检索结果-内蒙古大学图书馆

Ultra-low power MoS2 optoelectronic synapse with wavelength sensitivity for color target recognition

science China(Information sciences) 2025年第4期68卷 187-196页

作者： Bo WEI Yabo CHEN Xiaotong HAN Yan KANG Bujia LIANG Cheng LI Xiaokuo YANG Liang FANG Yuanxi PENG Institute for Quantum Information & State Key Laboratory of High Performance Computing College of ComputerNational University of Defense Technology Fundamentals Department Air Force Engineering University College of Advanced Interdisciplinary Studies National University of Defense Technology Institute of Quantum Information Science and Technology College of ScienceNational University of Defense Technology College of Computer National University of Defense Technology

Optoelectronic synapses that integrate visual perception and pre-processing hold significant potential for neuromorphic vision systems（NVSs）. However, due to a lack of wavelength sensitivity, existing NVS mainly focuses on gray-scale image processing, making it challenging to recognize color images. Additionally, the high power consumption of optoelectronic synapses, compared to the 10 fJ energy consumption of biological synapses, limits their broader application. To address these challenges, an energy-efficient NVS capable of color target recognition in a noisy environment was developed,utilizing a MoS2optoelectronic synapse with wavelength sensitivity. Benefiting from the distinct photon capture capabilities of 450, 535, and 650 nm light, the optoelectronic synapse exhibits wavelength-dependent synaptic plasticity, including excitatory postsynaptic current（EPSC）, paired-pulse facilitation（PPF）, and long-term plasticity（LTP）. These properties can effectively mimic the visual memory and color discrimination functions of the human vision system. Results demonstrate that the NVS, based on MoS2optoelectronic synapses, can eliminate the color noise at the sensor level, increasing color image recognition accuracy from 50% to 90%. Importantly, the optoelectronic synapse operates at a low voltage spike of0.0005 V, consuming only 0.075 fJ per spike, surpassing the energy efficiency of both existing optoelectronic and biological synapses. This ultra-low power, color-sensitive device eliminates the need for color filters and offers great promise for future deployment in filter-free NVS.

关键词： optoelectronic synapse neuromorphic vision system color recognition 2D materials image pre-processing

来源：评论

学校读者我要写书评

暂无评论

Assimilation of MetOp-C AMSU-A Data Using the ARMS as an Observation Operator in the YH4DVAR System

引用

Journal of Meteorological Research 2025年第02期39卷 252-271页

作者： Tengling LUO Shuo MA Weimin ZHANG Yanlai ZHAO Yi YU Jinhui YANG Shaoying LI College of Meteorology and Oceanography National University of Defense Technology College of Computer Science and Technology National University of Defense Technology

The Advanced Radiative Transfer Modeling System (ARMS), a computationally efficient satellite observation operator, has been successfully integrated into the YinHe four-dimensional variational data assimilation (YH4DVAR)system. This study investigates the impacts of assimilating Advanced Microwave Sounding Unit-A (AMSU-A) observations from the Meteorological Operational Satellite-C (MetOp-C) on the performance of YH4DVAR. Through a month-long global statistical analysis and a case study of Typhoon Hinnamnor, we evaluate the benefits of AMSUA data assimilation under clear sky conditions. Key findings are as follows.(1) ARMS achieves simulation accuracy comparable to RTTOV (Radiative Transfer for the Television and InfraRed Observation Satellite Operational Vertical sounder) version 11.2, demonstrating only a 0.5%discrepancy in data retention after quality control.(2) Implementation of ARMS as an operator in YH4DVAR enhances forecast accuracy for the 850-hPa temperature and 500-hPa geopotential height in the tropical region.(3) Compared to RTTOV, ARMS has improved the intensity forecast of Typhoon Hinnamnor and reduced mean wind speed errors by approximately 2%and central pressure errors by approximately1%.ARMShasnowbeenoperationallyadoptedasanalternativeobservationaloperatorwithin YH4DVAR, demonstrating exceptional numerical stability, computational efficiency, and promising potential for future satellite data assimilation applications.

关键词： Advanced Microwave Sounding Unit-A (AMSU-A) Advanced Radiative Transfer Modeling System (ARMS) data assimilation Radiative Transfer for the Television and Infrared Observation Satellite Operational Vertical Sounder (RTTOV)

来源：评论

学校读者我要写书评

暂无评论

Hybrid Deep Learning Approach for Automating App Review Classification:Advancing Usability Metrics Classification with an Aspect-Based Sentiment Analysis Framework

引用

computers, Materials & Continua 2025年第1期82卷 949-976页

作者： Nahed Alsaleh Reem Alnanih Nahed Alowidi Department of Computer Science Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Computer Science College of Computer Science and EngineeringUniversity of HailHail81451Saudi Arabia

App reviews are crucial in influencing user decisions and providing essential feedback for developers to improve their *** the analysis of these reviews is vital for efficient review *** traditional machine learning(ML)models rely on basic word-based feature extraction,deep learning(DL)methods,enhanced with advanced word embeddings,have shown superior *** research introduces a novel aspectbased sentiment analysis(ABSA)framework to classify app reviews based on key non-functional requirements,focusing on usability factors:effectiveness,efficiency,and *** propose a hybrid DL model,combining BERT(Bidirectional Encoder Representations from Transformers)with BiLSTM(Bidirectional Long Short-Term Memory)and CNN(Convolutional Neural Networks)layers,to enhance classification *** analysis against state-of-the-art models demonstrates that our BERT-BiLSTM-CNN model achieves exceptional performance,with precision,recall,F1-score,and accuracy of 96%,87%,91%,and 94%,*** contributions of this work include a refined ABSA-based relabeling framework,the development of a highperformance classifier,and the comprehensive relabeling of the Instagram App Reviews *** advancements provide valuable insights for software developers to enhance usability and drive user-centric application development.

关键词： Requirements Engineering(RE) app review analysis usabilitymetrics hybrid deep learning BERT-BiLSTM-CNN

来源：评论

学校读者我要写书评

暂无评论

A Novel Reliable and Trust Objective Function for RPL-Based IoT Routing Protocol

引用

computers, Materials & Continua 2025年第2期82卷 3467-3497页

作者： Mariam A.Alotaibi Sami S.Alwakeel Aasem N.Alyahya Department of Computer Engineering College of Computer ScienceKing Saud UniversityRiyadh11543Saudi Arabia Department of Computer Science and Information Technology Shaqra UniversityShaqra11961Saudi Arabia

The Internet of Things (IoT) integrates diverse devices into the Internet infrastructure, including sensors, meters, and wearable devices. Designing efficient IoT networks with these heterogeneous devices requires the selection of appropriate routing protocols, which is crucial for maintaining high Quality of Service (QoS). The Internet Engineering Task Force’s Routing Over Low Power and Lossy Networks (IETF ROLL) working group developed the IPv6 Routing Protocol for Low Power and Lossy Networks (RPL) to meet these needs. While the initial RPL standard focused on single-metric route selection, ongoing research explores enhancing RPL by incorporating multiple routing metrics and developing new Objective Functions (OFs). This paper introduces a novel Objective Function (OF), the Reliable and Secure Objective Function (RSOF), designed to enhance the reliability and trustworthiness of parent selection at both the node and link levels within IoT and RPL routing protocols. The RSOF employs an adaptive parent node selection mechanism that incorporates multiple metrics, including Residual Energy (RE), Expected Transmission Count (ETX), Extended RPL Node Trustworthiness (ERNT), and a novel metric that measures node failure rate (NFR). In this mechanism, nodes with a high NFR are excluded from the parent selection process to improve network reliability and stability. The proposed RSOF was evaluated using random and grid topologies in the Cooja Simulator, with tests conducted across small, medium, and large-scale networks to examine the impact of varying node densities. The simulation results indicate a significant improvement in network performance, particularly in terms of average latency, packet acknowledgment ratio (PAR), packet delivery ratio (PDR), and Control Message Overhead (CMO), compared to the standard Minimum Rank with Hysteresis Objective Function (MRHOF).

关键词： IoT LLNs RPL objective function OF MRHOF OF0 routing metrics reliability trustworthiness

来源：评论

学校读者我要写书评

暂无评论

Dynamic Spatial Focus in Alzheimer’s Disease Diagnosis via Multiple CNN Architectures and Dynamic GradNet

引用

computers, Materials & Continua 2025年第5期83卷 2109-2142页

作者： Jasem Almotiri Department of Computer Science College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia

The evolving field of Alzheimer’s disease(AD)diagnosis has greatly benefited from deep learning models for analyzing brain magnetic resonance(MR)*** study introduces Dynamic GradNet,a novel deep learning model designed to increase diagnostic accuracy and interpretability for multiclass AD ***,four state-of-the-art convolutional neural network(CNN)architectures,the self-regulated network(RegNet),residual network(ResNet),densely connected convolutional network(DenseNet),and efficient network(EfficientNet),were comprehensively compared via a unified preprocessing pipeline to ensure a fair *** these models,EfficientNet consistently demonstrated superior performance in terms of accuracy,precision,recall,and F1 *** a result,EfficientNetwas selected as the foundation for implementing Dynamic *** GradNet incorporates gradient weighted class activation mapping(GradCAM)into the training process,facilitating dynamic adjustments that focus on critical brain regions associated with early dementia *** adjustments are particularly effective in identifying subtle changes associated with very mild dementia,enabling early diagnosis and *** model was evaluated with the OASIS dataset,which contains greater than 80,000 brain MR images categorized into four distinct stages of AD *** proposed model outperformed the baseline architectures,achieving remarkable generalizability across all *** findingwas especially evident in early-stage dementia detection,where Dynamic GradNet significantly reduced false positives and enhanced classification *** findings highlight the potential of Dynamic GradNet as a robust and scalable approach for AD diagnosis,providing a promising alternative to traditional attention-based *** model’s ability to dynamically adjust spatial focus offers a powerful tool in artificial intelligence(AI)assisted precisionmedicine,particularly in the early det

关键词： Spatial focus GradCAM medical image classification deep learning early dementia detection neurodegenerative disease MRI analysis Alzheimer’s attention CNN

来源：评论

学校读者我要写书评

暂无评论

Ensemble Deep Learning Approaches in Health Care:A Review

引用

computers, Materials & Continua 2025年第3期82卷 3741-3771页

作者： Aziz Alotaibi Department of Computer Science College of Computing and Information TechnologyTaif UniversityTaif21974Saudi Arabia

Deep learning algorithms have been rapidly incorporated into many different applications due to the increase in computational power and the availability of massive amounts of ***,both deep learning and ensemble learning have been used to recognize underlying structures and patterns from high-level features to make predictions/*** the growth in popularity of deep learning and ensemble learning algorithms,they have received significant attention from both scientists and the industrial community due to their superior ability to learn features from big *** deep learning has exhibited significant performance in enhancing learning generalization through the use of multiple deep learning *** ensemble deep learning has large quantities of training parameters,which results in time and space overheads,it performs much better than traditional ensemble *** deep learning has been successfully used in several areas,such as bioinformatics,finance,and health *** this paper,we review and investigate recent ensemble deep learning algorithms and techniques in health care domains,medical imaging,health care data analytics,genomics,diagnosis,disease prevention,and drug *** cover several widely used deep learning algorithms along with their architectures,including deep neural networks(DNNs),convolutional neural networks(CNNs),recurrent neural networks(RNNs),and generative adversarial networks(GANs).Common healthcare tasks,such as medical imaging,electronic health records,and genomics,are also ***,in this review,the challenges inherent in reducing the burden on the healthcare system are discussed and ***,future directions and opportunities for enhancing healthcare model performance are discussed.

关键词： Deep learning ensemble learning deep ensemble learning deep learning approaches for health care health care

来源：评论

学校读者我要写书评

暂无评论

CRT and PUF-based Self/Mutual-healing Key Distribution Protocol with Collusion Resistance and Revocation Capability

引用

IEEE Transactions on Mobile Computing 2025年第6期24卷 4607-4622页

作者： Othman, Wajdy Hong, Zhong Fuyou, Miao Xue, Kaiping Hawbani, Ammar Amin, Ruhul Zhao, Liang Li, Tao Nankai University Haihe Lab of ITAI College of Cyber Science Tianjin China Anhui University School of Computer Science and Technology China University of Science and Technology of China School of Computer Science and Technology School of Information Science and Technology Anhui Hefei China Shenyang Aerospace University School of Computer Science Shenyang110136 China Department of Computer Science & Engineering IIIT-NR China Nankai University Haihe Lab of ITAI College of Cyber Science China

Self-healing group key distribution (SGKD) protocols guarantee the security of group communications by allowing authorized users to independently recover missed previous session keys from the current broadcast without retransmission. However, existing SGKD protocols have flaws: (1) collusion resistance and revocable nodes are both upper-bounded by the degree of polynomials used, (2) the disclosure of personal secrets enables the recovery of group key, (3) temporary revocation of a group member is not possible, and (4) a revoked node may obtain the session key when initiating mutual healing, moreover, a malicious node may cause the recovery of false group keys. To address these limitations, we propose an SGKD protocol using the Chinese remainder theorem (CRT) and Physical Unclonable Function (PUF). Our proposed SGKD protocol generates a PUF-based dynamic secret by stimulating nodes' PUF using a polynomial-based encrypted challenge. This secret is then employed to retrieve a CRT-based encrypted group key. By combining PUF and CRT, we can generate dynamic secrets on the fly and reduce computation time significantly. Utilizing such a technique, our protocol achieves superior security goals, including resistance to any coalition of group nodes even if nodes' personal secrets were disclosed. Furthermore, the proposed protocol provides an unlimited number of revocable nodes. Additionally, a revoked node can rejoin its group in later sessions without affecting backward secrecy. Moreover, the protocol provides a backward secrecy guaranteed mutual-healing feature free from desynchronization. Our performance and security analyses (i.e., theorem-based formal analysis, NS3-based experiment, and formal verification using the AVIPSA tool) show that our proposed protocol achieves stronger security goals and better efficiency in terms of computation, communication, and storage costs compared to existing SGKD schemes. © 2002-2012 IEEE.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

Performance issue monitoring, identification and diagnosis of SaaS software:a survey

引用

Frontiers of computer science 2025年第1期19卷 71-95页

作者： Rui WANG Xiangbo TIAN Shi YING College of Mining and Safety Engineering Shandong University of Science and TechnologyQingdao 266590China School of Computer Science Wuhan UniversityWuhan 430072China

SaaS (Software-as-a-Service) is a service model provided by cloud computing. It has a high requirement for QoS (Quality of Software) due to its method of providing software service. However, manual identification and diagnosis for performance issues is typically expensive and laborious because of the complexity of the application software and the dynamic nature of the deployment environment. Recently, substantial research efforts have been devoted to automatically identifying and diagnosing performance issues of SaaS software. In this survey, we comprehensively review the different methods about automatically identifying and diagnosing performance issues of SaaS software. We divide them into three steps according to their function: performance log generation, performance issue identification and performance issue diagnosis. We then comprehensively review these methods by their development history. Meanwhile, we give our proposed solution for each step. Finally, the effectiveness of our proposed methods is shown by experiments.

关键词： SaaS software performance log generation performance issue identification performance issue diagnosis

来源：评论

学校读者我要写书评

暂无评论

A dynamic saliency enhanced fusion network for multimodal sleep recognition

引用

Multimedia Tools and Applications 2025年 1-26页

作者： Zhao, Aite Wu, Huimin Chen, Ming Wang, Nana College of Computer Science and Technology Qingdao University Ningxia Road Qingdao266071 China

Monitoring and identifying sleep postures, states or stages is a prerequisite for diagnosing sleep disorders, and provides crucial information for the treatment of sleep disorders. At present, there is no universal multimodal sleep recognition model, and most of the existing methods are limited to accurate modal sleep data. To address these challenges, we propose a dynamic saliency enhanced fusion network, which ranks the features based on data saliency and dynamically selects feature vectors with high attention and coherence, a two-block module is designed for multi-scale convolution and sequence features. We utilized datasets from three distinct sources (the Sleep Bioradiolocation Dataset, the Pressure Map Dataset, and the PSG Dataset), dataset-collecting over 100,000 training samples from dozens of healthy subjects and patients with Parkinson’s disease for our model to learn from. The experimental results show that the model has a 2% -3% improvement compared to existing algorithms, with a promising practical application prospects in sleep recognition applications such as smart healthcare and smart home. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Sleep research

来源：评论

学校读者我要写书评

暂无评论

Comprehensive study on object detection for security and surveillance: A concise review

引用

Multimedia Tools and Applications 2025年 1-32页

作者： Alamri, Faisal Department of Computer Science and Information Technology Jubail Industrial College Jubail Saudi Arabia

In recent years, object detection (OD) has become essential in computer vision for identifying and localizing objects in digital images, prompting various sectors to adopt this technology. However, increased reliance on OD has also revealed vulnerabilities to attacks, highlighting the need for effective detection methods to mitigate potential risks. Therefore, the present paper primarily surveys existing studies on OD in the context of security and surveillance, highlighting its significance in these critical areas. The discussion includes an examination of conventional techniques such as HOG, DPM, and the Viola‒Jones detector. While these traditional methods have laid the groundwork for object detection, they are often considered inadequate because of their time-consuming and labor-intensive nature. Consequently, the focus shifts to DL (deep learning)-based OD models such as YOLO (you only look once), single shot detector (SSD), and Fast R-CNN. Among these, the present survey paper emphasizes YOLO models for their speed and efficiency, as they utilize a unified architecture for both region proposal and classification, making them particularly suitable for real-time applications. However, the distinguishing feature of the proposed survey lies in its comprehensive coverage, which not only encompasses YOLO models but also integrates an analysis of generative AI (GenAI) models and metaheuristic approaches. This multifaceted exploration allows for a richer understanding of the current landscape in computer vision and AI, highlighting the synergies and potential applications that arise from combining these diverse methodologies. Furthermore, the paper explores a wide range of applications for OD in real-time security and surveillance settings, illustrating its effectiveness in addressing contemporary security challenges. This highlights how advanced OD techniques can enhance situational awareness and response capabilities in various scenarios. By focusing on these aspect

关键词： Object detection

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：