检索结果-内蒙古大学图书馆

An efficient speech emotion recognition based on a dual-stream CNN-transformer fusion network

International Journal of Speech Technology 2023年第2期26卷 541-557页

作者： Tellai, Mohammed Gao, Lijian Mao, Qirong Department of Computer Science and Communication Engineering Jiangsu University Jiangsu Zhenjiang212013 China Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications Jiangsu Zhenjiang212013 China

The use of machine learning and artificial intelligence enables us to create intelligent systems. Speech emotion recognition system analyzes the speaker’s speech to determine his/her emotional state. Speech emotion recognition is a challenging pattern recognition task. This paper proposes a new robust and lightweight speech emotion recognition system based on a dual-stream CNN-Transformer fusion network that effectively captures spatial and temporal information disentangled in long-distance raw features by exploring both MFCCs and Mel-spectrograms in a parallel mechanism. Experiments are performed on the widely used emotional benchmark datasets. Our approach has shown to be quite efficient. It outperforms the best-known state-of-the-art models with an accuracy of 97.64%, 99.42%, and 97.53% on RAVDESS, TESS, and EMO-DB datasets respectively. The results demonstrate the significant advantages of the proposed model and the ability of this architecture to learn to recognize emotional data features accurately. © 2023, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

High-Performance and Resource-Efficient Dynamic Memory Management in High-Level Synthesis 24

High-Performance and Resource-Efficient Dynamic Memory Manag...

引用

61st ACM/IEEE Design Automation Conference, DAC 2024

作者： Wang, Qinggang Zheng, Long An, Zhaozeng Huang, Haoqin Zhu, Haoran Huang, Yu Yao, Pengcheng Liao, Xiaofei Jin, Hai National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab Cluster and Grid Computing Lab Huazhong University of Science and Technology Wuhan China Zhejiang Lab Hangzhou China

ISBN: (纸本)9798400706011

With the merits of high productivity and ease of use, highlevel synthesis (HLS) tools bring hope to fast FPGA-based architecture development. However, their usability and popularity are still limited due to lack of support for dynamic memory management (DMM). Though HLS-compatible DMM solutions have been proposed recently, nevertheless, based on our investigation, none of them can hit high performance (i.e., minimal memory (de-)allocation latency) and resource efficiency (i.e., managing arbitrarily sized memory with minimal FPGA resource consumption) with one stone, seriously limiting their practicality. In response, we propose HeroDMM, a high-performance and resource-efficient dynamic memory manager for HLS. Specifically, HeroDMM organizes the managed memory area with a novel cartesian-like tree (CT) structure, a key to resolving the dilemma between (de-)allocation latency and resource efficiency standing in front of prior efforts. With the CT structure, HeroDMM further devises a delicate memory management algorithm and specializes the hardware implementation for achieving ever-higher performance while ensuring resource efficiency. Results show that HeroDMM outperforms state-of-the-art HLS-compatible DMM solutions by 61.69%∼99.99% in performance improvement and 23.79%∼97.22% in resource consumption savings. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Memory management

来源：评论

学校读者我要写书评

暂无评论

Towards Predictable Process and Consequence Attributes of data-Driven Group Work: Primary Analysis for Assisting Teachers with Automatic Group Formation

引用

Educational Technology and Society 2023年第4期26卷 90-103页

作者： Liang, Changhao Horikoshi, Izumi Majumdar, Rwitajit Flanagan, Brendan Ogata, Hiroaki Graduate School of Informatics Kyoto University Japan Academic Center for Computing and Media Studies Kyoto University Japan Center for Innovative Research and Education in Data Science Kyoto University Japan

data-driven platforms with rich data and learning analytics applications provide immense opportunities to support collaborative learning such as algorithmic group formation systems based on learning logs. However, teachers can still get overwhelmed since they have to manually set the parameters to create groups and it takes time to understand the meaning of each indicator. Therefore, it is imperative to explore predictive indicators for algorithmic group formation to release teachers from the dilemma with explainable group formation indicators and recommended settings based on group work purposes. Employing learning logs of group work from a reading-based university course, this study examines how learner indicators from different dimensions before the group work connect to the subsequent group work processes and consequences attributes through correlation analysis. Results find that the reading engagement and previous peer ratings can reveal individual achievement of the group work, and a homogeneous grouping strategy based on reading annotations and previous group work experience can predict desirable group performance for this learning context. In addition, it also proposes the potential of automatic group formation with recommended parameter settings that leverage the results of predictive indicators. © (2023). All Rights Reserved.

关键词： Correlation analysis CSCL GLOBE Group formation Group work indicator Group work prediction Teacher assistance

来源：评论

学校读者我要写书评

暂无评论

Towards High-throughput and Low-latency Billion-scale Vector Search via CPU/GPU Collaborative Filtering and Re-ranking 23

Towards High-throughput and Low-latency Billion-scale Vector...

引用

23rd USENIX Conference on File and Storage Technologies, FAST 2025

作者： Tian, Bing Liu, Haikun Tang, Yuhang Xiao, Shihai Duan, Zhuohui Liao, Xiaofei Jin, Hai Zhang, Xuecang Zhu, Junhua Zhang, Yu National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China Huawei Technologies Co. Ltd. China

ISBN: (纸本)9781939133458

Approximate nearest neighbor search (ANNS) has emerged as a crucial component of database and AI infrastructure. Ever-increasing vector datasets pose significant challenges in terms of performance, cost, and accuracy for ANNS services. None of modern ANNS systems can address these issues simultaneously. In this paper, we present FusionANNS, a high-throughput, low-latency, cost-efficient, and high-accuracy ANNS system for billion-scale datasets using SSDs and only one entry-level GPU. The key idea of FusionANNS lies in CPU/GPU collaborative filtering and re-ranking mechanisms, which significantly reduce I/O operations across CPUs, GPU, and SSDs to break through the I/O performance bottleneck. Specifically, we propose three novel designs: (1) multi-tiered indexing to avoid data swapping between CPUs and GPU, (2) heuristic re-ranking to eliminate unnecessary I/Os and computations while guaranteeing high accuracy, and (3) redundant-aware I/O deduplication to further improve I/O efficiency. We implement FusionANNS and compare it with the state-of-the-art SSD-based ANNS system-SPANN and GPU-accelerated in-memory ANNS system-RUMMY. Experimental results show that FusionANNS achieves 1) 9.4-13.1× higher query per second (QPS) and 5.7-8.8× higher cost efficiency compared with SPANN;2) and 2-4.9× higher QPS and 2.3-6.8× higher cost efficiency compared with RUMMY, while guaranteeing low latency and high accuracy. © 2025 FAST. All Rights Reserved.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Design of a Blind Guidance System Based on RealSense and the Improved YOLOv5 Algorithm 38th

Design of a Blind Guidance System Based on RealSense and the...

引用

38th CCF National Conference of Computer Applications, CCF NCCA 2023

作者： Zhang, Zhao Shen, Xiaobin Ge, Jing Zha, Yingying Liu, Lisai Liu, Sheng College of Computer Science and Technology Huaibei Normal University Huaibei235000 China Anui Engineering Research Center for Intelligent Computing and Application on Cognitive Behavior Huaibei235000 China

ISBN: (纸本)9789819987634

To assist blind people in travelling and solve the problems of high hardware costs, insufficient portability of blind assistance devices, and vulnerability to environmental impacts, a modified YOLOv5 algorithm (YOLOv5-CM) based on ground plane segmentation and Euclidean clustering algorithms is proposed and applied to a blind guidance system based on RealSense D435. This proposed algorithm adds coordinate attention and uses MobileNetv3 as the backbone network for YOLOv5s to extract the main features. Compared with those of the YOLOv5 model, the mAP was improved by 0.7%, the model size was decreased by 79.1%, and the number of parameters was reduced by 80.3%. In this study, the YOLOv5-CM algorithm was applied to design a blind guidance system. When the system detects a traffic light, the RealSense D435 is used to obtain depth images to detect and measure the distance from the pedestrian traffic light. The system provides warnings based on the measured distance. When the system does not detect a traffic light, it utilizes the ground plane segmentation and Euclidean clustering algorithms to obtain the location and distance of obstacles. This information is conveyed to the blind through voice guidance, which aids navigation. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Using analytic hierarchy process to evaluate deep learning for infrared target recognition

引用

Multimedia Tools and Applications 2024年第38期83卷 86229-86245页

作者： Xu, Laixiang Cao, Bingxu Wei, Xinhong Li, Bei Su, Jingfeng Ning, Shiyuan Zhao, Junmin School of Computer and Data Science Henan University of Urban Construction Pingdingshan467036 China School of Information Engineering Luohe Vocational Technology College Henan University of Technology Luohe Institute of Technology Luohe462000 China School of Computer and Data Science Innovation Laboratory of Smart Traffic and Big Data Development of Hainan Province Pingdingshan467036 China School of Computer and Data Science Research Center of Smart City and Big Data Engineering of Henan Province Henan University of Urban Construction Pingdingshan467036 China Department of Software Information China Electronics Technology Group Corporation 36-th Research Institute Jiaxing314033 China School of Computer and Data Science Research Center of Smart City and Big Data Engineering of Henan Province Research Center of Intelligent Campus Application Engineering of Henan Province Innovation Laboratory of Smart Traffic and Big Data Development of Hainan Province Henan University of Urban Construction Pingdingshan467036 China

In order to promote the evaluation performance of deep learning infrared automatic target recognition (ATR) algorithms in the complex environment of air-to-air missile research, we proposed an analytic hierarchy process (AHP) evaluation system consisting of the target recognition ability, the generalization recognition ability, the anti-interference ability, the background suppression ability, and the cost metrics ability. According to detailed quantitative analysis and experimental results, we establish probability evaluation models and get their probability values. Compared with traditional evaluation systems, our proposed method implementation is showing high reliability. Similar superior performances are also achieved, such as quick, comprehensive, and scientific. Through the above research, the key technology of deep learning performance evaluation in automatic target recognition has been broken through, which provides some basis and guidance for the analysis of infrared imaging-guided weapon systems. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

Seer: Accelerating Block chain Transaction Execution by Fine-Grained Branch Prediction 51st

Seer: Accelerating Block chain Transaction Execution by Fine...

引用

51st International Conference on Very Large data Bases, VLDB 2025

作者： Zhang, Shijie Cheng, Ru Liu, Xinpeng Xiao, Jiang Jin, Hai Li, Bo National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong

Increasingly popular decentralized applications (dApps) with complex application logic incur significant overhead for executing smart contract transactions, which greatly limits public block chain performance. Pre-executing transactions off the critical path can mitigate substantial I/O and computation costs during execution. However, pre-execution does not yield any state transitions, rendering the system state inconsistent with actual execution. This inconsistency can lead to deviations in pre-execution paths when processing smart contracts with multiple state-related branches, thus diminishing pre-execution effectiveness. In this paper, we develop Seer, a novel public block chain execution engine that incorporates fine-grained branch prediction to fully exploit pre-execution effectiveness. Seerpredicts state-related branches using a two-level prediction approach, reducing inconsistent execution paths more efficiently than executing all possible branches. To enable effective reuse of pre execution results, Seer employs checkpoint-based fast-path execution, enhancing transaction execution for both successful and unsuccessful predictions. Evaluations with realistic block chain workloads demonstrate that Seer delivers an average of 27.7× transaction-level speedup and an overall 20.6× speedup in the execution phase over vanilla Ethereum, outperforming existing block chain execution acceleration solutions. © 2025, VLDB Endowment, All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Improved Finite-time Analysis of Temporal Difference Learning with Deep Neural Networks 41

An Improved Finite-time Analysis of Temporal Difference Lear...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Ke, Zhifa Wen, Zaiwen Zhang, Junyu Center for Data Science Peking University China Beijing International Center for Mathematical Research Center for Machine Learning Research Changsha Institute for Computing and Digital Economy Beijing China Department of Industrial Systems Engineering and Management National University of Singapore Singapore

Temporal difference (TD) learning algorithms with neural network function parameterization have well-established empirical success in many practical large-scale reinforcement learning tasks. However, theoretical understanding of these algorithms remains challenging due to the nonlinearity of the action-value approximation. In this paper, we develop an improved non-asymptotic analysis of the neural TD method with a general L-layer neural network. New proof techniques are developed and an improved new Õ(ϵ-1) sample complexity is derived. To our best knowledge, this is the first finite-time analysis of neural TD that achieves an Õ(ϵ-1) complexity under the Markovian sampling, as opposed to the best known Õ(ϵ-2) complexity in the existing literature. Copyright 2024 by the author(s)

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Can Gaussian Sketching Converge Faster on a Preconditioned Landscape? 41

Can Gaussian Sketching Converge Faster on a Preconditioned L...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Wang, Yilong Ye, Haishan Dai, Guang Tsang, Ivor W. Center for Intelligent Decision-Making and Machine Learning School of Management Xi'an Jiaotong University China SGIT AI Lab State Grid Corporation of China China Singapore College of Computing and Data Science NTU Singapore

This paper focuses on the large-scale optimization which is very popular in the big data era. The gradient sketching is an important technique in the large-scale optimization. Specifically, the random coordinate descent algorithm is a kind of gradient sketching method with the random sampling matrix as the sketching matrix. In this paper, we propose a novel gradient sketching called GSGD (Gaussian Sketched Gradient Descent). Compared with the classical gradient sketching methods such as the random coordinate descent and SEGA (Hanzely et al., 2018), our GSGD does not require the importance sampling but can achieve a fast convergence rate matching the ones of these methods with importance sampling. Furthermore, if the objective function has a non-smooth regularization term, our GSGD can also exploit the implicit structure information of the regularization term to achieve a fast convergence rate. Finally, our experimental results substantiate the effectiveness and efficiency of our algorithm. Copyright 2024 by the author(s)

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

An Integrated Analysis of Yield Prediction Models:A Comprehensive Review of Advancements and Challenges

引用

Computers, Materials & Continua 2024年第7期80卷 389-425页

作者： Nidhi Parashar Prashant Johri Arfat Ahmad Khan Nitin Gaur Seifedine Kadry School of Computer Science and Engineering Galgotias UniversityGreater Noida203201India Department of Applied Data Science Noroff University CollegeKristiansand4612Norway Artificial Intelligence Research Center(AIRC) Ajman UniversityAjman346United Arab Emirates MEU Research Unit Middle East UniversityAmman11831Jordan Department of Computer Science College of ComputingKhon Kaen UniversityKhon Kaen40002Thailand

The growing global requirement for food and the need for sustainable farming in an era of a changing climate and scarce resources have inspired substantial crop yield prediction *** learning(DL)and machine learning(ML)models effectively deal with such *** research paper comprehensively analyses recent advancements in crop yield prediction from January 2016 to March *** addition,it analyses the effectiveness of various input parameters considered in crop yield prediction *** conducted an in-depth search and gathered studies that employed crop modeling and AI-based methods to predict crop *** total number of articles reviewed for crop yield prediction using ML,meta-modeling(Crop models coupled with ML/DL),and DL-based prediction models and input parameter selection is *** conduct the research by setting up five objectives for this research and discussing them after analyzing the selected research *** study is assessed based on the crop type,input parameters employed for prediction,the modeling techniques adopted,and the evaluation metrics used for estimatingmodel *** also discuss the ethical and social impacts of AI on ***,various approaches presented in the scientific literature have delivered impressive predictions,they are complicateddue to intricate,multifactorial influences oncropgrowthand theneed for accuratedata-driven ***,thorough research is required to deal with challenges in predicting agricultural output.

关键词： Machine learning crop yield prediction deep learning remote sensing long short-term memory time series prediction systematic literature review

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：