检索结果-内蒙古大学图书馆

2nd International Conference on Artificial Intelligence and Smart Energy, ICAIS 2022

作者： Dinesh, G. Singh, Amarjeet Shinz, Nehar Sravanya, Mogalluru Venkata Agrawal, Gaurangi Srm Institute of Science and Technology School of Computing Department of Computational Intelligence Kattankulathur Chennai India New Horizon College of Engineering Department of Computer Science Engineering Bangalore India

ISBN: (纸本)9781665400527

This paper involves utilizing modules to create an efficient and accurate machine learning face mask detection model that can give an accuracy close to 100 percent and a value loss of less than 5%. This paper sees up to the fact that it is the local clusters that need to take care of themselves and this is what will eventually help the society on the larger scale as a whole and aims to aid the concerning authorities in keeping their crowd wearing masks at their respective premises. This is done by programming a system that can recognize the visuals from a camera at the entrance of such premises flagging offenders who do not wear a face mask and notifying authorities as it happens. This can be implemented in private organizations like educational institutions or company offices making it possible to combine it with a facial recognition model thereby notifying the offenders themselves via their cell phones by fetching their information from database resources that would be already existing in the case of these private organizations. © 2022 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Emotion Detection from EEG Signals for Human-Machine Interaction 5

Deep Learning-Based Emotion Detection from EEG Signals for H...

引用

5th International Conference on Information Management and Machine Intelligence, ICIMMI 2023

作者： Raj, Saurabh Sakhare, Nitin N. Sharma, Yogesh Soni, Monika Bhange, Anup Deshmukh, Pradeep Kundlik Pune India Department of Computer Engineering BRACT'S Vishwakarma Institute of Information Technology Maharashtra Pune India VIIT Pune India Auricle Global Society of Education and Research Sudarshan Nagar Rajasthan Bikaner India Department of Computer Science & Engineering KDK College of Engineering Maharashtra Nagpur India Department of Computer Science and Engineering School of Computational Sciences COEP Technological University Pune India

ISBN: (纸本)9798400709418

Detecting emotions helps create more intuitive and responsive technology interfaces between humans and machines. This study introduces deep learning-based emotion detection using EEG signals. Our research uses Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM) networks, and a proposed hybrid of CNN and LSTM (ConvLSTM) along with Particle Swarm Optimization (PSO) for hyperparameter optimization. The presented study aims to improve EEG-based emotion detection, which will help create more unified and emotionally intelligent human-machine interfaces. Recent deep learning advances have advanced emotion detection. These advances have allowed systems to understand and respond to human emotions. Electroencephalography (EEG) signals can capture neural patterns linked to different emotions, giving a unique view of the brain's emotional state. However, extracting meaningful emotional information from these complex signals is difficult. EEG spatial patterns are captured using CNN and LSTM networks model data temporal dependencies. A hybrid ConvLSTM model integrates spatial and temporal information for a complete EEG analysis. The study presents a method that helps to detect emotions from EEG signals with accuracy of 99.63%. This study's high accuracy is a significant advancement in the field and has great potential for improving human-machine interaction systems. Due to the use of deep learning-based emotion detection, these systems are able to intuitively respond to the feelings of their users. They allow for deeper and more genuine connections to be made between humans and machines. The presented methodology achieves remarkable precision and lays the groundwork for emotionally intelligent technologies that can impact virtual assistants, healthcare, and entertainment. This research advances emotionally intelligent human-machine interfaces, paving the way for technology to understand and respond to human emotions with precision and sensitivity. © 2023 ACM.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Boosting Performance and QoS for Concurrent GPU B+trees by Combining-Based Synchronization 23

Boosting Performance and QoS for Concurrent GPU B+trees by C...

引用

28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming, PPoPP 2023

作者： Zhang, Weihua Zhao, Chuanlei Peng, Lu Lin, Yuzhe Zhang, Fengzhe Lu, Yunping School of Computer Science Fudan University China Institute of Big Data Fudan University China State Key Laboratory of Mathematical Engineering and Advanced Computing China Parallel Processing Institute Fudan University China Department of Computer Science Tulane University United States

ISBN: (纸本)9798400700156

Concurrent B+trees have been widely used in many systems. With the scale of data requests increasing exponentially, the systems are facing tremendous performance pressure. GPU has shown its potential to accelerate concurrent B+trees performance. When many concurrent requests are processed, the conflicts should be detected and resolved. Prior methods guarantee the correctness of concurrent GPU B+trees through lock-based or software transactional memory (STM)-based approaches. However, these methods complicate the request processing logic, increase the number of memory accesses and bring execution path divergence. They lead to performance degradation and variance in response time increasing. Moreover, previous methods do not guarantee linearizability among concurrent requests. In this paper, we design a combined-based concurrency control framework, called Eirene, for GPU B+tree to reduce the overhead of conflict detection and resolution. First, a combining-based synchronization method is designed to combine and issue requests. It combines the requests with the same key, constructs their dependence, decides the issued request, and determines their return values. Since only one request for each key is issued, key conflicts are eliminated. Then, an optimistic STM method is used to reduce structure conflicts. The query and the update requests are partitioned into different kernels. For the update kernels, STM is involved only when the number of the retry reaches a threshold. Finally, a locality-aware warp reorganization optimization is proposed to improve memory behavior and reduce conflicts by exploiting the locality among requests. Evaluations on an NVIDIA A100 GPU show that Eirene is efficient (a throughput of 2.4 billion per second) and can guarantee linearizability. Compared to the state-of-the-art GPU B+tree, it can achieve a speedup of 7.43X and reduce the response time variance from 36% to 5%. © 2023 ACM.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Adaptive energy-preserving algorithms for guiding center system

引用

Plasma science and Technology 2023年第4期25卷 11-22页

作者：朱贝贝刘健张嘉炜祝爱卿唐贻发 Department of Applied Mathematics School of Mathematics and PhysicsUniversity of Science and Technology BeijingBeijing 100083Peopleʼs Republic of China School of Nuclear Science and Technology University of Science and Technology of ChinaHefei 230026Peopleʼs Republic of China Advanced algorithm Joint Lab Shandong Computer Science CenterQilu University of TechnologyJinan 250014Peopleʼs Republic of China The State Key Laboratory of Scientific and Engineering Computing The Institute of Computational Mathematics and Scientific/Engineering ComputingAcademy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190Peopleʼs Republic of China School of Mathematical Sciences University of Chinese Academy of SciencesBeijing 100049Peopleʼs Republic of China

We develop two types of adaptive energy preserving algorithms based on the averaged vector field for the guiding center dynamics,which plays a key role in magnetized *** adaptive scheme is applied to the Gauss Legendre’s quadrature rules and time stepsize respectively to overcome the energy drift problem in traditional energy-preserving *** new adaptive algorithms are second order,and their algebraic order is carefully *** results show that the global energy errors are bounded to the machine precision over long time using these adaptive algorithms without massive extra computation cost.

关键词： guiding center system energy-preserving methods adaptive energy conservation

来源：评论

学校读者我要写书评

暂无评论

Secure E-Voting System using Deep Learning Techniques 2

Secure E-Voting System using Deep Learning Techniques

引用

2nd International Conference on Innovative Sustainable computational Technologies, CISCT 2022

作者： Kanchana, M. Gopirajan, P.V. Ramar, Kaladevi Hariharan, Shanmugasundaram School of Computing Srm Institute of Science and Technology Department of Computing Technologies Tamil Nadu India Srm Institute of Science and Technology School of Computing Department of Computational Intelligence Chennai India Department of Computer Science and Engineering Chennai India Vardhaman College of Engineering Department of Computer Science and Engineering Hyderabad India

ISBN: (纸本)9781665474160

Democracy is vital in many emerging economies because it places power in control of the general public, who choose government via the electoral procedure. Elections rely heavily on polling places and people. Numerous changes have happened in electoral processes since the year of the republic till now. Subsequently, Ballot sheets were implemented as a voting medium, but this was later replaced by electronic voting machines, in which voters must select from a list of buttons, each symbolizing a symbol. This paper proposes techniques for ensuring voter identification and privacy through fingerprint scanners and other biometric identification techniques-based machine learning algorithms. As a result, we offered a new approach to speed up the voting process and eliminate similar issues. For face identification, we employed Convolutional Neural Network (CNN) architectures such as Alex Net, Visual Geometry Group (VGG-16), and Random Forest Algorithms in this study. The accuracy provided by Alex Net, VGG-16, and Random Forest (R.F.) Algorithms was 94.16%, 98.45%, and 92%, respectively. VGG-16 architecture outperformed all other algorithms with a 98.45% accuracy. We utilized an ATmega328-based Arduino for finger detection. © 2022 IEEE.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

AcciRadar: Real Time Automatic Accident Detection and Reporting Framework

AcciRadar: Real Time Automatic Accident Detection and Report...

引用

International Conference on computer and Communications Technologies (ICCCT)

作者： M Fathima Mubarakkaa S. Hemavathi V. Kavitha Aarthi M Varshini K Janani Sindhu P Department of Computer Science and Engineering Sri Sairam Engineering College Chennai India Department of Computational Intelligence SRM Institute of Science and Technology Kattankulathur India

ISBN: (数字)9798331537579

ISBN: (纸本)9798331537586

Every year, millions are injured or killed in road accidents, with a high economic and social cost to communities. Speeding, impaired driving (alcohol, drugs), distracted driving (texting, phone use), and adverse weather conditions significantly contribute to accidents. Accidents that occur in places with low population density, such as highways, can lead to loss of life due to the unavailability of emergency medical assistance and longer response times. Highways, where accidents often happen, now have more cameras. Therefore, utilizing these cameras can help automatically detect accidents. Thus, this proposal outlines a real-time automatic accident detection system using surveillance cameras and Convolutional Neural Networks (CNN) technology, combined with GPS for location tracking. The system would identify nearby hospitals and alert them via phone call and message, providing the accident location. This helps to save lives in danger and ensures that immediate medical care and treatment is provided to the injured person.

关键词： Road transportation Road accidents Hospitals Surveillance Cameras Real-time systems Convolutional neural networks Time factors Accidents Global Positioning System

来源：评论

学校读者我要写书评

暂无评论

Preface to the 13th Workshop on Bibliometric-enhanced Information Retrieval at ECIR 2023 13

Preface to the 13th Workshop on Bibliometric-enhanced Inform...

引用

13th International Workshop on Bibliometric-Enhanced Information Retrieval, BIR 2023

作者： Frommholz, Ingo Mayr, Philipp Cabanac, Guillaume Verberne, Suzan Brennan, Jordan School of Engineering Computing and Mathematical Sciences University of Wolverhampton United Kingdom GESIS Leibniz-Institute for the Social Sciences Cologne Germany University of Toulouse Computer Science Department IRIT UMR 5505 France Leiden Institute of Advanced Computer Science Leiden University Netherlands

This preface summarizes the 13th Workshop on Bibliometric-enhanced Information Retrieval (BIR). BIR 2023 was held as hybrid event at April 2nd, 2023, co-located with the 45th European Conference on Information Retriev...

关键词：

来源：评论

学校读者我要写书评

暂无评论

Proactive Network Optimization Using Deep Learning in Predicting IoT Traffic Dynamics 4

Proactive Network Optimization Using Deep Learning in Predic...

引用

4th International Conference on Innovative Practices in Technology and Management, ICIPTM 2024

作者： Priya, S. Anu Bhat, Niyati Kanna, B. Rajesh Rajalakshmi, S. Jeyavathana, R. Beaulah Srimathi, S. Department of Computer Applications Chennai600117 India University of Mumbai B.E Computer Engineering Mumbai India Alagappa Chettiyar College of Engineering and Technology Department of Electronics and Communication Engineering Karaikudi India Rmk College of Engineering and Technology Department of Electronics and Communication Engineering India Srm Institute of Science and Technology Computational Intelligence Kattankulathur Chennai India Simats Saveetha School of Engineering Department of Bio Technology Tamilnadu Chennai India

ISBN: (纸本)9798350307757

Problems have arisen in allocating and managing network resources effectively because of the proliferation of IoT gadgets. This study aims to provide a deep learning-based strategy for forecasting and analyzing IoT traffic patterns to solve this problem. The model uses recurrent neural networks (RNNs) with Long Short-Term Memory (LSTM) cells to capture the complex temporal dependencies in IoT data streams. Following careful data gathering from various IoT sources, a thorough preprocessing phase is performed to account for missing values and outliers. Effective modeling is enabled by applying feature engineering approaches to distill meaningful information and by temporally aggregating the dataset. The heart of the study is the creation of a sequence-to-sequence architecture that allows for reliable forecasting of future IoT traffic trends. Mean Squared Error (MSE) and other performance metrics measure the quality of the proposed model's predictions. In addition to its predictive abilities, the model's analytical section reveals interesting facts about the fundamental habits underpinning IoT traffic. This dual purpose helps network managers better comprehend the ever-changing IoT ecosystem and allocate scarce resources. The results of this study have important implications for network optimization, providing a preventative strategy for dealing with the difficulties posed by the exponential growth of IoT data traffic. Regarding accuracy and interpretability, the suggested deep learning model significantly contributes to the development of intelligent network resource management in the IoT era. © 2024 IEEE.

关键词： Time series analysis

来源：评论

学校读者我要写书评

暂无评论

Co-linear Chaining with Overlaps and Gap Costs 26th

Co-linear Chaining with Overlaps and Gap Costs

引用

26th International Conference on Research in computational Molecular Biology, RECOMB 2022

作者： Jain, Chirag Gibney, Daniel Thankachan, Sharma V. Department of Computational and Data Sciences Indian Institute of Science Bangalore India School of Computer Science and Engineering Georgia Institute of Technology Atlanta United States Department of Computer Science University of Central Florida Orlando United States

ISBN: (纸本)9783031047480

Co-linear chaining has proven to be a powerful heuristic for finding near-optimal alignments of long DNA sequences (e.g., long reads or a genome assembly) to a reference. It is used as an intermediate step in several alignment tools that employ a seed-chain-extend strategy. Despite this popularity, efficient subquadratic-time algorithms for the general case where chains support anchor overlaps and gap costs are not currently known. We present algorithms to solve the co-linear chaining problem with anchor overlaps and gap costs in O~ (n) time, where n denotes the count of anchors. We also establish the first theoretical connection between co-linear chaining cost and edit distance. Specifically, we prove that for a fixed set of anchors under a carefully designed chaining cost function, the optimal ‘anchored’ edit distance equals the optimal co-linear chaining cost. Finally, we demonstrate experimentally that optimal co-linear chaining cost under the proposed cost function can be computed orders of magnitude faster than edit distance, and achieves correlation coefficient above 0.9 with edit distance for closely as well as distantly related sequences. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Anchors

来源：评论

学校读者我要写书评

暂无评论

Optimization Algorithm for Estimating the Velocity Characteristics of Complex Medium

Optimization Algorithm for Estimating the Velocity Character...

引用

2022 IEEE International Multi-Conference on engineering, computer and Information sciences, SIBIRCON 2022

作者： Pinigina, Daria L. Oksana, Kopylova A. Novosibirsk State Technical University Department of Computer Engineering Novosibirsk Russia Laboratory of Geophysical Informatics Department of Computer Engineering Institute of Computational Mathematics and Mathematical Geophysics SB RAS Novosibirsk State Technical University Novosibirsk Russia

ISBN: (纸本)9781665464802

An optimization computational grid algorithm and the results of its application for estimating the velocity characteristics of complex medium based on experimentally obtained seismic wave arrival times are presented. An increase in the resolution of the algorithm for detecting inhomogeneities is achieved by adaptively selecting the grid step in areas with a pronounced heterogeneity of the medium structure. The algorithm automatically identifies zones of inhomogeneity, taking into account non-linear variations in the hodograph of seismic waves. The restriction on the minimum allowable grid step is deter-mined taking into account the upper limiting frequency of sounding oscillations generated by the vibration source and the number of intersections of seismic wave fronts at the grid nodes. The proposed algorithm has been tested on experimental data obtained from vibration sounding of mud volcano zones and the Baikal Rift Zone (BRZ). The consistency of the reconstructed theoretical velocity hodograph with the geological structure of the heterogeneity of the structure of medium in the areas of field works is shown. © 2022 IEEE.

关键词： Seismic waves

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：