检索结果-内蒙古大学图书馆

CMD: A Cache-Assisted GPU Memory Deduplication Architecture

IEEE Transactions on Computer-Aided Design of Integrated Circuits and systems 2025年

作者： Zhao, Wei Feng, Dan Tong, Wei Wei, Xueliang Wu, Bing Ministry of Education of China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of data storage systems and Technology China

Massive off-chip accesses in GPUs are the main performance bottleneck. We find that many writes are duplicate, and the duplication can be inter-dup and intra-dup. While inter-dup means different memory blocks are identical, and intra-dup means all the 4B elements in a line are the same. In this work, we propose a cache-assisted GPU memory deduplication architecture named CMD to reduce the off-chip accesses via utilizing the data duplication in GPU applications. CMD includes three key design contributions which aim to reduce the three kinds of accesses: (1) A novel GPU memory deduplication architecture that removes the intra-dup and inter-dup lines. We design several techniques to manage duplicate blocks, reducing massive off-chip writes. (2) We propose a cache-assisted read scheme to reduce the reads to duplicate data. When an L2 cache miss wants to read the duplicate block, if the reference block has been fetched to L2 and it is clean, we can copy it to the L2 missed block without accessing off-chip DRAM. As for the reads to intra-dup data, CMD uses the on-chip metadata cache to get the data. (3) When a cache line is evicted, the clean sectors in the line are invalidated while the dirty sectors are written back. However, most read-only victims are re-referenced from DRAM more than twice. Therefore, we add a full-associate FIFO to accommodate the read-only (it is also clean) victims to reduce the re-reference counts. Experiments show that CMD can decrease the off-chip accesses by 31.01%, reduce the energy by 32.78% and improve performance by 42.53%. Besides, CMD can improve the performance of memory-intensive workloads by 57.56%. © 2025 IEEE.

关键词： Cache memory

来源：评论

学校读者我要写书评

暂无评论

Iterative Feature Boosting for Explainable Speech Emotion Recognition 22

Iterative Feature Boosting for Explainable Speech Emotion Re...

引用

22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023

作者： Nfissi, Alaa Bouachir, Wassim Bouguila, Nizar Mishara, Brian L. Data Science Laboratory Montreal Canada Concordia Institute for Information Systems Engineering Concordia University Montreal Canada Centre for Research and Intervention on Suicide Ethical Issues and End-of-Life Practices Montreal Canada University of Quebec at Montreal Psychology Department Montreal Canada

ISBN: (纸本)9798350345346

In speech emotion recognition (SER), using predefined features without considering their practical importance may lead to high dimensional datasets, including redundant and irrelevant information. Consequently, high-dimensional learning often results in decreasing model accuracy while increasing computational complexity. Our work underlines the importance of carefully considering and analyzing features in order to build efficient SER systems. We present a new supervised SER method based on an efficient feature engineering approach. We pay particular attention to the explainability of results to evaluate feature relevance and refine feature sets. This is performed iteratively through feature evaluation loop, using Shapley values to boost feature selection and improve overall framework performance. Our approach allows thus to balance the benefits between model performance and transparency. The proposed method outperforms human-level performance (HLP) and state-of-the-art machine learning methods in emotion recognition on the TESS dataset. The source code of this paper is publicly available at Iterative-Feature-Boosting-for-Explainable-Speech-Emotion-Recoanition. © 2023 IEEE.

关键词： Acoustic analysis Explainable AI Feature selection Speech emotion recognition Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Mobile Bot Rotation Using Sound Source Localization And Distant Speech Recognition

Mobile Bot Rotation Using Sound Source Localization And Dist...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Swapnil Sontakke Pradyoth Hegde Prashant Bannulmath Deepak K T Department of Data Science and Intelligent Systems Indian Institute of Information Technology Dharwad Karnataka India Department of Electronics & Communication Engineering Indian Institute of Information Technology Dharwad Karnataka India

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

In the last few years, mobile robots such as floor cleaners, assistive robots, and home telepresence have become an essential part of our day-to-day activities. In human-robot interaction, speech is the preferred way of communication, especially in indoor environments. This paper proposes a speech module to rotate the mobile robot. It has two components, namely, a distant automatic speech recognizer and a sound source localizer. To build distant speech recognizer, far-field speech data is collected at 1, 3, and 5-meters distances. The model performs well even at a 5-meters distance with a Word Error Rate of 40.38% and a Character Error Rate of 28.85%. The direction of arrival of the speech signal is computed from the 4-mic circular array microphone. The speech module is integrated with the Robot Operating System and physically demonstrated on Turtlebot3 Waffle Pi. It is observed that the speech recognizer and sound source localizer work well in the reverberant indoor environment with a small single-board computer.

关键词： Location awareness Telepresence Error analysis Operating systems Human-robot interaction Speech recognition Microphone arrays

来源：评论

学校读者我要写书评

暂无评论

Learnable Deep Wavelet Packet Transform for Speech Emotion Recognition in High-Risk Suicide Calls 23

Learnable Deep Wavelet Packet Transform for Speech Emotion R...

引用

23rd IEEE International Conference on Machine Learning and Applications, ICMLA 2024

作者： Nfissi, Alaa Bouachir, Wassim Bouguila, Nizar Mishara, Brian Data Science Laboratory Montréal Canada Concordia Institute for Information Systems Engineering Concordia University Montréal Canada Centre for Research and Intervention on Suicide Ethical Issues and End-of-Life Practices Montréal Canada University of Québec at Montréal Psychology Department Montréal Canada

ISBN: (纸本)9798350374889

In human-computer interaction and psychological evaluation, speech emotion recognition (SER) is crucial for interpreting emotional states from spoken language. Although there have been advancements, challenges such as system complexity, issues with feature distinctiveness, and noise interference continue to persist. This paper presents a novel end-to-end (E2E) deep learning multi-resolution framework for SER, which tackles these limitations by deriving significant representations directly from raw speech waveform signals. By leveraging the properties of wavelet packet transform (WPT), our approach introduces a learnable model for both wavelet bases and denoising through deep learning techniques. Unlike discrete wavelet transform (DWT), WPT offers a more detailed analysis by decomposing both approximation and detail coefficients, providing a finer resolution in the time-frequency domain. This capability enhances feature extraction by capturing more nuanced signal characteristics across different frequency bands. The framework incorporates a learnable activation function for asymmetric hard thresholding of wavelet packet coefficients. Our approach exploits the capabilities of wavelet packets for effective localization in both time and frequency domains. We then combine one-dimensional dilated convolutional neural networks (1D dilated CNN) with a spatial attention layer and bidirectional gated recurrent units (Bi-GRU) with a temporal attention layer to efficiently capture emotional features' nuanced spatial and temporal characteristics. By handling variable-length speech without segmentation and eliminating the need for pre or post-processing, the proposed model outperforms state-of-the-art methods on our NSPL-CRISE dataset and on the public IEMOCAP dataset. The source code of this paper is shared on this repository: https://***/alaaNfissi/WPT-Deep-Learning-SER-for-Suicide-Monitoring. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

IoT for Water Quality Categorization 5

IoT for Water Quality Categorization

引用

5th International Conference on Cybernetics and Intelligent systems, ICORIS 2023

作者： Sastrohartono, Hermantoro Krisdiarto, Andreas Wahyu Uktoro, Arief Ika Rahutomo, Reza Suparyanto, Teddy Pardamean, Bens Institute of Agriculture Stiper Faculty of Agricultural Technology Agricultural Engineering Department Yogyakarta Indonesia Bina Nusantara University School of Information Systems Information System Department Jakarta11480 Indonesia Bina Nusantara University Bioinformatics & Data Science Research Center Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program Master of Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350369489

In agricultural water research, the adoption of Internet of Things (IoT) technology has emerged as a pivotal approach for large-scale data collection. Water availability in the context of water quality is very important, both for domestic and industrial purposes. For domestic purposes, drinking water and bathing water are separated. Meanwhile, for the palm oil industry, boiler filler is differentiated from additional process water (dilution water). Water quality parameters can be assessed from turbidity and Total Dissolve Solid (TDS). Measurements using measuring instruments separately and repeatedly require significant energy, time, and costs. This research was conducted with the primary objective of presenting a novel method for categorizing water quality with the approach of IoT sensor technology. The research methodology entailed the utilization of an integrated IoT water sensors system in conjunction with manual water categorization. The methods consist of (1) system design, (2) design and installation of sensor and IoT-based microcontrollers, and (3) accuracy and precision testing compared with laboratory measurements. The precision of the integrated IoT water sensors was assessed through a dedicated sensor precision test, resulting in an accuracy rate of 94.4% for the turbidity sensor and 97.5% for the TDS sensor. Notably, this approach successfully discriminated drinking water with valid categorization, while other water types, including groundwater, water with tea, and water with coffee, yielded null categorization results. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Intrusion Detection System with Integration of Blockchain Technology and Internet of Things

Deep Learning Based Intrusion Detection System with Integrat...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical systems, ICSES 2024

作者： Uganya, G. Rajalakshmi, D. Kumar, K. Ashok Ravi, S. Sunheriya, Neeraj Kanan, Mohammad Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Ece Chennai India Srm Institute of Science and Technology Department of Data Science and Business Systems Kattankulathur Chennai India St Joseph's college of Engineering Department of Information Technology OMR Chennai India Department of Vlsi Microeelctronics Chennai India Yeshwantrao Chavan College of Engineering Department of Mechanical Engineering Nagpur India College of Engineering University of Business and Technology Department of Industrial Engineering Jeddah21448 Saudi Arabia College of Engineering Zarqa University Department of Mechanical Engineering Zarqa Jordan

ISBN: (纸本)9798331543617

The number of people and objects linked to the Internet of Things (IoT) has expanded dramatically due to its fast development, giving consumers more opportunities to interact with and manage their physical surroundings. IoT is susceptible to a number of security risks, because of its openness, connectedness, and constrained device resources. It is essential to guarantee the dependability and security of data transmitted in IoT networks. In order to solve these security problems, this work provides intrusion detection system that combines IoT with and Blockchain technology. As well as, deep learning method is integrated to improve the security. This work uses the SHA-256 algorithm to secure the data, the Adaptive Optimization algorithm for generating the keys, Rivest, Shamir, and Adleman (RSA) algorithm for encryption. and Deep Neural Network (DNN) for identifying intrusions in Internet of Things. Through identification and mitigation of possible risks, this framework successfully protects IoT networks and ensures the integrity of communications, as demonstrated by a comparison analysis with existing models. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Remote Patient Monitoring systems Network Adaptation Scenarios

Remote Patient Monitoring Systems Network Adaptation Scenari...

引用

2022 IEEE International Conference on Current Development in engineering and Technology, CCET 2022

作者： Khujamatov, Halimjon Akhmedov, Nurshod Lazarev, Amir Arsheen, Sobiya Tashkent University of Information Technologies Dean of the Faculty of Computer Engineering Tashkent Uzbekistan Tashkent University of Information Technologies Data Transmission Networks and Systems Department Tashkent Uzbekistan Maulana Azad National Urdu University Department of Computer Science and Information Technology India

ISBN: (纸本)9781665454155

This article is devoted to the actual topic of studying scenarios for adapting a network infrastructure to a network of remote patient monitoring systems (PCMS). The paper presents an overview and analysis of scenarios for adapting the network infrastructure of monitoring systems. The stages of scenario execution have been studied and simulation models of the RPMS network infrastructure have been developed that implement various adaptation scenarios. A comparative analysis of adaptation scenarios was carried out according to several criteria, such as the speed of request delivery, delivery time, and network load. Simulation models built in the Anylogic environment, a powerful simulator of mass service system, showed the effectiveness of the mesh topology in relation to the ad-hoc topology according to several criteria. The theoretical significance of the work lies in carrying out analytical work on scenarios for adapting the network infrastructure of the RPMS, as well as in studying the network architecture. The practical significance of the work lies in the development of a simulation model that allows you to explore scenarios for adapting the network architecture. © 2022 IEEE.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Exploring Television White Space as an Alternative for Wireless Broadband Connectivity 2

Exploring Television White Space as an Alternative for Wirel...

引用

2nd International Conference on Multidisciplinary engineering and Applied science, ICMEAS 2023

作者： Ifijeh, Ayodele H. Adetiba, Emmanuel Adewale, Adeyinka Thakur, Surrendra Moyo, Sibusiso Emmanuel, Dare O. Ukpong, Udeme C. Dept. of Electrical and Information Engineering Nigeria HRA Institute for Systems Science Durban University of Technology Durban South Africa Covenant University Dept. of Electrical and Information Engineering Ota Canaanland Nigeria Durban University of Technology KZN E-skills CoLab Durban4001 South Africa School for Data Science and Computational Thinking Stellenbosch University Department of Mathematical Sciences Stellenbosch7602 South Africa

ISBN: (纸本)9798350358834

Advancement in wireless transmission has enabled the communication among multiple devices all over the world, as well as expanding the frontiers of wireless Internet access. As a result of these advancement, numerous devices are questing for wireless connectivity thereby congesting the existing spectrum. If new measures are not taken to reduce depletion of the reserved radio resource, new allocations of wireless Internet access will be impossible, thereby risking the development of the entire wireless ecosystem. The demands for resourceful spectrum consumption have continually driven researchers and stakeholders in the wireless industry to search for spare radio spectrum to offer affordable and reliable wireless connectivity. The TV broadcasting is not fully utilizing the spectrum in some geographical zone. These TV unused spaces called TV White Spaces (TVWS), are well-thought-out to be the probable future resolutions for unavailability of spectrum. The low frequency band (470 to 694 MHz) of the unutilized TV channel has exceptional broadcast features over extensive distances and enables transmissions through high-rise buildings, trees, and mountains. These features allow the applications of TVWS in Internet of Things (IoT), wireless sensor network, wireless connectivity, wireless switching, smart grid and cities, automated transportation, and logistics as well as connectivity in cloud infrastructure. This paper presents a study on the advantages and benefits of television white space as an alternative to wireless broadband connectivity. © 2023 IEEE.

关键词： Tall buildings

来源：评论

学校读者我要写书评

暂无评论

Predicting Crops Based on Soil and Environmental Characteristics Using ARIMA and LSTM Model 4

Predicting Crops Based on Soil and Environmental Characteris...

引用

4th IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2024

作者： Naresh Kumar, U. Madhana Mohan, K. Pragadeeswaran, S. Scaria, Jobin M. Baseera, A. Seenivasan, D. Annamacharya University Department of Artificial intelligence & Data science Rajampet India Sri Sairam Engineering College Department of Electronics and Instrumentation Engineering Chennai India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Cse Chennai India School of Information Technology Ibs University Mt. Eriama Campus Port Moresby Papua New Guinea School of Computing Science and Engineering Vit Bhopal University Sehore India M. Kumarasamy College of Engineering Department of Computer Science and Business Systems Karur India

ISBN: (纸本)9798350352931

Food producers are under pressure to meet rising demand as the world's population and natural resources diminish. Overuse of pesticides and fertilizers has caused soil erosion and land degradation. Future food needs will require environmentally sustainable farming strategies. The suggested strategy includes model training, feature extraction, sensor integration, and model preparation. data preparation involves processing data before storing it machine-readable. SFFS and RFE select features. The model was trained using a hybrid ARIMA-LSTM technique, which blends deep learning and time-series forecasting. The ARIMA-LSTM model outperforms solo ARIMA and LSTM models with an average accuracy of 93.54%. Increased accuracy shows the model's capacity to anticipate sustainable agriculture approaches. data-driven and environmentally sustainable ways are needed to overcome global food production concerns, according to this study. When paired with good preprocessing and feature selection, ARIMA-LSTM can boost agricultural productivity while minimizing environmental impact. © 2024 IEEE.

关键词： crop productivity long short-term memory (lstm) soil management

来源：评论

学校读者我要写书评

暂无评论

Evaluation Method of Motor Coordination Ability in Children Based on Machine Vision

引用

Tsinghua science and Technology 2025年第2期30卷 633-649页

作者： Yi Lei Dawei Shu Miao Yu Donglin Shi Jianqiang Li Yanjie Chen Faculty of Information Technology Beijing University of TechnologyBeijing 100124China Department of Automation Tsinghua UniversityBeijing 100084China Pharmacovigilance Research Center for information technology and Data Science Cross-strait Tsinghua Research InstituteXiamen 361000China Institute of Systems Engineering Dalian University of TechnologyDalian 116024China Physical Education Department Hebei Sports UniversityShijiazhuang 050049China Department of Children’s Health Care Center Beijing Children’s HospitalCapital Medical UniversityNational Center for Children’s HealthBeijing 100045China

Motor coordination is crucial for preschoolers’development and is a key factor in assessing childhood *** diagnostic methods often rely on subjective manual *** paper presents a machine vision-based approach aimed at improving the objectivity and adaptability of *** method proposed involves the extraction of key points from the human skeleton through the utilization of a lightweight pose estimation network,thereby transforming video assessments into evaluations of keypoint *** study uses different methods to handle static and dynamic actions,including regularization and Dynamic Time Warping(DTW)for spatial alignment and temporal discrepancies.A penalty-adjusted single-frame pose similarity method is used to evaluate *** lightweight pose estimation model reduces parameters by 85%,uses only 6.6%of the original computational load,and has an average detection missing rate of less than 1%.The average error for static actions is 0.071 with a correlation coefficient of 0.766,and for dynamic actions it is 0.145 with a correlation coefficient of *** results confirm the proposed method’s effectiveness,which includes customized visual components like motion waveform graphs to improve accuracy in pediatric healthcare diagnoses.

关键词： developmental coordination disorder action quality assessment pose estimation dynamic time warping decision support system

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：