检索结果-内蒙古大学图书馆

59th Annual Conference on Information sciences and Systems, CISS 2025

作者： Wei, Dongyu Zhang, Qianqian Liu, Yuchen Chen, Mingzhe Rowan University Department of Electrical and Computer Engineering GlassboroNJ08028 United States Nc State University Department of Computer Science RaleighNC27695 United States University of Miami Department of Electrical and Computer Engineering Coral GablesFL33146 United States University of Miami Frost Institute for Data Science and Computing Coral GablesFL33146 United States

ISBN: (纸本)9798331513269

In this paper, a deceptive signal-assisted private split learning is investigated. In our model, several edge devices jointly perform collaborative training, and some eavesdroppers aim to collect the model and data information from devices. To prevent the eavesdropper from collecting model and data information, a subset of devices can transmit deceptive signals. Therefore, it is necessary to determine the subset of devices used for deceptive signal transmission, the subset of model training devices, and the models assigned to each model training device. This problem is formulated as an optimization problem whose goal is to minimize the eavesdropped information while meeting the model training energy consumption and delay constraints. To solve this problem, we propose an actor-critic deep reinforcement learning (AC-DRL) framework that enables a centralized agent to dynamically determine the model training devices, the deceptive signal transmission devices, the transmit power, and sub-models assigned to each model training device while considering network topology and device properties (e.g., energy and privacy constraints). The proposed AC-DRL framework integrates an actor network to generate optimal actions and a critic network to stabilize the learning process by evaluating the cumulative rewards. Simulation results demonstrate that the proposed method improves the convergence rate by 3× and the accumulated reward by up to 40% compared with the proximal policy optimization (PPO) algorithm. © 2025 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Speech Separation for Low-Resource Languages

Speech Separation for Low-Resource Languages

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Borsdorf, Marvin Pan, Zexu Himmelmann, Pascal Li, Haizhou Schultz, Tanja Machine Listening Lab University of Bremen Bremen Germany Alibaba Group Singapore Department of Mathematics and Computer Science FernUniversität in Hagen Hagen Germany School of Data Science Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen China Department of Electrical and Computer Engineering National University of Singapore Singapore Cognitive Systems Lab University of Bremen Bremen Germany

ISBN: (纸本)9798350368741

Speech separation aims to equip machines with the human ability of selective listening, i.e. to focus attention on specific information in spoken communication. Studies have shown that the language spoken in a cocktail party scenario matters. While the development of speech separation models can leverage extensive databases, for the majority of languages only very limited data is available. This work presents the very first study on speech separation for low-resource languages. We choose blind source separation as the task to be studied and analyze three strategies to overcome the data scarcity of two low-resource languages from the GlobalPhoneMS2 database. We show that data from other languages can be used to develop models that work for low-resource languages. Finetuning additionally boosts the performance, and training on multiple languages increases both performance and robustness. We show that dynamic mixing in the development helps to find a trade-off between performance and development time. © 2025 IEEE.

关键词： cocktail party problem GlobalPhone low-resource language multilingual speech separation

来源：评论

学校读者我要写书评

暂无评论

Assessing Software Practitioners’ Work Engagement and Job Satisfaction in a Large Software Company—What We Have Learned

引用

SN computer science 2025年第3期6卷 1-24页

作者： Cerqueira, Lidiany Nunes, Lourene Guerra, Renan Malheiros, Viviane Freire, Sávio Carneiro, Glauco Leite, Julio Cesar Spínola, Rodrigo Macedo Santos, José Amancio Mendonça, Manoel Department of Computer Science Federal University of Bahia Bahia Salvador 40170-115 Brazil Data Processing Federal Service DF Brasília 70836-900 Brazil Teaching Department Federal Institute of Ceará Ceará Morada Nova 62.940-000 Brazil Department of Computer Science Federal University of Sergipe Sergipe São Cristóvão 610101 Brazil Department of Computer Science Virginia Commonwealth University Richmond 23284 VA United States Department of Technology State University of Feira de Santana Bahia Feira de Santana 44036-900 Brazil

Social aspects of software practitioners strongly influence software engineering outcomes. For instance, software companies seek to measure how factors like work engagement and job satisfaction impact employee productivity and software quality. Work engagement represents a positive, fulfilling, work-related mental state, while job satisfaction reflects how content professionals are with their roles. Our study aims to highlight the social aspects of software practitioners considering a large organization. We investigate the work engagement and job satisfaction of software practitioners working remotely at a large software organization in the public sector. We surveyed 891 software practitioners and analyzed their responses qualitatively and quantitatively. The survey participants indicated strong work engagement. They perceived their teams as effective, but there is room for improving social aspects, such as communication within the teams, promoting discussions about career development, and consistent feedback. Most professionals are satisfied with their teams, though a small minority expressed concerns that may influence their willingness to recommend their teams. Our findings provide relevant information about the engagement and satisfaction of employees within this particular type of organization and expand the knowledge base on the subject, supporting new research efforts in the area. © The Author(s) 2025.

关键词： Human factors Job satisfaction Productivity Remote work Work engagement

来源：评论

学校读者我要写书评

暂无评论

CH-YOLO-Lite: a lightweight object detection model with context-aware progressive aggregation and hierarchical feature aggregation for aerial imagery

引用

Journal of Electronic Imaging 2025年第2期34卷

作者： Wang, Le Jiang, Wangyu Dharejo, Fayaz Ali Sun, Meng Timofte, Radu Mao, Guojun Fujian University of Technology School of Computer Science and Mathematics Fuzhou China Fujian University of Technology Fujian Provincial Key Laboratory of Big Data Mining and Applications Fuzhou China Technology Innovation Center of Factored Transaction Data in Tourist Attractions Ministry of Culture and Tourism Fuzhou China University of Wurzburg Computer Vision Lab CAIDAS IFI Wurzburg Germany University of Wurzburg Biocenter Department of Bioinformatics Wurzburg Germany

Object detection in aerial images poses significant challenges due to the high proportion of small objects, drastic scale variations, and resource constraints. We propose a lightweight object detection model, CH-YOLO-Lite, based on context-aware progressive aggregation and hierarchical feature augmentation. First, we designed a context-aware progressive aggregator (CPA) to integrate multi-scale contextual information through a progressive fusion strategy, enhancing the model's perception of its environment and improving small object detection in complex scenes. Second, we designed a hierarchical feature aggregation (HFA) module and an improved adaptive spatial feature fusion (iASFF) method to construct the feature augmentation neck, which significantly enhances the model's multi-scale detection capability in scenarios dominated by small objects. The HFA introduces more low-level detail features into the feature pyramid through cross-level branches, strengthening the model's feature representation for small objects. Meanwhile, iASFF adaptively learns the spatial fusion weights of feature maps at different scales, effectively solving the issue of scale inconsistency during feature fusion, further improving detection accuracy. Finally, to further simplify the model, channel pruning is used, which significantly reduces the parameters of the model while maintaining the detection performance. Experiments on the test set of the VisDrone dataset show that CH-YOLO-Lite significantly improves mAP0.5 by 7.2% and reduces parameters by 67% compared with the baseline model YOLOv7-Tiny. The mAP0.5 of CH-YOLO-Lite is also improved by 4.9% on NWPU VHR-10 datasets, which validates the generalization of our proposed algorithm. © 2025 SPIE and IS&T.

关键词： Aerial photography

来源：评论

学校读者我要写书评

暂无评论

Network intrusion detection based on feature fusion of attack dimension

引用

Journal of Supercomputing 2025年第6期81卷 1-33页

作者： Sun, Xiaolong Gu, Zhengyao Zhang, Hao Gu, Jason Liu, Yanhua Dong, Chen Ye, Junwei College of Computer and Data Science Fuzhou University Fuzhou350116 China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350116 China Engineering Research Center of Big Data Intelligence Chinese Ministry of Education Fuzhou350116 China Department of Electrical and Computer Engineering Dalhousie University HalifaxNSB3J 1Z1 Canada

Network traffic anomaly detection involves the rapid identification of intrusions within a network through the detection, analysis, and classification of network traffic data. The variety of cyberattacks encompasses diverse attack principles. Employing an indiscriminate feature selection strategy may lead to the neglect of key features highly correlated with specific attack types. This oversight could diminish the recognition rate for that category, thereby impacting the overall performance of the detection model. To address this issue, this paper proposes a network traffic anomaly detection model based on the fusion of attack-dimensional features. Firstly, construct binary classification datasets independently for each attack class and perform individual feature selection to extract positively correlated features for each class. The features are then fused by employing a combination methods. Subsequently, based on the fused sub-datasets, base classifiers are trained. Finally, an ensemble learning approach is introduced to integrate the predictions of individual classifiers, enhancing the robustness of the model. The proposed approach, validated on NSL-KDD and UNSW-NB15 benchmark datasets, outperforms the latest methods in the field by achieving a 2% and 7% increase in precision on weighted averages. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Real-Time Sign Language Recognition System for Physically Challenged Community Using Deep Learning Technique 8th

Real-Time Sign Language Recognition System for Physically Ch...

引用

8th International Conference on Microelectronics Electromagnetics and Telecommunications, ICMEET 2023

作者： Devi, V. Anjana Bhuvaneswari, E. Tummala, Rama Krishna Professor Department of Computer Science and Engineering Rajalakshmi Institute of Technology Tamil Nadu Chennai India Associate Professor Department of Artificial Intelligence and Data Science Panimalar Engineering College Tamil Nadu Chennai India Accenture Solutions Pvt. Ltd Chennai India

ISBN: (纸本)9789819784219

Language disparities have always existed in human civilization. In their community, deaf individuals use sign languages to communicate with one another, but it can be difficult to do so when interacting with the wider population. The project comprises a real-time sign language recognition system that enables hearing-impaired individuals and persons who do not know sign language to effortlessly communicate. The most used sign language in South Asian nations is Indian sign language. Convolution neural networks, specifically Tensor Flow object detection, are utilized to assess and train the model on the images that are used. The transfer training approach is used to train the deep learning model with various hand movements. Loss is anticipated to be decreased. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

EDM10: A Polyphonic Stereo dataset with Identical BGM for Musical Instrument Identification 27th

EDM10: A Polyphonic Stereo Dataset with Identical BGM for ...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Mukherjee, Himadri Marciano, Matteo Dhar, Ankita Roy, Kaushik TISA Lab Department of Computer Science West Bengal State University Barasat India Gazelien Records Lab Department of Arts and Humanities Music Program New York University Abu Dhabi Abu Dhabi United Arab Emirates Department of Computer Science and Engineering Sister Nivedita University New Town India

ISBN: (纸本)9783031784972

Music Signal Processing has significantly evolved in the past decades. One of the major areas of interest in this field has been automatic music transcription. It is a challenging task by itself that aggravates even more when the input audio is polyphonic (multiple instruments and timbres are played simultaneously). This requires the identification of musical instruments in the piece at the outset. The field of music signal processing that deals with this aspect is known as automatic music instrument identification. This field also has the potential of categorizing and recommending music based on instruments. Disparate datasets have been proposed to date for this task but none of them have interclass background similarity to the best of our knowledge. Further, the lead melody being played also varies from class to class in most cases. These aspects can introduce a possible bias for the machine learning models that can get manipulated unfairly by the additional variances in the classes other than the lead instrument itself. This sets the stage for a dataset where the classes are different only in terms of the tone of the lead instrument alone. In this paper, we introduce the first musical instrument dataset of 10 musical instruments with Electronic Dance Music melodies (EDM10) having identical background music (BGM) across instruments. This dataset is the first of its kind wherein synthetic tones have been used that have taken over the Globe. We introduce out-of-mood testing using exotic scales for musical instrument identification. The dataset is composed of 35800 polyphonic clips of 3 s each and a baseline result of 89.73% was obtained using a deep learning-based approach. The dataset is freely available for research purposes. https://***/yV5e36TK1jHMKjpC6. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Electronic musical instruments

来源：评论

学校读者我要写书评

暂无评论

Intelligent Innovation dataset on Scientific Research Outcomes and Patents

引用

Journal of Social Computing 2025年第1期6卷 63-73页

作者： Wu, Xinran Zou, Hui Xing, Yidan Qu, Jingjing Guo, Weiwei Fu, Xiaoming School of Computer Science Fudan University Shanghai Key Laboratory of Intelligent Information Processing Shanghai200433 China Shanghai University Department of Library and Information Science Shanghai200444 China Big Data Technology Co. Ltd. Shanghai200082 China Shanghai Artificial Intelligence Laboratory Shanghai200082 China Fudan University Department of Management Shanghai200433 China Fudan University Shanghai Key Laboratory of Intelligent Information Processing Shanghai200433 China Institute of Computer Science University of Göttingen Göttingen37073 Germany

Various stakeholders, such as researchers, government agencies, businesses, and research laboratories require a large volume of reliable scientific research outcomes including research articles and patent data to support their work. These data are crucial for a variety of application, such as advancing scientific research, conducting business evaluations, and undertaking policy analysis. However, collecting such data is often a time-consuming and laborious task. Consequently, many users turn to using openly accessible data for their research. However, these existing open dataset releases typically suffer from lack of relationship between different data sources and a limited temporal coverage. To address this issue, we present a new open dataset, the Intelligent Innovation dataset (IIDS), which comprises six interrelated datasets spanning nearly 120 years, encompassing paper information, paper citation relationships, patent details, patent legal statuses, and funding information. The extensive contextual and extensive temporal coverage of the IIDS dataset will provide researchers and practitioners and policy maker with comprehensive data support, enabling them to conduct indepth scientific research and comprehensive data analyses. © 2020 Tsinghua University Press.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Parametric Scaling Law of Tuning Bias in Conformal Prediction

arXiv

引用

arXiv 2025年

作者： Zeng, Hao Liu, Kangdao Jing, Bingyi Wei, Hongxin Department of Statistics and Data Science Southern University of Science and Technology China Department of Computer and Information Science University of Macau China

Conformal prediction is a popular framework of uncertainty quantification that constructs prediction sets with coverage guarantees. To uphold the exchangeability assumption, many conformal prediction methods necessitate an additional holdout set for parameter tuning. Yet, the impact of violating this principle on coverage remains underexplored, making it ambiguous in practical applications. In this work, we empirically find that the tuning bias - the coverage gap introduced by leveraging the same dataset for tuning and calibration, is negligible for simple parameter tuning in many conformal prediction methods. In particular, we observe the scaling law of the tuning bias: this bias increases with parameter space complexity and decreases with calibration set size. Formally, we establish a theoretical framework to quantify the tuning bias and provide rigorous proof for the scaling law of the tuning bias by deriving its upper bound. In the end, we discuss how to reduce the tuning bias, guided by the theories we developed. © 2025, CC BY.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Development of Fast Prediction System of User Action for a Fully Autonomous Smart Home System 4

Development of Fast Prediction System of User Action for a F...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Rajalakshmi, N.R. Sharmila, L. Prabu, S. Veeramakali, T. Arulkumaran, G. Chourasia, Pranshu Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu India School of Computing Srm Institute of Science and Technology Department of Computing Technologies Kattankulathur Chennai India School of Computing Srm Institute of Science and Technology Department of Data Science and Business Systems Kattankulathur Chennai India School of Computing and Information Technology Reva University Karnataka Bangalore560064 India

ISBN: (纸本)9798331523923

The HVAC system, energy storage building, distributed power supply, and other equipment are integrated into the scheduling algorithm, which is aimed at reducing household electricity consumption. It is also assumed that users can provide energy to the grid according to their own conditions. Taking electricity cost and comfort level as optimization targets, a home energy optimization control model for the coordinated management of hybrid energy sources is built. A smart scheduling mechanism based on the improved adaptive particle swarm optimization approach is proposed in order to derive the best time intervals for electric appliances, necessary power for the control of the room temperature for every time frame, and power for charging and discharging of the storage battery at various moments. Simulation results show that through the incorporation of distributed photovoltaic power generation, backup storage by battery, and home energy optimization control, the system efficiently balances between user comfort and electricity consumption. This offers great technical support to the development of home energy management systems. By using time-of-use electricity price for energy acquisition and supply, the optimization control goal is minimizing both power use and cost as well as preserving comfort levels. The hybrid energy management's proposed home energy optimization control model uses an adaptive particle swarm optimization algorithm to find the optimal operation schedules of the electrical appliances, the required power for temperature control in a room, and the charge/discharge power level of the storage battery at each time interval. As per the optimization principle, the proposed dynamic programming algorithm converts the multi-stage problem into a sequence of single-stage problems and solves them separately. This method successfully resolves intricate problems that cannot be addressed through greedy algorithms or divide-and-conquer. In this research, management ac

关键词： Decision making

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：