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

Pricing Policy for a Dynamic Spectrum Allocation Scheme with Batch Requests and Impatient Packets in Cognitive Radio Networks

引用

Journal of systems science and systems engineering 2022年第2期31卷 133-149页

作者： Haixing Wu Shunfu Jin Wuyi Yue School of Information Science and Engineering Yanshan UniversityQinhuangdao 066004China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Yanshan UniversityQinhuangdao 066004China Department of Intelligence and Informatics Konan UniversityKobe 658-8501Japan

In cognitive radio networks(CRNs),multiple secondary users may send out requests simultaneously and one secondary user may send out multiple requests at one time,i.e.,request arrivals usually show an aggregate ***,a secondary user packet waiting in the buffer may leave the system due to impatience before it is transmitted,and this impatient behavior inevitably has an impact on the system *** to investigate the influence of the aggregate behavior of requests and the likelihood of impatience on a dynamic spectrum allocation scheme in CRNs,in this paper a batch arrival queueing model with possible reneging and potential transmission interruption is *** constructing a Markov chain and presenting a transition rate matrix,the steady-state distribution of the queueing model along with a dynamic spectrum allocation scheme is derived to analyze the stochastic behavior of the ***,some important performance measures such as the loss rate,the balk rate and the average delay of secondary user packets are ***,system experiments are carried out to show the change trends of the performance measures with respect to batch arrival rates of secondary user packets for different impatience parameters,different batch sizes of secondary user packets,and different arrival rates of primary user ***,a pricing policy for secondary users is presented and the dynamic spectrum allocation scheme is socially optimized.

关键词： Cognitive radio networks dynamic spectrum scheme batch arrival impatient packets Markov chain social optimization

来源：评论

学校读者我要写书评

暂无评论

CapsNet-FR: Capsule Networks for Improved Recognition of Facial Features

引用

computers, Materials & Continua 2024年第5期79卷 2169-2186页

作者： Mahmood Ul Haq Muhammad Athar Javed Sethi Najib Ben Aoun Ala Saleh Alluhaidan Sadique Ahmad Zahid farid Department of Computer System Engineering University of Engineering&TechnologyPeshawar25000Pakistan College of Computer Science and Information Technology Al-Baha UniversityAlaqiq65779-7738Saudi Arabia REGIM-Lab:Research Groups in Intelligent Machines National School of Engineers of Sfax(ENIS)University of SfaxSfax3038Tunisia Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh84428Saudi Arabia EIAS:Data Science and Blockchain Laboratory College of Computer and Information SciencesPrince Sultan UniversityRiyadh11586Saudi Arabia Department of Computer Sciences Bahria University Karachi CampusKarachi541004Pakistan Department of Electrical Engineering Abasyn UniversityPeshawar25000Pakistan

Face recognition (FR) technology has numerous applications in artificial intelligence including biometrics, security,authentication, law enforcement, and surveillance. Deep learning (DL) models, notably convolutional neuralnetworks (CNNs), have shown promising results in the field of FR. However CNNs are easily fooled since theydo not encode position and orientation correlations between features. Hinton et al. envisioned Capsule Networksas a more robust design capable of retaining pose information and spatial correlations to recognize objects morelike the brain does. Lower-level capsules hold 8-dimensional vectors of attributes like position, hue, texture, andso on, which are routed to higher-level capsules via a new routing by agreement algorithm. This provides capsulenetworks with viewpoint invariance, which has previously evaded CNNs. This research presents a FR model basedon capsule networks that was tested using the LFW dataset, COMSATS face dataset, and own acquired photos usingcameras measuring 128 × 128 pixels, 40 × 40 pixels, and 30 × 30 pixels. The trained model outperforms state-ofthe-art algorithms, achieving 95.82% test accuracy and performing well on unseen faces that have been blurred orrotated. Additionally, the suggested model outperformed the recently released approaches on the COMSATS facedataset, achieving a high accuracy of 92.47%. Based on the results of this research as well as previous results, capsulenetworks perform better than deeper CNNs on unobserved altered data because of their special equivarianceproperties.

关键词： CapsNet face recognition artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of RouteSegmentation Algorithm in Identifying Perimeter Area Around Travel Route 16

Performance Analysis of RouteSegmentation Algorithm in Ident...

引用

16th International Conference on information Technology and Electrical engineering, ICITEE 2024

作者： Bachmid, Muhammad Avied Anshari Haq, Muhammad Yasir Mumtaz, Muhammad Rafly Pinandito, Aryo Universitas Brawijaya Faculty of Computer Science Media Game and Mobile Laboratory Department of Informatics Engineering Malang Indonesia Universitas Brawijaya Faculty of Computer Science Malang Indonesia Universitas Brawijaya Faculty of Computer Science Media Game and Mobile Laboratory Department of Information System Malang Indonesia

ISBN: (纸本)9798350375817

Prior study has developed the RouteSegmentation algorithm to identify the perimeter area surrounding a route. In this study, a comparative experiment was carried out to investigate the performance of the RouteSegmentation algorithm implementation in contrast to the RouteBoxer algorithm. Both algorithms play a crucial role in geographical information systems (GIS), particularly in enhancing navigational tools by identifying points of interest along specified routes. Through systematic experimentation using various perimeter distance values and types of route, the trade-offs between processing efficiency and the granularity of the area identified by these algorithms were evaluated. The results demonstrate that RouteSegmentation maintained relatively consistent performance across different perimeter distance values and statistically significantly faster processing time than RouteBoxer. Furthermore, while the RouteBoxer algorithm benefits from larger perimeter distance values by reducing processing time, it compromises the coverage results of the algorithm and potentially undermines its usefulness in practical scenarios. This study not only provides insights into the optimal use of perimeter distance values for each algorithm but also guides users in selecting the appropriate algorithm based on their specific application needs, balancing detailed geographical analysis and runtime efficiency. © 2024 IEEE.

关键词： Transportation routes

来源：评论

学校读者我要写书评

暂无评论

Intelligent Computational Model for Energy Efficiency and AI Automation of Network Devices in 5G Communication Environment

引用

Tsinghua science and Technology 2024年第6期29卷 1728-1751页

作者： Ashish Bagwari Jaganathan Logeshwaran M.Raja P.Devisivasankari Jyotshana Bagwari Vikas Rathi Asma Mohammed Elbashir Saad Department of Electronics and Communication Engineering Uttarakhand Technical UniversityDehradun 248007India Department of Electronics and Communication Engineering Sri Eshwar College of EngineeringCoimbatore 641202India Department of Computer Science and Engineering CMR Institute of TechnologyKarnataka 560037India Department of Information Science and Engineering CMR Institute of TechnologyKarnataka 560037India Advanced and Innovative Research Laboratory Dehradun 248001India Department of Electronics and Communication Engineering Graphic Era(Deemed to be University)Dehradun 248007India Department of Physics College of Science and HumanitiesPrince Sattam Bin Abdulaziz UniversityAl-Kharj 16273Saudi Arabia

Currently, the 4G network service has caused massive digital growth in high use. Video calling has become the go-to Internet application for many people, downloading even huge files in minutes. Everyone is looking for and buying only 4G Subscriber Identity Module (SIM)-capable mobiles. In this case, the expectation of 5G has increased in line with 2G, 3G, and 4G, where the G stands for generation, and it does not indicate Internet or Internet speed. 5G includes next-generation features that are more advanced than those available in 4G network services. The main objective of 5G is uninterrupted telecommunication service in hybrid energy storage system. This paper proposes an intelligent networking model to obtain the maximum energy efficiency and Artificial Intelligence (AI) automation of 5G networks. There is currently an issue where the signal cuts out when crossing an area with one tower and traveling to an area with another tower. The problem of “call drop”, where the call is disconnected while talking, is not present in 5G. The proposed Intelligent Computational Model (ICM) model obtained 96.31% network speed management, 90.63% battery capacity management, 92.27% network device management, 93.57% energy efficiency, and 88.41% AI automation.

关键词： hybrid energy storage system 4G digital growth 5G downloading Subscriber Identity Module(SIM) generation network energy efficiency Artificial Intelligence(Al)automation

来源：评论

学校读者我要写书评

暂无评论

MLPFormer: MLP-integrated transformer for colorectal histopathology whole slide image segmentation

引用

Neural Computing and Applications 2025年第6期37卷 4651-4661页

作者： Wang, Yuxuan Li, Dan Li, Xuechen Guo, Yan Zuo, Yanfei Shen, Linlin Department of Computer Science Wenzhou-Kean University Wenzhou China School of Electronics and Information Engineering Wuyi University Jiangmen China Department of Histo Pathology Shanghai Histo Pathology Diagnostic Center Shanghai China College of Computer Sicence and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

Colorectal intraepithelial neoplasia is a precancerous lesion of colorectal cancer, which is mainly diagnosed using pathological images. According to the characteristics of lesions, precancerous lesions can be classified into four different grades, i.e., background, normal, low and high level. However, due to the continuity of lesion development, tissue in different stages has high similarity. Recently, visual transformers have achieved impressive results in different visual tasks, due to their capacity of capturing long-range dependencies. However, due to computational cost, transformer cannot well extract detailed feature, which is important for lesion grading. To accurately segment pathological tissues with high similarity, in this work, we embed the multi-head MLP mixer module in the transformer network to extract cell and edge information. Furthermore, we propose a hierarchical MLP decoder to facilitate multi-scale feature fusion. The proposed transformer, namely MLPFormer, achieves remarkable results against competitive baselines on the Histo-CRC Biopsy dataset. The experimental results demonstrate that MLPFormer significantly outperforms the competitive baselines, i.e., a 3% dice improvement is achieved over the SegFormer series. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

LASS: A Novel and Economical Data Augmentation Framework Based on Language Models for Debiasing Opinion Summarization 31

LASS: A Novel and Economical Data Augmentation Framework Bas...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Zhang, Yanyue Li, Pengfei Lai, Yilong He, Yulan Zhou, Deyu School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China Department of Informatics King's College London United Kingdom The Alan Turing Institute United Kingdom

ISBN: (纸本)9798891761964

As more than 70% of reviews in the existing opinion summary data set are positive, current opinion summarization approaches are hesitant to generate negative summaries given the input of negative texts. To address such sentiment bias, a direct approach without the reliance on a specific structure is to generate additional data based on large language models to balance the emotional distribution of the dataset. However, large-scale data augmentation based on large language models faces an apparent disadvantage, the expensive costs. Therefore, in this paper, we propose LASS, a novel data augmentation framework based on both LArge and Small language models for debiaSing opinion summarization. Specifically, a small number of synthesized negative reviews is obtained by rewriting the positive text via a large language model. Then, a disentangle reconstruction model is trained based on the generated data. After training, a large amount of synthetic data can be obtained by decoding the new representation obtained from the combination of different sample representations and filtering based on perplexity degree and sentiment classification. Experiments have proved that LASS can effectively alleviate emotional bias, similar to using only large models, but in a more economical way. © 2025 Association for Computational Linguistics.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

Protecting machine learning systems using blockchain: solutions, challenges and future prospects

引用

Multimedia Tools and Applications 2024年 1-28页

作者： Hajlaoui, Rejab Dhahri, Salah Mahfoudhi, Sami Moulahi, Tarek Alotibi, Gaseb Department of Computer and Informtion Sciences College of Computer Science and Engineering University of Hail Hail City Saudi Arabia Laboratory of Advanced Multifunctional Materials and Technological Applications Faculty of Science and Technology of Sidi Bouzid University of Kairouan Sidi Bouzid Tunisia Department of Information and Technology Management Mediterranean School of Business South Mediterranean University Tunis Tunisia Department of Information Technology College of Computer Qassim University Buraidah Saudi Arabia Department of Computers and Information Technology Alwajah College University of Tabuk Tabuk Saudi Arabia

Machine learning-based systems have emerged as the primary means for achieving the highest levels of productivity and efficiency. They have become the most influential competitive factor for many technologies and business companies such as Cloud AI Companies (Google, Facebook…) and Health Care AI Companies (Tempus, Nanox …). However, privacy and security issues have become the biggest challenge facing all ML applications. These threats are known as Adversarial Machine Learning (AML). Their main goal is to maliciously manipulate training data and model parameters to obtain misleading results. To overcome these challenges, several research studies have proven that Blockchain, which relies on cryptographic technologies, constitutes a promising solution for securing ML applications. It provides high guarantees to make the system scalable, reliable and more secure. In this survey, we provide an overview of ML applications and the most hostile attacks they face. Then, we define the blockchain technique and its distinctive features. After that, we conduct a comprehensive and detailed survey of the latest and best blockchain-based research to address security issues in ML applications (integrity, confidentiality and availability). We analyze, compare and comment on all the proposed solutions. In the end, we discuss in detail the various challenges that hinder the adoption of blockchain technology and we extract the most important scientific trends that will serve as guidance and support for researchers in their future works. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

UAV-Assisted Dynamic Avatar Task Migration for Vehicular Metaverse Services: A Multi-Agent Deep Reinforcement Learning Approach

引用

IEEE/CAA Journal of Automatica Sinica 2024年第2期11卷 430-445页

作者： Jiawen Kang Junlong Chen Minrui Xu Zehui Xiong Yutao Jiao Luchao Han Dusit Niyato Yongju Tong Shengli Xie IEEE School of Automation Guangdong University of TechnologyGuangzhou 510006China 111 Center for Intelligent Batch Manufacturing based on IoT Technology Guangzhou 510006China Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of EducationGuangzhou 510006China School of Computer Science and Engineering Nanyang Technological UniversitySingaporeSingapore Pillar of Information Systems Technology and Design Singapore University of Technology and DesignSingaporeSingapore College of Communication Engineering Army Engineering University of PLANanjing 210007China National Natural Science Foundation of China Beijing 100085China Key Laboratory of Intelligent Detection and IoT in Manufacturing Ministry of EducationGuangzhou 510006China Guangdong Key Laboratory of IoT Information Technology Guangzhou 510006China

Avatars, as promising digital representations and service assistants of users in Metaverses, can enable drivers and passengers to immerse themselves in 3D virtual services and spaces of UAV-assisted vehicular Metaverses. However, avatar tasks include a multitude of human-to-avatar and avatar-to-avatar interactive applications, e.g., augmented reality navigation,which consumes intensive computing resources. It is inefficient and impractical for vehicles to process avatar tasks locally. Fortunately, migrating avatar tasks to the nearest roadside units(RSU)or unmanned aerial vehicles(UAV) for execution is a promising solution to decrease computation overhead and reduce task processing latency, while the high mobility of vehicles brings challenges for vehicles to independently perform avatar migration decisions depending on current and future vehicle status. To address these challenges, in this paper, we propose a novel avatar task migration system based on multi-agent deep reinforcement learning(MADRL) to execute immersive vehicular avatar tasks dynamically. Specifically, we first formulate the problem of avatar task migration from vehicles to RSUs/UAVs as a partially observable Markov decision process that can be solved by MADRL algorithms. We then design the multi-agent proximal policy optimization(MAPPO) approach as the MADRL algorithm for the avatar task migration problem. To overcome slow convergence resulting from the curse of dimensionality and non-stationary issues caused by shared parameters in MAPPO, we further propose a transformer-based MAPPO approach via sequential decision-making models for the efficient representation of relationships among agents. Finally, to motivate terrestrial or non-terrestrial edge servers(e.g., RSUs or UAVs) to share computation resources and ensure traceability of the sharing records, we apply smart contracts and blockchain technologies to achieve secure sharing management. Numerical results demonstrate that the proposed approach

关键词： Avatar blockchain metaverses multi-agent deep reinforcement learning transformer UAVs

来源：评论

学校读者我要写书评

暂无评论

Polarization-induced photocurrent switching effect in heterojunction photodiodes

引用

Nano Research 2023年第4期16卷 5503-5510页

作者： Dingbo Chen Yu-Chang Chen Guang Zeng Yu-Chun Li Xiao-Xi Li Dong Li Chao Shen Nan Chi Boon S.Ooi David Wei Zhang Hong-Liang Lu State Key Laboratory of ASIC and System Shanghai Institute of Intelligent Electronics&SystemsSchool of MicroelectronicsFudan UniversityShanghai 200433China Key Laboratory for Information Science of Electromagnetic Waves Department of Communication Science and EngineeringFudan UniversityShanghai 200433China Photonics Laboratory Division of ComputerElectricaland Mathematical Sciences and EngineeringKing Abdullah University of Science and Technology(KAUST)Thuwal 23955-6900Kingdom of Saudi Arabia

The unipolar photocurrent in conventional photodiodes(PDs)based on photovoltaic effect limits the output modes and potential versatility of these devices in *** photodiodes with photocurrent switching are emerging as a promising solution for obtaining photoelectric devices with unique and attractive functions,such as optical logic ***,we design an all-solid-state chip-scale ultraviolet(UV)PD based on a hybrid GaN heterojunction with engineered bipolar polarized electric *** introducing the polarization-induced photocurrent switching effect,the photocurrent direction can be switched in response to the wavelength of incident light at 0 V *** particular,the photocurrent direction exhibits negative when the irradiation wavelength is less than 315 nm,but positive when the wavelength is longer than 315 *** device shows a responsivity of up to−6.7 mA/W at 300 nm and 5.3 mA/W at 340 nm,*** particular,three special logic gates in response to different dual UV light inputs are demonstrated via a single bipolar PD,which may be beneficial for future multifunctional UV photonic integrated devices and systems.

关键词： GaN heterostructure ultraviolet(UV)photodiodes bipolar photocurrent optical logic device

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：