检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Li, Lingjie Xuan, Manlin Lin, Qiuzhen Jiang, Min Ming, Zhong Tan, Kay Chen The College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China The School of Informatics Xiamen University Xiamen361005 China The Department of Computing The Hong Kong Polytechnic University Hong Kong

Recently, evolutionary multitasking (EMT) has been successfully used in the field of high-dimensional classification. However, the generation of multiple tasks in the existing EMT-based feature selection (FS) methods is relatively simple, using only the Relief-F method to collect related features with similar importance into one task, which cannot provide more diversified tasks for knowledge transfer. Thus, this paper devises a new EMT algorithm for FS in high-dimensional classification, which first adopts different filtering methods to produce multiple tasks and then modifies a competitive swarm optimizer to efficiently solve these related tasks via knowledge transfer. First, a diversified multiple task generation method is designed based on multiple filtering methods, which generates several relevant low-dimensional FS tasks by eliminating irrelevant features. In this way, useful knowledge for solving simple and relevant tasks can be transferred to simplify and speed up the solution of the original high-dimensional FS task. Then, a competitive swarm optimizer is modified to simultaneously solve these relevant FS tasks by transferring useful knowledge among them. Numerous empirical results demonstrate that the proposed EMT-based FS method can obtain a better feature subset than several state-of-the-art FS methods on eighteen high-dimensional datasets. Copyright © 2022, The Authors. All rights reserved.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Development of Innovative Algorithm for Sound Detection Based on FFT and Goertzel Algorithms

Development of Innovative Algorithm for Sound Detection Base...

引用

Intelligent Data Communication Technologies and Internet of Things (IDCIoT), International Conference on

作者： Senthil Kumar S P. Umaeswari B.Veera Jyothi G.R. Gnana King Trupti Patil R. Gukendran Department of Mechanical Engineering R.M.K College of Engineering and Technology Chennai Tamil Nadu India Department of Computer Science and Business Systems R. M. K. Engineering College Kavaraipettai Department of Information Technology Chaitanya Bharathi Institute of Technology Hyderabad India Department of Electronics and Communication Engineering Sahrdaya College of Engineering and Technology Thrissur Kerala Department of Engineering and Technology Bharati Vidyapeeth Deemed to be University Navi Mumbai Maharashtra India Department of Mechanical engineering Kongu Engineering College Perundurai

The field of sound detection and analysis has witnessed remarkable advancements in recent years, driven by the increasing demand for applications such as speech recognition, environmental monitoring, and acoustic event detection. This work presents the development of an innovative algorithm for sound detection, leveraging the power of the Fast Fourier Transform (FFT) and Goertzel algorithms. The proposed algorithm combines the strengths of both the FFT and Goertzel algorithms to enhance the accuracy and efficiency of sound detection. The FFT is employed for its rapid transformation of time-domain audio signals into the frequency domain, providing valuable insights into the spectral characteristics of the input signal. Simultaneously, the Goertzel algorithm is applied to identify specific target frequencies with high precision and minimal computational overhead. This innovative approach addresses the limitations commonly associated with conventional sound detection algorithms, such as those relying solely on FFT or Goertzel. By harnessing the FFT's spectral analysis capabilities and the Goertzel algorithm's fine-grained frequency detection, the algorithm can effectively detect and classify sound events in various real-world scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Rankings vs Realities: Exploring Competency Differences in Graduate Data science Programs

Rankings vs Realities: Exploring Competency Differences in G...

引用

Frontiers in Education (FIE) Conference

作者： Duo Li Elizabeth Milonas Qiping Zhang Department of Big Data Management and Application Shenyang Institute of Technology Fushun China Computer Systems Technology New York City College of Technology (CUNY) Brooklyn USA Palmer School of Library and Information Science Long Island University Brookville USA

Numerous educational institutions, including those specializing in computer science, engineering, business, and science, now offer graduate programs in data science. However, it remains uncertain whether the data science programs provided by universities with different rankings deliver similar or distinct data science competencies. This study aims to compare the competencies of graduate data science programs offered in the United States. It addressed the research question of “Are there any differences in graduate data science program competencies based on their university rankings?” The program competencies of 228 data science graduate programs as well as their U.S. News university rankings were collected and compared. The findings indicate that regardless of their national rankings, all universities offer most of the competencies required for data science programs, except for Machine Learning and Sensor Networks. Forty-six percent of data science programs are offered in universities that hold national rankings within the top 75, focusing on majors such as data science and business analytics. Furthermore, the top-ranked universities provide data science programs across all departments or schools, with the most prominent ones being Business, computer science, Information science & Technology, and Math/Statistics. The primary research contribution of this study revolves around conducting a comprehensive analysis of data science program competencies within the United States. The implications of the findings have significant relevance to computing education. The study provides valuable guidelines for educational practices in the field of data science: 1) naming the new majors as either “Data science” or “Business Analytics”; 2) housing the new data science programs within existing departments or schools specializing in Business, computer science, Information science & Technology, and Math/Statistics; 3) incorporating all ACM Data science competencies into the curriculum

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Self-Supervised Learning-based Approach to Clustering Multivariate Time-Series Data with Missing Values (SLAC-Time): An Application to TBI Phenotyping

arXiv

引用

arXiv 2023年

作者： Ghaderi, Hamid Foreman, Brandon Nayebi, Amin Tipirneni, Sindhu Reddy, Chandan K. Subbian, Vignesh Department of Systems and Industrial Engineering University of Arizona TucsonAZ United States College of Medicine University of Cincinnati CincinnatiOH United States Department of Computer Science Virginia Tech ArlingtonVA United States Department of Biomedical Engineering University of Arizona TucsonAZ United States

Self-supervised learning approaches provide a promising direction for clustering multivariate time-series data. However, real-world time-series data often include missing values, and the existing approaches require imputing missing values before clustering, which may cause extensive computations and noise and result in invalid interpretations. To address these challenges, we present a Self-supervised Learning-based Approach to Clustering multivariate Time-series data with missing values (SLAC-Time). SLAC-Time is a Transformer-based clustering method that uses time-series forecasting as a proxy task for leveraging unlabeled data and learning more robust time-series representations. This method jointly learns the neural network parameters and the cluster assignments of the learned representations. It iteratively clusters the learned representations with the K-means method and then utilizes the subsequent cluster assignments as pseudo-labels to update the model parameters. To evaluate our proposed approach, we applied it to clustering and phenotyping Traumatic Brain Injury (TBI) patients in the Transforming Research and Clinical Knowledge in Traumatic Brain Injury (TRACK-TBI) study. Clinical data associated with TBI patients are often measured over time and represented as time-series variables characterized by missing values and irregular time intervals. Our experiments demonstrate that SLAC-Time outperforms the baseline K-means clustering algorithm in terms of silhouette coefficient, Calinski Harabasz index, Dunn index, and Davies Bouldin index. We identified three TBI phenotypes that are distinct from one another in terms of clinically significant variables as well as clinical outcomes, including the Extended Glasgow Outcome Scale (GOSE) score, Intensive Care Unit (ICU) length of stay, and mortality rate. The experiments show that the TBI phenotypes identified by SLAC-Time can be potentially used for developing targeted clinical trials and therapeutic strategies. © 2

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

A SUCCESSIVE TWO-STAGE METHOD FOR SPARSE GENERALIZED EIGENVALUE PROBLEMS

arXiv

引用

arXiv 2023年

作者： Li, Qia Liao, Jianmin Shen, Lixin Zhang, Na School of Computer Science and Engineering Guangdong Province Key Laboratory of Computational Science Sun Yat-sen University Guangdong Province Guangzhou510275 China Department of Mathematics Syracuse University SyracuseNY13244 United States Department of Applied Mathematics College of Mathematics and Informatics South China Agricultural University Guangdong Province Guangzhou510642 China

The Sparse Generalized Eigenvalue Problem (sGEP), a pervasive challenge in statistical learning methods including sparse principal component analysis, sparse Fisher's discriminant analysis, and sparse canonical correlation analysis, presents significant computational complexity due to its NP-hardness. The primary aim of sGEP is to derive a sparse vector approximation of the largest generalized eigenvector, effectively posing this as a sparse optimization problem. Conventional algorithms for sGEP, however, often succumb to local optima and exhibit significant dependency on initial points. This predicament necessitates a more refined approach to avoid local optima and achieve an improved solution in terms of sGEP's objective value, which we address in this paper through a novel successive two-stage method. The first stage of this method incorporates an algorithm for sGEP capable of yielding a stationary point from any initial point. The subsequent stage refines this stationary point by adjusting its support, resulting in a point with an enhanced objective value relative to the original stationary point. This support adjustment is achieved through a novel procedure we have named support alteration. The final point derived from the second stage then serves as the initial point for the algorithm in the first stage, creating a cyclical process that continues until a predetermined stopping criterion is satisfied. We also provide a comprehensive convergence analysis of this process. Through extensive experimentation under various settings, our method has demonstrated significant improvements in the objective value of sGEP compared to existing methodologies, underscoring its potential as a valuable tool in statistical learning and *** Codes 90C26, 90C32, 90C59, 90C90 Copyright © 2023, The Authors. All rights reserved.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Affective posture recognition: Human factors and modelling 20

Affective posture recognition: Human factors and modelling

引用

20th British computer Society Conference on Human-computer Interaction: Engage, HCI 2006

作者： Kleinsmith, Andrea Bianchi-Berthouze, Nadia Department of Information Systems University of Aizu Aizu-Wakamatsu Japan Department of Computer Science University College London London United Kingdom

Through technology, it has become increasingly important to create more natural and effective interactive interfaces that are capable of communicating with the user through affective channels to improve user experience. The role of body posture in affect recognition, and the importance of emotion in the development and support of intelligent and social behavior have been widely accepted. Our focus is on creating an affective posture recognition system that incrementally learns to recognize users' affective behaviors, such as posture. This information may then be used to inform another application. Thus far, my research has progressed in three main directions. Towards understanding to what extent culture and gender may be important for recognizing affective states, what aspects of affect should be modelled and how, and the identification of a set of low-level, posture features. © BCS HCI Group Conference: Engage, HCI *** right reserved.

关键词： Social behavior

来源：评论

学校读者我要写书评

暂无评论

Computing Power in the Sky: Digital Twin-assisted Collaborative Computing with Multi-UAV Networks

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Wang, Chao Han, Yu Zhang, Long Jia, Ziye Zhang, Hongliang Hong, Choong Seon Han, Zhu Hebei University of Engineering School of Information and Electrical Engineering Handan056038 China Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Jinan250014 China Nanjing University of Aeronautics and Astronautics College of Electronic and Information Engineering Nanjing211106 China Southeast University National Mobile Communications Research Laboratory Jiangsu Nanjing211111 China Peking University State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Beijing100871 China Kyung Hee University Department of Computer Science and Engineering Gyeonggi-do Yongin-si17104 Korea Republic of University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

The collaboration of computing powers (CPs) among unmanned aerial vehicles (UAVs)-mounted edge servers is essential to handle data-intensive tasks of user equipments (UEs). This paper presents a multi-UAV computing power network (CPN) that orchestrates the CP resources of edge servers to cooperatively process tasks through collaborative computing. Due to the frequent interactions among edge servers and the increased complexities for large-scale task executions, we propose a digital twin (DT)-driven multi-UAV CPN framework, where the aerial DT network is created as a digital replica of the multi-UAV network to assist collaborative computing. A joint optimization problem of the service association, offloading power control, task partitions, CP allocation, and UAV trajectory design is formulated to minimize the long-term average delay of UEs. We use the Lyapunov technique to tackle the long-term energy constraint, forming a tractable optimization problem, which is modeled as a Markov decision process to balance the UAV's deficit queue stability and the UE's task completion delay. A hybrid soft actor-critic based deep reinforcement learning algorithm is developed to optimize the joint design by sampling the hybrid action from the Gumbel and Gaussian distributions. Simulation results verify that the multi-UAV CPN contributes to significant performance gains when supported by DTs. © 2025 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Retrospective for the dynamic sensorium competition for predicting large-scale mouse primary visual cortex activity from videos 24

Retrospective for the dynamic sensorium competition for pred...

引用

Proceedings of the 38th International Conference on Neural Information Processing systems

作者： Polina Turishcheva Paul G. Fahey Michaela Vystrčilová Laura Hansel Rachel Froebe Kayla Ponder Yongrong Qiu Konstantin F. Willeke Mohammad Bashiri Ruslan Baikulov Yu Zhu Lei Ma Shan Yu Tiejun Huang Bryan M. Li Wolf De Wulf Nina Kudryashova Matthias H. Hennig Nathalie L. Rochefort Arno Onken Eric Wang Zhiwei Ding Andreas S. Tolias Fabian H. Sinz Alexander S. Ecker Institute of Computer Science and Campus Institute Data Science University of Göttingen Germany Department of Neuroscience & Center for Neuroscience and Artificial Intelligence Baylor College of Medicine Houston Texas and Department of Ophthalmology Byers Eye Institute Stanford University School of Medicine Stanford CA and Stanford Bio-X Stanford University Stanford CA and Wu Tsai Neurosciences Institute Stanford University Stanford CA Department of Neuroscience & Center for Neuroscience and Artificial Intelligence Baylor College of Medicine Houston Texas Institute of Computer Science and Campus Institute Data Science University of Göttingen Germany and Department of Ophthalmology Byers Eye Institute Stanford University School of Medicine Stanford CA and Stanford Bio-X Stanford University Stanford CA and Wu Tsai Neurosciences Institute Stanford University Stanford CA Institute of Computer Science and Campus Institute Data Science University of Göttingen Germany and International Max Planck Research School for Intelligent Systems Tübingen Germany and Institute for Bioinformatics and Medical Informatics Tübingen University Germany lRomul Russia Institute of Automation Chinese Academy of Sciences China and Beijing Academy of Artificial Intelligence China Beijing Academy of Artificial Intelligence China Institute of Automation Chinese Academy of Sciences China The Alan Turing Institute UK and School of Informatics University of Edinburgh UK School of Informatics University of Edinburgh UK Centre for Discovery Brain Sciences University of Edinburgh UK and Simons Initiative for the Developing Brain University of Edinburgh UK Department of Neuroscience & Center for Neuroscience and Artificial Intelligence Baylor College of Medicine Houston Texas and Department of Ophthalmology Byers Eye Institute Stanford University School of Medicine Stanford CA and Stanford Bio-X Stanford University Stanford CA and Wu Tsai Neurosciences Institute Stanford University Stanf

ISBN: (纸本)9798331314385

Understanding how biological visual systems process information is challenging because of the nonlinear relationship between visual input and neuronal responses. Artificial neural networks allow computational neuroscientists to create predictive models that connect biological and machine vision. Machine learning has benefited tremendously from benchmarks that compare different models on the same task under standardized conditions. However, there was no standardized benchmark to identify state-of-the-art dynamic models of the mouse visual system. To address this gap, we established the SENSORIUM 2023 Benchmark Competition with dynamic input, featuring a new large-scale dataset from the primary visual cortex of ten mice. This dataset includes responses from 78,853 neurons to 2 hours of dynamic stimuli per neuron, together with behavioral measurements such as running speed, pupil dilation, and eye movements. The competition ranked models in two tracks based on predictive performance for neuronal responses on a held-out test set: one focusing on predicting in-domain natural stimuli and another on out-of-distribution (OOD) stimuli to assess model generalization. As part of the NeurIPS 2023 Competition Track, we received more than 160 model submissions from 22 teams. Several new architectures for predictive models were proposed, and the winning teams improved the previous state-of-the-art model by 50%. Access to the dataset as well as the benchmarking infrastructure will remain online at ***.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Potential Sharing in TV Band using Cognitive Wireless Networks

Potential Sharing in TV Band using Cognitive Wireless Networ...

引用

International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)

作者： Hashim Elshafie Suleiman Zubair Mosab Hamdan Paul Rodrigues Quadri Noorulhasan Naveed Shamimul Qamar College of Computer Science King Khalid University Al Farah Abha Saudi Arabia Department of Telecommunication Engineering Federal University of Technology Minna Niger State Nigeria Interdisciplinary Research Center for Intelligent Secure Systems (IRC-ISS) King Fahd University of Petroleum and Minerals Dhahran Saudi Arabia

ISBN: (数字)9798350351484

ISBN: (纸本)9798350351491

Cognitive wireless networks (CWNs) are advanced wireless systems where network nodes are equipped via smart engines, enabling them to exhibit intelligent behavior across the entire network. This advancement holds promise for improving commercial data services and facilitating the establishment of new emergency and surveillance and military communication services. An illustration of this is the exploration of sharing between licensed TV bands (primary user) and unlicensed WiMax (secondary user). Despite the allocation of a significant portion of the radio frequency spectrum to TV bands, much of it remains unused. This underutilization makes TV spectrum an attractive candidate for dynamic spectrum access (DSA). However, further investigation is necessary to ascertain the suitability of this spectrum for supporting secondary transmissions. Dynamic Frequency Selection (DFS) empowers radios to select bands by minimal interference, while Power Control (PC) facilitates communication at the lowest feasible power transmit. Time Agility (TA) allows radios to adjust according to the traffic patterns of one another, This helps reduce disruption in challenging channel situations. These techniques were evaluated through simulations conducted using the network simulator NS2. The proposed network is TV Based station as primary user and many WiMax connected together as mesh network. The result proves that WiMax transmitting data within TV Channels when TV channels not transmitting and WiMax within same geographical coverage of TV Base Station.

关键词： Mesh networks TV Wireless networks Surveillance Power control Standardization WiMAX

来源：评论

学校读者我要写书评

暂无评论

Human Expansion-Induced Biodiversity Crisis over Asia from 2000 to 2020

引用

Research 2024年第2期2023卷 647-658页

作者： Chao Yang Qingquan Li Xuqing Wang Aihong Cui Junyi Chen Huizeng Liu Wei Ma Xuanyan Dong Tiezhu Shi Fanyi Meng Xiaohu Yan Kai Ding Guofeng Wu MNR Key Laboratory for Geo-Environmental Monitoring of Great Bay Area&Guangdong Key Laboratory of Urban Informatics&Shenzhen Key Laboratory of Spatial Smart Sensing and Services Shenzhen UniversityShenzhen 518060China School of Architecture and Urban Planning Shenzhen UniversityShenzhen 518060China College of Civil and Transportation Engineering Shenzhen UniversityShenzhen 518060China Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ) Shenzhen 518107China Center for Hydrogeology and Environmental Geology China Geological SurveyBaoding 071051China Department of Geography Hong Kong Baptist UniversityHong Kong Special Administrative Region 999077China Faculty of Land Resource Engineering Kunming University of Science and TechnologyKunming 650093China institute for Advanced Study and Tiandu-Shenzhen University Deep Space Joint Laboratory Shenzhen UniversityShenzhen 518060China School of Civil Engineering Chongqing Jjiaotong UniversityChongging 400074China Department of Cil and Environmental Engineering Tohoku UniversitySendai 980-8579Japan School of Artificial Intelligence Shenzhen PolytechnicShenzhen 518055China School of Computer Science and Technology Dongguan University of TechnologyDongguan 523419China

Asia stands out as a priority for urgent biodiversity conservation due to its large protected areas(PAs)and threatened *** the 21st century,both the highlands and lowlands of Asia have been experiencing the dramatic human ***,the threat degree of human expansion to biodiversity is poorly ***,the threat degree of human expansion to biodiversity over 2000 to 2020 in Asia at the continental(Asia),national(48 Asian countries),and hotspot(6,502 Asian terrestrial PAs established before 2000)scales is investigated by integrating multiple large-scale *** results show that human expansion poses widespread threat to biodiversity in Asia,especially in Southeast Asia,with Malaysia,Cambodia,and Vietnam having the largest threat degrees(~1.5 to 1.7 times of the Asian average level).Human expansion in highlands induces higher threats to biodiversity than that in lowlands in one-third Asian countries(most Southeast Asian countries).The regions with threats to biodiversity are present in~75%terrestrial PAs(including 4,866 PAs in 26 countries),and human expansion in PAs triggers higher threat degrees to biodiversity than that in *** findings provide novel insight for the Sustainable Development Goal 15(SDG-15 Life on Land)and suggest that human expansion in Southeast Asian countries and PAs might hinder the realization of *** reduce the threat degree,Asian developing countries should accelerate economic transformation,and the developed countries in the world should reduce the demands for commodity trade in Southeast Asian countries(i.e.,trade leading to the loss of wildlife habitats)to alleviate human expansion,especially in PAs and highlands.

关键词： Human terrestrial integrating

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：