检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Chen, Yun-Chih Chang, Yuan-Hao Kuo, Tei-Wei The Department of Computer Science TU Dortmund Germany The Institute of Information Science Academia Sinica Taipei115 Taiwan Department of Computer Science and Information Engineering High Performance and Scientific Computing Center Center of Data Intelligence: Technologies Applications and Systems of National Taiwan University Taiwan

To index the increasing volume of data, modern data indexes are typically stored on SSDs and cached in DRAM. However, searching such an index has resulted in significant I/O traffic due to limited access locality and inefficient cache utilization. At the heart of index searching is the operation of filtering through vast data spans to isolate a small, relevant subset, which involves basic equality tests rather than the complex arithmetic provided by modern CPUs. We introduce the Search-in-Memory (SiM) chip, which demonstrates the feasibility of performing data filtering directly within a NAND flash memory chip, transmitting only relevant search results rather than complete pages. Instead of adding complex circuits, we propose repurposing existing circuitry for efficient and accurate bitwise parallel matching. We demonstrate how different data structures can use our flexible SIMD command interface to offload index searches. This strategy not only frees up the CPU for more computationally demanding tasks, but it also optimizes DRAM usage for write buffering, significantly lowering energy consumption associated with I/O transmission between the CPU and DRAM. Extensive testing across a wide range of workloads reveals up to a 9X speedup in write-heavy workloads and up to 45% energy savings due to reduced read and write I/O. Furthermore, we achieve significant reductions in median and tail read latencies of up to 89% and 85% respectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Message Verification Protocol Based on Bilinear Pairings and Elliptic Curves for Enhanced Security in Vehicular Ad Hoc Networks

引用

Computers, Materials & Continua 2024年第10期81卷 1029-1057页

作者： Vincent Omollo Nyangaresi Arkan A.Ghaib Hend Muslim Jasim Zaid Ameen Abduljabbar Junchao Ma Mustafa A.Al Sibahee Abdulla J.Y.Aldarwish Ali Hasan Ali Husam A.Neamah Department of Computer Science and Software Engineering Jaramogi Oginga Odinga University of Science and TechnologyBondo40601Kenya Department of Applied Electronics Saveetha School of EngineeringSIMATSChennaiTamilnadu602105India Information Technology Department Management Technical CollegeSouthern Technical UniversityBasrah61004Iraq Department of Computer Science College of Education for Pure SciencesUniversity of BasrahBasrah61004Iraq College of Big Data and Internet Shenzhen Technology UniversityShenzhen518118China Huazhong University of Science and Technology Shenzhen InstituteShenzhen518000China National Engineering Laboratory for Big Data System Computing Technology Shenzhen UniversityShenzhen518060China Computer Technology Engineering Department Iraq University CollegeBasrah61004Iraq Department of Mathematics College of Education for Pure SciencesUniversity of BasrahBasrah61004Iraq Institute of Mathematics University of DebrecenDebrecenH-4002Hungary Department of Electrical Engineering and Mechatronics Faculty of EngineeringUniversity of DebrecenDebrecen4028Hungary

Vehicular ad hoc networks(VANETs)provide intelligent navigation and efficient route management,resulting in time savings and cost reductions in the transportation ***,the exchange of beacons and messages over public channels among vehicles and roadside units renders these networks vulnerable to numerous attacks and privacy *** address these challenges,several privacy and security preservation protocols based on blockchain and public key cryptography have been proposed ***,most of these schemes are limited by a long execution time and massive communication costs,which make them inefficient for on-board units(OBUs).Additionally,some of them are still susceptible to many *** such,this study presents a novel protocol based on the fusion of elliptic curve cryptography(ECC)and bilinear pairing(BP)*** formal security analysis is accomplished using the Burrows–Abadi–Needham(BAN)logic,demonstrating that our scheme is verifiably *** proposed scheme’s informal security assessment also shows that it provides salient security features,such as non-repudiation,anonymity,and ***,the scheme is shown to be resilient against attacks,such as packet replays,forgeries,message falsifications,and *** the performance perspective,this protocol yields a 37.88%reduction in communication overheads and a 44.44%improvement in the supported security ***,the proposed scheme can be deployed in VANETs to provide robust security at low overheads.

关键词： Attacks bilinear elliptic curve cryptography(ECC) privacy security vehicular ad hoc network(VANET)

来源：评论

学校读者我要写书评

暂无评论

Extending Whisper for Emotion Prediction Using Word-level Pseudo Labels

Extending Whisper for Emotion Prediction Using Word-level Ps...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Chin Yuen Kwok Sheng Li Jia Qi Yip Chenhui Chu Tatsuya Kawahara Eng Siong Chng Digital Trust Centre Nanyang Technological University Singapore College of Computing and Data Science Nanyang Technological University Singapore National Institute of Information & Communications Technology (NICT) Japan Kyoto University Japan

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

This paper extends Whisper’s automatic speech recognition (ASR) capabilities to perform speech-based emotion recognition (SER) by incorporating word-level emotion classification alongside ASR output. We generate four emotion pseudo-labels (neutral, happy, sad, angry) for each word using a pretrained frame-level SER model, and Whisper is fine-tuned for joint ASR and emotion classification at the word level. Sentence-level emotion labels are masked during training to encourage the transformer to use the ASR output for word-level emotion prediction. During inference, word-level predictions are combined with sentence-level predictions through majority voting to generate the final sentence-level label. When evaluated on the IEMOCAP dataset, our method maintains Whisper’s ASR word error rate while improving the SER weighted accuracy from 74.4% to 76.4% and the unweighted average recall from 77.1% to 79.0%.

关键词： Training Emotion recognition Accuracy Error analysis Signal processing Predictive models Transformers Acoustics Speech processing Automatic speech recognition

来源：评论

学校读者我要写书评

暂无评论

Study on Improved YOLOv7-based Algorithm for Detecting Crack Defects in Ancient Buildings 24

Study on Improved YOLOv7-based Algorithm for Detecting Crack...

引用

3rd International Conference on Computer, Artificial Intelligence and Control Engineering, CAICE 2024

作者： Fang, Tianke Hui, Zhenxing Rey, William P Xie, Zhiying Yang, Aihua He, Yuanrong School of Information Technology Mapua University Manila1200 Philippines Big Data Institute of Digital Natural Disaster Monitoring in Fujian Xiamen University of Technology Xiamen Fujian361024 China School of Computing and Information Engineering Xiamen University of Technology Xiamen Fujian361024 China School of Information Media Zhangzhou Vocational College of Science and Technology Zhangzhou Fujian363200 China Hunan Key Laboratory of Remote Sensing Monitoring of Ecological Environment Dongting Lake Area Changsha Hunan410004 China

ISBN: (纸本)9798400716942

In the protection and restoration work of ancient buildings, the detection and analysis of the cracks and defects of the exterior walls of ancient buildings is a crucial task. In this paper, an improved YOLOv7 algorithm is proposed to detect the defects of ancient external walls, aiming to achieve efficient and accurate detection of the defects of ancient external walls. The method involves preprocessing the image using a rectangle clipping algorithm, graying the image using the maximum method, and denoising the image with a median filter. Next, the image is labeled using the LabelImg tool, and the data is split into training, validation, and test sets. During model training, a CBAM-Net module is inserted after several CBS modules in the backbone network, the GIOU loss function is replaced by CIOU, and feature task extraction is performed. The realized attention mechanism is added to the Yolov7 model. The results show that the mAP value of crack detection after the improved algorithm reaches 81.2%. In contrast to the initial YOLOv7 algorithm, the precision of the model has been boosted to 87.2%, exhibiting a 6.0% enhancement in accuracy and an 85.2% improvement in recall rate. The improved YOLOv7 crack detection algorithm reduces network calculation and improves crack classification and recognition ability. This approach is crucial in safeguarding ancient buildings as it enables varying levels of maintenance depending on the severity of cracks. © 2024 ACM.

关键词： Attention mechanism Deep learning Defect detection Image processing YOLOv7

来源：评论

学校读者我要写书评

暂无评论

Predicting Microsatellite Instability from Histology Images with Dilated Neighborhood Attention Transformer in Colorectal Cancer 24

Predicting Microsatellite Instability from Histology Images ...

引用

24th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2024

作者： Chen, Yun-Chi Chao, Tung Phandita, Wimaya Nitya Sun, Tzu-Yu Wang, Huai-Zhi Hsieh, Yi-Hsien Hsu, Le-Yin Lin, Che Taipei Taiwan College of Bioresources and Agriculture NTU Taipei Taiwan National Taiwan University of Science and Technology Department of Computer Science and Information Engineering Taipei Taiwan Graduate Institute of Communication Engineering NTU Taipei Taiwan NTU Data Science Degree Program Taipei Taiwan NTU Department of Electrical Engineering Taipei Taiwan Center for Advanced Computing and Imaging in Biomedicine NTU Taipei Taiwan NTU Smart Medicine and Health Informatics Program Taipei Taiwan

ISBN: (纸本)9798331518622

Microsatellite instability (MSI) is a pivotal genetic marker influencing the efficacy of immunotherapy in colorectal cancer. Traditional MSI examination often requires additional genetic or immunohistochemical tests, whereas histology images, widely available in colorectal cancer diagnosis, offer a valuable alternative for MSI prediction. Although Transformer-based models have demonstrated promising outcomes in predicting MSI from histology images, they are hampered by traditional local attention mechanisms that struggle to capture long-range interdependencies and establish a comprehensive global receptive field. In this study, we introduce DiNAT-MSI, a novel framework for histology-based MSI prediction that incorporates the Dilated Neighborhood Attention Transformer (DiNAT). This model enhances global context recognition and substantially expands receptive fields, all without additional computational burden. Our results demonstrate that DiNAT-MSI achieves a superior patientwise AUROC compared to ResNet18 and Swin Transformer, along with commendable explainability. Our work not only illustrates a more accessible diagnostic tool for leveraging histological data but also underscores the potential of Transformerbased models with sophisticated attention designs in advancing precision medicine for colorectal cancer patients. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Stock Market Prediction Using Machine Learning Based Techniques

Stock Market Prediction Using Machine Learning Based Techniq...

引用

Intelligent Signal Processing and Effective Communication Technologies (INSPECT), IEEE International Conference on

作者： Aditya Dubey Ramnaresh Sharma Dhananjay Bisen Nookala Venu Varshali Jaiswal Bhagat Singh Raghuwanshi Khemchand Shakywar Centre for Internet of Things Madhav Institute of Technology & Science Gwalior India Centre for AI Madhav Institute of Technology & Science Gwalior India Data Science and Quantum Computing ABV Indian Institute of Information Technology and Management Gwalior India School of Engineering Avantika University Ujjain MP

ISBN: (数字)9798350379525

ISBN: (纸本)9798350379532

Many methods have been used to forecast stock market trends in the big data age, including real numbers, fuzzy time series data, fuzzy sets design, and conventional time series data. The control of semantic value data is made possible by the use of fuzzy time series data in stock market prediction, which makes accurate value predictions possible. These techniques are mostly used to forecast dynamic, non-linear datasets in a variety of industries, such as stock markets and cryptocurrencies. In order to predict stock prices, artificial intelligence (AI) methods such as neural networks (NN) have become increasingly important. Many methods have been developed to validate parametric and non-parametric theories for predicting trends and gains in the stock market using the feed-forward (FF) NN technique. A variety of soft computing techniques have been investigated in order to provide ways for decision-making based on profit and loss criteria without relying on artificial intelligence. This paper's main goal is to perform a comprehensive examination of the different prediction techniques used to estimate price and return in the stock market. The study includes a comparative review of several approaches as well as a variety of stock market forecasting strategies.

关键词： Computational modeling Time series analysis Signal processing algorithms Predictive models Prediction algorithms Market research Vectors Stock markets Forecasting Investment

来源：评论

学校读者我要写书评

暂无评论

Impurity explicit optimal Machine learning and statistical perfect construction for air quality prediction 2

Impurity explicit optimal Machine learning and statistical p...

引用

2nd IEEE International Conference on Networking and Communications, ICNWC 2024

作者： Nareshkumar, R. Shalinikumari, R. Kowsalya, S. Sri Nandhini Vijay Anand, P. Mohamed, Ajmal Gayathri, S. SRM Institute of Science and Technology School of Computing College of Engineering and Technology Department of Networking and Communications Tamilnadu Kattankulathur India Bharath Institute of Higher Education and Research Selaiyur Department of Architecture Tamilnadu Chennai India Veltech Multitech Dr.Rangarajan Dr.Sakunthala Engineering College Department of Information Technology Tamilnadu Chennai India CMR Institute of Technology Department of Artificial Intelligence and Data Science Bengaluru India Saveetha School of Engineering Department of Computer Science and Engineering Chennai India K. Ramakrishnan College of Technology Department of Computer Science and Engineering Tamilnadu Trichy India

ISBN: (纸本)9798350365269

The air quality index (AQI) is a metric used to report air quality levels. There has been a substantial rise in the level of air pollution in Indian cities. Multiple methodologies exist for formulating a mathematical equation to ascertain the air quality index. Multiple studies have established a correlation between exposure to air pollution and negative health effects in the general population. The objective of this study is to determine the optimal approach for predicting AQI in order to aid in climate regulation. Nine separate Machine learning (ML) algorithms have been employed in the suggested study to ascertain the AQI. The use of the SMOTE algorithm in the datasets in ML resulted in improved accuracy when comparing the outcomes. Furthermore, all of the implementations have been thoroughly documented using graphs and metrics, which clearly illustrate the differences in outcomes and aid in identifying the specific factors that led to the improvement in accuracy. © 2024 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Blockchain-based data Sharing Framework for Malaysia Government Aid Management System

Blockchain-based Data Sharing Framework for Malaysia Governm...

引用

2023 International Conference on Digital Applications, Transformation and Economy, ICDATE 2023

作者： Azmi, Azman Yahya, Farashazillah Moung, Ervin Gubin Sallehudin, Hasimi Utomo, Rio Guntur Azman, Nur Afrina Universiti Malaysia Sabah Advanced Machine Intelligence Research Lab Faculty of Computing and Informatics Sabah Kota Kinabalu Malaysia Universiti Malaysia Sabah Data Technologies and Application Research Lab Faculty of Computing and Informatics Sabah Kota Kinabalu Malaysia Universiti Kebangsaan Malaysia Centre for Software Technology and Management Faculty of Information Science and Technology Malaysia Telkom University School of Computing Bandung Indonesia Foundation Study and Language Institute University of Reading Malaysia Johor Iskandar Puteri Malaysia

ISBN: (纸本)9798350310689

The Covid-19 pandemic has impacted the world economy, and Malaysia is no exception. Due to the closure of businesses, the rate of unemployment has been recorded at an all-time high. The Malaysian Government through its agencies is assisting citizens through an online platform for incentives and an aid-giving platform. The current architecture of data sharing is using centralized, organization-oriented authentication and is not immutable for audit capability. In addition, the blockchain network is still a proof of concept in the digital government ecosystem. This paper studies the current aid data-sharing ecosystem and analyzes the potential of having a state government consortium blockchain framework that will be used in the Government Network Infrastructure for decentralized, transparent data sharing with audit capability. Several works involving Blockchain adoption based on domain, Blockchain consortium architecture and Government applications using blockchain are being presented. The need for a framework in implementing decentralized data sharing using consortium blockchain architecture for multi-agencies data sharing focusing on Malaysia Government Aid Management is discussed in this paper to provide the opportunity for the research domain. The findings in this paper will be used for future work on the requirement of a proposed government multi-layer consortium blockchain framework for data sharing in the Malaysian Government specifically for the Johore State Government ecosystem. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Exploring the Impact of IoT data Diversity on Machine Learning Model

Exploring the Impact of IoT Data Diversity on Machine Learni...

引用

Sustainable Communication Networks and Application (ICSCNA), International Conference on

作者： Dhananjay Bisen Nookala Venu Aditya Dubey Priyanka Garg Suresh Salendra T. Lakshmi Devi Center for Internet of Things Madhav Institute of Technology & Science Gwalior M.P India Data Science and Quantum Computing ABV Indian Institute of Information Technology and Management Gwalior M.P India Dept. of Compter Science and Engineering Balaji Institute of Technology & Science Warangal Telangana India Dept.of CSE-Data Science Siddhartha Institute of Engineering and Technology Hyderabad India

ISBN: (数字)9798331530013

ISBN: (纸本)9798331530020

The past few years have witnessed a remarkable change by the rapid expansion of the Internet of Things (IoT). The increasing spread of networked devices in various areas of the Internet of Things has resulted in a huge amount of machine data. This data contains rich information that can be harnessed across domains such as healthcare, agriculture, smart cities, and manufacturing. To effectively analyze and capitalize this information, the integration of machine learning (ML) methods is essential. Thus, well-known machine learning techniques including Logistic Regression, Decision Tree, KNN, SVM, Random Forest, and Naive Bayes are used in paper. The performance of the algorithms is analyzed using three diverse IoT datasets and compared to one another using pre-defined measures such as accuracy, precision, recall, F1-score and execution time. Furthermore, test findings shown that the random forest algorithm consistently outperformed other algorithms for a variety of datasets with up to 98% accuracy.

关键词： Support vector machines Logistic regression Accuracy Machine learning algorithms Nearest neighbor methods Real-time systems Bayes methods Internet of Things Decision trees Random forests

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Felsenstein Method to Reinvigorate Phylogenetic Starting in the Big data 6

Enhancing the Felsenstein Method to Reinvigorate Phylogeneti...

引用

6th International Conference on Contemporary computing and Informatics, IC3I 2023

作者： Saxena, Ashendra Kumar Vishwkarma, Priyanka Kumar, Sandeep Thangarasu, N. Bhuvaneshwari, K.S. Ashok, Bhandari Mahesh College of Computing Science and Information Technology Teerthankar Magaveer University Uttar Pradesh Moradabad India Invertis University Department of Computer Science & Engineering Uttar Pradesh Bareilly India School of Commerce and Management IIMT University Uttar Pradesh Meerut India Karpagam Academy of Higher Education Department of Computer Science Tamil Nadu Coimbatore India Karpagam College of Engineering Department of Artificial Intelligence and Data Science Tamilnadu Coimbatore India Vishwakarma Institute of Information Technology Maharashtra Pune India

ISBN: (纸本)9798350304480

The present research examines how the Felsenstein approach might be improved in light of huge data and evolutionary inference. The Felsenstein approach, phylogeny starting points, huge data, statistical techniques, and testing hypotheses are among the important ideas and terms covered in the overview. It emphasizes the importance of repeatability in evolutionary inferences as well as the difficulties brought on by rogue genera and bootstrapping proportions. The article suggests a brand-new strategy to increase the accuracy of phylogenetic investigations that makes use of transfer separation and bipartition distance. The abstract's conclusion emphasizes the need of better methods for managing huge datasets and for recognizing instability taxonomic. © 2023 IEEE.

关键词： ABC Between trees Big data Bipartition distance Bootstrap Confidence intervals Felsenstein method Homogenization Hypothesis testing Phylogenetic estimation Phylogenetic starting Reboot method Rogue taxa Statistical approach Taxonomic units Transfer distance

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：