检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Peng, Shifeng Hou, Xuefeng Shen, Zhishu Zheng, Qiushi Jin, Jiong Tagami, Atsushi Yuan, Jingling School of Computer Science and Artificial Intelligence Wuhan University of Technology China School of Science Computing and Engineering Technologies Swinburne University of Technology Australia KDDI Research Inc. Japan

Satellite computing has emerged as a promising technology for next-generation wireless networks. This innovative technology provides data processing capabilities, which facilitates the widespread implementation of artificial intelligence (AI)-based applications, especially for image processing tasks involving deep neural network (DNN). With the limited computing resources of an individual satellite, independently handling DNN tasks generated by diverse user equipments (UEs) becomes a significant challenge. One viable solution is dividing a DNN task into multiple subtasks and subsequently distributing them across multiple satellites for collaborative computing. However, it is challenging to partition DNN appropriately and allocate subtasks into suitable satellites while ensuring load balancing. To this end, we propose a collaborative satellite computing system designed to improve task processing efficiency in satellite networks. Based on this system, a workload-balanced adaptive task splitting scheme is developed to equitably distribute the workload of DNN slices for collaborative inference, consequently enhancing the utilization of satellite computing resources. Additionally, a self-adaptive task offloading scheme based on a genetic algorithm (GA) is introduced to determine optimal offloading decisions within dynamic network environments. The numerical results illustrate that our proposal can outperform comparable methods in terms of task completion rate, delay, and resource utilization. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Quarks: A Secure and Decentralized Blockchain-Based Messaging Network 10

Quarks: A Secure and Decentralized Blockchain-Based Messagin...

引用

10th IEEE International Conference on Cyber Security and Cloud computing and 9th IEEE International Conference on Edge computing and Scalable Cloud, CSCloud-EdgeCom 2023

作者： Shuhan, Mirza K. B. Islam, Tariqul Shuvo, Enam A. Bappy, Faisal H. Hasan, Kamrul Caicedo, Carlos Software Research and Engineering BKash Limited Dhaka Bangladesh SyracuseNY United States Asia Pacific University of Technology and Innovation School of Computing Kuala Lumpur Malaysia Tennessee State University NashvilleTN United States

ISBN: (纸本)9798350312461

Over the past two decades, the popularity of messaging systems has increased both in enterprise and consumer level. Many of these systems used secure protocols like end-to-end encryption to ensure strong security features such as 'future secrecy' for one-to-one communication. However, the majority of them rely on centralized servers owned by big IT companies, which allows them to use their users' personal data. Also it allows the government to track and regulate their citizens' activities, which poses significant threats to 'digital freedom'. Also, these systems have failed to achieve security attributes like confidentiality, integrity, privacy, and future secrecy for group communications. In this paper, we present a novel blockchain-based secure messaging system named Quarks that overcomes the security pitfalls of the existing systems and eliminates the centralized control. We have analyzed our design of the system with security models and definitions from existing literature to demonstrate the system's reliability and usability. We have developed a Proof of Concept (PoC) of the Quarks system leveraging Distributed Ledger technology (DLT), and conducted load testing on that. We noticed that our PoC system achieves all the desired attributes that are prevalent in a traditional centralized messaging scheme despite the limited capacity of the development and testing environment. Therefore, this assures us the applicability of such systems in near future if scaled up properly. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Selective State Space Model for Monaural Speech Enhancement

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Chen, Moran Zhang, Qiquan Wang, Mingjiang Zhang, Xiangyu Liu, Hexin Ambikairaiah, Eliathamby Chen, Deying Harbin Institute of Technology School of Electronic and Information Engineering Shenzhen518055 China The University of New South Wales School of Electrical Engineering and Telecommunications Sydney2052 Australia Nanyang Technological University College of Computing and Data Science Singapore Singapore

Voice user interfaces (VUIs) have facilitated the efficient interactions between humans and machines through spoken commands. Since real-word acoustic scenes are complex, speech enhancement plays a critical role for robust VUI. Transformer and its variants, such as Conformer, have demonstrated cutting-edge results in speech enhancement. However, both of them suffers from the quadratic computational complexity with respect to the sequence length, which hampers their ability to handle long sequences. Recently a novel State Space Model called Mamba, which shows strong capability to handle long sequences with linear complexity, offers a solution to address this challenge. In this paper, we propose a novel hybrid convolution-Mamba backbone, denoted as MambaDC, for speech enhancement. Our MambaDC marries the benefits of convolutional networks to model the local interactions and Mamba's ability for modeling long-range global dependencies. We conduct comprehensive experiments within both basic and state-of-the-art (SoTA) speech enhancement frameworks, on two commonly used training targets. The results demonstrate that MambaDC outperforms Transformer, Conformer, and the standard Mamba across all training targets. Built upon the current advanced framework, the use of MambaDC backbone showcases superior results compared to existing SoTA systems. This sets the stage for efficient long-range global modeling in speech enhancement. © 2025 IEEE.

关键词： State space methods

来源：评论

学校读者我要写书评

暂无评论

Humanoid Robot Collaborative Lifting Integrating Executable Judgment

Humanoid Robot Collaborative Lifting Integrating Executable ...

引用

2022 IEEE International Symposium on Product Compliance engineering - Asia, ISPCE-ASIA 2022

作者： Chang, Hua Yi, Pengfei Liu, Rui Dong, Jing Hou, Yaqing Zhou, Dongsheng The Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian University Dalian China Dalian University of Technology Dalian China

ISBN: (数字)9798350332483

ISBN: (纸本)9798350332483

Humanoid robot collaborative lifting can be used in a variety of scenarios that require repetitive lifting tasks. Most existing studies of humanoid robot collaboration often assume that objects can always be lifted, which may result in damage to both the robot and the object if objects are too heavy to lift. To avoid such situations as much as possible, a collaborative lifting approach integrating executable judgment is proposed. First, a target search and localization method is constructed using monocular vision and marker points to identify the task object. Then, an executable judgment strategy is designed to determine whether the object is overweight or not according to robot force analysis. Finally, a multi-robot joint control model is proposed based on collaborative communication to perform collaborative tasks with different loads based on the judgment results. Experiments on two humanoid robots for different types and weights of targets show the effectiveness of the proposed approach. © 2022 IEEE.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

FusionANNS: An Efficient CPU/GPU Cooperative Processing Architecture for Billion-scale Approximate Nearest Neighbor Search

arXiv

引用

arXiv 2024年

作者： Tian, Bing Liu, Haikun Tang, Yuhang Xiao, Shihai Duan, Zhuohui Liao, Xiaofei 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

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. 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 collabo rative filtering and re-ranking mechanisms, which signifi cantly 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 imple ment 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. Copyright © 2024, The Authors. All rights reserved.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Enhancing Disaster Response: A Dual-Drone Approach for Efficient Area Scanning and Life Detection 7th

Enhancing Disaster Response: A Dual-Drone Approach for Effic...

引用

7th International Conference on Soft computing and Signal Processing, ICSCSP 2024

作者： Mummoorthy, A. Balamurugan, P. Patibandla, Anitha Department of Information Technology Malla Reddy College of Engineering and Technology Hyderabad India School of Computing SRM Institute of Science and Technology Tamil Nadu Kattankulathur603203 India Department of ECE Malla Reddy College of Engineering and Technology Hyderabad India

ISBN: (纸本)9789819799251

The paper proposes a new methodology for utilizing drones and UAVs during natural disasters such as floods and earthquakes. Natural disasters represent some of the most devastating events imaginable, underscoring the critical importance of preparedness to swiftly aid affected individuals. While natural disasters occur with varying frequency across the globe, their occurrence can severely impede human communication and mobility within affected regions. Providing assistance and procuring necessary equipment become significantly challenging, compounded by the constrained time available for response efforts. The initial 72 h following a disaster is pivotal for rescue operations. Developing an optimal rescue plan from ground-level assessments proves impractical. This is where drones and Unmanned Aerial Vehicles (UAVs) come into play. With advancements in drone technology, it becomes imperative to devise intelligent strategies for their deployment during natural disasters. This paper endeavors to propose an intuitive methodology aimed at analyzing affected areas, providing optimized routes, and predicting safe zones through modern machine learning algorithms. The proposed methodology seeks to expedite the analysis of current conditions and enhance the efficiency and safety of rescue operations. Central to this project is the establishment of reliable communication between the two drones and the server, along with the development of efficient task allocation strategies for each drone. Additionally, the methodology includes an interactive user interface housing all the information communicated and computed by the system. In conclusion, the proposed methodology aims to streamline rescue operations during natural disasters by harnessing the capabilities of drones and UAVs. Through improved efficiency and informed decision-making, this approach endeavors to enhance the effectiveness of disaster response efforts, ultimately contributing to saving lives and mitigating the impact

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Study on Relative Distances of Hand Landmarks Approach for American Sign Language Gesture

引用

Augmented Human Research 2024年第1期9卷 1-12页

作者： Shah, Shail Vaidya, Jaynil Pipariya, Kishan Shah, Manan Department of Computer Science North Carolina State University Raleigh USA School of Computing and Augmented Intelligence Arizona State University Tempe USA Department of Computer Engineering School of Technology Pandit Deendayal Energy University Gandhinagar India Department of Chemical Engineering School of Energy Technology Pandit Deendayal Energy University Gandhinagar India

Communication with people with hearing or speaking disabilities is always difficult when there is no knowledge of sign language. The presence of sign language is not enough to communicate smoothly, this process requires another easy medium for communication to make it more efficient, that is, via a digital medium. This paper proposes using Feed-Forward Neural Networks on hand landmarks for real-time sign language identification. The hand landmarks identification was carried out using the MediaPipe Hands library. This approach would make the classification problem efficient by making it faster and requiring less memory. Through this, we aim to bridge the gap between the difficulties that arise during communication between people who do and do not know American Sign Language.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Review of Job Postings in India Concerning Artificial Intelligence and Machine Learning Skills 2nd

A Review of Job Postings in India Concerning Artificial Inte...

引用

2nd International Conference on Global Economic Revolutions, ICGER 2023

作者： Lamkuche, Hemraj Shobharam Masih, Jolly Bhagwat, Abhijit Morya, Shakti Onker, Vandana Singh, Krishna Kumar School of Computing Science and Engineering VIT Bhopal University Kothrikalan Madhya Pradesh Sehore466114 India School of Management BML Munjal University Haryana Gurugram India Symbiosis Centre for Management and Human Resource Development Pune India Sai Developers Indore India Pune India Symbiosis Centre for Information Technology Pune India

ISBN: (纸本)9783031505171

In order to effectively communicate, keep records, make decisions, and evaluate data, businesses require access to information. Recently, jobs in data science domain have skyrocketed in popularity thanks to abundant data and cheap processing power. Degree programmes in Information technology strive to keep up with the industry's rising demand. The authors looked at a large number of job listings from different sites to determine what skills and experiences are necessary for positions involving artificial intelligence and machine learning. The author also analyses the necessary abilities for each vocation and provides an evaluation. Furthermore, they compared the locations of ML and AI head-to-head. Data engineering, exploratory data analysis, programming, statistics, the internet of things, applied mathematics, neural network architectures, language, multimedia processing, and big data were all found to be more highly valued by employers in roles requiring ML and AI. Instead, communication skills and a generalist mindset are valued more highly in AI positions. Having these clearly defined abilities could also aid in the job search and in adapting existing course material to match the growing needs of the market. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Learning manipulation of steep granular slopes for fast Mini Rover turning

Learning manipulation of steep granular slopes for fast Mini...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Deniz Kerimoglu Daniel Soto Malone Lincoln Hemsley Joseph Brunner Sehoon Ha Tingnan Zhang Daniel I. Goldman School of Physics Georgia Institute of Technology Atlanta USA Department of Applied Physics and Engineering Morehouse College Atlanta USA School of Interactive Computing Georgia Institute of Technology Atlanta USA

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Future planetary exploration missions will require reaching challenging regions such as craters and steep slopes. Such regions are ubiquitous and present science-rich targets potentially containing information regarding the planet’s internal structure. Steep slopes consisting of low-cohesion regolith are prone to flow downward under small disturbances, making it challenging for autonomous rovers to traverse. Moreover, the navigation trajectories of rovers are heavily limited by the terrain topology and future systems will need to maneuver on flowable surfaces without getting trapped, allowing them to further expand their reach and increase mission *** this work, we used a robophysical rover model and performed maneuvering experiments on a steep granular slope of poppy seeds to explore the rover’s turning capabilities. The rover is capable of lifting, sweeping, and spinning its wheels, allowing it to execute leg-like gait patterns. The high-dimensional actuation capabilities of the rover facilitate effective manipulation of the underlying granular surface. We used Bayesian Optimization (BO) to gain insight into successful turning gaits in high dimensional search space and found strategies such as differential wheel spinning and pivoting around a single sweeping wheel. We then used these insights to further fine-tune the turning gait, enabling the rover to turn nearly 90 degrees at just above 4 seconds with minimal downhill slip. Combining gait optimization and human-tuning approaches, we found that fast turning is empowered by creating anisotropic torques with the sweeping wheel.

关键词： Systematics Navigation Wheels Turning Bayes methods Trajectory Topology

来源：评论

学校读者我要写书评

暂无评论

Construction of Simulation Environment and Design of Path Planning for Maze Robot

Construction of Simulation Environment and Design of Path Pl...

引用

International Conference on Information Systems and Computer Aided Education (ICISCAE)

作者： Wei Xie Qian Wang Dengyun Peng School of Information Science and Engineering Harbin Institute of Technology at Weihai Weihai China School of Computing Harbin Institute of Technology at Weihai Weihai China

Aiming at environment modeling and path planning search of the maze robot, a method how to construct simulation environment and design path planning algorithm is presented in this paper. On the basis of WPF framework, Using XAML interface description language and C# to build simulation environment, a multi-functional open maze generation interface and maze solution and verification platform is provided. The user can intuitively design the maze grid map to simulate the maze solving process by animation. They also can easily add new and verify algorithms by inheriting or rewriting the abstract class provided. What’s more, based on the traditional maze algorithm breadth-first searching strategy and depth-first searching strategy, the shortest path planning algorithm using a combination of breadth and depth is brought forward for demonstration. And the final test result has shown the feasibility and effectiveness of this method.

关键词：

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：