检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Waite, Thomas Robey, Alexander Hassani, Hamed Pappas, George J. Ivanov, Radoslav Dept. of Computer Science Rensselaer Polytechnic Institute United States Dept. of Electrical and Systems Engineering University of Pennsylvania United States

This paper addresses the problem of data-driven modeling and verification of perception-based autonomous systems. We assume the perception model can be decomposed into a canonical model (obtained from first principles or a simulator) and a noise model that contains the measurement noise introduced by the real environment. We focus on two types of noise, benign and adversarial noise, and develop a data-driven model for each type using generative models and classifiers, respectively. We show that the trained models perform well according to a variety of evaluation metrics based on downstream tasks such as state estimation and control. Finally, we verify the safety of two systems with high-dimensional data-driven models, namely an image-based version of mountain car (a reinforcement learning benchmark) as well as the F1/10 car, which uses LiDAR measurements to navigate a racing track. Copyright © 2023, The Authors. All rights reserved.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Kid Activity Recognition: A Comprehensive study of kid activity recognition with monitoring activity level using YOLOv8s Algorithms 3

Kid Activity Recognition: A Comprehensive study of kid activ...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Bisla, Tiya Shukla, Ritik Dhawan, Mansi Islam, Md. Rahatul Koyasu, Takao Teramoto, Keisuke Kataoka, Yui Horio, Keiichi Dronacharya Group of Institution Dept. of Computer Science & Engineering Greater Noida India Kyushu Institute of Technology Graduate School of Life Science and Systems Engineering Fukuoka Japan Kyushu Women's Junior College Fukuoka Japan Aichi University of Education Aichi Japan Fukuoka Kodomo Junior College Fukuoka Japan

ISBN: (纸本)9798350372120

Recognizing human activities and behavior is a cutting-edge field of research because of the complexity and limited availability of data. Our research involves the use of the trending YOLOv8s deep learning algorithm for the classification of active states (sitting, standing, running, laying, and jumping). The research focuses on the detection of a child's activities in the kindergarten playroom. To train the model, we created the KAR (Kids Action Recognition) dataset using our own sources. We labeled over 6,489 images in the dataset using ***. Each image is annotated with activity labels and the location of the student (in a room or on a mat). This assisted in presenting insights on the student's vitality level and physical involvement over a period of approximately an hour. We analyzed the whole activity and compared it with the times. Standing in the room and mat, standing in the room, and jumping in the room and mat are most of the activities of the kid. The model achieved an impressive overall accuracy of 88.7 %. We conducted all the training in a Google collaborative environment with A-100 GPU specifications. The results demonstrate that the model can identify and classify each activity with high precision. © 2024 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Conversational Voice Interfaces: Translating Research Into Actionable Design

Conversational Voice Interfaces: Translating Research Into A...

引用

2025 CHI Conference on Human Factors in Computing systems, CHI EA 2025

作者： Murad, Christine Munteanu, Cosmin Penn, Gerald University of Waterloo Waterloo ON Canada Carleton University Ottawa ON Canada Department of Systems Design Engineering University of Waterloo Waterloo ON Canada University of Toronto Toronto ON Canada Dept. of Computer Science University of Toronto Toronto ON Canada

ISBN: (纸本)9798400713958

HCI research has for long been dedicated to better and more naturally facilitating information transfer between humans and machines. Unfortunately, humans’ most natural form of communication, speech, is also one of the most difficult modalities to be understood by machines – despite, and perhaps, because it is the highest-bandwidth communication channel we possess. As significant research efforts in engineering have been spent on improving machines’ ability to understand speech, research is only beginning to make the same improvements in understanding how to appropriately design these speech interfaces to be user-friendly and adoptable. Issues such as variations in error rates when processing speech, and difficulties in learnability and explainability (to name a few), are often in contrast with claims of success from industry. Along with this, designers themselves are making the transition to designing for speech and voice-enabled interfaces. Recent research has demonstrated the struggle for designers to translate their current experiences in graphical user interface design into speech interface design. Research has also noted the lack of any user-centered design principles or consideration for usability or usefulness in the same ways as graphical user interfaces have benefited from heuristic design guidelines. The goal of this course is to inform the CHI community of the current state of speech and natural language research, to dispel some of the myths surrounding speech-based interaction, as well as to inform participants about currently existing design tools, methods and resources for speech interfaces (and provide hands-on experience with working with them). Through this, we hope that HCI researchers and practitioners will learn how to combine recent advances in speech processing with user-centred principles in designing more usable and useful speech-based interactive systems. © 2025 Copyright held by the owner/author(s).

关键词： conversational voice interfaces speech interface design speech interfaces

来源：评论

学校读者我要写书评

暂无评论

DCGAN-based Medical Image Augmentation to Improve ELM Classification Performance 11

DCGAN-based Medical Image Augmentation to Improve ELM Classi...

引用

11th IEEE International Conference on Communication, Networks and Satellite, COMNETSAT 2022

作者： Rando Setiawan, Noor Akhmad Permanasari, Adhistya Erna Rulaningtyas, Riries Suksmono, Andriyan Bayu Sitanggang, Imas Sukaesih Universitas Gadjah Mada Dept. of Electrical and Information Engineering Yogyakarta Indonesia Biomedical Engineering Program Dept. of Physics Universitas Airlangga Surabaya Indonesia Institut Teknologi Bandung School of Electrical Engineering and Informatics Bandung Indonesia Ipb University Department of Computer Science Bogor Indonesia

ISBN: (纸本)9781665460309

Cervical cancer is one of the deadliest diseases in women. One of the cervical cancer screening methods is pap smear method. However, using a pap smear method to detect cervical cancer takes a long time for a pathologist to diagnose. Hence, a rapid development of medical computerization for early detection to get the results quickly is needed. This paper proposes synthetic data augmentation by using Deep Convolutional Generative Adversarial Network (DCGAN) to increase number of pap smear samples in dataset. Gray Level Co-occurrence Matrix (GLCM) is employed to extract features from dataset. Classification of 3 classes which are Adenocarcinoma, High-Grade Squamous Intraepithelial Lesion (HSIL), and Squamous Cell Carcinoma (SCC) is conducted using Extreme Learning Machine (ELM). The result shows that the addition of synthetic data improves the performance of ELM with the accuracy of 90%. This accuracy is better than the accuracy of ELM using only the original dataset which is 85%. © 2022 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Building Collaborative Learning: Exploring Social Annotation in Introductory programming

arXiv

引用

arXiv 2024年

作者： de Oliveira Neto, Francisco Gomes Dobslaw, Felix Chalmers The University of Gothenburg Dept. of Computer Science and Engineering Gothenburg Sweden Mid Sweden University Dept. of Quality Mngmt Communication and Inf. Systems Östersund Sweden

The increasing demand for software engineering education presents learning challenges in courses due to the diverse range of topics that require practical applications, such as programming or software design, all of which are supported by group work and interaction. Social Annotation (SA) is an approach to teaching that can enhance collaborative learning among students. In SA, both students and teachers utilize platforms like Feedback Fruits, Perusall, and Diigo to collaboratively annotate and discuss course materials. This approach encourages students to share their thoughts and answers with their peers, fostering a more interactive learning environment. We share our experience of implementing social annotation via Perusall as a preparatory tool for lectures in an introductory programming course aimed at undergraduate students in Software engineering. We report the impact of Perusall on the examination results of 112 students. Our results show that 81% of students engaged in meaningful social annotation successfully passed the course. Notably, the proportion of students passing the exam tends to rise as they complete more Perusall assignments. In contrast, only 56% of students who did not participate in Perusall discussions managed to pass the exam. We did not enforce mandatory Perusall participation in the course. Yet, the feedback from our course evaluation questionnaire reveals that most students ranked Perusall among their favorite components of the course and that their interest in the subject has increased. © 2024, CC BY.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Ensuring Electronic Health Record (EHR) Privacy using Zero Knowledge Proofs (ZKP) and Secure Encryption Schemes on Blockchain

Ensuring Electronic Health Record (EHR) Privacy using Zero K...

引用

Advancements in Computing (ICAC), International Conference on

作者： Ranaweera T.A.V.Y Hewage H.N.H Hapuhinna H.K.D.W.M.C.B. Preethilal K.L.K.T Amila Senarathne Laneesha Ruggahakotuwa Dept. Computer Systems Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka

In the haste of EHR digitization, the protection of patient data becomes paramount, casting a spotlight on small healthcare clinics grappling with the threats of an ever more interconnected healthcare sector. That is due to the existing centralized system and traditional password-based authentications which cause a single point of failure. Besides this patient consent for EHR sharing is narrowed to a one-time consent. To overcome these problems, this study suggests a robust solution that makes data sharing utilizing blockchain while achieving privacy using web-based Zero Knowledge Proofs (ZKP) authentication and Homomorphic Encryption (HE). The research also considers securely outsourcing EHRs to research organizations to improve data exchange for research purposes. Along with patient-controlled encryption, consent control, and time-limited data access, it also explores dynamic consent management while complying with healthcare standards. Lastly, this study stream-lines secure data sharing with insurance providers while ensuring patient privacy and defending against insurance fraud.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Respect the Difference: Reinforcement Learning for Heterogeneous FPGA Placement

Respect the Difference: Reinforcement Learning for Heterogen...

引用

IEEE International Conference on Field-programmable Technology (FPT)

作者： Fatemehsadat Mahmoudi Mohamed A. Elgammal Soheil Gholami Shahrouz Kevin E. Murray Vaughn Betz Dept. of Electrical & Computer Engineering University of Toronto Toronto Canada Cerebras Systems Toronto Canada

Simulated Annealing (SA) is widely used for FPGA placement due to its ability to adapt to different architectures and optimization goals. However, as FPGA capacity has grown and the devices have become more heterogeneous, the solution space has become very large, making efficient approaches to explore the space critical. We present RLPlace 2.0, an FPGA placer based on simulated annealing that utilizes Reinforcement Learning (RL) and better-than-random initial placement for efficient solution space exploration. The RL agent decides not only on the move types to use at each point in the anneal but also the type of block to move. The RL agent that controls the process is trained entirely online, enabling automatic adaptation to the architecture and design. For traditional FPGA benchmarks, RLPlace 2.0 outperforms both VPR 8 and RLPlace 1.0 in wirelength (WL) and critical path delay (CPD) at all runtime points. For example, on average over the Koios benchmark suite, RLPlace 2.0 reduces CPD by 3% and WL by 1.8% while cutting placement time by 54% at the default run time point vs. VPR 8. On more complex and heterogeneous FPGAs that incorporate a hard Network on Chip (NoC), RLPlace 2.0 enables more efficient co-optimization of NoC and programmable routing metrics by learning when and how to move the NoC routers throughout the anneal. On average for benchmarks containing NoC routers, RLPlace 2.0 achieves the same WL and CPD, 41% reduced NoC latency, and 6% improved NoC bandwidth usage in 50% less time compared to RLPlace 1.0.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Building Collaborative Learning: Exploring Social Annotation in Introductory programming

Building Collaborative Learning: Exploring Social Annotation...

引用

Software engineering: Software engineering Education and Training (ICSE-SEET), IEEE/ACM International Conference on

作者： Francisco Gomes De Oliveira Neto Felix Dobslaw Dept. of Computer Science and Engineering Chalmers and the University of Gothenburg Gothenburg Sweden Dept. of Quality Mngmt Communication and Inf. Systems Mid Sweden University Östersund Sweden

ISBN: (数字)9798400704987

ISBN: (纸本)9798350352115

关键词： Training Software design Annotations Federated learning Buildings programming profession Software engineering

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cybersecurity Through Advanced Fraud and Anomaly Detection Techniques: A Systematic Review

Enhancing Cybersecurity Through Advanced Fraud and Anomaly D...

引用

Science, engineering and Business for Sustainable Development Goals (SEB-SDG), International Conference on

作者： Oluwambo Tolulope Olowe Ayodele A. Adebiyi Adebiyi O. Marion Olowe Mofiyinfoluwa Tobi Deborah Olaniyan Julius Olaniyan Aderemi Emmanuel Kayode Akindeji Dept of Computer Science Landmark University Omuaran Nigeria Dept. of Industrial & Systems Engineering University of Pretoria Pretoria South Africa Dept. of Power Electric Engineering Durban University of Technology Durban South Africa

ISBN: (数字)9798350358155

ISBN: (纸本)9798350358162

Fraud and anomaly detection in cybersecurity have become critical areas of research, prompting a comprehensive review of recent developments and model effectiveness. This study investigates prevalent trends and challenges in fraud and anomaly detection, focusing on data science approaches within e-commerce and smart cities. Through the analysis, key factors influencing detection efficacy, such as deep learning models and hybrid approaches, are examined. Findings highlight the multidimensional nature of cyber threats across various domains and underscore the importance of proactive security measures, including robust authentication, network fortification, and employee training. This paper contributes to enhancing awareness and understanding of evolving cyber threats while offering actionable insights for bolstering detection capabilities and mitigating risks.

关键词： Deep learning Training Systematics Authentication Data science Market research Software

来源：评论

学校读者我要写书评

暂无评论

Automated Boundary Identification for Machine Learning Classifiers

Automated Boundary Identification for Machine Learning Class...

引用

Search-Based and Fuzz Testing (SBFT), IEEE/ACM International Workshop on

作者： Felix Dobslaw Robert Feldt Dept. of Quality Mngmt Communication and Inf. Systems Mid Sweden University Östersund Sweden Dept. of Computer Science and Engineering Chalmers University of Technology Gothenburg Sweden

ISBN: (数字)9798400705625

ISBN: (纸本)9798350376012

AI and Machine Learning (ML) models are increasingly used as (critical) components in software systems, even safety-critical ones. This puts new demands on the degree to which we need to test them and requires new and expanded testing methods. Recent boundary-value identification methods have been developed and shown to automatically find boundary candidates for traditional, non-ML software: pairs of nearby inputs that result in (highly) differing outputs. These can be shown to developers and testers, who can judge if the boundary is where it is supposed to ***, we explore how this method can identify decision boundaries of ML classification models. The resulting ML Boundary Spanning Algorithm (ML-BSA) is a search-based method extending previous work in two main ways. We empirically evaluate ML-BSA on seven ML datasets and show that it better spans and thus better identifies the entire classification boundary(ies). The diversity objective helps spread out the boundary pairs more broadly and evenly. This, we argue, can help testers and developers better judge where a classification boundary actually is, compare to expectations, and then focus further testing, validation, and even further training and model refinement on parts of the boundary where behaviour is not ideal.

关键词： Training Conferences Machine learning Fuzzing Software systems Classification algorithms Testing

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：