With the rapid advancement of wearable devices,Human Activities Recognition(HAR)based on these devices has emerged as a prominent research field.The objective of this study is to enhance the recognition performance of...With the rapid advancement of wearable devices,Human Activities Recognition(HAR)based on these devices has emerged as a prominent research field.The objective of this study is to enhance the recognition performance of HAR by proposing an LSTM-1DCNN recognition algorithm that utilizes a single triaxial accelerometer.This algorithm comprises two branches:one branch consists of a Long and Short-Term Memory Network(LSTM),while the other parallel branch incorporates a one-dimensional Convolutional Neural Network(1DCNN).The parallel architecture of LSTM-1DCNN initially extracts spatial and temporal features from the accelerometer data separately,which are then concatenated and fed into a fully connected neural network for information fusion.In the LSTM-1DCNN architecture,the 1DCNN branch primarily focuses on extracting spatial features during convolution operations,whereas the LSTM branch mainly captures temporal features.Nine sets of accelerometer data from five publicly available HAR datasets are employed for training and evaluation purposes.The performance of the proposed LSTM-1DCNN model is compared with five other HAR algorithms including Decision Tree,Random Forest,Support Vector Machine,1DCNN,and LSTM on these five public datasets.Experimental results demonstrate that the F1-score achieved by the proposed LSTM-1DCNN ranges from 90.36%to 99.68%,with a mean value of 96.22%and standard deviation of 0.03 across all evaluated metrics on these five public datasets-outperforming other existing HAR algorithms significantly in terms of evaluation metrics used in this study.Finally the proposed LSTM-1DCNN is validated in real-world applications by collecting acceleration data of seven human activities for training and testing purposes.Subsequently,the trained HAR algorithm is deployed on Android phones to evaluate its performance.Experimental results demonstrate that the proposed LSTM-1DCNN algorithm achieves an impressive F1-score of 97.67%on our self-built dataset.In conclusion,the fusion of temporal and spatial information in the measured data contributes to the excellent HAR performance and robustness exhibited by the proposed 1DCNN-LSTM architecture.展开更多
Dear Editor, This letter focuses on the protocol-based non-fragile state estimation problem for a class of recurrent neural networks(RNNs). With the development of communication technology, the networked systems have ...Dear Editor, This letter focuses on the protocol-based non-fragile state estimation problem for a class of recurrent neural networks(RNNs). With the development of communication technology, the networked systems have received particular attentions. The networked system brings advantages such as easy to implement.展开更多
This paper investigates the anomaly-resistant decentralized state estimation(SE) problem for a class of wide-area power systems which are divided into several non-overlapping areas connected through transmission lines...This paper investigates the anomaly-resistant decentralized state estimation(SE) problem for a class of wide-area power systems which are divided into several non-overlapping areas connected through transmission lines. Two classes of measurements(i.e., local measurements and edge measurements) are obtained, respectively, from the individual area and the transmission lines. A decentralized state estimator, whose performance is resistant against measurement with anomalies, is designed based on the minimum error entropy with fiducial points(MEEF) criterion. Specifically, 1) An augmented model, which incorporates the local prediction and local measurement, is developed by resorting to the unscented transformation approach and the statistical linearization approach;2) Using the augmented model, an MEEF-based cost function is designed that reflects the local prediction errors of the state and the measurement;and 3) The local estimate is first obtained by minimizing the MEEF-based cost function through a fixed-point iteration and then updated by using the edge measuring information. Finally, simulation experiments with three scenarios are carried out on the IEEE 14-bus system to illustrate the validity of the proposed anomaly-resistant decentralized SE scheme.展开更多
Accurate detection of pipeline leakage is essential to maintain the safety of pipeline transportation.Recently,deep learning(DL)has emerged as a promising tool for pipeline leakage detection(PLD).However,most existing...Accurate detection of pipeline leakage is essential to maintain the safety of pipeline transportation.Recently,deep learning(DL)has emerged as a promising tool for pipeline leakage detection(PLD).However,most existing DL methods have difficulty in achieving good performance in identifying leakage types due to the complex time dynamics of pipeline data.On the other hand,the initial parameter selection in the detection model is generally random,which may lead to unstable recognition performance.For this reason,a hybrid DL framework referred to as parameter-optimized recurrent attention network(PRAN)is presented in this paper to improve the accuracy of PLD.First,a parameter-optimized long short-term memory(LSTM)network is introduced to extract effective and robust features,which exploits a particle swarm optimization(PSO)algorithm with cross-entropy fitness function to search for globally optimal parameters.With this framework,the learning representation capability of the model is improved and the convergence rate is accelerated.Moreover,an anomaly-attention mechanism(AM)is proposed to discover class discriminative information by weighting the hidden states,which contributes to amplifying the normalabnormal distinguishable discrepancy,further improving the accuracy of PLD.After that,the proposed PRAN not only implements the adaptive optimization of network parameters,but also enlarges the contribution of normal-abnormal discrepancy,thereby overcoming the drawbacks of instability and poor generalization.Finally,the experimental results demonstrate the effectiveness and superiority of the proposed PRAN for PLD.展开更多
In order to study the sintering characteristics of Ca-rich iron ore,chemical analysis,laser diffraction,scanning electron microscopy,XRD-Rietveld method,and micro-sintering were used to analyze the mineralogical prope...In order to study the sintering characteristics of Ca-rich iron ore,chemical analysis,laser diffraction,scanning electron microscopy,XRD-Rietveld method,and micro-sintering were used to analyze the mineralogical properties and sintering pot tests were used to study the sintering behavior.In addition,a grey correlation mathematical model was used to calculate and compare the comprehensive sintering performance under different calcium-rich iron ore contents.The results demonstrate that the Ca-rich iron ore has coarse grain size and strong self-fusing characteristics with Ca element in the form of calcite(CaCO_(3)) and the liquid phase produced by the self-fusing of the calcium-rich iron ore is well crystallized.Its application with a 20wt%content in sintering improves sinter productivity,reduces fuel consumption,enhances reduction index,and improves gas permeability in blast furnace by 0.45 t/(m^(2)·h),6.11 kg/t,6.17%,and 65.39 kPa·℃,respectively.The Ca-rich iron ore sintering can improve the calorific value of sintering flue gas compared with magnetite sintering,which is conducive to recovering heat for secondary use.As the content of the Ca-rich iron ore increases,sinter agglomeration shifts from localized liquid-phase bonding to a combination of localized liquid-phase bonding and iron oxide crystal connection.Based on an examination of the greater weight value of productivity with grey correlation analysis,the Ca-rich iron ore is beneficial for the comprehensive index of sintering in the range of 0-20wt%content.Therefore,it may be used in sintering with magnetite concentrates as the major ore species.展开更多
The Ordos Basin is the largest continental multi-energy mineral basin in China,which is rich in coal,oil and gas,and uranium resources.The exploitation of mineral resources is closely related to reservoir water.The ch...The Ordos Basin is the largest continental multi-energy mineral basin in China,which is rich in coal,oil and gas,and uranium resources.The exploitation of mineral resources is closely related to reservoir water.The chemical properties of reservoir water are very important for reservoir evaluation and are significant indicators of the sealing of reservoir oil and gas resources.Therefore,the caprock of the Chang 6 reservoir in the Yanchang Formation was evaluated.The authors tested and analyzed the chemical characteristics of water samples selected from 30 wells in the Chang 6 reservoir of Ansai Oilfield in the Ordos Basin.The results show that the Chang 6 reservoir water in Ansai Oilfield is dominated by calcium-chloride water type with a sodium chloride coefficient of generally less than 0.5.The chloride magnesium coefficients are between 33.7 and 925.5,most of which are greater than 200.The desulfurization coefficients range from 0.21 to 13.4,with an average of 2.227.The carbonate balance coefficients are mainly concentrated below 0.01,with an average of 0.008.The calcium and magnesium coefficients are between 0.08 and 0.003,with an average of 0.01.Combined with the characteristics of the four-corner layout of the reservoir water,the above results show that the graphics are basically consistent.The study indicates that the Chang 6 reservoir in Ansai Oilfield in the Ordos Basin is a favorable block for oil and gas storage with good sealing properties,great preservation conditions of oil and gas,and high pore connectivity.展开更多
High-dimensional and incomplete(HDI)data subject to the nonnegativity constraints are commonly encountered in a big data-related application concerning the interactions among numerous nodes.A nonnegative latent factor...High-dimensional and incomplete(HDI)data subject to the nonnegativity constraints are commonly encountered in a big data-related application concerning the interactions among numerous nodes.A nonnegative latent factor analysis(NLFA)model can perform representation learning to HDI data efficiently.However,existing NLFA models suffer from either slow convergence rate or representation accuracy loss.To address this issue,this paper proposes a proximal alternating-directionmethod-of-multipliers-based nonnegative latent factor analysis(PAN)model with two-fold ideas:(1)adopting the principle of alternating-direction-method-of-multipliers to implement an efficient learning scheme for fast convergence and high computational efficiency;and(2)incorporating the proximal regularization into the learning scheme to suppress the optimization fluctuation for high representation learning accuracy to HDI data.Theoretical studies verify that PAN converges to a Karush-KuhnTucker(KKT)stationary point of its nonnegativity-constrained learning objective with its learning scheme.Experimental results on eight HDI matrices from real applications demonstrate that the proposed PAN model outperforms several state-of-the-art models in both estimation accuracy for missing data of an HDI matrix and computational efficiency.展开更多
Artificial Intelligence(AI)is one of the most promising and rapidly evolving fields in modern science.It is increasingly being applied to a wide range of domains,including medicine,where it holds enormous potential fo...Artificial Intelligence(AI)is one of the most promising and rapidly evolving fields in modern science.It is increasingly being applied to a wide range of domains,including medicine,where it holds enormous potential for improving patient care,reducing costs,and enhancing clinical decision-making.One area of AI that has shown great promise in the medical domain is data mining,which is the process of extracting useful information and knowledge from large data sets.展开更多
Dear editor,This letter focuses on the encoding-decoding-based recursive filtering problem for a class of fractional-order systems.For the purpose of protecting security of the wireless communication network,a dynamic...Dear editor,This letter focuses on the encoding-decoding-based recursive filtering problem for a class of fractional-order systems.For the purpose of protecting security of the wireless communication network,a dynamic-quantization-based encoding-decoding mechanism is introduced to encrypt the transmitted measurement.Specifically,the measurement outputs are first encoded by the encoder into codewords which are then transmitted over the wireless communication network.After received by the decoder,the codewords are decoded and then sent to the filter.In light of the mathematical properties of truncated Gaussian distribution,the variance of the encoding-decoding-induced error between the decoded measurement and the real measurement is derived.An upper bound on the filtering error covariance is first obtained based on the variance of the encoding-decoding-induced error.Then,the minimal upper bound is derived by choosing proper filter gain.Finally,the efficiency and superiority of the proposed algorithm are verified through a simulation example.展开更多
This paper will prove Riemann conjecture(RC): All zeros of <span style="white-space:nowrap;"><span style="white-space:nowrap;"><em>ξ</em></span>(<span style="...This paper will prove Riemann conjecture(RC): All zeros of <span style="white-space:nowrap;"><span style="white-space:nowrap;"><em>ξ</em></span>(<span style="white-space:nowrap;"><span style="white-space:nowrap;"><span style="white-space:nowrap;"><span style="white-space:nowrap;"><em>τ</em></span></span></span></span>)</span> lie on critical line. Denote <img src="Edit_189dc2b2-73ef-4036-9f06-ecf8a47fe58b.png" width="140" height="16" alt="" />, and <img src="Edit_a8ec55cb-e4c4-4156-ba23-ae01a31d1bc8.png" width="110" height="22" alt="" /> on critical line. We have found two mysteries in Riemann’s paper. <em>The first mystery</em> is the equivalence: <img src="Edit_3c075830-3c6c-4a23-9851-5b7d219e8000.png" width="140" height="21" alt="" /> is uniquely determined by its initial value <span style="white-space:nowrap;"><em>u</em> (<em>t</em>)</span>. <em>The second mystery</em> is Riemamm conjecture 2 (RC2): Using all zeros <span style="white-space:nowrap;"><em>t<sub>j</sub> </em></span>of <em>u</em> (<em>t</em>) can uniquely express <img src="Edit_b15d9c18-b55b-49e3-97a1-d2e03ccb6343.png" width="175" height="23" alt="" />. We find that the proof of RC is hidden in it. Our basic idea as follows. Consider functional equation <img src="Edit_f5295ff4-90b2-4465-851a-cad140b181c8.png" width="305" height="20" alt="" />. It is known that on critical line <img src="Edit_b45bff49-6d09-456b-9d1f-4259c66293d3.png" width="310" height="23" alt="" /> and <img src="Edit_4182ba79-0fcb-4f84-b7e7-c7574406596e.png" width="85" height="26" alt="" />, then we have the upper bound of growth <img src="Edit_d3d84d75-cc56-47b8-a9a7-ef8a9a5f07b1.png" width="250" height="33" alt="" /> To prove RC2 (or RC), by contradiction. If <span style="white-space:nowrap;"><em>ξ</em>(<em>τ</em>)</span> has conjugate complex roots <em>t</em>'<span style="white-space:nowrap;">±<em>i</em><span style="white-space:nowrap;"><em>β</em></span>'’</span>, <span style="white-space:nowrap;"><em>β</em>'>0</span>, <em>R</em><sup>2</sup>=t'<sup>2</sup>+<span style="white-space:nowrap;"><em>β</em>'<sup>2</sup></span>, by symmetry <span style="white-space:nowrap;"><em>ξ</em>(<em>τ</em>)=<span style="white-space:nowrap;"><em>ξ</em>(-<em>τ</em>)</span></span>, then -(<em>t</em>'<span style="white-space:nowrap;">±<em>i</em><em>β</em>''</span>) do yet. So <em>ξ</em> must contain four factors. Then <em>u</em>(<em>t</em>) contains a real factor <img src="Edit_ac03c1a5-0480-4efa-aac4-7788852a42a9.png" width="225" height="22" alt="" /> and <span style="white-space:nowrap;">ln|<em>u</em>(<em>t</em>)|</span> contains a term (the lower bound) <img src="Edit_6e94ad71-a310-4717-99ee-90384b0d89ba.png" width="230" height="19" alt="" /> which contradicts to the growth above. So <span style="white-space:nowrap;"><em>ξ</em></span> can not have the complex roots and <em>u</em>(<em>t</em>) does not have the factor <em>p</em>(<em>t</em>). Therefore both RC2 and RC are proved. We have seen that the two-dimensional problem is reduced to one-dimension and the one-dimensional <span style="white-space:nowrap;"><em>u</em>(<em>t</em>)</span> is reduced to its product expression. Perhaps this is close to the original idea of Riemann. Other results are also discussed by geometric analysis in the last section.展开更多
The purpose of this article is to extend the theory of circulant matrix to general ideal matrix, and to construct more general NTRU cryptosystem combined with the φ-cyclic code. To understand our construction, ...The purpose of this article is to extend the theory of circulant matrix to general ideal matrix, and to construct more general NTRU cryptosystem combined with the φ-cyclic code. To understand our construction, first we discuss a more general form of the ordinary cyclic code, namely φ-cyclic code, which firstly appeared in [1] and [2], thus we give a more generalized NTRUEncrypt by replacing finite field with real number field R.展开更多
Timely information updates are critical for real-time monitoring and control applications in the Internet of Things(IoT). In this paper, we consider a multi-antenna cellular IoT for state update where a base station(B...Timely information updates are critical for real-time monitoring and control applications in the Internet of Things(IoT). In this paper, we consider a multi-antenna cellular IoT for state update where a base station(BS) collects information from randomly distributed IoT nodes through time-varying channel.Specifically, multiple IoT nodes are allowed to transmit their state update simultaneously in a spatial multiplex manner. Inspired by age of information(AoI),we introduce a novel concept of age of transmission(AoT) for the sceneries in which BS cannot obtain the generation time of the packets waiting to be transmitted. The deadline-constrained AoT-optimal scheduling problem is formulated as a restless multi-armed bandit(RMAB) problem. Firstly, we prove the indexability of the scheduling problem and derive the closed-form of the Whittle index. Then, the interference graph and complementary graph are constructed to illustrate the interference between two nodes. The complete subgraphs are detected in the complementary graph to avoid inter-node interference. Next, an AoT-optimal scheduling strategy based on the Whittle index and complete subgraph detection is proposed.Finally, numerous simulations are conducted to verify the performance of the proposed strategy.展开更多
The value of the high-resolution data lies in the high-precision information discovery.The fine-detailed landform element extraction is thus the basis of high-fidelity application of the high-resolution digital elevat...The value of the high-resolution data lies in the high-precision information discovery.The fine-detailed landform element extraction is thus the basis of high-fidelity application of the high-resolution digital elevation models(DEMs).However,the results of landform element extraction generated by classical methods might be ungrounded on high-resolution DEMs.This paper presents our research on using the aspect to reinforce the applicability and robustness of the classical approaches in landform element extraction.First,according to the research of pattern recognition,we assume that aspect-enhanced landform representation is robust to rotation,scaling and affine variance.To testify the role of aspect,we respectively integrated the aspect into three classical approaches:mean curvaturebased fuzzy classification,elevation-based feature descriptor,and object-based segmentation.In the experiment,based on four types of high-resolution DEMs(1 m,2 m,4 m and 8 m),we compare each classical approaches and their corresponding aspect-enhanced approaches based on extracting the rims of two craters having different landforms,and the ridgelines and valleylines of a region covered by few vegetables and man-made buildings.In comparison to the results generated by curvature-based fuzzy classification,the aspect enhanced curvature-based fuzzy classification can effectively filter a number of noises outperforms the curvature-based one.Otherwise,the aspect-enhanced feature descriptor can detect more landform elements than the elevation-based feature descriptor.Moreover,the aspect-based segmentation can detect the main structure of landform,while the boundaries segmented by classical approaches are messing and meaningless.The systematic experiments on meter-level resolution DEMs proved that the aspect in topography could effectively to improve the classical method-system,including fuzzy-based classification,feature descriptors-based detection and object-based segmentation.The value of aspect is significantly great to be worthy of attentions in landform representation.展开更多
Recommender systems are rapidly transforming the digital world into intelligent information hubs.The valuable context information associated with the users’prior transactions has played a vital role in determining th...Recommender systems are rapidly transforming the digital world into intelligent information hubs.The valuable context information associated with the users’prior transactions has played a vital role in determining the user preferences for items or rating prediction.It has been a hot research topic in collaborative filtering-based recommender systems for the last two decades.This paper presents a novel Context Based Rating Prediction(CBRP)model with a unique similarity scoring estimation method.The proposed algorithm computes a context score for each candidate user to construct a similarity pool for the given subject user-item pair and intuitively choose the highly influential users to forecast the item ratings.The context scoring strategy has an inherent capability to incorporate multiple conditional factors to filter down the most relevant recommendations.Compared with traditional similarity estimation methods,CBRP makes it possible for the full use of neighboring collaborators’choice on various conditions.We conduct experiments on three publicly available datasets to evaluate our proposed method with random user-item pairs and got considerable improvement in prediction accuracy over the standard evaluation measures.Also,we evaluate prediction accuracy for every user-item pair in the system and the results show that our proposed framework has outperformed existing methods.展开更多
Causality is the science of cause and effect.It is through causality that explanations can be derived,theories can be formed,and new knowledge can be discovered.This paper presents a modern look into establishing caus...Causality is the science of cause and effect.It is through causality that explanations can be derived,theories can be formed,and new knowledge can be discovered.This paper presents a modern look into establishing causality within structural engineering systems.In this pursuit,this paper starts with a gentle introduction to causality.Then,this paper pivots to contrast commonly adopted methods for inferring causes and effects,i.e.,induction(empiricism)and deduc-tion(rationalism),and outlines how these methods continue to shape our structural engineering philosophy and,by extension,our domain.The bulk of this paper is dedicated to establishing an approach and criteria to tie principles of induction and deduction to derive causal laws(i.e.,mapping functions)through explainable artificial intelligence(XAI)capable of describing new knowledge pertaining to structural engineering phenomena.The proposed approach and criteria are then examined via a case study.展开更多
In this article, we introduce the discrete subgroup in ℝ<sup>n</sup> as preliminaries first. Then we provide some theories of cyclic lattices and ideal lattices. By regarding the cyclic lattices...In this article, we introduce the discrete subgroup in ℝ<sup>n</sup> as preliminaries first. Then we provide some theories of cyclic lattices and ideal lattices. By regarding the cyclic lattices and ideal lattices as the correspondences of finitely generated R-modules, we prove our main theorem, i.e. the correspondence between cyclic lattices in ℝ<sup>n</sup> and finitely generated R-modules is one-to-one. Finally, we give an explicit and countable upper bound for the smoothing parameter of cyclic lattices.展开更多
Given an undirected graph,the Maximum Clique Problem(MCP)is to find a largest complete subgraph of the graph.MCP is NP-hard and has found many practical applications.In this paper,we propose a parallel Branch-and-Boun...Given an undirected graph,the Maximum Clique Problem(MCP)is to find a largest complete subgraph of the graph.MCP is NP-hard and has found many practical applications.In this paper,we propose a parallel Branch-and-Bound(BnB)algorithm to tackle this NP-hard problem,which carries out multiple bounded searches in parallel.Each search has its upper bound and shares a lower bound with the rest of the searches.The potential benefit of the proposed approach is that an active search terminates as soon as the best lower bound found so far reaches or exceeds its upper bound.We describe the implementation of our highly scalable and efficient parallel MCP algorithm,called PBS,which is based on a state-of-the-art sequential MCP algorithm.The proposed algorithm PBS is evaluated on hard DIMACS and BHOSLIB instances.The results show that PBS achieves a near-linear speedup on most DIMACS instances and a superlinear speedup on most BHOSLIB instances.Finally,we give a detailed analysis that explains the good speedups achieved for the tested instances.展开更多
In the field of precision agriculture,diagnosing rice diseases from images remains challenging due to high error rates,multiple influencing factors,and unstable conditions.While machine learning and convolutional neur...In the field of precision agriculture,diagnosing rice diseases from images remains challenging due to high error rates,multiple influencing factors,and unstable conditions.While machine learning and convolutional neural networks have shown promising results in identifying rice diseases,they were limited in their ability to explain the relationships among disease features.In this study,we proposed an improved rice disease classification method that combines a convolutional neural network(CNN)with a bidirectional gated recurrent unit(BiGRU).Specifically,we introduced a residual mechanism into the Inception module,expanded the module's depth,and integrated an improved Convolutional Block Attention Module(CBAM).We trained and tested the improved CNN and BiGRU,concatenated the outputs of the CNN and BiGRU modules,and passed them to the classification layer for recognition.Our experiments demonstrate that this approach achieves an accuracy of 98.21%in identifying four types of rice diseases,providing a reliable method for rice disease recognition research.展开更多
High sensitivity and fast response are the figures of merit for benchmarking commercial sensors.Due to the advantages of intrinsic signal amplification,bionic ability,and mechanical flexibility,electrochemical transis...High sensitivity and fast response are the figures of merit for benchmarking commercial sensors.Due to the advantages of intrinsic signal amplification,bionic ability,and mechanical flexibility,electrochemical transistors(ECTs)have recently gained increasing popularity in constructing various sensors.In the current work,we have proposed a pulse-driven synaptic ECT for supersensitive and ultrafast biosensors.By pulsing the presynaptic input(drain bias,VD)and setting the modulation potential(gate bias)near transconductance intersection(VG,i),the synaptic ECT-based pH sensor can achieve a record high sensitivity up to 124 mV pH^(-1)(almost twice the Nernstian limit,59.2 mV pH^(-1))and an ultrafast response time as low as 8.75 ms(7169 times faster than the potentiostatic sensors,62.73 s).The proposed synaptic sensing strategy can effectively eliminate the transconductance fluctuation issue during the calibration process of the pH sensor and significantly reduce power consumption.Besides,the most sensitive working point at VG,i has been elaborately figured out through a series of detailed mathematical derivations,which is of great significance to provide higher sensitivity with quasi-nonfluctuating amplification capability.The proposed electrochemical synaptic transistor paired with an optimized operating gate offers a new paradigm for standardizing and commercializing high-performance biosensors.展开更多
Carbon nanotube(CNT)composite materials are very attractive for use in neural tissue engineering and biosensor coatings.CNT scaffolds are excellent mimics of extracellular matrix due to their hydrophilicity,viscosity,...Carbon nanotube(CNT)composite materials are very attractive for use in neural tissue engineering and biosensor coatings.CNT scaffolds are excellent mimics of extracellular matrix due to their hydrophilicity,viscosity,and biocompatibility.CNTs can also impart conductivity to other insulating materials improve mechanical stability guide neuronal cell behavior and trigger axon regeneration.The performance of chitosan(CS)/polyethylene glycol(PEG)composite scaffolds could be optimized by introducing multi-walled CNTs(MWCNTs).CS/PEG/CNT composite scaffolds with CNT content of 1%,3%,and 5%(1%=0.01 g/mL)were prepared by freeze-drying.Their physical and chemical properties and biocompatibility were evaluated.Scanning electron microscopy(SEM)showed that the composite scaffolds had a highly connected porous structure.Transmission electron microscope(TEM)and Raman spectroscopy proved that the CNTs were well dispersed in the CS/PEG matrix and combined with the CS/PEG nanofiber bundles.MWCNTs enhanced the elastic modulus of the scaffold.The porosity of the scaffolds ranged from 83%to 96%.They reached a stable water swelling state within 24 h,and swelling decreased with increasing MWCNT concentration.The electrical conductivity and cell adhesion rate of the scaffolds increased with increasing MWCNT content.Immunofluorescence showed that rat pheochromocytoma(PC12)cells grown in the scaffolds had characteristics similar to nerve cells.We measured changes in the expression of nerve cell markers by quantitative real-time polymerase chain reaction(qRT-PCR),and found that PC12 cells cultured in the scaffolds expressed growth-associated protein 43(GAP43),nerve growth factor receptor(NGFR),and class IIIβ-tubulin(TUBB3)proteins.Preliminary research showed that the prepared CS/PEG/CNT scaffold has good biocompatibility and can be further applied to neural tissue engineering research.展开更多
基金supported by the Guangxi University of Science and Technology,Liuzhou,China,sponsored by the Researchers Supporting Project(No.XiaoKeBo21Z27,The Construction of Electronic Information Team supported by Artificial Intelligence Theory and Three-dimensional Visual Technology,Yuesheng Zhao)supported by the 2022 Laboratory Fund Project of the Key Laboratory of Space-Based Integrated Information System(No.SpaceInfoNet20221120,Research on the Key Technologies of Intelligent Spatiotemporal Data Engine Based on Space-Based Information Network,Yuesheng Zhao)supported by the 2023 Guangxi University Young and Middle-Aged Teachers’Basic Scientific Research Ability Improvement Project(No.2023KY0352,Research on the Recognition of Psychological Abnormalities in College Students Based on the Fusion of Pulse and EEG Techniques,Yutong Luo).
文摘With the rapid advancement of wearable devices,Human Activities Recognition(HAR)based on these devices has emerged as a prominent research field.The objective of this study is to enhance the recognition performance of HAR by proposing an LSTM-1DCNN recognition algorithm that utilizes a single triaxial accelerometer.This algorithm comprises two branches:one branch consists of a Long and Short-Term Memory Network(LSTM),while the other parallel branch incorporates a one-dimensional Convolutional Neural Network(1DCNN).The parallel architecture of LSTM-1DCNN initially extracts spatial and temporal features from the accelerometer data separately,which are then concatenated and fed into a fully connected neural network for information fusion.In the LSTM-1DCNN architecture,the 1DCNN branch primarily focuses on extracting spatial features during convolution operations,whereas the LSTM branch mainly captures temporal features.Nine sets of accelerometer data from five publicly available HAR datasets are employed for training and evaluation purposes.The performance of the proposed LSTM-1DCNN model is compared with five other HAR algorithms including Decision Tree,Random Forest,Support Vector Machine,1DCNN,and LSTM on these five public datasets.Experimental results demonstrate that the F1-score achieved by the proposed LSTM-1DCNN ranges from 90.36%to 99.68%,with a mean value of 96.22%and standard deviation of 0.03 across all evaluated metrics on these five public datasets-outperforming other existing HAR algorithms significantly in terms of evaluation metrics used in this study.Finally the proposed LSTM-1DCNN is validated in real-world applications by collecting acceleration data of seven human activities for training and testing purposes.Subsequently,the trained HAR algorithm is deployed on Android phones to evaluate its performance.Experimental results demonstrate that the proposed LSTM-1DCNN algorithm achieves an impressive F1-score of 97.67%on our self-built dataset.In conclusion,the fusion of temporal and spatial information in the measured data contributes to the excellent HAR performance and robustness exhibited by the proposed 1DCNN-LSTM architecture.
基金supported in part by the National Natural Science Foundation of China (U21A2019, 61933007)the Hainan Province Science and Technology Special Fund (ZDYF2022SHFZ105)。
文摘Dear Editor, This letter focuses on the protocol-based non-fragile state estimation problem for a class of recurrent neural networks(RNNs). With the development of communication technology, the networked systems have received particular attentions. The networked system brings advantages such as easy to implement.
基金supported in part by the National Natural Science Foundation of China(61933007, U21A2019, 62273005, 62273088, 62303301)the Program of Shanghai Academic/Technology Research Leader of China (20XD1420100)+2 种基金the Hainan Province Science and Technology Special Fund of China(ZDYF2022SHFZ105)the Natural Science Foundation of Anhui Province of China (2108085MA07)the Alexander von Humboldt Foundation of Germany。
文摘This paper investigates the anomaly-resistant decentralized state estimation(SE) problem for a class of wide-area power systems which are divided into several non-overlapping areas connected through transmission lines. Two classes of measurements(i.e., local measurements and edge measurements) are obtained, respectively, from the individual area and the transmission lines. A decentralized state estimator, whose performance is resistant against measurement with anomalies, is designed based on the minimum error entropy with fiducial points(MEEF) criterion. Specifically, 1) An augmented model, which incorporates the local prediction and local measurement, is developed by resorting to the unscented transformation approach and the statistical linearization approach;2) Using the augmented model, an MEEF-based cost function is designed that reflects the local prediction errors of the state and the measurement;and 3) The local estimate is first obtained by minimizing the MEEF-based cost function through a fixed-point iteration and then updated by using the edge measuring information. Finally, simulation experiments with three scenarios are carried out on the IEEE 14-bus system to illustrate the validity of the proposed anomaly-resistant decentralized SE scheme.
基金This work was supported in part by the National Natural Science Foundation of China(U21A2019,61873058),Hainan Province Science and Technology Special Fund of China(ZDYF2022SHFZ105)the Alexander von Humboldt Foundation of Germany.
文摘Accurate detection of pipeline leakage is essential to maintain the safety of pipeline transportation.Recently,deep learning(DL)has emerged as a promising tool for pipeline leakage detection(PLD).However,most existing DL methods have difficulty in achieving good performance in identifying leakage types due to the complex time dynamics of pipeline data.On the other hand,the initial parameter selection in the detection model is generally random,which may lead to unstable recognition performance.For this reason,a hybrid DL framework referred to as parameter-optimized recurrent attention network(PRAN)is presented in this paper to improve the accuracy of PLD.First,a parameter-optimized long short-term memory(LSTM)network is introduced to extract effective and robust features,which exploits a particle swarm optimization(PSO)algorithm with cross-entropy fitness function to search for globally optimal parameters.With this framework,the learning representation capability of the model is improved and the convergence rate is accelerated.Moreover,an anomaly-attention mechanism(AM)is proposed to discover class discriminative information by weighting the hidden states,which contributes to amplifying the normalabnormal distinguishable discrepancy,further improving the accuracy of PLD.After that,the proposed PRAN not only implements the adaptive optimization of network parameters,but also enlarges the contribution of normal-abnormal discrepancy,thereby overcoming the drawbacks of instability and poor generalization.Finally,the experimental results demonstrate the effectiveness and superiority of the proposed PRAN for PLD.
基金financially supported by the National Natural Science Foundation of China(No.52174291)。
文摘In order to study the sintering characteristics of Ca-rich iron ore,chemical analysis,laser diffraction,scanning electron microscopy,XRD-Rietveld method,and micro-sintering were used to analyze the mineralogical properties and sintering pot tests were used to study the sintering behavior.In addition,a grey correlation mathematical model was used to calculate and compare the comprehensive sintering performance under different calcium-rich iron ore contents.The results demonstrate that the Ca-rich iron ore has coarse grain size and strong self-fusing characteristics with Ca element in the form of calcite(CaCO_(3)) and the liquid phase produced by the self-fusing of the calcium-rich iron ore is well crystallized.Its application with a 20wt%content in sintering improves sinter productivity,reduces fuel consumption,enhances reduction index,and improves gas permeability in blast furnace by 0.45 t/(m^(2)·h),6.11 kg/t,6.17%,and 65.39 kPa·℃,respectively.The Ca-rich iron ore sintering can improve the calorific value of sintering flue gas compared with magnetite sintering,which is conducive to recovering heat for secondary use.As the content of the Ca-rich iron ore increases,sinter agglomeration shifts from localized liquid-phase bonding to a combination of localized liquid-phase bonding and iron oxide crystal connection.Based on an examination of the greater weight value of productivity with grey correlation analysis,the Ca-rich iron ore is beneficial for the comprehensive index of sintering in the range of 0-20wt%content.Therefore,it may be used in sintering with magnetite concentrates as the major ore species.
基金supported by the Jiangsu Natural Science Foundation project(SBK2021045820)the Chongqing Natural Science Foundation general Project(cstc2021jcyj-msxmX0624)+1 种基金the Graduate Innovation Program of China University of Mining and Technology(2022WLKXJ002)the Postgraduate Research&Practice Innovation Program of Jiangsu Province(KYCX22_2600).
文摘The Ordos Basin is the largest continental multi-energy mineral basin in China,which is rich in coal,oil and gas,and uranium resources.The exploitation of mineral resources is closely related to reservoir water.The chemical properties of reservoir water are very important for reservoir evaluation and are significant indicators of the sealing of reservoir oil and gas resources.Therefore,the caprock of the Chang 6 reservoir in the Yanchang Formation was evaluated.The authors tested and analyzed the chemical characteristics of water samples selected from 30 wells in the Chang 6 reservoir of Ansai Oilfield in the Ordos Basin.The results show that the Chang 6 reservoir water in Ansai Oilfield is dominated by calcium-chloride water type with a sodium chloride coefficient of generally less than 0.5.The chloride magnesium coefficients are between 33.7 and 925.5,most of which are greater than 200.The desulfurization coefficients range from 0.21 to 13.4,with an average of 2.227.The carbonate balance coefficients are mainly concentrated below 0.01,with an average of 0.008.The calcium and magnesium coefficients are between 0.08 and 0.003,with an average of 0.01.Combined with the characteristics of the four-corner layout of the reservoir water,the above results show that the graphics are basically consistent.The study indicates that the Chang 6 reservoir in Ansai Oilfield in the Ordos Basin is a favorable block for oil and gas storage with good sealing properties,great preservation conditions of oil and gas,and high pore connectivity.
基金supported by the National Natural Science Foundation of China(62272078,U21A2019)the Hainan Province Science and Technology Special Fund of China(ZDYF2022SHFZ105)the CAAI-Huawei MindSpore Open Fund(CAAIXSJLJJ-2021-035A)。
文摘High-dimensional and incomplete(HDI)data subject to the nonnegativity constraints are commonly encountered in a big data-related application concerning the interactions among numerous nodes.A nonnegative latent factor analysis(NLFA)model can perform representation learning to HDI data efficiently.However,existing NLFA models suffer from either slow convergence rate or representation accuracy loss.To address this issue,this paper proposes a proximal alternating-directionmethod-of-multipliers-based nonnegative latent factor analysis(PAN)model with two-fold ideas:(1)adopting the principle of alternating-direction-method-of-multipliers to implement an efficient learning scheme for fast convergence and high computational efficiency;and(2)incorporating the proximal regularization into the learning scheme to suppress the optimization fluctuation for high representation learning accuracy to HDI data.Theoretical studies verify that PAN converges to a Karush-KuhnTucker(KKT)stationary point of its nonnegativity-constrained learning objective with its learning scheme.Experimental results on eight HDI matrices from real applications demonstrate that the proposed PAN model outperforms several state-of-the-art models in both estimation accuracy for missing data of an HDI matrix and computational efficiency.
基金from any funding agency in the public,commercial,or not-for-profit sect.We thank Dr.Richard Shane Palmer for editing the English text of a draft of this manuscript.
文摘Artificial Intelligence(AI)is one of the most promising and rapidly evolving fields in modern science.It is increasingly being applied to a wide range of domains,including medicine,where it holds enormous potential for improving patient care,reducing costs,and enhancing clinical decision-making.One area of AI that has shown great promise in the medical domain is data mining,which is the process of extracting useful information and knowledge from large data sets.
基金supported in part by the National Natural Science Foundation of China(U21A2019,61873058,61933007,62103095)the Hainan Province Science and Technology Special Fund(ZDYF2022SHFZ105)+1 种基金the Natural Science Foundation of Heilongjiang Province of China(LH2021F005)the Alexander von Humboldt Foundation of Germany。
文摘Dear editor,This letter focuses on the encoding-decoding-based recursive filtering problem for a class of fractional-order systems.For the purpose of protecting security of the wireless communication network,a dynamic-quantization-based encoding-decoding mechanism is introduced to encrypt the transmitted measurement.Specifically,the measurement outputs are first encoded by the encoder into codewords which are then transmitted over the wireless communication network.After received by the decoder,the codewords are decoded and then sent to the filter.In light of the mathematical properties of truncated Gaussian distribution,the variance of the encoding-decoding-induced error between the decoded measurement and the real measurement is derived.An upper bound on the filtering error covariance is first obtained based on the variance of the encoding-decoding-induced error.Then,the minimal upper bound is derived by choosing proper filter gain.Finally,the efficiency and superiority of the proposed algorithm are verified through a simulation example.
文摘This paper will prove Riemann conjecture(RC): All zeros of <span style="white-space:nowrap;"><span style="white-space:nowrap;"><em>ξ</em></span>(<span style="white-space:nowrap;"><span style="white-space:nowrap;"><span style="white-space:nowrap;"><span style="white-space:nowrap;"><em>τ</em></span></span></span></span>)</span> lie on critical line. Denote <img src="Edit_189dc2b2-73ef-4036-9f06-ecf8a47fe58b.png" width="140" height="16" alt="" />, and <img src="Edit_a8ec55cb-e4c4-4156-ba23-ae01a31d1bc8.png" width="110" height="22" alt="" /> on critical line. We have found two mysteries in Riemann’s paper. <em>The first mystery</em> is the equivalence: <img src="Edit_3c075830-3c6c-4a23-9851-5b7d219e8000.png" width="140" height="21" alt="" /> is uniquely determined by its initial value <span style="white-space:nowrap;"><em>u</em> (<em>t</em>)</span>. <em>The second mystery</em> is Riemamm conjecture 2 (RC2): Using all zeros <span style="white-space:nowrap;"><em>t<sub>j</sub> </em></span>of <em>u</em> (<em>t</em>) can uniquely express <img src="Edit_b15d9c18-b55b-49e3-97a1-d2e03ccb6343.png" width="175" height="23" alt="" />. We find that the proof of RC is hidden in it. Our basic idea as follows. Consider functional equation <img src="Edit_f5295ff4-90b2-4465-851a-cad140b181c8.png" width="305" height="20" alt="" />. It is known that on critical line <img src="Edit_b45bff49-6d09-456b-9d1f-4259c66293d3.png" width="310" height="23" alt="" /> and <img src="Edit_4182ba79-0fcb-4f84-b7e7-c7574406596e.png" width="85" height="26" alt="" />, then we have the upper bound of growth <img src="Edit_d3d84d75-cc56-47b8-a9a7-ef8a9a5f07b1.png" width="250" height="33" alt="" /> To prove RC2 (or RC), by contradiction. If <span style="white-space:nowrap;"><em>ξ</em>(<em>τ</em>)</span> has conjugate complex roots <em>t</em>'<span style="white-space:nowrap;">±<em>i</em><span style="white-space:nowrap;"><em>β</em></span>'’</span>, <span style="white-space:nowrap;"><em>β</em>'>0</span>, <em>R</em><sup>2</sup>=t'<sup>2</sup>+<span style="white-space:nowrap;"><em>β</em>'<sup>2</sup></span>, by symmetry <span style="white-space:nowrap;"><em>ξ</em>(<em>τ</em>)=<span style="white-space:nowrap;"><em>ξ</em>(-<em>τ</em>)</span></span>, then -(<em>t</em>'<span style="white-space:nowrap;">±<em>i</em><em>β</em>''</span>) do yet. So <em>ξ</em> must contain four factors. Then <em>u</em>(<em>t</em>) contains a real factor <img src="Edit_ac03c1a5-0480-4efa-aac4-7788852a42a9.png" width="225" height="22" alt="" /> and <span style="white-space:nowrap;">ln|<em>u</em>(<em>t</em>)|</span> contains a term (the lower bound) <img src="Edit_6e94ad71-a310-4717-99ee-90384b0d89ba.png" width="230" height="19" alt="" /> which contradicts to the growth above. So <span style="white-space:nowrap;"><em>ξ</em></span> can not have the complex roots and <em>u</em>(<em>t</em>) does not have the factor <em>p</em>(<em>t</em>). Therefore both RC2 and RC are proved. We have seen that the two-dimensional problem is reduced to one-dimension and the one-dimensional <span style="white-space:nowrap;"><em>u</em>(<em>t</em>)</span> is reduced to its product expression. Perhaps this is close to the original idea of Riemann. Other results are also discussed by geometric analysis in the last section.
文摘The purpose of this article is to extend the theory of circulant matrix to general ideal matrix, and to construct more general NTRU cryptosystem combined with the φ-cyclic code. To understand our construction, first we discuss a more general form of the ordinary cyclic code, namely φ-cyclic code, which firstly appeared in [1] and [2], thus we give a more generalized NTRUEncrypt by replacing finite field with real number field R.
基金supported by the Fundamental Research Funds for the Central Universities (2020ZDPYMS26)the National Natural Science Foundation of China (62071472, 51734009)+3 种基金the Natural Science Foundation o Jiangsu Province (BK20210489, BK20200650)China Postdoctoral Science Foundation (2019M660133)the Future Network Scientific Research Fund Project (FNSRFP-2021-YB-12)the Program for “Industrial IoT and Emergency Collaboration” Innovative Research Team in CUMT (No.2020ZY002)。
文摘Timely information updates are critical for real-time monitoring and control applications in the Internet of Things(IoT). In this paper, we consider a multi-antenna cellular IoT for state update where a base station(BS) collects information from randomly distributed IoT nodes through time-varying channel.Specifically, multiple IoT nodes are allowed to transmit their state update simultaneously in a spatial multiplex manner. Inspired by age of information(AoI),we introduce a novel concept of age of transmission(AoT) for the sceneries in which BS cannot obtain the generation time of the packets waiting to be transmitted. The deadline-constrained AoT-optimal scheduling problem is formulated as a restless multi-armed bandit(RMAB) problem. Firstly, we prove the indexability of the scheduling problem and derive the closed-form of the Whittle index. Then, the interference graph and complementary graph are constructed to illustrate the interference between two nodes. The complete subgraphs are detected in the complementary graph to avoid inter-node interference. Next, an AoT-optimal scheduling strategy based on the Whittle index and complete subgraph detection is proposed.Finally, numerous simulations are conducted to verify the performance of the proposed strategy.
基金Under the auspices of Priority Academic Program Development of Jiangsu Higher Education Institutions(No.140119001)Science&Technology Department of Liaoning Province(No.20180550831)。
文摘The value of the high-resolution data lies in the high-precision information discovery.The fine-detailed landform element extraction is thus the basis of high-fidelity application of the high-resolution digital elevation models(DEMs).However,the results of landform element extraction generated by classical methods might be ungrounded on high-resolution DEMs.This paper presents our research on using the aspect to reinforce the applicability and robustness of the classical approaches in landform element extraction.First,according to the research of pattern recognition,we assume that aspect-enhanced landform representation is robust to rotation,scaling and affine variance.To testify the role of aspect,we respectively integrated the aspect into three classical approaches:mean curvaturebased fuzzy classification,elevation-based feature descriptor,and object-based segmentation.In the experiment,based on four types of high-resolution DEMs(1 m,2 m,4 m and 8 m),we compare each classical approaches and their corresponding aspect-enhanced approaches based on extracting the rims of two craters having different landforms,and the ridgelines and valleylines of a region covered by few vegetables and man-made buildings.In comparison to the results generated by curvature-based fuzzy classification,the aspect enhanced curvature-based fuzzy classification can effectively filter a number of noises outperforms the curvature-based one.Otherwise,the aspect-enhanced feature descriptor can detect more landform elements than the elevation-based feature descriptor.Moreover,the aspect-based segmentation can detect the main structure of landform,while the boundaries segmented by classical approaches are messing and meaningless.The systematic experiments on meter-level resolution DEMs proved that the aspect in topography could effectively to improve the classical method-system,including fuzzy-based classification,feature descriptors-based detection and object-based segmentation.The value of aspect is significantly great to be worthy of attentions in landform representation.
基金This work is supported by National Natural Science Foundation of China(No.61672133)Sichuan Science and Technology Program(No.2019YFG0535)the 111 Project(No.B17008).
文摘Recommender systems are rapidly transforming the digital world into intelligent information hubs.The valuable context information associated with the users’prior transactions has played a vital role in determining the user preferences for items or rating prediction.It has been a hot research topic in collaborative filtering-based recommender systems for the last two decades.This paper presents a novel Context Based Rating Prediction(CBRP)model with a unique similarity scoring estimation method.The proposed algorithm computes a context score for each candidate user to construct a similarity pool for the given subject user-item pair and intuitively choose the highly influential users to forecast the item ratings.The context scoring strategy has an inherent capability to incorporate multiple conditional factors to filter down the most relevant recommendations.Compared with traditional similarity estimation methods,CBRP makes it possible for the full use of neighboring collaborators’choice on various conditions.We conduct experiments on three publicly available datasets to evaluate our proposed method with random user-item pairs and got considerable improvement in prediction accuracy over the standard evaluation measures.Also,we evaluate prediction accuracy for every user-item pair in the system and the results show that our proposed framework has outperformed existing methods.
文摘Causality is the science of cause and effect.It is through causality that explanations can be derived,theories can be formed,and new knowledge can be discovered.This paper presents a modern look into establishing causality within structural engineering systems.In this pursuit,this paper starts with a gentle introduction to causality.Then,this paper pivots to contrast commonly adopted methods for inferring causes and effects,i.e.,induction(empiricism)and deduc-tion(rationalism),and outlines how these methods continue to shape our structural engineering philosophy and,by extension,our domain.The bulk of this paper is dedicated to establishing an approach and criteria to tie principles of induction and deduction to derive causal laws(i.e.,mapping functions)through explainable artificial intelligence(XAI)capable of describing new knowledge pertaining to structural engineering phenomena.The proposed approach and criteria are then examined via a case study.
文摘In this article, we introduce the discrete subgroup in ℝ<sup>n</sup> as preliminaries first. Then we provide some theories of cyclic lattices and ideal lattices. By regarding the cyclic lattices and ideal lattices as the correspondences of finitely generated R-modules, we prove our main theorem, i.e. the correspondence between cyclic lattices in ℝ<sup>n</sup> and finitely generated R-modules is one-to-one. Finally, we give an explicit and countable upper bound for the smoothing parameter of cyclic lattices.
基金supported by the National Natural Science Foundation of China under Grant No.62162066the Open Funding of Engineering Research Center of Cyberspace of Ministry of Education of China under Grant No.WLKJAQ202011010+1 种基金the Education Department Funding of Yunnan Province of China under Grant No.2021J0006the Spanish AEI project PID2019-111544GB-C2.
文摘Given an undirected graph,the Maximum Clique Problem(MCP)is to find a largest complete subgraph of the graph.MCP is NP-hard and has found many practical applications.In this paper,we propose a parallel Branch-and-Bound(BnB)algorithm to tackle this NP-hard problem,which carries out multiple bounded searches in parallel.Each search has its upper bound and shares a lower bound with the rest of the searches.The potential benefit of the proposed approach is that an active search terminates as soon as the best lower bound found so far reaches or exceeds its upper bound.We describe the implementation of our highly scalable and efficient parallel MCP algorithm,called PBS,which is based on a state-of-the-art sequential MCP algorithm.The proposed algorithm PBS is evaluated on hard DIMACS and BHOSLIB instances.The results show that PBS achieves a near-linear speedup on most DIMACS instances and a superlinear speedup on most BHOSLIB instances.Finally,we give a detailed analysis that explains the good speedups achieved for the tested instances.
基金the National Natural Science Foundation of China under Grants U21A2019,61873058 and 61933007the Hainan Province Science and Technology Special Fund under Grant ZDYF2022-SHFZ105+1 种基金Heilongjiang Natural Science Foundation of China under Grant LH2020F042the Scientific Research Starting Foundation for Post Doctor from Heilongjiang under Grant LBH-Q17134.
文摘In the field of precision agriculture,diagnosing rice diseases from images remains challenging due to high error rates,multiple influencing factors,and unstable conditions.While machine learning and convolutional neural networks have shown promising results in identifying rice diseases,they were limited in their ability to explain the relationships among disease features.In this study,we proposed an improved rice disease classification method that combines a convolutional neural network(CNN)with a bidirectional gated recurrent unit(BiGRU).Specifically,we introduced a residual mechanism into the Inception module,expanded the module's depth,and integrated an improved Convolutional Block Attention Module(CBAM).We trained and tested the improved CNN and BiGRU,concatenated the outputs of the CNN and BiGRU modules,and passed them to the classification layer for recognition.Our experiments demonstrate that this approach achieves an accuracy of 98.21%in identifying four types of rice diseases,providing a reliable method for rice disease recognition research.
基金National Natural Science Foundation of China,Grant/Award Numbers:61703298,51975400,52073031,52175542Natural Science Foundation of Shanxi Province,Grant/Award Number:20210302123136+3 种基金China Postdoctoral Science Foundation,Grant/Award Number:2020M673646National Key Research and Development Program of China,Grant/Award Numbers:2021YFB3200304,2016YFA0202703Beijing Nova Program,Grant/Award Number:Z211100002121148Patent Transformation Special Program of Shanxi Province,Grant/Award Number:202304012。
文摘High sensitivity and fast response are the figures of merit for benchmarking commercial sensors.Due to the advantages of intrinsic signal amplification,bionic ability,and mechanical flexibility,electrochemical transistors(ECTs)have recently gained increasing popularity in constructing various sensors.In the current work,we have proposed a pulse-driven synaptic ECT for supersensitive and ultrafast biosensors.By pulsing the presynaptic input(drain bias,VD)and setting the modulation potential(gate bias)near transconductance intersection(VG,i),the synaptic ECT-based pH sensor can achieve a record high sensitivity up to 124 mV pH^(-1)(almost twice the Nernstian limit,59.2 mV pH^(-1))and an ultrafast response time as low as 8.75 ms(7169 times faster than the potentiostatic sensors,62.73 s).The proposed synaptic sensing strategy can effectively eliminate the transconductance fluctuation issue during the calibration process of the pH sensor and significantly reduce power consumption.Besides,the most sensitive working point at VG,i has been elaborately figured out through a series of detailed mathematical derivations,which is of great significance to provide higher sensitivity with quasi-nonfluctuating amplification capability.The proposed electrochemical synaptic transistor paired with an optimized operating gate offers a new paradigm for standardizing and commercializing high-performance biosensors.
基金This study was supported by the National Natural Science Foundation of China(Nos.51975400 and 62031022)the Shanxi Provincial Key Medical Scientific Research Project(No.2020XM06),China.
文摘Carbon nanotube(CNT)composite materials are very attractive for use in neural tissue engineering and biosensor coatings.CNT scaffolds are excellent mimics of extracellular matrix due to their hydrophilicity,viscosity,and biocompatibility.CNTs can also impart conductivity to other insulating materials improve mechanical stability guide neuronal cell behavior and trigger axon regeneration.The performance of chitosan(CS)/polyethylene glycol(PEG)composite scaffolds could be optimized by introducing multi-walled CNTs(MWCNTs).CS/PEG/CNT composite scaffolds with CNT content of 1%,3%,and 5%(1%=0.01 g/mL)were prepared by freeze-drying.Their physical and chemical properties and biocompatibility were evaluated.Scanning electron microscopy(SEM)showed that the composite scaffolds had a highly connected porous structure.Transmission electron microscope(TEM)and Raman spectroscopy proved that the CNTs were well dispersed in the CS/PEG matrix and combined with the CS/PEG nanofiber bundles.MWCNTs enhanced the elastic modulus of the scaffold.The porosity of the scaffolds ranged from 83%to 96%.They reached a stable water swelling state within 24 h,and swelling decreased with increasing MWCNT concentration.The electrical conductivity and cell adhesion rate of the scaffolds increased with increasing MWCNT content.Immunofluorescence showed that rat pheochromocytoma(PC12)cells grown in the scaffolds had characteristics similar to nerve cells.We measured changes in the expression of nerve cell markers by quantitative real-time polymerase chain reaction(qRT-PCR),and found that PC12 cells cultured in the scaffolds expressed growth-associated protein 43(GAP43),nerve growth factor receptor(NGFR),and class IIIβ-tubulin(TUBB3)proteins.Preliminary research showed that the prepared CS/PEG/CNT scaffold has good biocompatibility and can be further applied to neural tissue engineering research.