检索结果-南通市图书馆

Efficient and Cost-Effective Vehicle Detection in FoggyWeather for Edge/Fog-Enabled Traffic Surveillance and Collision Avoidance Systems

引用

Computers, Materials and Continua 2024年第1期81卷 911-931页

作者： Raza, Naeem Habib, Muhammad Asif Ahmad, Mudassar abbas, qaisar Aldajani, Mutlaq B. Latif, Muhammad Ahsan Department of Computer Science National Textile University Faisalabad 37610 Pakistan College of Computer and Information Sciences Imam Mohammad Ibn Saud Islamic University (IMSIU) Riyadh 11432 Saudi Arabia Department of Computer Science University of Agriculture Faisalabad 38000 Pakistan

Vision-based vehicle detection in adverse weather conditions such as fog, haze, and mist is a challenging research area in the fields of autonomous vehicles, collision avoidance, and Internet of Things (IoT)-enabled edge/fog computing traffic surveillance and monitoring systems. Efficient and cost-effective vehicle detection at high accuracy and speed in foggy weather is essential to avoiding road traffic collisions in real-time. To evaluate vision-based vehicle detection performance in foggy weather conditions, state-of-the-art Vehicle Detection in Adverse Weather Nature (DAWN) and Foggy Driving (FD) datasets are self-annotated using the YOLO LABEL tool and customized to four vehicle detection classes: cars, buses, motorcycles, and trucks. The state-of-the-art single-stage deep learning algorithms YOLO-V5, and YOLO-V8 are considered for the task of vehicle detection. Furthermore, YOLO-V5s is enhanced by introducing attention modules Convolutional Block Attention Module (CBAM), Normalized-based Attention Module (NAM), and Simple Attention Module (SimAM) after the SPPF module as well as YOLO-V5l with BiFPN. Their vehicle detection accuracy parameters and running speed is validated on cloud (Google Colab) and edge (local) systems. The mAP50 score of YOLO-V5n is 72.60%, YOLOV5s is 75.20%, YOLO-V5m is 73.40%, and YOLO-V5l is 77.30%; and YOLO-V8n is 60.20%, YOLO-V8s is 73.50%, YOLO-V8m is 73.80%, and YOLO-V8l is 72.60% on DAWN dataset. The mAP50 score of YOLO-V5n is 43.90%, YOLO-V5s is 40.10%, YOLO-V5m is 49.70%, and YOLO-V5l is 57.30%; and YOLO-V8n is 41.60%, YOLO-V8s is 46.90%, YOLO-V8m is 42.90%, and YOLO-V8l is 44.80% on FD dataset. The vehicle detection speed of YOLOV5n is 59 Frame Per Seconds (FPS), YOLO-V5s is 47 FPS, YOLO-V5m is 38 FPS, and YOLO-V5l is 30 FPS; and YOLO-V8n is 185 FPS, YOLO-V8s is 109 FPS, YOLO-V8m is 72 FPS, and YOLO-V8l is 63 FPS on DAWNdataset. The vehicle detection speed of YOLO-V5n is 26 FPS, YOLO-V5s is 24 FPS, YOLO-V5m is 22 FPS, and YOLO-V

关键词： Fog computing

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A Semantic Adversarial Network for Detection and Classification of Myopic Maculopathy

引用

Computers, Materials & Continua 2023年第4期75卷 1483-1499页

作者： qaisar abbas Abdul Rauf Baig Ayyaz Hussain College of Computer and Information Sciences Imam Mohammad Ibn Saud Islamic University(IMSIU)Riyadh11432Saudi Arabia Department of Computer Science Quaid-i-Azam UniversityIslamabad44000Pakistan

The diagnosis of eye disease through deep learning (DL) technologyis the latest trend in the field of artificial intelligence (AI). Especially indiagnosing pathologic myopia (PM) lesions, the implementation of DL is adifficult task because of the classification complexity and definition system ofPM. However, it is possible to design an AI-based technique that can identifyPM automatically and help doctors make relevant decisions. To achieve thisobjective, it is important to have adequate resources such as a high-qualityPM image dataset and an expert team. The primary aim of this research isto design and train the DLs to automatically identify and classify PM intodifferent classes. In this article, we have developed a new class of DL models(SAN-FSL) for the segmentation and detection of PM through semanticadversarial networks (SAN) and few-short learning (FSL) methods, *** to DL methods, the conventional segmentation methodsuse supervised learning models, so they (a) require a lot of data for trainingand (b) fixed weights are used after the completion of the training *** solve such problems, the FSL technique was employed for model trainingwith few samples. The ability of FSL learning in UNet architectures is beingexplored, and to fine-tune the weights, a few new samples are being providedto the UNet. The outcomes show improvement in the detection area andclassification of PM stages. Betterment in the result is observed by sensitivity(SE) of 95%, specificity (SP) of 96%, and area under the receiver operatingcurve (AUC) of 98%, and the higher F1-score is achieved using 10-fold ***, the obtained results confirmed the superiority of theSAN-FSL method.

关键词： Artificial intelligence cardiovascular vision loss deep learning few-shot learning semantic segmentation myopic maculopathy

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Hypo-Driver: A Multiview Driver Fatigue and Distraction Level Detection System

引用

Computers, Materials & Continua 2022年第4期71卷 1999-2017页

作者： qaisar abbas Mostafa EAIbrahim Shakir Khan Abdul Rauf Baig College of Computer and Information Sciences Imam Mohammad Ibn Saud Islamic University(IMSIU)Riyadh11432Saudi Arabia Department of Electrical Engineering Benha Faculty of EngineeringBenha UniversityQalubiaBenha13518Egypt

Traffic accidents are caused by driver fatigue or distraction in many *** prevent accidents,several low-cost hypovigilance(hypo-V)systems were developed in the past based on a multimodal-hybrid(physiological and behavioral)feature *** in this paper,real-time driver inattention and fatigue(Hypo-Driver)detection system is proposed through multi-view cameras and biosignal sensors to extract hybrid *** considered features are derived from non-intrusive sensors that are related to the changes in driving behavior and visual facial *** get enhanced visual facial features in uncontrolled environment,three cameras are deployed on multiview points(0◦,45◦,and 90◦)of the *** develop a Hypo-Driver system,the physiological signals(electroencephalography(EEG),electrocardiography(ECG),electro-myography(sEMG),and electrooculography(EOG))and behavioral information(PERCLOS70-80-90%,mouth aspect ratio(MAR),eye aspect ratio(EAR),blinking frequency(BF),head-titled ratio(HT-R))are collected and pre-processed,then followed by feature selection and fusion *** driver behaviors are classified into five stages such as normal,fatigue,visual inattention,cognitive inattention,and *** improved hypo-Driver system utilized trained behavioral features by a convolutional neural network(CNNs),recurrent neural network and long short-term memory(RNN-LSTM)model is used to extract physiological *** fusion of these features,the Hypo-Driver system is classified hypo-V into five stages based on trained layers and dropout-layer in the deep-residual neural network(DRNN)*** test the performance of a hypo-Driver system,data from 20 drivers are *** results of Hypo-Driver compared to state-of-theart methods are *** to the state-of-the-art Hypo-V system,on average,the Hypo-Driver system achieved a detection accuracy(AC)of 96.5%.The obtained results indicate that the Hypo-Driver system based on multimodal and multivie

关键词： Internet of things(IoT) intelligent transportation sensors multiview points transfer learning convolutional neural network recurrent neural network residual neural network multimodal features

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Transfer Learning-based Computer-aided Diagnosis System for Predicting Grades of Diabetic Retinopathy

引用

Computers, Materials & Continua 2022年第6期71卷 4573-4590页

作者： qaisar abbas Mostafa E.A.Ibrahim Abdul Rauf Baig College of Computer and Information Sciences Imam Mohammad Ibn Saud Islamic University(IMSIU)Riyadh11432Saudi Arabia Department of Electrical Engineering Benha Faculty of EngineeringBenha UniversityQalubiaBenha13518Egypt

Diabetic retinopathy(DR)diagnosis through digital fundus images requires clinical experts to recognize the presence and importance of many intricate *** task is very difficult for ophthalmologists and ***,many computer-aided diagnosis(CAD)systems were developed to automate this screening process *** this paper,aCAD-DR system is proposed based on preprocessing and a pre-train transfer learningbased convolutional neural network(PCNN)to recognize the five stages of DR through retinal fundus *** develop this CAD-DR system,a preprocessing step is performed in a perceptual-oriented color space to enhance the DR-related lesions and then a standard pre-train PCNN model is improved to get high classification *** architecture of the PCNN model is based on three main ***,the training process of the proposed PCNN is accomplished by using the expected gradient length(EGL)to decrease the image labeling efforts during the training of the CNN ***,themost informative patches and images were automatically selected using a few pieces of training labeled ***,the PCNN method generated useful masks for prognostication and identified regions of ***,the DR-related lesions involved in the classification task such as micro-aneurysms,hemorrhages,and exudates were detected and then used for recognition of *** PCNN model is pre-trained using a high-end graphical processor unit(GPU)on the publicly available Kaggle *** obtained results demonstrate that the CAD-DR system outperforms compared to other state-of-the-art in terms of sensitivity(SE),specificity(SP),and accuracy(ACC).On the test set of 30,000 images,the CAD-DR system achieved an average SE of 93.20%,SP of 96.10%,and ACC of 98%.This result indicates that the proposed CAD-DR system is appropriate for the screening of the severity-level of DR.

关键词： Diabetic Retinopathy retinal fundus images computer-aided diagnosis system deep learning transfer learning convolutional neural network

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A Flexible Boundary Procedure for Hyperbolic Problems: Multiple Penalty Terms Applied in a Domain

引用

Communications in Computational Physics 2014年第7期16卷 541-570页

作者： Jan Nordstrom qaisar abbas Brittany A.Erickson Hannes Frenander Department of Mathematics Division of Computational MathematicsLinkoping UniversitySE-58183 Link¨opingSweden Department of Information Technology Division of Scientific ComputingUppsala UniversitySE-75105 UppsalaSweden Department of Geological Sciences San Diego State UniversitySan DiegoCA 92182-1020USA Department of Mathematics Division of Computational MathematicsLinkoping UniversitySE-58183 Link¨opingSweden.

A new weak boundary procedure for hyperbolic problems is *** consider high order finite difference operators of summation-by-parts form with weak boundary conditions and generalize that *** new boundary procedure is applied near boundaries in an extended domain where data is *** show how to raise the order of accuracy of the scheme,how to modify the spectrum of the resulting operator and how to construct non-reflecting properties at the *** new boundary procedure is cheap,easy to implement and suitable for all numerical methods,not only finite difference methods,that employ weak boundary *** results that corroborate the analysis are presented.

关键词： Summation-by-parts weak boundary conditions penalty technique high-order accuracy finite difference schemes stability steady-state non-reflecting boundary conditions

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Strengths,weaknesses,opportunities,and threats(SWOT)analysis of supercapacitors:A review

引用

Journal of Energy Chemistry 2023年第4期79卷 611-638页

作者： Pragati A.Shinde qaisar abbas Nilesh R.Chodankar Katsuhiko Ariga Mohammad Ali Abdelkareem Abdul Ghani Olabi Sustainable Energy&Power Systems Research Centre RISEUniversity of SharjahP.O.Box 27272SharjahUnited Arab Emirates International Center for Materials Nanoarchitectonics(WPI-MANA) National Institute for Materials Science(NIMS)1-1 NamikiTsukuba 305-0044Japan Department of Energy and Material Engineering Dongguk University-SeoulSeoul 04620Republic of Korea Graduate School of Frontier Sciences The University of Tokyo5-1-5 KashiwanohaKashiwaChiba 277-8561Japan Mechanical Engineering and Design School of Engineering and Applied ScienceAston UniversityAston TriangleBirmingham B47ETUK School of Computing Engineering and Physical SciencesUniversity of The West of ScotlandGlasgowPA12BEUK

The development of clean and sustainable energy sources has received widespread interest in the past few decades due to the rolling energy demands while extenuating the rising tiers of greenhouse gases and environmental *** to their intermittent nature,these green and sustainable sources require appropriate energy storage *** different energy storage technologies,electrochemical energy storage devices,particularly supercapacitors(SCs),have fascinated global attention for their utilization in electric vehicles,power supports,portable electronics,and many others application requiring electric energy devices for their ***,the growth of SCs in the commercial market has squeezed requirements,and further developments are obligatory for their effective *** the meantime,SCs also face technical complications and contests for their introduction in industrial settings because of their low energy density and high Levelized *** present study combines core strengths,weaknesses,opportunities,and threats(SWOT)analysis of SCs with new perspectives and recent *** challenges and the future progressive prospects of SCs are also presented in *** review will afford consistent direction and new superhighways for the further development of SCs as standalone and complementary energy storage systems.

关键词： Supercapacitors Energy storage Strengths Opportunities

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Artificial Intelligence Based Meteorological Parameter Forecasting for Optimizing Response of Nuclear Emergency Decision Support System

引用

原子能科学技术 2024年第10期58卷 2068-2076页

作者： BILAL Ahmed Khan HASEEB ur Rehman qaisar Nadeem MUHAMMAD Ahmad Naveed Qureshi JAWARIA Ahad MUHAMMAD Naveed Akhtar AMJAD Farooq MASROOR Ahmad Pakistan Institute of Engineering and Applied Sciences Islamabad 44000Pakistan

This paper presents a novel artificial intelligence (AI) based approach to predict crucial meteorological parameters such as temperature,pressure,and wind speed,typically calculated from computationally intensive weather research and forecasting (WRF) *** meteorological data is indispensable for simulating the release of radioactive effluents,especially in dispersion modeling for nuclear emergency decision support *** of meteorological conditions during nuclear emergencies using the conventional WRF model is very complex and ***,a new artificial neural network (ANN) based technique was proposed as a viable alternative for meteorological prediction.A multi-input multi-output neural network was trained using historical site-specific meteorological data to forecast the meteorological *** evaluation of this technique was conducted to test its performance in forecasting various parameters including atmospheric pressure,temperature,and wind speed components in both East-West and North-South *** performance of developed network was evaluated on an unknown dataset,and acquired results are within the acceptable range for all meteorological *** show that ANNs possess the capability to forecast meteorological parameters,such as temperature and pressure,at multiple spatial locations within a grid with high accuracy,utilizing input data from a single ***,accuracy is slightly compromised when predicting wind speed *** mean square error (RMSE) was utilized to report the accuracy of predicted results,with values of 1.453℃for temperature,77 Pa for predicted pressure,1.058 m/s for the wind speed of U-component and 0.959 m/s for the wind speed of *** conclusion,this approach offers a precise,efficient,and wellinformed method for administrative decision-making during nuclear emergencies.

关键词： prediction of meteorological parameters weather research and forecasting model artificial neural networks nuclear emergency support system

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Structural, morphological, Raman, optical, magnetic, and antibacterial characteristics of CeO2 nanostructures

引用

International Journal of Minerals,Metallurgy and Materials 2016年第1期23卷 102-108页

作者： Fazal abbas Javed Iqbal Tariq Jan Noor Badshah qaisar Mansoor Muhammad Ismail Laboratory of Nanoscience and Technology Department of Physics International Islamic University H-10 Islamabad 44000 Pakistan Department of Basic Science University of Engineering and Technology Peshawar 26000 Pakistan Institute of Biomedical and Genetic Engineering (IBGE) Islamabad 44000 Pakistan

In this study, CeO2 nanostructures were synthesized by a soft chemical method. A hydrothermal treatment was observed to lead to an interesting morphological transformation of the nanoparticles into homogeneous microspheres composed of nanosheets with an average thickness of 40 nm. Structural analysis revealed the formation of a single-phase cubic fluorite structure of CeO2 for both samples. A Raman spectroscopic study confirmed the XRD results and furthermore indicated the presence of a large number of oxygen vacancies in the nanosheets. These oxygen vacancies led to room-temperature ferromagnetism （RTFM） of the CeO2 nanosheets with enhanced magnetic characteristics. Amazingly, the nanosheets exhibited substantially greater antibacterial activity than the nanoparticles. This greater antibacte- rial activity was attributed to greater exposure of high-surface-energy polar surfaces and to the presence of oxygen vacancies.

关键词： ceciurn oxide nanosheets chemical synthesis ferromagnetism oxygen vacancies antibacterial properties

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Isolation and characteristics of Arthrobacter *** CW-1 for biodegradation of PAEs

引用

Journal of Zhejiang University-Science A(Applied Physics & Engineering) 2007年第9期8卷 1469-1474页

作者： MAHMOOD qaisar Department of Environmental Engineering Zhejiang UniversityHangzhou 310029China

Isolation of new bacterial strains and recognition of their metabolic activities are highly desirable for sustainability of natural ecosystems. Biodegradation of dimethyl phthalate （DMP） under anoxic conditions has been shown to occur as a series of sequential steps using strain CW-1 isolated from digested sludge of Sibao Wastewater Treatment Plant in Hangzhou, China. The microbial colony on LB medium was yellowish, 3-5 mm in diameter, convex in the center, and embedded in mucous externally. The individual cells of strain CW-1 are irregular rods, measuring （0.6-0.7）×（0.9-1.0） pm, V-shaped, with clubbed ends, Gram positive and without any filaments. 16S rDNA （ 1438 bp） sequence analysis showed that the strain was related to Arthrobacter sp. CW-1 and can degrade PAEs utilizing nitrate as electron acceptor, but cannot mineralize DMP completely. The degradation pathway was recommended as： dimethyl phthalate （DMP）→monomethyl phthalate （MMP）--,phthalic acid （PA）. DMP biodegradation was a first order reaction with degradation rate constant of 0.3033 d 1 and half-life 2.25 d. The DMP conversion to PA by CW-1 could be described by using sequential kinetic model.

关键词： Denitrifying bacteria Arthrobacter sp. strain CW-1 Dimethyl phthalate (DMP) Phthalic acid (PA) DMP degradation pathway

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Control strategy of shortcut nitrification

引用

Journal of Environmental Sciences 2006年第1期18卷 58-61页

作者： qaisar Mahmood Department of Environmental Engineering Zhejiang University Hangzhou 310029 China.

Shortcut nitrification for ammonium-rich wastewater is energy-saving and cost-effective procedure that has become one of the hotspots in the field of biological denitrogenation. An orthogonal experiment was performed to study the combined effects of operational parameters on the performance of internal-loop airlift bioreactor for shortcut nitrification. The optimum operational parameters for the shortcut nitrification were fotmd as temperature 35 ℃, pH 8.0, dissolved oxygen concentration 1.0 mg/L, ammonium concentration 4 mmol/L and HRT 16 h, which have different influence on the performance of shortcut nitrification reactor. The pH, temperature and dissolved oxygen concentration have significant bearing on the process. The results showed that the shortcut nitrification reactor could be successfully started up within 42 d, and the reactor performance is steady with minimum NO2-/NOx- of 85.2%, maximum 93.4% and average value of 91.4% in effluent. Based on the analysis of experimental data, a new control strategy named “priority ＋ combination” for shortcut nitrification was suggested. Through this strategy, the startup and operation of shortcut nitrification for ammonium-rich sludge digester liquids were optimized. The control strategy works well to keep the reactor operation in steady state and in achieving high-efficiency for shortcut nitrification.

关键词： internal-loop airlift bioreactor shortcut nitrification orthogonal experiment control strategy sludge digester liquids

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：