检索结果-内蒙古大学图书馆

International Conference on Microelectronics, MIEL

作者： L. Stankovic T. Nikolic T. Talaska R. Dlugosz Faculty of Electronic Engineering University of Nis Nis Serbia Faculty of Telecommunication Computer Science and Electrical Engineering Bydgoszcz University of Science and Technology Bydgoszcz Poland

Accurate weed mapping is essential for the implementation of weed management in order to maintain high crop yields and less chemical pollution. This paper focuses on the performance evaluation of YOLO models for automatic crop and weed detection. The research aims to develop weed detection models using one-stage deep learning-based object detectors by transferring pre-trained object detection models to a selected weed dataset. The models are trained on annotated images from a public dataset and evaluated based on detection accuracy. Results demonstrate promising training performance, with approximately 70% mean average precision achieved in 100 training epochs. YOLOv5x exhibits the best performance among the studied models, achieving the highest precision, recall, and mean average precision (0.72, 0.75, and 0.74, respectively). The findings indicate that models with deeper or larger backbone networks tend to provide higher detection accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Explainable AI for Epileptic Seizure Prediction: A SHAPE and LIME Approach

Explainable AI for Epileptic Seizure Prediction: A SHAPE and...

引用

Information technology (ACIT)

作者： Md. Simul Hasan Talukder Sohag Kumar Mondal Oyshi Tabassum Aditi Mohammad Aljaidi Rejwan Bin Sulaiman Ahmad Al-Qerem Electrical and Electronic Engineering Dhaka University of Engineering & Technology Gazipur Bangladesh Electrical and Electronic Engineering Khulna University of Engineering and Technology Khulna Bangladesh Khulna Bangladesh Department of Computer Science and Engineering Daffodil International University Savar Bangladesh Department of Computer Science Faculty of Information Technology Zarqa University Zarqa Jordan College of Engineering University of Business and Technology Jeddah Saudi Arabia School of Computer Science & Technology Northumbria University Newcastle Tayne United Kingdom

ISBN: (数字)9798331540012

ISBN: (纸本)9798331540029

Epilepsy is a neurological chaos typified by frequent, spontaneous seizures. Early recognition of epilepsy by utilising AI techniques to scan EEG signals can enhance the prevention and management of it. This study aims to improve the classification of epileptic seizures by using the preprocessed version of the Epileptic Seizure (ERS) dataset. The preprocessed dataset is subjected to multiple stages in order to improve its quality and achieve balanced class representation. Data cleaning, outlier management, merging, and oversampling are those. After that, an 80:20 split of the dataset is made into subsets for testing and training. Next, training, testing, and evaluation are performed on the models of Gradient Boosting Classifier (GBC), Decision Tree Classifier (DTC), Random Forest Classifier (RFC), CatBoost Classifier (CBC), and ExtraTree Classifier (ETC). The ExtraTree Classifier is remarkably accurate, with a 99.51% accuracy rate, which is the highest accuracy. Finally, explainable artificial intelligence (SHAP and LIME) is used to clarify the ExtraTree Classifier's decision-making procedure. By providing a visual representation of significant variables and their influence on the model's predictions, this interpretability tool improves comprehension of the classification results.

关键词： Training Visualization Accuracy Shape Prevention and mitigation Epilepsy Predictive models Brain modeling Random forests Testing

来源：评论

学校读者我要写书评

暂无评论

PeanutAD: A Real-World Dataset for Anomaly Detection in Agricultural Product Processing Line

PeanutAD: A Real-World Dataset for Anomaly Detection in Agri...

引用

International Conference on Communications and electronics, ICCE

作者： Duc-Hai Nguyen Trong-Hiep Do Quoc-Khanh Nguyen Hoang-Linh-Phuong Nguyen Thi-Huong Nguyen Duc-Tan Tran Van-Toi Nguyen Faculty of Computer Science PHENIKAA University Hanoi Vietnam Hanoi College of High Technology Hanoi Vietnam Faculty of Electrical and Electronic Engineering PHENIKAA University Hanoi Vietnam

ISBN: (数字)9798350379792

ISBN: (纸本)9798350379808

Anomaly detection in production lines - automatically detecting defects in product processes - plays a vital role across several domains. Several industrial anomaly detection datasets have been built with severe challenges to overcome. However, the need for more amount and diversity of training data in specific systems in the real world, especially in agricultural product processing lines, remains to be considered. In this work, we introduce a peanut anomaly detection dataset (PeanutAD), a real-world dataset for anomaly detection tasks, reflecting the actual conditions in production lines. Experiments on this dataset demonstrated significant room for improvement because of some challenges. With PeanutAD, we aim to expand the anomaly detection database quantitatively and qualitatively, allowing researchers to further enhance and evaluate anomaly detection techniques with the most realistic setup possible. PeanutAD and experimental results on baseline methods shall be kept fully open-source as a contribution to the research community 1 .

关键词： Databases Training data Production Agricultural products Task analysis Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

A novel hybrid cryptosystem based on DQFrFT watermarking and 3D-CLM encryption for healthcare services

引用

Frontiers of Information technology & electronic engineering 2023年第7期24卷 1045-1061页

作者： Fatma KHALLAF Walid EL-SHAFAI El-Sayed M.EL-RABAIE Naglaa F.SOLIMAN Fathi EAbd E.L-SAMIE Department of Electronics and Electrical Communications Engineering Faculty of Electronic EngineeringMenoufia UniversityMenouf 32952Egypt Department of Electrical Engineering Faculty of EngineeringAhram Canadian University6^(th)October CityGiza 12451Egypt Security Engineering Lab Computer Science DepartmentPrince Sultan UniversityRiyadh I1586Saudi Arabia Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh 11671Saudi Arabia

Quaternion algebra has been used to apply the fractional Fourier transform(FrFT)to color images in a comprehensive ***,the discrete fractional random transform(DFRNT)with adequate basic randomness remains to be *** paper presents a novel multistage privacy system for color medical images based on discrete quaternion fractional Fourier transform(DQFrFT)watermarking and three-dimensional chaotic logistic map(3D-CLM)***,we describe quaternion DFRNT(QDFRNT),which generalizes DFRNT to handle quaternion signals effectively,and then use QDFRNT to perform color medical image adaptive *** efficiently evaluate QDFRNT,this study derives the relationship between the QDFRNT of a quaternion signal and the four components of the DFRNT ***,it uses the human vision system's(HVS)masking qualities of edge,texture,and color tone immediately from the color host image to adaptively modify the watermark strength for each block in the color medical image using the QDFRNT-based adaptive watermarking and support vector machine(SVM)*** limitations of watermark embedding are also explained to conserve watermarking ***,3D-CLM encryption is employed to improve the system's security and efficiency,allowing it to be used as a multistage privacy *** proposed security system is effective against many types of channel noise attacks,according to simulation results.

关键词： Color medical image Quaternion Adaptive watermarking Encryption Fractional transform Three-dimensional chaotic logistic map(3D-CLM)

来源：评论

学校读者我要写书评

暂无评论

Effect of pH on Electrochemical, Morphological and Optical Properties of Electrodeposited Molybdenum Sulfide Thin Film

Effect of pH on Electrochemical, Morphological and Optical P...

引用

IEEE International Conference on Semiconductor electronics (ICSE)

作者： Iskandar Dzulkarnain Rummaja Muhammad Idzdihar Idris Radi Husin Ramlee Zul Atfyi Mohammed Napiah Marziani Rashid Ahmad Muhajer Abdul Aziz Faculty of Electronic and Computer Technology and Engineering Universiti Teknikal Malaysia Melaka (UTeM) Melaka Malaysia Micro and Nano Research Group (MINE) Centre for Telecomunication Research and Innovation (CeTRI) Faculty of Electronic and Computer Technology and Engineering Universiti Teknikal Malaysia Melaka (UTeM) Melaka Malaysia School of Physics Universiti Sains Malaysia Penang Malaysia

ISBN: (数字)9798350378313

ISBN: (纸本)9798350378320

Third-generation dye-sensitized solar cells (DSSC) provide many benefits over ordinary solar cells. DSSCs efficiently convert visible light into electrical energy and work well in low light environments. Platinum is a common counter electrode due to its electrocatalytic, conductivity, and reflection properties. Due to its drawbacks, alternative counter electrode materials have been explored. The potential counter electrode of DSSC is molybdenum Sulfide (MoS 2 ), an inorganic compound of molybdenum and sulphur which has good properties in terms of electrochemical properties and long-term stability. Electrodeposition is one of the deposition techniques used in thin film deposition. Due to several challenges in thin deposition techniques with control over film properties, complexity and cost, electrodeposition is a good alternative due to its cost-effectiveness, simplicity, and deposition control. In this work, we studied the effect of deposition electrolyte condition (acidic, neutral, alkaline) to the electrochemical, morphological, and optical properties of molybdenum sulfide thin film. Overall, the study reveals that MoS 2 films exhibit good hydrogen evolution reaction (HER) activity at pH 6 and pH 8, with pH 6 showing the highest performance, while also indicating minimal variation in grain size across different pH levels and highlighting the influence of pH on optical and electronic properties.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep reinforcement learning for near-fieldwideband beamforming in STAR-RIS networks

引用

Frontiers of Information technology & electronic engineering 2024年第12期25卷 1651-1663页

作者： Ji WANG Jiayi SUN Wei FANG Zhao CHEN Yue LIU Yuanwei LIU Department of Electronics and Information Engineering College of Physical Science and TechnologyCentral China Normal UniversityWuhan 430079China Beijing National Research Center for Information Science and Technology Tsinghua UniversityBeijing 100084China Faculty of Applied Sciences Macao Polytechnic UniversityMacao SARChina School of Electronic Engineering and Computer Science Queen Mary University of LondonLondon E14NSUK Department of Electrical and Electronic Engineering The University of Hong KongHong Kong 999077China

A simultaneously transmitting and reflecting reconfigurable intelligent surface(STAR-RIS)assisted multiuser near-field wideband communication system is investigated,in which a robust deep reinforcement learning(DRL)based algorithm is proposed to enhance the users’achievable rate by jointly optimizing the active beamforming at the base station(BS)and passive beamforming at the *** mitigate the beam split issue,the delay-phase hybrid precoding structure is introduced to facilitate wideband *** the coupled nature of the STARRIS phase-shift model,the passive beamforming design is formulated as a problem of hybrid continuous and discrete phase-shift control,and the proposed algorithm controls the high-dimensional continuous action through hybrid action ***,to address the issue of biased estimation encountered by existing DRL algorithms,a softmax operator is introduced into the algorithm to mitigate this *** results illustrate that the proposed algorithm outperforms existing algorithms and overcomes the issues of overestimation and underestimation.

关键词： Deep reinforcement learning Near-field beamforming Simultaneously transmitting and reflecting reconfigurable intelligent surface(STAR-RIS) Wideband beam split

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligent Applications in Smart Cities

Artificial Intelligent Applications in Smart Cities

引用

Smart Information Systems and Technologies (SIST), IEEE International Conference on

作者： Ruhi Zafer Caglayan Korhan Kayisli Resul Coteli Ruslan Omirgaliyev Nurkhat Zhakiyev Electrical-Electronic Engineering Faculty of Engineering Gazi University Ankara Turkiye Computer Engineering Faculty of Engineering TED University Ankara Turkiye Energy Engireering Faculty of Technology Firat University Elazig Turkiye Department of Computer Engineering Astana IT University Astana Kazakhstan Department of Science and Innovation Astana IT University Astana Kazakhstan

ISBN: (数字)9798350374865

ISBN: (纸本)9798350374872

History shows us that people move towards a more stable lifestyle after undergoing significant changes. During these times, the way communities and buildings were designed started to change too. Different periods in history are known for their standout moments, each bringing its own set of needs and tech breakthroughs. Nowadays, tech keeps evolving. People nowadays aim for a more straightforward life, and technology has been shaping up to meet this need. We live in times highlighted by the rise of smart technology, like artificial intelligence and the Internet of Things, which not only make daily tasks easier but also transform how we think about our cities and personal spaces. This piece focuses on exploring the smart city idea, touching upon various associated subjects. As we delve into these areas, we'll also look at some important research related to them.

关键词： Accuracy Smart cities Reviews Buildings Transforms Internet of Things History

来源：评论

学校读者我要写书评

暂无评论

A versatile framework for analyzing galaxy image data by incorporating Human-in-the-loop in a large vision model

引用

Chinese Physics C 2024年第9期48卷 176-187页

作者： Ming-Xiang Fu Yu Song Jia-Meng Lv Liang Cao Peng Jia Nan Li Xiang-Ru Li Ji-Feng Liu A-Li Luo Bo Qiu Shi-Yin Shen Liang-Ping Tu Li-Li Wang Shou-Lin Wei Hai-Feng Yang Zhen-Ping Yi Zhi-Qiang Zou National Astronomical Observatories Chinese Academy of SciencesBeijing 100101China College of Electronic Information and Optical Engineering Taiyuan University of TechnologyTaiyuan 030024China School of Astronomy and Space Science University of Chinese Academy of SciencesBeijing 101408China Key lab of Space Astronomy and Technology National Astronomical ObservatoriesBeijing 100101China School of Computer Science South China Normal UniversityGuangzhou 510631China CAS Key Laboratory of Optical Astronomy National Astronomical ObservatoriesBeijing 100101China University of Chinese Academy of Sciences NanjingNanjing 211135China University of Science and Technology Beijing Beijing 100083China Shanghai Astronomical Observatory Chinese Academy of SciencesShanghai 200030China School of Computer and Information Dezhou UniversityDezhou 253023China Faculty of Information Engineering and Automation Kunming University of Science and TechnologyKunming 650500China School of Computer Science and Technology Taiyuan University of Science and TechnologyTaiyuan 30024China School of Mechanical Electrical and Information EngineeringShandong UniversityWeihai 264209China Nanjing University of Posts&Telecommunications Nanjing 210023China School of Science University of Science and Technology LiaoningAnshan 114051China

The exponential growth of astronomical datasets provides an unprecedented opportunity for humans to gain insight into the ***,effectively analyzing this vast amount of data poses a significant *** response,astronomers are turning to deep learning techniques,but these methods are limited by their specific training sets,leading to considerable duplicate *** overcome this issue,we built a framework for the general analysis of galaxy images based on a large vision model(LVM)plus downstream tasks(DST),including galaxy morphological classification,image restoration object detection,parameter extraction,and *** the low signal-to-noise ratios of galaxy images and the imbalanced distribution of galaxy categories,we designed our LVM to incorporate a Human-in-the-loop(HITL)module,which leverages human knowledge to enhance the reliability and interpretability of processing galaxy images *** proposed framework exhibits notable fewshot learning capabilities and versatile adaptability for all the abovementioned tasks on galaxy images in the DESI Legacy Imaging *** particular,for the object detection task,which was trained using 1000 data points,our DST in the LVM achieved an accuracy of 96.7%,while ResNet50 plus Mask R-CNN reached an accuracy of 93.1%.For morphological classification,to obtain an area under the curve(AUC)of~0.9,LVM plus DST and HITL only requested 1/50 of the training sets that ResNet18 *** addition,multimodal data can be integrated,which creates possibilities for conducting joint analyses with datasets spanning diverse domains in the era of multi-messenger astronomy.

关键词： artificial intelligence large vision model human-in-the-loop astronomy galaxies

来源：评论

学校读者我要写书评

暂无评论

Lightweight Transfer Learning Models for Ultrasound-Guided Classification of COVID-19 Patients

引用

computers, Materials & Continua 2021年第11期69卷 2295-2312页

作者： Mohamed Esmail Karar Omar Reyad Mohammed Abd-Elnaby Abdel-Haleem Abdel-Aty Marwa Ahmed Shouman College of Computing and Information Technology Shaqra UniversityShaqra11961Saudi Arabia Department of Industrial Electronics and Control Engineering Faculty of Electronic Engineering(FEE)Menoufia UniversityMenouf32952Egypt Department of Mathematics and Computer Science Faculty of ScienceSohag UniversitySohag82524Egypt Department of Computer Engineering College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia Department of Physics College of SciencesUniversity of BishaBisha61922Saudi Arabia Department of Physics Faculty of ScienceAl-Azhar UniversityAssiut71524Egypt Department of Computer Science and Engineering Faculty of Electronic Engineering(FEE)Menoufia UniversityMenouf32952Egypt

Lightweight deep convolutional neural networks(CNNs)present a good solution to achieve fast and accurate image-guided diagnostic procedures of COVID-19 ***,advantages of portable Ultrasound(US)imaging such as simplicity and safe procedures have attracted many radiologists for scanning suspected COVID-19 *** this paper,a new framework of lightweight deep learning classifiers,namely COVID-LWNet is proposed to identify COVID-19 and pneumonia abnormalities in US *** to traditional deep learning models,lightweight CNNs showed significant performance of real-time vision applications by using mobile devices with limited hardware *** main lightweight deep learning models,namely MobileNets,ShuffleNets,MENet and MnasNet have been proposed to identify the health status of lungs using US *** image dataset(POCUS)was used to validate our proposed COVID-LWNet framework *** classes of infectious COVID-19,bacterial pneumonia,and the healthy lung were investigated in this *** results showed that the performance of our proposed MnasNet classifier achieved the best accuracy score and shortest training time of 99.0%and 647.0 s,*** paper demonstrates the feasibility of using our proposed COVID-LWNet framework as a new mobilebased radiological tool for clinical diagnosis of COVID-19 and other lung diseases.

关键词： Coronavirus medical image processing artificial intelligence ultrasound

来源：评论

学校读者我要写书评

暂无评论

A Hybrid-Logic Scheme for High-Performance and Low-Power Decoders in 7nm Process

A Hybrid-Logic Scheme for High-Performance and Low-Power Dec...

引用

International Conference on Solid-State and Integrated Circuit technology

作者： Donghao Xia Yuejun Zhang Mengfan Xu Liang Wen Yiting Guo Faculty of Electrical Engineering and Computer Science Ningbo University Zhejiang China Department of Electronic Technology China Coast Guard Academy Ningbo China

ISBN: (数字)9798350361834

ISBN: (纸本)9798350361841

Advancing memory circuitry has heightened the performance criteria for memory in diverse chip applications. Decoders, serving as peripheral circuits to memory devices, have be a prominent area of academic interest. The new NAND/NOR gate circuits are proposed using pass-transistor logic (PTL) and transmission gate logic (TGL). The two hybrid-logic design schemes of high-performance and low-power (HPLP) and HPLP inverting (HPLPI) utilizing PTL and TGL gate in combination with static CMOS logic for decoders are proposed, while achieving fewer transistors, faster speed, lower power dissipation as compared to conventional circuits. Experiments are conducted in TSMC 7nm FinFET process for hybrid-logic decoders. The simulation results indicate that, in comparison to conventional decoders, the proposed hybrid-logic 3–8 decoder demonstrates improvements, with the HPLP design reducing delay by over 19% and power by over 71%, and the HPLPI design reducing delay by over 17% and power by over 48%.

关键词： Performance evaluation Simulation Voltage Logic gates FinFETs Decoding Delays Power dissipation Transistors Logic

来源：评论

学校读者我要写书评

暂无评论

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

请选择保存的检索档案：

请选择收藏分类：

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

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

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：