Flash Crowd attacks are a form of Distributed Denial of Service(DDoS)attack that is becoming increasingly difficult to detect due to its ability to imitate normal user behavior in Cloud Computing(CC).Botnets are often...Flash Crowd attacks are a form of Distributed Denial of Service(DDoS)attack that is becoming increasingly difficult to detect due to its ability to imitate normal user behavior in Cloud Computing(CC).Botnets are often used by attackers to perform a wide range of DDoS attacks.With advancements in technology,bots are now able to simulate DDoS attacks as flash crowd events,making them difficult to detect.When it comes to application layer DDoS attacks,the Flash Crowd attack that occurs during a Flash Event is viewed as the most intricate issue.This is mainly because it can imitate typical user behavior,leading to a substantial influx of requests that can overwhelm the server by consuming either its network bandwidth or resources.Therefore,identifying these types of attacks on web servers has become crucial,particularly in the CC.In this article,an efficient intrusion detection method is proposed based on White Shark Optimizer and ensemble classifier(Convolutional Neural Network(CNN)and LighGBM).Experiments were conducted using a CICIDS 2017 dataset to evaluate the performance of the proposed method in real-life situations.The proposed IDS achieved superior results,with 95.84%accuracy,96.15%precision,95.54%recall,and 95.84%F1 measure.Flash crowd attacks are challenging to detect,but the proposed IDS has proven its effectiveness in identifying such attacks in CC and holds potential for future improvement.展开更多
The challenge faced by the visually impaired persons in their day-today lives is to interpret text from documents.In this context,to help these people,the objective of this work is to develop an efficient text recogni...The challenge faced by the visually impaired persons in their day-today lives is to interpret text from documents.In this context,to help these people,the objective of this work is to develop an efficient text recognition system that allows the isolation,the extraction,and the recognition of text in the case of documents having a textured background,a degraded aspect of colors,and of poor quality,and to synthesize it into speech.This system basically consists of three algorithms:a text localization and detection algorithm based on mathematical morphology method(MMM);a text extraction algorithm based on the gamma correction method(GCM);and an optical character recognition(OCR)algorithm for text recognition.A detailed complexity study of the different blocks of this text recognition system has been realized.Following this study,an acceleration of the GCM algorithm(AGCM)is proposed.The AGCM algorithm has reduced the complexity in the text recognition system by 70%and kept the same quality of text recognition as that of the original method.To assist visually impaired persons,a graphical interface of the entire text recognition chain has been developed,allowing the capture of images from a camera,rapid and intuitive visualization of the recognized text from this image,and text-to-speech synthesis.Our text recognition system provides an improvement of 6.8%for the recognition rate and 7.6%for the F-measure relative to GCM and AGCM algorithms.展开更多
Localisation of machines in harsh Industrial Internet of Things(IIoT)environment is necessary for various applications.Therefore,a novel localisation algorithm is proposed for noisy range measurements in IIoT networks...Localisation of machines in harsh Industrial Internet of Things(IIoT)environment is necessary for various applications.Therefore,a novel localisation algorithm is proposed for noisy range measurements in IIoT networks.The position of an unknown machine device in the network is estimated using the relative distances between blind machines(BMs)and anchor machines(AMs).Moreover,a more practical and challenging scenario with the erroneous position of AM is considered,which brings additional uncertainty to the final position estimation.Therefore,the AMs selection algorithm for the localisation of BMs in the IIoT network is introduced.Only those AMs will participate in the localisation process,which increases the accuracy of the final location estimate.Then,the closed‐form expression of the proposed greedy successive anchorization process is derived,which prevents possible local convergence,reduces computation,and achieves Cramér‐Rao lower bound accuracy for white Gaussian measurement noise.The results are compared with the state‐of‐the‐art and verified through numerous simulations.展开更多
Exploration for primary gold in tropical settings is often problematic because of deep weathering and the development of a thick soil cover. In this paper we present the results of both chargeability and resistivity s...Exploration for primary gold in tropical settings is often problematic because of deep weathering and the development of a thick soil cover. In this paper we present the results of both chargeability and resistivity surveys carried out over the Belikombone hill gold prospect (14?00' - 14?25'E, 5?25' - 6?00'N) in the Betare Oya area (eastern Cameroon), where previous soil sampling had identified gold anomalies. The geophysical data were obtained using Syscal Junior 48 resistivity meter and the Schlumberger configuration array for both the vertical electrical soundings (VES) and horizontal profiling. These data were further built into a GIS framework and the continuity of favourable gold-bearing structures at depth modeled using WINSEV, RED2INV and SURFER extensions softwares. IP (Induced Polarization)-chargeability and resistivity data combined, have identified irregular anomalous zones trending NE-SW. This trend is consistent with the attitude of most auriferous quartz veins exposed in artisanal pits and parallel to the regional shear zone system and foliations. The high resistivity anomalies correspond to quartz veins while the relatively high IP anomalies correspond to low sulphide ± gold concentrations in the quartz veins. Modeling IP-chargeability and resistivity data prepared as contours and 3D maps, culminated to the development of an inferred, irregular and discontinuous mineralized body at depths of up to 95 m. The size and shape of this mineralized body can only later be tested by drilling to ascertain the resource.展开更多
Three monogenetic cones in the Baossi–Warack area, Ngaoundéré, Adamawa Plateau forming part of the Cameroon Volcanic Line(CVL) are documented in this study. Basaltic lavas(<1 km^3) scattered around these...Three monogenetic cones in the Baossi–Warack area, Ngaoundéré, Adamawa Plateau forming part of the Cameroon Volcanic Line(CVL) are documented in this study. Basaltic lavas(<1 km^3) scattered around these vents and restricted volcaniclastic deposits were emplaced by Hawaiian and mild strombolian style eruptions. The lavas are porphyritic, mainly composed of olivine(chrysolite) and clinopyroxene(diopside and augite) phenocrysts and plagioclase(andesine) microphenocrysts. Accessory minerals include titano-magnetite and titano-hematite, nepheline,apatite and amphibole xenocrysts. Sanidine occurs in some samples and sodi-potassic albite in others. Some olivines and clinopyroxenes exhibit resorbed margins and thin reaction rims while plagioclase displays oscillatory zoning, and sieved textures as a result of magma mixing. Whole-rock geochemistry data indicates that the lavas are silica-undersaturated, composed of basanites and basalts, showing little compositional variations(SiO_2: 39.20 wt.%–48.01 wt.%,MgO: 5.29 wt.%–9.70 wt.%). Trace elements patterns of these lavas suggest they are enriched in LILE including Pb,probably due to crustal contamination. REE patterns suggest cogenetic magmas below Baossi 1 and Baossi 2 volcanoes,and distinct sources below Warack volcano and nearby lavas.The lavas studied show affinity to high-μ(HIMU), enriched type Ⅰ(EM1) and Oceanic Island Basalt(OIB)-like mantle signatures and thus indicate a heterogeneous mantle source underneath the vents as noted at other monogenetic and polygenetic volcanoes along the CVL. Primary melts derived from low degrees of partial melting(0.5%–2%) and encountered low rates of fractionation, and crustal contamination coupled with magma mixing. These melts evolved independently through structural weaknesses in the basement.展开更多
Stream sediment geochemistry remains a versatile tool in exploration especially in regions where knowledge of the primary mineralization is lacking and the exploration activities are still at reconnaissance stage. In ...Stream sediment geochemistry remains a versatile tool in exploration especially in regions where knowledge of the primary mineralization is lacking and the exploration activities are still at reconnaissance stage. In this study, we investigate the concentrations of gold and associated elements in stream sediment samples from the Vaimba-Lidi drainage system in northern Cameroon;a relatively remote area where alluvial gold is worked locally, and exploration activities are at early stage. The main river and its principal first and second order tributaries were sampled, panned for gold grain recovery and the 100 μm size fraction analyzed for Au by fire assay with Ni finish. A suite of other elements were analyzed for by inductively coupled plasma mass spectrometry (ICP-MS). Gold grades estimated by the panning and weighing technique rarely exceed1 g/t while the Au concentrations from chemical analysis range from 3.0 to 354.0 ppm. The spatial distribution of gold and all the other elements are presented as point symbol maps and the data analyzed using multivariate statistics. From the principal component analysis (PCA), the As-Mo-W-Ag as well as the Au-Zn factors point to the presence of primary hydrothermal gold-sulphide mineralization in the area and this can be further investigated. These results highlight the importance of multielement analysis and multivariate statistical interpretation of sediment geochemical data in inferring the nature of the underlying primary mineralization in any region.展开更多
Stream sediments are widely employed in reconnaissance exploration for gold especially in areas where outcrops are scarce and the overburden thick such as in the eastern Cameroon goldfields. In this study, 337 stream ...Stream sediments are widely employed in reconnaissance exploration for gold especially in areas where outcrops are scarce and the overburden thick such as in the eastern Cameroon goldfields. In this study, 337 stream sediment samples were collected from the Lom river drainage basin. The study aims at identifying the main geological processes affecting the geochemical data from the sediments by considering the multi-elements relationships and spatial features of single elements. The samples were collected in duplicate. One set was panned, gold grains picked and weighed while the second set was wet sieved and the ≤100 microns size fraction retained. This fraction was eventually analyzed for gold by fire assay and a suite of elements by inductively coupled plasma mass spectrometry (ICP-MS). Single element maps were constructed using ArcGIS and the relationship between elements measured using Pearson correlation and principal component analysis (PCA). Gold concentrations in the samples are erratic, most below the detection limit and attain a high of 450 ppm. Five factors are derived from the PCA including single element factors for As and Au reflecting bedrock-hosted mineralization. The Cu-Zn-Y-Nb-Pb factor suggests sulphide mineralization perhaps related to felsic intrusions while the Sr-Ba-La-Ce-Zr factor is linked to lithologic control. These results demonstrate the usefulness of multi-element analysis and data interpretation using GIS tools in the exploration efforts for gold worldwide.展开更多
Earth observation data are typically compressed using general-purpose single-threaded compression algorithms that operate at a fraction of the bandwidth of modern storage and processing systems.We present evidence tha...Earth observation data are typically compressed using general-purpose single-threaded compression algorithms that operate at a fraction of the bandwidth of modern storage and processing systems.We present evidence that recently developed multi-threaded compression codecs offer substantial benefits over widely used single-threaded codecs in terms of compression efficiency when applied to a selection of moderate resolution imaging spectroradiometer(MODIS)datasets stored in the HDF5 format.Compression codecs from the LZ77 and Rice families are shown to vary in efficacy when applied to different MODIS data products,highlighting the need for compression strategies to be tailored to different classes of data.We also introduce LPC-Rice,a new multi-threaded codec,that performs particularly well when applied to time-series data.展开更多
This article is aimed at providing a detailed description of the Flood Validation Exercise organised by the Independent Service Validation Group of the Global Monitoring for Environment and Security(GMES)RESPOND proje...This article is aimed at providing a detailed description of the Flood Validation Exercise organised by the Independent Service Validation Group of the Global Monitoring for Environment and Security(GMES)RESPOND project.The aims of the validation exercise were:(1)providing a practical example of validation procedures in the frame of the GMES Emergency Response services;(2)executing a full-scale validation exercise able to cope with the requirements of an emergency service;and(3)better understanding the performances and limitations of Earth observation services for Flood Damage Mapping.This validation exercise is a first step of the main task to define the whole validation process for GMES services.When this is achieved,there will be knowledge concerning how well services meet the service specifications derived from the user needs.The present exercise has the purpose of gathering this knowledge.The output of this validation exercise can be used to characterise and qualify the performance and timeliness of Crisis and Damage Mapping Services.This paper summarises the methodology for the flood exercise validation and the results of product validation and inter-comparison.展开更多
Though studies showed the potential of high-resolution optical sensors for crop yield prediction,several factors have limited their wider application.The main factors are obstruction of cloud,identification of phenolo...Though studies showed the potential of high-resolution optical sensors for crop yield prediction,several factors have limited their wider application.The main factors are obstruction of cloud,identification of phenology,demand for high computing infrastructure and the complexity of statistical methods.In this research,we created a novel approach by combining four methods.First,we implemented the cloud restoration algorithm called gapfill to restore missed Normalized Difference Vegetation Index(NDVI)values derived from Sentinel-2 sensor(S2)due to cloud obstruction.Second,we created square tiles as a solution for high computing infrastructure demand due to the use of high-resolution sensor.Third,we implemented gapfill following critical crop phenology stage.Fourth,observations from restored images combined with original(from cloud-free images)values and applied for winter wheat prediction.We applied seven base machine learning as well as two groups of super learning ensembles.The study successfully applied gapfill on high-resolution image to get good quality estimates for cloudy pixels.Consequently,yield prediction accuracy increased due to the incorporation of restored values in the regression process.Base models such as Generalized Linear Regression(GLM)and Random Forest(RF)showed improved capacity compared to other base and ensemble models.The two models revealed RMSE of 0.001 t/ha and 0.136 t/ha on the holdout group.The twomodels also revealed consistent and better performance using scatter plot analysis across three datasets.The approach developed is useful to predict wheat yield at field scale,which is a rarely available but vital in many developmental projects,using optical sensors.展开更多
基金The authors gratefully acknowledge the approval and the support of this research study by grant no.SCIA-2022-11-1551 from the Deanship of Scientific Research at Northern Border University,Arar,K.S.A.
文摘Flash Crowd attacks are a form of Distributed Denial of Service(DDoS)attack that is becoming increasingly difficult to detect due to its ability to imitate normal user behavior in Cloud Computing(CC).Botnets are often used by attackers to perform a wide range of DDoS attacks.With advancements in technology,bots are now able to simulate DDoS attacks as flash crowd events,making them difficult to detect.When it comes to application layer DDoS attacks,the Flash Crowd attack that occurs during a Flash Event is viewed as the most intricate issue.This is mainly because it can imitate typical user behavior,leading to a substantial influx of requests that can overwhelm the server by consuming either its network bandwidth or resources.Therefore,identifying these types of attacks on web servers has become crucial,particularly in the CC.In this article,an efficient intrusion detection method is proposed based on White Shark Optimizer and ensemble classifier(Convolutional Neural Network(CNN)and LighGBM).Experiments were conducted using a CICIDS 2017 dataset to evaluate the performance of the proposed method in real-life situations.The proposed IDS achieved superior results,with 95.84%accuracy,96.15%precision,95.54%recall,and 95.84%F1 measure.Flash crowd attacks are challenging to detect,but the proposed IDS has proven its effectiveness in identifying such attacks in CC and holds potential for future improvement.
基金This work was funded by the Deanship of Scientific Research at Jouf University under Grant Number(DSR2022-RG-0114).
文摘The challenge faced by the visually impaired persons in their day-today lives is to interpret text from documents.In this context,to help these people,the objective of this work is to develop an efficient text recognition system that allows the isolation,the extraction,and the recognition of text in the case of documents having a textured background,a degraded aspect of colors,and of poor quality,and to synthesize it into speech.This system basically consists of three algorithms:a text localization and detection algorithm based on mathematical morphology method(MMM);a text extraction algorithm based on the gamma correction method(GCM);and an optical character recognition(OCR)algorithm for text recognition.A detailed complexity study of the different blocks of this text recognition system has been realized.Following this study,an acceleration of the GCM algorithm(AGCM)is proposed.The AGCM algorithm has reduced the complexity in the text recognition system by 70%and kept the same quality of text recognition as that of the original method.To assist visually impaired persons,a graphical interface of the entire text recognition chain has been developed,allowing the capture of images from a camera,rapid and intuitive visualization of the recognized text from this image,and text-to-speech synthesis.Our text recognition system provides an improvement of 6.8%for the recognition rate and 7.6%for the F-measure relative to GCM and AGCM algorithms.
文摘Localisation of machines in harsh Industrial Internet of Things(IIoT)environment is necessary for various applications.Therefore,a novel localisation algorithm is proposed for noisy range measurements in IIoT networks.The position of an unknown machine device in the network is estimated using the relative distances between blind machines(BMs)and anchor machines(AMs).Moreover,a more practical and challenging scenario with the erroneous position of AM is considered,which brings additional uncertainty to the final position estimation.Therefore,the AMs selection algorithm for the localisation of BMs in the IIoT network is introduced.Only those AMs will participate in the localisation process,which increases the accuracy of the final location estimate.Then,the closed‐form expression of the proposed greedy successive anchorization process is derived,which prevents possible local convergence,reduces computation,and achieves Cramér‐Rao lower bound accuracy for white Gaussian measurement noise.The results are compared with the state‐of‐the‐art and verified through numerous simulations.
文摘Exploration for primary gold in tropical settings is often problematic because of deep weathering and the development of a thick soil cover. In this paper we present the results of both chargeability and resistivity surveys carried out over the Belikombone hill gold prospect (14?00' - 14?25'E, 5?25' - 6?00'N) in the Betare Oya area (eastern Cameroon), where previous soil sampling had identified gold anomalies. The geophysical data were obtained using Syscal Junior 48 resistivity meter and the Schlumberger configuration array for both the vertical electrical soundings (VES) and horizontal profiling. These data were further built into a GIS framework and the continuity of favourable gold-bearing structures at depth modeled using WINSEV, RED2INV and SURFER extensions softwares. IP (Induced Polarization)-chargeability and resistivity data combined, have identified irregular anomalous zones trending NE-SW. This trend is consistent with the attitude of most auriferous quartz veins exposed in artisanal pits and parallel to the regional shear zone system and foliations. The high resistivity anomalies correspond to quartz veins while the relatively high IP anomalies correspond to low sulphide ± gold concentrations in the quartz veins. Modeling IP-chargeability and resistivity data prepared as contours and 3D maps, culminated to the development of an inferred, irregular and discontinuous mineralized body at depths of up to 95 m. The size and shape of this mineralized body can only later be tested by drilling to ascertain the resource.
基金financially supported by the Ministry of Higher Education, Cameroon, through the Special Allocation for the Modernization of Research (SAMR) granted to the first author
文摘Three monogenetic cones in the Baossi–Warack area, Ngaoundéré, Adamawa Plateau forming part of the Cameroon Volcanic Line(CVL) are documented in this study. Basaltic lavas(<1 km^3) scattered around these vents and restricted volcaniclastic deposits were emplaced by Hawaiian and mild strombolian style eruptions. The lavas are porphyritic, mainly composed of olivine(chrysolite) and clinopyroxene(diopside and augite) phenocrysts and plagioclase(andesine) microphenocrysts. Accessory minerals include titano-magnetite and titano-hematite, nepheline,apatite and amphibole xenocrysts. Sanidine occurs in some samples and sodi-potassic albite in others. Some olivines and clinopyroxenes exhibit resorbed margins and thin reaction rims while plagioclase displays oscillatory zoning, and sieved textures as a result of magma mixing. Whole-rock geochemistry data indicates that the lavas are silica-undersaturated, composed of basanites and basalts, showing little compositional variations(SiO_2: 39.20 wt.%–48.01 wt.%,MgO: 5.29 wt.%–9.70 wt.%). Trace elements patterns of these lavas suggest they are enriched in LILE including Pb,probably due to crustal contamination. REE patterns suggest cogenetic magmas below Baossi 1 and Baossi 2 volcanoes,and distinct sources below Warack volcano and nearby lavas.The lavas studied show affinity to high-μ(HIMU), enriched type Ⅰ(EM1) and Oceanic Island Basalt(OIB)-like mantle signatures and thus indicate a heterogeneous mantle source underneath the vents as noted at other monogenetic and polygenetic volcanoes along the CVL. Primary melts derived from low degrees of partial melting(0.5%–2%) and encountered low rates of fractionation, and crustal contamination coupled with magma mixing. These melts evolved independently through structural weaknesses in the basement.
文摘Stream sediment geochemistry remains a versatile tool in exploration especially in regions where knowledge of the primary mineralization is lacking and the exploration activities are still at reconnaissance stage. In this study, we investigate the concentrations of gold and associated elements in stream sediment samples from the Vaimba-Lidi drainage system in northern Cameroon;a relatively remote area where alluvial gold is worked locally, and exploration activities are at early stage. The main river and its principal first and second order tributaries were sampled, panned for gold grain recovery and the 100 μm size fraction analyzed for Au by fire assay with Ni finish. A suite of other elements were analyzed for by inductively coupled plasma mass spectrometry (ICP-MS). Gold grades estimated by the panning and weighing technique rarely exceed1 g/t while the Au concentrations from chemical analysis range from 3.0 to 354.0 ppm. The spatial distribution of gold and all the other elements are presented as point symbol maps and the data analyzed using multivariate statistics. From the principal component analysis (PCA), the As-Mo-W-Ag as well as the Au-Zn factors point to the presence of primary hydrothermal gold-sulphide mineralization in the area and this can be further investigated. These results highlight the importance of multielement analysis and multivariate statistical interpretation of sediment geochemical data in inferring the nature of the underlying primary mineralization in any region.
文摘Stream sediments are widely employed in reconnaissance exploration for gold especially in areas where outcrops are scarce and the overburden thick such as in the eastern Cameroon goldfields. In this study, 337 stream sediment samples were collected from the Lom river drainage basin. The study aims at identifying the main geological processes affecting the geochemical data from the sediments by considering the multi-elements relationships and spatial features of single elements. The samples were collected in duplicate. One set was panned, gold grains picked and weighed while the second set was wet sieved and the ≤100 microns size fraction retained. This fraction was eventually analyzed for gold by fire assay and a suite of elements by inductively coupled plasma mass spectrometry (ICP-MS). Single element maps were constructed using ArcGIS and the relationship between elements measured using Pearson correlation and principal component analysis (PCA). Gold concentrations in the samples are erratic, most below the detection limit and attain a high of 450 ppm. Five factors are derived from the PCA including single element factors for As and Au reflecting bedrock-hosted mineralization. The Cu-Zn-Y-Nb-Pb factor suggests sulphide mineralization perhaps related to felsic intrusions while the Sr-Ba-La-Ce-Zr factor is linked to lithologic control. These results demonstrate the usefulness of multi-element analysis and data interpretation using GIS tools in the exploration efforts for gold worldwide.
文摘Earth observation data are typically compressed using general-purpose single-threaded compression algorithms that operate at a fraction of the bandwidth of modern storage and processing systems.We present evidence that recently developed multi-threaded compression codecs offer substantial benefits over widely used single-threaded codecs in terms of compression efficiency when applied to a selection of moderate resolution imaging spectroradiometer(MODIS)datasets stored in the HDF5 format.Compression codecs from the LZ77 and Rice families are shown to vary in efficacy when applied to different MODIS data products,highlighting the need for compression strategies to be tailored to different classes of data.We also introduce LPC-Rice,a new multi-threaded codec,that performs particularly well when applied to time-series data.
文摘This article is aimed at providing a detailed description of the Flood Validation Exercise organised by the Independent Service Validation Group of the Global Monitoring for Environment and Security(GMES)RESPOND project.The aims of the validation exercise were:(1)providing a practical example of validation procedures in the frame of the GMES Emergency Response services;(2)executing a full-scale validation exercise able to cope with the requirements of an emergency service;and(3)better understanding the performances and limitations of Earth observation services for Flood Damage Mapping.This validation exercise is a first step of the main task to define the whole validation process for GMES services.When this is achieved,there will be knowledge concerning how well services meet the service specifications derived from the user needs.The present exercise has the purpose of gathering this knowledge.The output of this validation exercise can be used to characterise and qualify the performance and timeliness of Crisis and Damage Mapping Services.This paper summarises the methodology for the flood exercise validation and the results of product validation and inter-comparison.
文摘Though studies showed the potential of high-resolution optical sensors for crop yield prediction,several factors have limited their wider application.The main factors are obstruction of cloud,identification of phenology,demand for high computing infrastructure and the complexity of statistical methods.In this research,we created a novel approach by combining four methods.First,we implemented the cloud restoration algorithm called gapfill to restore missed Normalized Difference Vegetation Index(NDVI)values derived from Sentinel-2 sensor(S2)due to cloud obstruction.Second,we created square tiles as a solution for high computing infrastructure demand due to the use of high-resolution sensor.Third,we implemented gapfill following critical crop phenology stage.Fourth,observations from restored images combined with original(from cloud-free images)values and applied for winter wheat prediction.We applied seven base machine learning as well as two groups of super learning ensembles.The study successfully applied gapfill on high-resolution image to get good quality estimates for cloudy pixels.Consequently,yield prediction accuracy increased due to the incorporation of restored values in the regression process.Base models such as Generalized Linear Regression(GLM)and Random Forest(RF)showed improved capacity compared to other base and ensemble models.The two models revealed RMSE of 0.001 t/ha and 0.136 t/ha on the holdout group.The twomodels also revealed consistent and better performance using scatter plot analysis across three datasets.The approach developed is useful to predict wheat yield at field scale,which is a rarely available but vital in many developmental projects,using optical sensors.
