCs)performed comparably with constant-Q-based features.Finally,we proposed linear frequency variance-based cepstral coefficients(LVCCs)and linear frequency mean-based cepstral coefficients(LMCCs)for identification of speech spoofing.LVCCs and LMCCs could be attained by adding the frame variance or the mean to the log magnitude spectrum based on LFCC features.The proposed novel features were evaluated on ASVspoof 2019 datase.The experimental results show that compared with known hand-crafted features,LVCCs and LMCCs are more effective in resisting spoofed speech attack.展开更多
Sign language recognition is vital for enhancing communication accessibility among the Deaf and hard-of-hearing communities.In Japan,approximately 360,000 individualswith hearing and speech disabilities rely on Japane...Sign language recognition is vital for enhancing communication accessibility among the Deaf and hard-of-hearing communities.In Japan,approximately 360,000 individualswith hearing and speech disabilities rely on Japanese Sign Language(JSL)for communication.However,existing JSL recognition systems have faced significant performance limitations due to inherent complexities.In response to these challenges,we present a novel JSL recognition system that employs a strategic fusion approach,combining joint skeleton-based handcrafted features and pixel-based deep learning features.Our system incorporates two distinct streams:the first stream extracts crucial handcrafted features,emphasizing the capture of hand and body movements within JSL gestures.Simultaneously,a deep learning-based transfer learning stream captures hierarchical representations of JSL gestures in the second stream.Then,we concatenated the critical information of the first stream and the hierarchy of the second stream features to produce the multiple levels of the fusion features,aiming to create a comprehensive representation of the JSL gestures.After reducing the dimensionality of the feature,a feature selection approach and a kernel-based support vector machine(SVM)were used for the classification.To assess the effectiveness of our approach,we conducted extensive experiments on our Lab JSL dataset and a publicly available Arabic sign language(ArSL)dataset.Our results unequivocally demonstrate that our fusion approach significantly enhances JSL recognition accuracy and robustness compared to individual feature sets or traditional recognition methods.展开更多
Modern medicine is reliant on various medical imaging technologies for non-invasively observing patients’anatomy.However,the interpretation of medical images can be highly subjective and dependent on the expertise of...Modern medicine is reliant on various medical imaging technologies for non-invasively observing patients’anatomy.However,the interpretation of medical images can be highly subjective and dependent on the expertise of clinicians.Moreover,some potentially useful quantitative information in medical images,especially that which is not visible to the naked eye,is often ignored during clinical practice.In contrast,radiomics performs high-throughput feature extraction from medical images,which enables quantitative analysis of medical images and prediction of various clinical endpoints.Studies have reported that radiomics exhibits promising performance in diagnosis and predicting treatment responses and prognosis,demonstrating its potential to be a non-invasive auxiliary tool for personalized medicine.However,radiomics remains in a developmental phase as numerous technical challenges have yet to be solved,especially in feature engineering and statistical modeling.In this review,we introduce the current utility of radiomics by summarizing research on its application in the diagnosis,prognosis,and prediction of treatment responses in patients with cancer.We focus on machine learning approaches,for feature extraction and selection during feature engineering and for imbalanced datasets and multi-modality fusion during statistical modeling.Furthermore,we introduce the stability,reproducibility,and interpretability of features,and the generalizability and interpretability of models.Finally,we offer possible solutions to current challenges in radiomics research.展开更多
Time series anomaly detection is crucial in various industrial applications to identify unusual behaviors within the time series data.Due to the challenges associated with annotating anomaly events,time series reconst...Time series anomaly detection is crucial in various industrial applications to identify unusual behaviors within the time series data.Due to the challenges associated with annotating anomaly events,time series reconstruction has become a prevalent approach for unsupervised anomaly detection.However,effectively learning representations and achieving accurate detection results remain challenging due to the intricate temporal patterns and dependencies in real-world time series.In this paper,we propose a cross-dimension attentive feature fusion network for time series anomaly detection,referred to as CAFFN.Specifically,a series and feature mixing block is introduced to learn representations in 1D space.Additionally,a fast Fourier transform is employed to convert the time series into 2D space,providing the capability for 2D feature extraction.Finally,a cross-dimension attentive feature fusion mechanism is designed that adaptively integrates features across different dimensions for anomaly detection.Experimental results on real-world time series datasets demonstrate that CAFFN performs better than other competing methods in time series anomaly detection.展开更多
The safety and stability of high-speed maglev trains traveling on viaducts in crosswinds critically depend on their aerodynamic characteristics.Therefore,this paper uses an improved delayed detached eddy simulation(ID...The safety and stability of high-speed maglev trains traveling on viaducts in crosswinds critically depend on their aerodynamic characteristics.Therefore,this paper uses an improved delayed detached eddy simulation(IDDES)method to investigate the aerodynamic features of high-speed maglev trains with different marshaling lengths under crosswinds.The effects of marshaling lengths(varying from 3-car to 8-car groups)on the train’s aerodynamic performance,surface pressure,and the flow field surrounding the train were investigated using the three-dimensional unsteady compressible Navier-Stokes(N-S)equations.The results showed that the marshaling lengths had minimal influence on the aerodynamic performance of the head and middle cars.Conversely,the marshaling lengths are negatively correlated with the time-average side force coefficient(CS)and time-average lift force coefficient(Cl)of the tail car.Compared to the tail car of the 3-car groups,the CS and Cl fell by 27.77%and 18.29%,respectively,for the tail car of the 8-car groups.It is essential to pay more attention to the operational safety of the head car,as it exhibits the highest time average CS.Additionally,the mean pressure difference between the two sides of the tail car body increased with the marshaling lengths,and the side force direction on the tail car was opposite to that of the head and middle cars.Furthermore,the turbulent kinetic energy of the wake structure on the windward side quickly decreased as marshaling lengths increased.展开更多
Feature matching plays a key role in computer vision. However, due to the limitations of the descriptors, the putative matches are inevitably contaminated by massive outliers.This paper attempts to tackle the outlier ...Feature matching plays a key role in computer vision. However, due to the limitations of the descriptors, the putative matches are inevitably contaminated by massive outliers.This paper attempts to tackle the outlier filtering problem from two aspects. First, a robust and efficient graph interaction model,is proposed, with the assumption that matches are correlated with each other rather than independently distributed. To this end, we construct a graph based on the local relationships of matches and formulate the outlier filtering task as a binary labeling energy minimization problem, where the pairwise term encodes the interaction between matches. We further show that this formulation can be solved globally by graph cut algorithm. Our new formulation always improves the performance of previous localitybased method without noticeable deterioration in processing time,adding a few milliseconds. Second, to construct a better graph structure, a robust and geometrically meaningful topology-aware relationship is developed to capture the topology relationship between matches. The two components in sum lead to topology interaction matching(TIM), an effective and efficient method for outlier filtering. Extensive experiments on several large and diverse datasets for multiple vision tasks including general feature matching, as well as relative pose estimation, homography and fundamental matrix estimation, loop-closure detection, and multi-modal image matching, demonstrate that our TIM is more competitive than current state-of-the-art methods, in terms of generality, efficiency, and effectiveness. The source code is publicly available at http://github.com/YifanLu2000/TIM.展开更多
BACKGROUND Duodenal neuroendocrine tumours(DNETs)are rare neoplasms.However,the incidence of DNETs has been increasing in recent years,especially as an incidental finding during endoscopic studies.Regrettably,there is...BACKGROUND Duodenal neuroendocrine tumours(DNETs)are rare neoplasms.However,the incidence of DNETs has been increasing in recent years,especially as an incidental finding during endoscopic studies.Regrettably,there is no consensus regarding the ideal treatment of DNETs.Even there are few studies on the clinical features and survival analysis of DNETs.AIM To analyze the clinical characteristics and prognostic factors of patients with duodenal neuroendocrine tumours.METHODS The clinical data of DNETs diagnosed in the First Affiliated Hospital of Air Force Military Medical University from June 2011 to July 2022 were collected.Neuroen-docrine tumours located in the ampulla area of the duodenum were divided into the ampullary region group;neuroendocrine tumours in any part of the duo-denum outside the ampullary area were divided into the nonampullary region group.Using a retrospective study,the clinical characteristics of the two groups and risk factors affecting the survival of DNET patients were analysed.RESULTS Twenty-nine DNET patients were screened.The male to female ratio was 1:1.9,and females comprised the majority.The ampullary region group accounted for 24.1%(7/29),while the nonampullary region group accounted for 75.9%(22/29).When diagnosed,the clinical symptoms of the ampullary region group were mainly abdominal pain(85.7%),while those of the nonampullary region groups were mainly abdominal distension(59.1%).There were differences in the composition of staging of tumours between the two groups(Fisher's exact probability method,P=0.001),with nonampullary stage II tumours(68.2%)being the main stage(P<0.05).After the diagnosis of DNETs,the survival rate of the ampullary region group was 14.3%(1/7),which was lower than that of 72.7%(16/22)in the nonampullary region group(Fisher's exact probability method,P=0.011).The survival time of the ampullary region group was shorter than that of the nonampullary region group(P<0.000).The median survival time of the ampullary region group was 10.0 months and that of the nonampullary region group was 451.0 months.Multivariate analysis showed that tumours in the ampulla region and no surgical treatment after diagnosis were independent risk factors for the survival of DNET patients(HR=0.029,95%CI 0.004-0.199,P<0.000;HR=12.609,95%CI:2.889-55.037,P=0.001).Further analysis of nonampullary DNET patients showed that the survival time of patients with a tumour diameter<2 cm was longer than that of patients with a tumour diameter≥2 cm(t=7.243,P=0.048).As of follow-up,6 patients who died of nonampullary DNETs had a tumour diameter that was≥2 cm,and 3 patients in stage IV had liver metastasis.Patients with a tumour diameter<2 cm underwent surgical treatment,and all survived after surgery.CONCLUSION Surgical treatment is a protective factor for prolonging the survival of DNET patients.Compared to DNETs in the ampullary region,patients in the nonampullary region group had a longer survival period.The liver is the organ most susceptible to distant metastasis of nonampullary DNETs.展开更多
In air traffic control communications (ATCC), misunderstandings between pilots and controllers could result in fatal aviation accidents. Fortunately, advanced automatic speech recognition technology has emerged as a p...In air traffic control communications (ATCC), misunderstandings between pilots and controllers could result in fatal aviation accidents. Fortunately, advanced automatic speech recognition technology has emerged as a promising means of preventing miscommunications and enhancing aviation safety. However, most existing speech recognition methods merely incorporate external language models on the decoder side, leading to insufficient semantic alignment between speech and text modalities during the encoding phase. Furthermore, it is challenging to model acoustic context dependencies over long distances due to the longer speech sequences than text, especially for the extended ATCC data. To address these issues, we propose a speech-text multimodal dual-tower architecture for speech recognition. It employs cross-modal interactions to achieve close semantic alignment during the encoding stage and strengthen its capabilities in modeling auditory long-distance context dependencies. In addition, a two-stage training strategy is elaborately devised to derive semantics-aware acoustic representations effectively. The first stage focuses on pre-training the speech-text multimodal encoding module to enhance inter-modal semantic alignment and aural long-distance context dependencies. The second stage fine-tunes the entire network to bridge the input modality variation gap between the training and inference phases and boost generalization performance. Extensive experiments demonstrate the effectiveness of the proposed speech-text multimodal speech recognition method on the ATCC and AISHELL-1 datasets. It reduces the character error rate to 6.54% and 8.73%, respectively, and exhibits substantial performance gains of 28.76% and 23.82% compared with the best baseline model. The case studies indicate that the obtained semantics-aware acoustic representations aid in accurately recognizing terms with similar pronunciations but distinctive semantics. The research provides a novel modeling paradigm for semantics-aware speech recognition in air traffic control communications, which could contribute to the advancement of intelligent and efficient aviation safety management.展开更多
In the multi-radar networking system,aiming at the problem of locating long-distance targets synergistically with difficulty and low accuracy,a dual-station joint positioning method based on the target measurement err...In the multi-radar networking system,aiming at the problem of locating long-distance targets synergistically with difficulty and low accuracy,a dual-station joint positioning method based on the target measurement error feature complementarity is proposed.For dual-station joint positioning,by constructing the target positioning error distribution model and using the complementarity of spatial measurement errors of the same long-distance target,the area with high probability of target existence can be obtained.Then,based on the target distance information,the midpoint of the intersection between the target positioning sphere and the positioning tangent plane can be solved to acquire the target's optimal positioning result.The simulation demonstrates that this method greatly improves the positioning accuracy of target in azimuth direction.Compared with the traditional the dynamic weighted fusion(DWF)algorithm and the filter-based dynamic weighted fusion(FBDWF)algorithm,it not only effectively eliminates the influence of systematic error in the azimuth direction,but also has low computational complexity.Furthermore,for the application scenarios of multi-radar collaborative positioning and multi-sensor data compression filtering in centralized information fusion,it is recommended that using radar with higher ranging accuracy and the lengths of baseline between radars are 20–100 km.展开更多
Olive trees are susceptible to a variety of diseases that can cause significant crop damage and economic losses.Early detection of these diseases is essential for effective management.We propose a novel transformed wa...Olive trees are susceptible to a variety of diseases that can cause significant crop damage and economic losses.Early detection of these diseases is essential for effective management.We propose a novel transformed wavelet,feature-fused,pre-trained deep learning model for detecting olive leaf diseases.The proposed model combines wavelet transforms with pre-trained deep-learning models to extract discriminative features from olive leaf images.The model has four main phases:preprocessing using data augmentation,three-level wavelet transformation,learning using pre-trained deep learning models,and a fused deep learning model.In the preprocessing phase,the image dataset is augmented using techniques such as resizing,rescaling,flipping,rotation,zooming,and contrasting.In wavelet transformation,the augmented images are decomposed into three frequency levels.Three pre-trained deep learning models,EfficientNet-B7,DenseNet-201,and ResNet-152-V2,are used in the learning phase.The models were trained using the approximate images of the third-level sub-band of the wavelet transform.In the fused phase,the fused model consists of a merge layer,three dense layers,and two dropout layers.The proposed model was evaluated using a dataset of images of healthy and infected olive leaves.It achieved an accuracy of 99.72%in the diagnosis of olive leaf diseases,which exceeds the accuracy of other methods reported in the literature.This finding suggests that our proposed method is a promising tool for the early detection of olive leaf diseases.展开更多
Recently, there have been some attempts of Transformer in 3D point cloud classification. In order to reduce computations, most existing methods focus on local spatial attention,but ignore their content and fail to est...Recently, there have been some attempts of Transformer in 3D point cloud classification. In order to reduce computations, most existing methods focus on local spatial attention,but ignore their content and fail to establish relationships between distant but relevant points. To overcome the limitation of local spatial attention, we propose a point content-based Transformer architecture, called PointConT for short. It exploits the locality of points in the feature space(content-based), which clusters the sampled points with similar features into the same class and computes the self-attention within each class, thus enabling an effective trade-off between capturing long-range dependencies and computational complexity. We further introduce an inception feature aggregator for point cloud classification, which uses parallel structures to aggregate high-frequency and low-frequency information in each branch separately. Extensive experiments show that our PointConT model achieves a remarkable performance on point cloud shape classification. Especially, our method exhibits 90.3% Top-1 accuracy on the hardest setting of ScanObjectN N. Source code of this paper is available at https://github.com/yahuiliu99/PointC onT.展开更多
In a crowd density estimation dataset,the annotation of crowd locations is an extremely laborious task,and they are not taken into the evaluation metrics.In this paper,we aim to reduce the annotation cost of crowd dat...In a crowd density estimation dataset,the annotation of crowd locations is an extremely laborious task,and they are not taken into the evaluation metrics.In this paper,we aim to reduce the annotation cost of crowd datasets,and propose a crowd density estimation method based on weakly-supervised learning,in the absence of crowd position supervision information,which directly reduces the number of crowds by using the number of pedestrians in the image as the supervised information.For this purpose,we design a new training method,which exploits the correlation between global and local image features by incremental learning to train the network.Specifically,we design a parent-child network(PC-Net)focusing on the global and local image respectively,and propose a linear feature calibration structure to train the PC-Net simultaneously,and the child network learns feature transfer factors and feature bias weights,and uses the transfer factors and bias weights to linearly feature calibrate the features extracted from the Parent network,to improve the convergence of the network by using local features hidden in the crowd images.In addition,we use the pyramid vision transformer as the backbone of the PC-Net to extract crowd features at different levels,and design a global-local feature loss function(L2).We combine it with a crowd counting loss(LC)to enhance the sensitivity of the network to crowd features during the training process,which effectively improves the accuracy of crowd density estimation.The experimental results show that the PC-Net significantly reduces the gap between fullysupervised and weakly-supervised crowd density estimation,and outperforms the comparison methods on five datasets of Shanghai Tech Part A,ShanghaiTech Part B,UCF_CC_50,UCF_QNRF and JHU-CROWD++.展开更多
Feature Subset Selection(FSS)is an NP-hard problem to remove redundant and irrelevant features particularly from medical data,and it can be effectively addressed by metaheuristic algorithms.However,existing binary ver...Feature Subset Selection(FSS)is an NP-hard problem to remove redundant and irrelevant features particularly from medical data,and it can be effectively addressed by metaheuristic algorithms.However,existing binary versions of metaheuristic algorithms have issues with convergence and lack an effective binarization method,resulting in suboptimal solutions that hinder diagnosis and prediction accuracy.This paper aims to propose an Improved Binary Quantum-based Avian Navigation Optimizer Algorithm(IBQANA)for FSS in medical data preprocessing to address the suboptimal solutions arising from binary versions of metaheuristic algorithms.The proposed IBQANA’s contributions include the Hybrid Binary Operator(HBO)and the Distance-based Binary Search Strategy(DBSS).HBO is designed to convert continuous values into binary solutions,even for values outside the[0,1]range,ensuring accurate binary mapping.On the other hand,DBSS is a two-phase search strategy that enhances the performance of inferior search agents and accelerates convergence.By combining exploration and exploitation phases based on an adaptive probability function,DBSS effectively avoids local optima.The effectiveness of applying HBO is compared with five transfer function families and thresholding on 12 medical datasets,with feature numbers ranging from 8 to 10,509.IBQANA's effectiveness is evaluated regarding the accuracy,fitness,and selected features and compared with seven binary metaheuristic algorithms.Furthermore,IBQANA is utilized to detect COVID-19.The results reveal that the proposed IBQANA outperforms all comparative algorithms on COVID-19 and 11 other medical datasets.The proposed method presents a promising solution to the FSS problem in medical data preprocessing.展开更多
The precise and automatic segmentation of prostate magnetic resonance imaging(MRI)images is vital for assisting doctors in diagnosing prostate diseases.In recent years,many advanced methods have been applied to prosta...The precise and automatic segmentation of prostate magnetic resonance imaging(MRI)images is vital for assisting doctors in diagnosing prostate diseases.In recent years,many advanced methods have been applied to prostate segmentation,but due to the variability caused by prostate diseases,automatic segmentation of the prostate presents significant challenges.In this paper,we propose an attention-guided multi-scale feature fusion network(AGMSF-Net)to segment prostate MRI images.We propose an attention mechanism for extracting multi-scale features,and introduce a 3D transformer module to enhance global feature representation by adding it during the transition phase from encoder to decoder.In the decoder stage,a feature fusion module is proposed to obtain global context information.We evaluate our model on MRI images of the prostate acquired from a local hospital.The relative volume difference(RVD)and dice similarity coefficient(DSC)between the results of automatic prostate segmentation and ground truth were 1.21%and 93.68%,respectively.To quantitatively evaluate prostate volume on MRI,which is of significant clinical significance,we propose a unique AGMSF-Net.The essential performance evaluation and validation experiments have demonstrated the effectiveness of our method in automatic prostate segmentation.展开更多
Candida auris since it discovery in 2009 is becoming a severe threat to human health due to its very quickly spread, its worldwide high resistance to systemic antifungal drugs. In resource-constrained settings where s...Candida auris since it discovery in 2009 is becoming a severe threat to human health due to its very quickly spread, its worldwide high resistance to systemic antifungal drugs. In resource-constrained settings where several conditions are met for its emergence and spread, this worrisome fungus could cause large hospital and/or community-based outbreaks. This review aimed to summarize the available data on C. auris in Africa focusing on its epidemiology and antifungal resistance profile. Major databases were searched for articles on the epidemiology and antifungal resistance profile of C. auris in Africa. Out of 2,521 articles identified 22 met the inclusion criteria. In Africa, nearly 89% of African countries have no published data on C. auris. The prevalence of C. auris in Africa was 8.74%. The case fatality rate of C. auris infection in Africa was 39.46%. The main C. auris risk factors reported in Africa were cardiovascular disease, renal failure, diabetes, HIV, recent intake of antimicrobial drugs, ICU admissions, surgery, hemodialysis, parenteral nutrition and indwelling devices. Four phylogenetic clades were reported in Africa, namely clades I, II, III and IV. Candida auris showed a pan-African very high resistance rate to fluconazole, moderate resistance to amphotericin B, and high susceptibility to echinocandins. Finally, C. auris clade-specific mutations were observed within the ERG2, ERG3, ERG9, ERG11, FKS1, TAC1b and MRR1 genes in Africa. This systematic review showed the presence of C. auris in the African continent and a worrying unavailability of data on this resilient fungus in most African countries.展开更多
Geomorphological features are commonly used to identify potential landslides.Nevertheless,overemphasis on these features could lead to misjudgment.This research proposes a process-oriented approach for potential lands...Geomorphological features are commonly used to identify potential landslides.Nevertheless,overemphasis on these features could lead to misjudgment.This research proposes a process-oriented approach for potential landslide identification that considers time-dependent behaviors.The method integrates comprehensive remote sensing and geological analysis to qualitatively assess slope stability,and employs numerical analysis to quantitatively calculate aging stability.Specifically,a time-dependent stability calculation method for anticlinal slopes is developed and implemented in discrete element software,incorporating time-dependent mechanical and strength reduction calculations.By considering the time-dependent evolution of slopes,this method highlights the importance of both geomorphological features and time-dependent behaviors in landslide identification.This method has been applied to the Jiarishan slope(JRS)on the Qinghai-Tibet Plateau as a case study.The results show that the JRS,despite having landslide geomorphology,is a stable slope,highlighting the risk of misjudgment when relying solely on geomorphological features.This work provides insights into the geomorphological characterization and evolution history of the JRS and offers valuable guidance for studying slopes with similar landslide geomorphology.Furthermore,the process-oriented method incorporating timedependent evolution provides a means to evaluate potential landslides,reducing misjudgment due to excessive reliance on geomorphological features.展开更多
This paper proposes a novel open set recognition method,the Spatial Distribution Feature Extraction Network(SDFEN),to address the problem of electromagnetic signal recognition in an open environment.The spatial distri...This paper proposes a novel open set recognition method,the Spatial Distribution Feature Extraction Network(SDFEN),to address the problem of electromagnetic signal recognition in an open environment.The spatial distribution feature extraction layer in SDFEN replaces convolutional output neural networks with the spatial distribution features that focus more on inter-sample information by incorporating class center vectors.The designed hybrid loss function considers both intra-class distance and inter-class distance,thereby enhancing the similarity among samples of the same class and increasing the dissimilarity between samples of different classes during training.Consequently,this method allows unknown classes to occupy a larger space in the feature space.This reduces the possibility of overlap with known class samples and makes the boundaries between known and unknown samples more distinct.Additionally,the feature comparator threshold can be used to reject unknown samples.For signal open set recognition,seven methods,including the proposed method,are applied to two kinds of electromagnetic signal data:modulation signal and real-world emitter.The experimental results demonstrate that the proposed method outperforms the other six methods overall in a simulated open environment.Specifically,compared to the state-of-the-art Openmax method,the novel method achieves up to 8.87%and 5.25%higher micro-F-measures,respectively.展开更多
文摘Speech emotion recognition(SER)uses acoustic analysis to find features for emotion recognition and examines variations in voice that are caused by emotions.The number of features acquired with acoustic analysis is extremely high,so we introduce a hybrid filter-wrapper feature selection algorithm based on an improved equilibrium optimizer for constructing an emotion recognition system.The proposed algorithm implements multi-objective emotion recognition with the minimum number of selected features and maximum accuracy.First,we use the information gain and Fisher Score to sort the features extracted from signals.Then,we employ a multi-objective ranking method to evaluate these features and assign different importance to them.Features with high rankings have a large probability of being selected.Finally,we propose a repair strategy to address the problem of duplicate solutions in multi-objective feature selection,which can improve the diversity of solutions and avoid falling into local traps.Using random forest and K-nearest neighbor classifiers,four English speech emotion datasets are employed to test the proposed algorithm(MBEO)as well as other multi-objective emotion identification techniques.The results illustrate that it performs well in inverted generational distance,hypervolume,Pareto solutions,and execution time,and MBEO is appropriate for high-dimensional English SER.
文摘Machine Learning(ML)algorithms play a pivotal role in Speech Emotion Recognition(SER),although they encounter a formidable obstacle in accurately discerning a speaker’s emotional state.The examination of the emotional states of speakers holds significant importance in a range of real-time applications,including but not limited to virtual reality,human-robot interaction,emergency centers,and human behavior assessment.Accurately identifying emotions in the SER process relies on extracting relevant information from audio inputs.Previous studies on SER have predominantly utilized short-time characteristics such as Mel Frequency Cepstral Coefficients(MFCCs)due to their ability to capture the periodic nature of audio signals effectively.Although these traits may improve their ability to perceive and interpret emotional depictions appropriately,MFCCS has some limitations.So this study aims to tackle the aforementioned issue by systematically picking multiple audio cues,enhancing the classifier model’s efficacy in accurately discerning human emotions.The utilized dataset is taken from the EMO-DB database,preprocessing input speech is done using a 2D Convolution Neural Network(CNN)involves applying convolutional operations to spectrograms as they afford a visual representation of the way the audio signal frequency content changes over time.The next step is the spectrogram data normalization which is crucial for Neural Network(NN)training as it aids in faster convergence.Then the five auditory features MFCCs,Chroma,Mel-Spectrogram,Contrast,and Tonnetz are extracted from the spectrogram sequentially.The attitude of feature selection is to retain only dominant features by excluding the irrelevant ones.In this paper,the Sequential Forward Selection(SFS)and Sequential Backward Selection(SBS)techniques were employed for multiple audio cues features selection.Finally,the feature sets composed from the hybrid feature extraction methods are fed into the deep Bidirectional Long Short Term Memory(Bi-LSTM)network to discern emotions.Since the deep Bi-LSTM can hierarchically learn complex features and increases model capacity by achieving more robust temporal modeling,it is more effective than a shallow Bi-LSTM in capturing the intricate tones of emotional content existent in speech signals.The effectiveness and resilience of the proposed SER model were evaluated by experiments,comparing it to state-of-the-art SER techniques.The results indicated that the model achieved accuracy rates of 90.92%,93%,and 92%over the Ryerson Audio-Visual Database of Emotional Speech and Song(RAVDESS),Berlin Database of Emotional Speech(EMO-DB),and The Interactive Emotional Dyadic Motion Capture(IEMOCAP)datasets,respectively.These findings signify a prominent enhancement in the ability to emotional depictions identification in speech,showcasing the potential of the proposed model in advancing the SER field.
基金supported by the GRRC program of Gyeonggi Province(GRRC-Gachon2023(B02),Development of AI-based medical service technology).
文摘The performance of a speech emotion recognition(SER)system is heavily influenced by the efficacy of its feature extraction techniques.The study was designed to advance the field of SER by optimizing feature extraction tech-niques,specifically through the incorporation of high-resolution Mel-spectrograms and the expedited calculation of Mel Frequency Cepstral Coefficients(MFCC).This initiative aimed to refine the system’s accuracy by identifying and mitigating the shortcomings commonly found in current approaches.Ultimately,the primary objective was to elevate both the intricacy and effectiveness of our SER model,with a focus on augmenting its proficiency in the accurate identification of emotions in spoken language.The research employed a dual-strategy approach for feature extraction.Firstly,a rapid computation technique for MFCC was implemented and integrated with a Bi-LSTM layer to optimize the encoding of MFCC features.Secondly,a pretrained ResNet model was utilized in conjunction with feature Stats pooling and dense layers for the effective encoding of Mel-spectrogram attributes.These two sets of features underwent separate processing before being combined in a Convolutional Neural Network(CNN)outfitted with a dense layer,with the aim of enhancing their representational richness.The model was rigorously evaluated using two prominent databases:CMU-MOSEI and RAVDESS.Notable findings include an accuracy rate of 93.2%on the CMU-MOSEI database and 95.3%on the RAVDESS database.Such exceptional performance underscores the efficacy of this innovative approach,which not only meets but also exceeds the accuracy benchmarks established by traditional models in the field of speech emotion recognition.
基金National Natural Science Foundation of China(No.62001100)。
文摘The hidden danger of the automatic speaker verification(ASV)system is various spoofed speeches.These threats can be classified into two categories,namely logical access(LA)and physical access(PA).To improve identification capability of spoofed speech detection,this paper considers the research on features.Firstly,following the idea of modifying the constant-Q-based features,this work considered adding variance or mean to the constant-Q-based cepstral domain to obtain good performance.Secondly,linear frequency cepstral coefficients(LFCCs)performed comparably with constant-Q-based features.Finally,we proposed linear frequency variance-based cepstral coefficients(LVCCs)and linear frequency mean-based cepstral coefficients(LMCCs)for identification of speech spoofing.LVCCs and LMCCs could be attained by adding the frame variance or the mean to the log magnitude spectrum based on LFCC features.The proposed novel features were evaluated on ASVspoof 2019 datase.The experimental results show that compared with known hand-crafted features,LVCCs and LMCCs are more effective in resisting spoofed speech attack.
基金supported by the Competitive Research Fund of the University of Aizu,Japan.
文摘Sign language recognition is vital for enhancing communication accessibility among the Deaf and hard-of-hearing communities.In Japan,approximately 360,000 individualswith hearing and speech disabilities rely on Japanese Sign Language(JSL)for communication.However,existing JSL recognition systems have faced significant performance limitations due to inherent complexities.In response to these challenges,we present a novel JSL recognition system that employs a strategic fusion approach,combining joint skeleton-based handcrafted features and pixel-based deep learning features.Our system incorporates two distinct streams:the first stream extracts crucial handcrafted features,emphasizing the capture of hand and body movements within JSL gestures.Simultaneously,a deep learning-based transfer learning stream captures hierarchical representations of JSL gestures in the second stream.Then,we concatenated the critical information of the first stream and the hierarchy of the second stream features to produce the multiple levels of the fusion features,aiming to create a comprehensive representation of the JSL gestures.After reducing the dimensionality of the feature,a feature selection approach and a kernel-based support vector machine(SVM)were used for the classification.To assess the effectiveness of our approach,we conducted extensive experiments on our Lab JSL dataset and a publicly available Arabic sign language(ArSL)dataset.Our results unequivocally demonstrate that our fusion approach significantly enhances JSL recognition accuracy and robustness compared to individual feature sets or traditional recognition methods.
基金supported in part by the National Natural Science Foundation of China(82072019)the Shenzhen Basic Research Program(JCYJ20210324130209023)+5 种基金the Shenzhen-Hong Kong-Macao S&T Program(Category C)(SGDX20201103095002019)the Mainland-Hong Kong Joint Funding Scheme(MHKJFS)(MHP/005/20),the Project of Strategic Importance Fund(P0035421)the Projects of RISA(P0043001)from the Hong Kong Polytechnic University,the Natural Science Foundation of Jiangsu Province(BK20201441)the Provincial and Ministry Co-constructed Project of Henan Province Medical Science and Technology Research(SBGJ202103038,SBGJ202102056)the Henan Province Key R&D and Promotion Project(Science and Technology Research)(222102310015)the Natural Science Foundation of Henan Province(222300420575),and the Henan Province Science and Technology Research(222102310322).
文摘Modern medicine is reliant on various medical imaging technologies for non-invasively observing patients’anatomy.However,the interpretation of medical images can be highly subjective and dependent on the expertise of clinicians.Moreover,some potentially useful quantitative information in medical images,especially that which is not visible to the naked eye,is often ignored during clinical practice.In contrast,radiomics performs high-throughput feature extraction from medical images,which enables quantitative analysis of medical images and prediction of various clinical endpoints.Studies have reported that radiomics exhibits promising performance in diagnosis and predicting treatment responses and prognosis,demonstrating its potential to be a non-invasive auxiliary tool for personalized medicine.However,radiomics remains in a developmental phase as numerous technical challenges have yet to be solved,especially in feature engineering and statistical modeling.In this review,we introduce the current utility of radiomics by summarizing research on its application in the diagnosis,prognosis,and prediction of treatment responses in patients with cancer.We focus on machine learning approaches,for feature extraction and selection during feature engineering and for imbalanced datasets and multi-modality fusion during statistical modeling.Furthermore,we introduce the stability,reproducibility,and interpretability of features,and the generalizability and interpretability of models.Finally,we offer possible solutions to current challenges in radiomics research.
基金supported in part by the National Natural Science Foundation of China(Grants 62376172,62006163,62376043)in part by the National Postdoctoral Program for Innovative Talents(Grant BX20200226)in part by Sichuan Science and Technology Planning Project(Grants 2022YFSY0047,2022YFQ0014,2023ZYD0143,2022YFH0021,2023YFQ0020,24QYCX0354,24NSFTD0025).
文摘Time series anomaly detection is crucial in various industrial applications to identify unusual behaviors within the time series data.Due to the challenges associated with annotating anomaly events,time series reconstruction has become a prevalent approach for unsupervised anomaly detection.However,effectively learning representations and achieving accurate detection results remain challenging due to the intricate temporal patterns and dependencies in real-world time series.In this paper,we propose a cross-dimension attentive feature fusion network for time series anomaly detection,referred to as CAFFN.Specifically,a series and feature mixing block is introduced to learn representations in 1D space.Additionally,a fast Fourier transform is employed to convert the time series into 2D space,providing the capability for 2D feature extraction.Finally,a cross-dimension attentive feature fusion mechanism is designed that adaptively integrates features across different dimensions for anomaly detection.Experimental results on real-world time series datasets demonstrate that CAFFN performs better than other competing methods in time series anomaly detection.
基金supported by Wuyi University Hong Kong and Macao Joint Research and Development Fund(GrantsNos.2021WGALH15,2019WGALH17,2019WGALH15)the National Natural Science Foundation of China-Guangdong Joint Fund(GrantsNo.2019A1515111052)+2 种基金the National Natural Science Foundation of China(Grant No.52202426)a grant from the Research Grants Council(RGC)of the Hong Kong Special Administrative Region(SAR),China(Grants No.15205723)a grant from the Hong Kong Polytechnic University(Grant No.P0045325).
文摘The safety and stability of high-speed maglev trains traveling on viaducts in crosswinds critically depend on their aerodynamic characteristics.Therefore,this paper uses an improved delayed detached eddy simulation(IDDES)method to investigate the aerodynamic features of high-speed maglev trains with different marshaling lengths under crosswinds.The effects of marshaling lengths(varying from 3-car to 8-car groups)on the train’s aerodynamic performance,surface pressure,and the flow field surrounding the train were investigated using the three-dimensional unsteady compressible Navier-Stokes(N-S)equations.The results showed that the marshaling lengths had minimal influence on the aerodynamic performance of the head and middle cars.Conversely,the marshaling lengths are negatively correlated with the time-average side force coefficient(CS)and time-average lift force coefficient(Cl)of the tail car.Compared to the tail car of the 3-car groups,the CS and Cl fell by 27.77%and 18.29%,respectively,for the tail car of the 8-car groups.It is essential to pay more attention to the operational safety of the head car,as it exhibits the highest time average CS.Additionally,the mean pressure difference between the two sides of the tail car body increased with the marshaling lengths,and the side force direction on the tail car was opposite to that of the head and middle cars.Furthermore,the turbulent kinetic energy of the wake structure on the windward side quickly decreased as marshaling lengths increased.
基金supported by the National Natural Science Foundation of China (62276192)。
文摘Feature matching plays a key role in computer vision. However, due to the limitations of the descriptors, the putative matches are inevitably contaminated by massive outliers.This paper attempts to tackle the outlier filtering problem from two aspects. First, a robust and efficient graph interaction model,is proposed, with the assumption that matches are correlated with each other rather than independently distributed. To this end, we construct a graph based on the local relationships of matches and formulate the outlier filtering task as a binary labeling energy minimization problem, where the pairwise term encodes the interaction between matches. We further show that this formulation can be solved globally by graph cut algorithm. Our new formulation always improves the performance of previous localitybased method without noticeable deterioration in processing time,adding a few milliseconds. Second, to construct a better graph structure, a robust and geometrically meaningful topology-aware relationship is developed to capture the topology relationship between matches. The two components in sum lead to topology interaction matching(TIM), an effective and efficient method for outlier filtering. Extensive experiments on several large and diverse datasets for multiple vision tasks including general feature matching, as well as relative pose estimation, homography and fundamental matrix estimation, loop-closure detection, and multi-modal image matching, demonstrate that our TIM is more competitive than current state-of-the-art methods, in terms of generality, efficiency, and effectiveness. The source code is publicly available at http://github.com/YifanLu2000/TIM.
基金The study protocol was approved by the Clinical Research Ethics Committee of Honghui Hospital,Xi’an Jiaotong University(No.202401004).
文摘BACKGROUND Duodenal neuroendocrine tumours(DNETs)are rare neoplasms.However,the incidence of DNETs has been increasing in recent years,especially as an incidental finding during endoscopic studies.Regrettably,there is no consensus regarding the ideal treatment of DNETs.Even there are few studies on the clinical features and survival analysis of DNETs.AIM To analyze the clinical characteristics and prognostic factors of patients with duodenal neuroendocrine tumours.METHODS The clinical data of DNETs diagnosed in the First Affiliated Hospital of Air Force Military Medical University from June 2011 to July 2022 were collected.Neuroen-docrine tumours located in the ampulla area of the duodenum were divided into the ampullary region group;neuroendocrine tumours in any part of the duo-denum outside the ampullary area were divided into the nonampullary region group.Using a retrospective study,the clinical characteristics of the two groups and risk factors affecting the survival of DNET patients were analysed.RESULTS Twenty-nine DNET patients were screened.The male to female ratio was 1:1.9,and females comprised the majority.The ampullary region group accounted for 24.1%(7/29),while the nonampullary region group accounted for 75.9%(22/29).When diagnosed,the clinical symptoms of the ampullary region group were mainly abdominal pain(85.7%),while those of the nonampullary region groups were mainly abdominal distension(59.1%).There were differences in the composition of staging of tumours between the two groups(Fisher's exact probability method,P=0.001),with nonampullary stage II tumours(68.2%)being the main stage(P<0.05).After the diagnosis of DNETs,the survival rate of the ampullary region group was 14.3%(1/7),which was lower than that of 72.7%(16/22)in the nonampullary region group(Fisher's exact probability method,P=0.011).The survival time of the ampullary region group was shorter than that of the nonampullary region group(P<0.000).The median survival time of the ampullary region group was 10.0 months and that of the nonampullary region group was 451.0 months.Multivariate analysis showed that tumours in the ampulla region and no surgical treatment after diagnosis were independent risk factors for the survival of DNET patients(HR=0.029,95%CI 0.004-0.199,P<0.000;HR=12.609,95%CI:2.889-55.037,P=0.001).Further analysis of nonampullary DNET patients showed that the survival time of patients with a tumour diameter<2 cm was longer than that of patients with a tumour diameter≥2 cm(t=7.243,P=0.048).As of follow-up,6 patients who died of nonampullary DNETs had a tumour diameter that was≥2 cm,and 3 patients in stage IV had liver metastasis.Patients with a tumour diameter<2 cm underwent surgical treatment,and all survived after surgery.CONCLUSION Surgical treatment is a protective factor for prolonging the survival of DNET patients.Compared to DNETs in the ampullary region,patients in the nonampullary region group had a longer survival period.The liver is the organ most susceptible to distant metastasis of nonampullary DNETs.
基金This research was funded by Shenzhen Science and Technology Program(Grant No.RCBS20221008093121051)the General Higher Education Project of Guangdong Provincial Education Department(Grant No.2020ZDZX3085)+1 种基金China Postdoctoral Science Foundation(Grant No.2021M703371)the Post-Doctoral Foundation Project of Shenzhen Polytechnic(Grant No.6021330002K).
文摘In air traffic control communications (ATCC), misunderstandings between pilots and controllers could result in fatal aviation accidents. Fortunately, advanced automatic speech recognition technology has emerged as a promising means of preventing miscommunications and enhancing aviation safety. However, most existing speech recognition methods merely incorporate external language models on the decoder side, leading to insufficient semantic alignment between speech and text modalities during the encoding phase. Furthermore, it is challenging to model acoustic context dependencies over long distances due to the longer speech sequences than text, especially for the extended ATCC data. To address these issues, we propose a speech-text multimodal dual-tower architecture for speech recognition. It employs cross-modal interactions to achieve close semantic alignment during the encoding stage and strengthen its capabilities in modeling auditory long-distance context dependencies. In addition, a two-stage training strategy is elaborately devised to derive semantics-aware acoustic representations effectively. The first stage focuses on pre-training the speech-text multimodal encoding module to enhance inter-modal semantic alignment and aural long-distance context dependencies. The second stage fine-tunes the entire network to bridge the input modality variation gap between the training and inference phases and boost generalization performance. Extensive experiments demonstrate the effectiveness of the proposed speech-text multimodal speech recognition method on the ATCC and AISHELL-1 datasets. It reduces the character error rate to 6.54% and 8.73%, respectively, and exhibits substantial performance gains of 28.76% and 23.82% compared with the best baseline model. The case studies indicate that the obtained semantics-aware acoustic representations aid in accurately recognizing terms with similar pronunciations but distinctive semantics. The research provides a novel modeling paradigm for semantics-aware speech recognition in air traffic control communications, which could contribute to the advancement of intelligent and efficient aviation safety management.
文摘In the multi-radar networking system,aiming at the problem of locating long-distance targets synergistically with difficulty and low accuracy,a dual-station joint positioning method based on the target measurement error feature complementarity is proposed.For dual-station joint positioning,by constructing the target positioning error distribution model and using the complementarity of spatial measurement errors of the same long-distance target,the area with high probability of target existence can be obtained.Then,based on the target distance information,the midpoint of the intersection between the target positioning sphere and the positioning tangent plane can be solved to acquire the target's optimal positioning result.The simulation demonstrates that this method greatly improves the positioning accuracy of target in azimuth direction.Compared with the traditional the dynamic weighted fusion(DWF)algorithm and the filter-based dynamic weighted fusion(FBDWF)algorithm,it not only effectively eliminates the influence of systematic error in the azimuth direction,but also has low computational complexity.Furthermore,for the application scenarios of multi-radar collaborative positioning and multi-sensor data compression filtering in centralized information fusion,it is recommended that using radar with higher ranging accuracy and the lengths of baseline between radars are 20–100 km.
文摘Olive trees are susceptible to a variety of diseases that can cause significant crop damage and economic losses.Early detection of these diseases is essential for effective management.We propose a novel transformed wavelet,feature-fused,pre-trained deep learning model for detecting olive leaf diseases.The proposed model combines wavelet transforms with pre-trained deep-learning models to extract discriminative features from olive leaf images.The model has four main phases:preprocessing using data augmentation,three-level wavelet transformation,learning using pre-trained deep learning models,and a fused deep learning model.In the preprocessing phase,the image dataset is augmented using techniques such as resizing,rescaling,flipping,rotation,zooming,and contrasting.In wavelet transformation,the augmented images are decomposed into three frequency levels.Three pre-trained deep learning models,EfficientNet-B7,DenseNet-201,and ResNet-152-V2,are used in the learning phase.The models were trained using the approximate images of the third-level sub-band of the wavelet transform.In the fused phase,the fused model consists of a merge layer,three dense layers,and two dropout layers.The proposed model was evaluated using a dataset of images of healthy and infected olive leaves.It achieved an accuracy of 99.72%in the diagnosis of olive leaf diseases,which exceeds the accuracy of other methods reported in the literature.This finding suggests that our proposed method is a promising tool for the early detection of olive leaf diseases.
基金supported in part by the Nationa Natural Science Foundation of China (61876011)the National Key Research and Development Program of China (2022YFB4703700)+1 种基金the Key Research and Development Program 2020 of Guangzhou (202007050002)the Key-Area Research and Development Program of Guangdong Province (2020B090921003)。
文摘Recently, there have been some attempts of Transformer in 3D point cloud classification. In order to reduce computations, most existing methods focus on local spatial attention,but ignore their content and fail to establish relationships between distant but relevant points. To overcome the limitation of local spatial attention, we propose a point content-based Transformer architecture, called PointConT for short. It exploits the locality of points in the feature space(content-based), which clusters the sampled points with similar features into the same class and computes the self-attention within each class, thus enabling an effective trade-off between capturing long-range dependencies and computational complexity. We further introduce an inception feature aggregator for point cloud classification, which uses parallel structures to aggregate high-frequency and low-frequency information in each branch separately. Extensive experiments show that our PointConT model achieves a remarkable performance on point cloud shape classification. Especially, our method exhibits 90.3% Top-1 accuracy on the hardest setting of ScanObjectN N. Source code of this paper is available at https://github.com/yahuiliu99/PointC onT.
基金the Humanities and Social Science Fund of the Ministry of Education of China(21YJAZH077)。
文摘In a crowd density estimation dataset,the annotation of crowd locations is an extremely laborious task,and they are not taken into the evaluation metrics.In this paper,we aim to reduce the annotation cost of crowd datasets,and propose a crowd density estimation method based on weakly-supervised learning,in the absence of crowd position supervision information,which directly reduces the number of crowds by using the number of pedestrians in the image as the supervised information.For this purpose,we design a new training method,which exploits the correlation between global and local image features by incremental learning to train the network.Specifically,we design a parent-child network(PC-Net)focusing on the global and local image respectively,and propose a linear feature calibration structure to train the PC-Net simultaneously,and the child network learns feature transfer factors and feature bias weights,and uses the transfer factors and bias weights to linearly feature calibrate the features extracted from the Parent network,to improve the convergence of the network by using local features hidden in the crowd images.In addition,we use the pyramid vision transformer as the backbone of the PC-Net to extract crowd features at different levels,and design a global-local feature loss function(L2).We combine it with a crowd counting loss(LC)to enhance the sensitivity of the network to crowd features during the training process,which effectively improves the accuracy of crowd density estimation.The experimental results show that the PC-Net significantly reduces the gap between fullysupervised and weakly-supervised crowd density estimation,and outperforms the comparison methods on five datasets of Shanghai Tech Part A,ShanghaiTech Part B,UCF_CC_50,UCF_QNRF and JHU-CROWD++.
文摘Feature Subset Selection(FSS)is an NP-hard problem to remove redundant and irrelevant features particularly from medical data,and it can be effectively addressed by metaheuristic algorithms.However,existing binary versions of metaheuristic algorithms have issues with convergence and lack an effective binarization method,resulting in suboptimal solutions that hinder diagnosis and prediction accuracy.This paper aims to propose an Improved Binary Quantum-based Avian Navigation Optimizer Algorithm(IBQANA)for FSS in medical data preprocessing to address the suboptimal solutions arising from binary versions of metaheuristic algorithms.The proposed IBQANA’s contributions include the Hybrid Binary Operator(HBO)and the Distance-based Binary Search Strategy(DBSS).HBO is designed to convert continuous values into binary solutions,even for values outside the[0,1]range,ensuring accurate binary mapping.On the other hand,DBSS is a two-phase search strategy that enhances the performance of inferior search agents and accelerates convergence.By combining exploration and exploitation phases based on an adaptive probability function,DBSS effectively avoids local optima.The effectiveness of applying HBO is compared with five transfer function families and thresholding on 12 medical datasets,with feature numbers ranging from 8 to 10,509.IBQANA's effectiveness is evaluated regarding the accuracy,fitness,and selected features and compared with seven binary metaheuristic algorithms.Furthermore,IBQANA is utilized to detect COVID-19.The results reveal that the proposed IBQANA outperforms all comparative algorithms on COVID-19 and 11 other medical datasets.The proposed method presents a promising solution to the FSS problem in medical data preprocessing.
基金This work was supported in part by the National Natural Science Foundation of China(Grant#:82260362)in part by the National Key R&D Program of China(Grant#:2021ZD0111000)+1 种基金in part by the Key R&D Project of Hainan Province(Grant#:ZDYF2021SHFZ243)in part by the Major Science and Technology Project of Haikou(Grant#:2020-009).
文摘The precise and automatic segmentation of prostate magnetic resonance imaging(MRI)images is vital for assisting doctors in diagnosing prostate diseases.In recent years,many advanced methods have been applied to prostate segmentation,but due to the variability caused by prostate diseases,automatic segmentation of the prostate presents significant challenges.In this paper,we propose an attention-guided multi-scale feature fusion network(AGMSF-Net)to segment prostate MRI images.We propose an attention mechanism for extracting multi-scale features,and introduce a 3D transformer module to enhance global feature representation by adding it during the transition phase from encoder to decoder.In the decoder stage,a feature fusion module is proposed to obtain global context information.We evaluate our model on MRI images of the prostate acquired from a local hospital.The relative volume difference(RVD)and dice similarity coefficient(DSC)between the results of automatic prostate segmentation and ground truth were 1.21%and 93.68%,respectively.To quantitatively evaluate prostate volume on MRI,which is of significant clinical significance,we propose a unique AGMSF-Net.The essential performance evaluation and validation experiments have demonstrated the effectiveness of our method in automatic prostate segmentation.
文摘Candida auris since it discovery in 2009 is becoming a severe threat to human health due to its very quickly spread, its worldwide high resistance to systemic antifungal drugs. In resource-constrained settings where several conditions are met for its emergence and spread, this worrisome fungus could cause large hospital and/or community-based outbreaks. This review aimed to summarize the available data on C. auris in Africa focusing on its epidemiology and antifungal resistance profile. Major databases were searched for articles on the epidemiology and antifungal resistance profile of C. auris in Africa. Out of 2,521 articles identified 22 met the inclusion criteria. In Africa, nearly 89% of African countries have no published data on C. auris. The prevalence of C. auris in Africa was 8.74%. The case fatality rate of C. auris infection in Africa was 39.46%. The main C. auris risk factors reported in Africa were cardiovascular disease, renal failure, diabetes, HIV, recent intake of antimicrobial drugs, ICU admissions, surgery, hemodialysis, parenteral nutrition and indwelling devices. Four phylogenetic clades were reported in Africa, namely clades I, II, III and IV. Candida auris showed a pan-African very high resistance rate to fluconazole, moderate resistance to amphotericin B, and high susceptibility to echinocandins. Finally, C. auris clade-specific mutations were observed within the ERG2, ERG3, ERG9, ERG11, FKS1, TAC1b and MRR1 genes in Africa. This systematic review showed the presence of C. auris in the African continent and a worrying unavailability of data on this resilient fungus in most African countries.
基金This research was supported by the National Natural Science Foundation of China(Grant Nos.41972284 and 42090054)This work was also supported by the State Key Laboratory of Geohazard Prevention and Geoenvironment Protection Independent Research Project(Grant No.SKLGP2020Z005).
文摘Geomorphological features are commonly used to identify potential landslides.Nevertheless,overemphasis on these features could lead to misjudgment.This research proposes a process-oriented approach for potential landslide identification that considers time-dependent behaviors.The method integrates comprehensive remote sensing and geological analysis to qualitatively assess slope stability,and employs numerical analysis to quantitatively calculate aging stability.Specifically,a time-dependent stability calculation method for anticlinal slopes is developed and implemented in discrete element software,incorporating time-dependent mechanical and strength reduction calculations.By considering the time-dependent evolution of slopes,this method highlights the importance of both geomorphological features and time-dependent behaviors in landslide identification.This method has been applied to the Jiarishan slope(JRS)on the Qinghai-Tibet Plateau as a case study.The results show that the JRS,despite having landslide geomorphology,is a stable slope,highlighting the risk of misjudgment when relying solely on geomorphological features.This work provides insights into the geomorphological characterization and evolution history of the JRS and offers valuable guidance for studying slopes with similar landslide geomorphology.Furthermore,the process-oriented method incorporating timedependent evolution provides a means to evaluate potential landslides,reducing misjudgment due to excessive reliance on geomorphological features.
文摘This paper proposes a novel open set recognition method,the Spatial Distribution Feature Extraction Network(SDFEN),to address the problem of electromagnetic signal recognition in an open environment.The spatial distribution feature extraction layer in SDFEN replaces convolutional output neural networks with the spatial distribution features that focus more on inter-sample information by incorporating class center vectors.The designed hybrid loss function considers both intra-class distance and inter-class distance,thereby enhancing the similarity among samples of the same class and increasing the dissimilarity between samples of different classes during training.Consequently,this method allows unknown classes to occupy a larger space in the feature space.This reduces the possibility of overlap with known class samples and makes the boundaries between known and unknown samples more distinct.Additionally,the feature comparator threshold can be used to reject unknown samples.For signal open set recognition,seven methods,including the proposed method,are applied to two kinds of electromagnetic signal data:modulation signal and real-world emitter.The experimental results demonstrate that the proposed method outperforms the other six methods overall in a simulated open environment.Specifically,compared to the state-of-the-art Openmax method,the novel method achieves up to 8.87%and 5.25%higher micro-F-measures,respectively.
