检索结果-内蒙古大学图书馆

2023 Conference on Lasers and Electro-Optics Europe and European Quantum Electronics Conference, CLEO/Europe-EQEC 2023

作者： Tsirigotis, Aris Tsilikas, Ioannis Sozos, Kostas Bogris, Adonis Mesaritakis, Charis University of the Aegean Dept. Information and Communication Systems Engineering Palama 2 str. Karlovasi Samos83200 Greece National Technical University of Athens Dept. Applied Physics and Mathematics Iroon Polytechniou 9 Zografou Athens15772 Greece University of West Attica Dept. Informatics and Computer Engineering Ag. Spiridonos Egaleo12243 Greece

ISBN: (纸本)9798350345995

In this work, we demonstrate the impact of an unconventional convolutional photonic accelerator, based on an optical spectrum slicing (OSS) [1], on the classification accuracy of objects, generated through a high-frame rate neuromorphic event-based camera [2]. The experimental setup is depicted in Fig.1a. Ιt consists of a 5 mW-632 nm-LED source, two objective lenses with NA=0.65 that concentrate the light beam into a 100 μmX100 μm channel. In our experiments, the targeted objects consist of test spheres, of different diameters (12, 16, and 20 μm), used in aqua solutions. A pump regulated the sphere's speed to 0.8 m/s. The objects were recorded by a 10 kframe/s capable neuromorphic camera, with a temporal resolution of 1 μs. The camera detects pixel's contrast changes (events), similar to biological systems [2]. The recorded events were exported into 1 kframes/sec videos through a synthetic frame generator software, resulting to 2988 images per particle [2]. Images were post-processed using only noise reduction by frame subtraction and image cropping so as to reduce data volume to 100 x 100 pixels. © 2023 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Human Body Action Recognition based on 3D Feature Fusion over RGB Scenes

Human Body Action Recognition based on 3D Feature Fusion ove...

引用

International Conference on information Technology (ICIT)

作者： Heba Nsour Zaid Mustafa Maria Al-Sendah Dept. of Computer Science Al-Balqa Applied University Albalqa Jordan Dept. of Computer Information Systems Al-Balqa Applied University Albalqa Jordan

Human body action recognition (HBAR) is an important area of research in machine learning and image processing due to its vast range of applications. Similarly, estimating various components of human anatomy from RGB scenes are essential to human action tracking. The present study involves the implementation of human key body point detection for pose estimation. During abstracted silhouettes and vital human points, the proposed system has extracted two main features, such as 3D features and distance features. Once the relevant attributes have been incorporated, executing precise tasks and strategies is critical to achieving maximum features. Therefore, we used the t- SNE-based data refinement technique for optimal feature selection. Finally, for training, a classification model random forest is utilized. The presented system is verified on a recognized benchmark dataset, i.e., the UCF sports database. The experimental settings have revealed that our proposed system has attained better performance and outperformed other present state-of-the-art methods regarding mean recognition rate.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Secure and Efficient Key Management for Deduplicated Cloud Storage systems

Secure and Efficient Key Management for Deduplicated Cloud S...

引用

Security of information and Networks (SIN), International Conference on

作者： Jay Dave Anshul Kanodia Raj Srivastava Kushagra Singh Prithvi Hegde Hitaishi Desai Dept. of Computer Science & Information Systems Birla Institute of Technology & Science Pilani Hyderabad India

Deduplication is a ubiquitous compression technique for cloud storage servers. It reduces storage and bandwidth requirements by avoiding duplicate copies of data. However, developing an encryption scheme for deduplication is a critical challenge because traditional encryption techniques are not compatible with deduplication. The existing state-of-the-art encryption schemes are at risk of brute-force attacks as they use deterministic techniques for key generation. Moreover, the user in the recent schemes suffers from storage overhead of deduplication metadata and encryption keys. In this paper, we introduce a secure and efficient key management scheme for deduplication. In our scheme, the user divides the file into blocks and encrypts each block using a random key. As a result, our scheme protects against brute-force attacks. In addition, the user securely shares the encryption keys on public storage servers with the aid of a private server. As a result, the proposed approach causes lower storage overhead. We implement our scheme in a real cloud scenario and evaluate the performance of our approach in terms of storage and computation overhead.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EMDA-Net: Earth Mover’s Distance (EMD) influenced Attention-aided Neural Network for Medical Image Classification

EMDA-Net: Earth Mover’s Distance (EMD) influenced Attention...

引用

IEEE International Conference on Cognitive Machine Intelligence (CogMI)

作者： Surya Majumder Kushaj Mallick Wrick Pal Somenath Chakraborty Ram Sarkar Dept. of Computer Science & Engineering Heritage Institute of Technology Kolkata India Dept. of Electrical Engineering Jadavpur University Kolkata India Dept. of Computer Science & Information Systems West Virginia University Institute of Technology West Virginia USA Dept. of Computer Science & Engineering Jadavpur University Kolkata India

ISBN: (数字)9798350386721

ISBN: (纸本)9798350386738

Medical image analysis methods need to be more generalized in order to meet the substantial problems associated with cancer detection and treatment, including skin, cervical, and breast cancer. In this work, we propose a novel lightweight convolutional neural network (CNN) architecture, named EMDA-Net (Earth Mover’s Distance (EMD) influenced Attention-aided Neural Network), specifically designed to meet the requirements of cancer subtype classification. It is built on the MobileNetV2 backbone and is equipped with hybrid statistical mechanism-aided attention mechanisms. Our model ensures high-performance while maintaining a lightweight design by leveraging the capabilities of the MobileNetV2 architecture and the attention mechanism. To improve similarity detection across data channels, we present a novel EMD influenced attention technique. We have examined datasets related to skin, cervical, and breast cancer for experimentation. Our model especially outperforms the state-of-the-art techniques, demonstrating its effectiveness in maximizing diagnosis precision for various cancer types across the datasets. The code of the proposed model will be made public at: https://***/q5DlN

关键词： Earth Attention mechanisms Codes Neural networks Skin Breast cancer Convolutional neural networks Medical diagnostic imaging Machine intelligence Image classification

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

Optimal Auto Calling Algorithm for Real-Time Condition Reporting by Corruption Handling Officer 3

Optimal Auto Calling Algorithm for Real-Time Condition Repor...

引用

3rd International Conference on Electrical, Communication and computer Engineering, ICECCE 2021

作者： Ida Gani, Hamdan Faisal, Muhammad Rosnani Stmik Professional Dept. of Information System Makassar Indonesia Stmik Handayani Dept. of Computer Systems Makassar Indonesia

ISBN: (纸本)9781665438971

Corruption is a primary development challenge in Indonesia's economic and social field. In order to overcome these threats, Indonesia's government has been established the Corruption Eradication Commission (Komisi Pemberantasan Korupsi, abbreviated KPK). KPK's goal is to free Indonesia from corruption by investigating corruption cases and monitoring the governance process. KPK uses one effective method called 'hand arrest operation', abbreviated OTT, to handle corruption cases. However, the existing hand arrest operation that KPK used today is not always effective because, in real action, the KPK's official always overdue to find actual evidence of the communication between the suspect. Thus, there is a need for a rapid method to record the suspicious conversation or transaction voice between the suspect as actual evidence for a corruption case. Thus, this paper aims to propose a supporting tool for real-time hand arrest operations to support KPK officials in OTT action. The experimental results show that the proposed method can effectively record all the suspicious communication or transaction voices between the suspect in a scenario room. Finally, this study concluded that the proposed method is a promising way to help the work of KPK in OTT. © 2021 IEEE.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

CyberExpert: Towards an Automated Framework for Cybersecurity Expertise Acquisition and Mastery 53

CyberExpert: Towards an Automated Framework for Cybersecurit...

引用

53rd IEEE ASEE Frontiers in Education International Conference, FIE 2023

作者： Hatcher, William Harrison, Tyler Brown, Truman Hammad, Eman Texas A&m University - Commerce Rellis ISTAR Lab Computer Science & Information Systems Dept. BryanTX United States Texas A&m University ISTAR Lab College StationTX United States

ISBN: (纸本)9798350336429

The continuously increasing gap in cybersecurity workforce in numbers and in skill level, demands a fundamental shift in how we approach cybersecurity education and training. The complex and ever-evolving cybersecurity industry and threat landscape underscores the need for cybersecurity professionals with versatile skillset, growth mindset and resilient character to support organizations' cyber capabilities, preparedness and resilience. This makes it more challenging to develop and operate educational programs that effectively train cybersecurity talent, which is able to take on and perform in multiple roles and responsibilities, without tailoring the program to be very specific to such roles. Hence, cybersecurity educational programs must train professionals that can stand the test of time, in a fast-paced and quickly changing career. In this paper, we expand on innovative approaches we developed to support experiential learning and expertise acquisition for future cybersecurity professionals. The described approach is implemented and is continuously improved and enhanced as part of the educational framework for students in the Cybersecurity Bachelors offered at the Texas A&M University System - RELLIS Campus11Work performed while at Texas A&M University - Commerce. We developed a technology platform (virtual and hands-on) that extends the capabilities of existing similar frameworks (cyber-range) to enable higher levels of experiential learning. A cyber-range is a technology solution, used in industry and academia that provides a dedicated environment to enable several cybersecurity use-cases. The core capability of a cyber-range is to provide users with access to safe, isolated, monitored and secured sandbox environment. We propose and continue to develop an integrated cyber-range platform, CyberExpert cyber-range, that is designed and built using open-source and accessible tools. The CyberExpert cyber-range is equipped with data collection and analysis platforms

关键词： cyber-range cybersecurity experiential learning expertise acquisition virtual machines

来源：评论

学校读者我要写书评

暂无评论

Smart Greenhouse Control System using Multi-Objective Adaptive Policy Gradient and Neural Meta Controller 4

Smart Greenhouse Control System using Multi-Objective Adapti...

引用

4th International Conference on Ubiquitous Computing and Intelligent information systems, ICUIS 2024

作者： Himabindu, C.H. Sreeramu, M. Chaganti, Koushik Reddy Gutta, Pruthvi Krishna Nagesh, C. Ruksana, S. Vignan Institute of Technology and Science Dept of Mba Hyderabad India University of the Cumberlands Dept. of Computer and Information Systems KY United States Tesla Dept of It AustinTX United States Srinivasa Ramanujan Institute of Technology Department of Cse Anantapur India Gates Institute of Technology and Science Department of Cse Anantapur India

ISBN: (纸本)9798331529635

This confluence of escalating energy costs and upsurges in the demand for high-quality crop yields under uncertain environmental conditions makes a strong case for the urgent optimization of greenhouse operations. The most currently used control systems for smart greenhouses are founded upon static or even narrowly focused optimization approaches, which severely limit their adaptability and efficiency in dynamic settings. These methodologies fail to address the challenge of multiple objectives, such as the consumption of energy and crop yield, with unpreparedness for disturbances caused by external influences and computational bottlenecks. This paper brings about a collective framework for three of the most advanced RL methodologies: Multi-Objective Adaptive Policy Gradient with Environmental Feedback, Hierarchical Reinforcement Learning with Temporal Decision Decomposition, and Neural Meta-Controller with Self-Organizing Sub-Networks. MAPGEF utilizes real-time environmental feedback to dynamically adjust policy weights, thus achieving up to a 25% reduction in energy use and an 18% increase in crop yield through accurate environmental tuning. The HRL-TDD utilizes hierarchical RL combined with temporal decomposition in order to handle tough tasks of a greenhouse, thus improving a decision by up to 30%, with energy efficiency improved by 20% and crop yield stabilized with 15%. NMCSOS introduces a neural meta-controller coordinating self-organizing sub-networks, ensuring robust responses to external disturbances with 33% faster recovery, 22% better energy optimization, and 18% reduced yield variability levels. Together, these methodologies address the pressing need for adaptable, scalable, and energy-efficient greenhouse control systems. By integrating multi-objective learning, temporal decomposition, and self-organizing networks, this work significantly advances greenhouse management, promoting sustainable agriculture and resilience in the face of environmental uncert

关键词： Adaptive Policy Gradient Multi-Objective Reinforcement Learning Neural Meta-Controller Scenarios Smart Greenhouse Sustainable Agriculture

来源：评论

学校读者我要写书评

暂无评论

Secure Deduplication with Dynamic Key Management in Fog Enabled Internet of Things

Secure Deduplication with Dynamic Key Management in Fog Enab...

引用

IEEE Annual International computer Software and Applications Conference (COMPSAC)

作者： Jay Dave Nikumani Choudhury Utkarsh Tiwari Samyu Kamtam Kudapa Sai Rohith Dept. of Computer Science & Information Systems Birla Institute of Technology & Science Pilani Hyderabad India

Fog computing is an extension of cloud computing and presents additional devices called fog devices near IoT devices providing services on behalf of cloud servers. Although fog computing brings several advantages, rapid growth in the data generated by IoT devices increases communication and computational costs. As data sensed by IoT devices may correlate, there is a high possibility of duplicate copies in the sensed data. Data deduplication is a compression technique that reduces communication and storage overhead by skipping the upload and storage of duplicate copies of data. However, deduplication for a fog-enabled IoT system introduces new security issues. In this paper, we propose a novel secure deduplication approach with dynamic key management in a fog-enabled IoT system. We introduce a multilayer encryption scheme with dynamic key management to prevent the access of revoked users to the data. We implement the proposed scheme in a realistic scenario using Raspberry Pi and Firebase cloud services. The performance analysis shows that our approach achieves confidentiality and forward secrecy along with lower storage, computational, and communication costs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

What Kinds of Contracts Do ML APIs Need?

arXiv

引用

arXiv 2023年

作者： Khairunnesa, Samantha Syeda Ahmed, Shibbir Imtiaz, Sayem Mohammad Rajan, Hridesh Leavens, Gary T. Dept. of Computer Science and Information Systems Bradley University United States Dept. of Computer Science Iowa State University United States Dept. of Computer Science University of Central Florida United States

Recent work has shown that Machine Learning (ML) programs are error-prone and called for contracts for ML code. Contracts, as in the design by contract methodology, help document APIs and aid API users in writing correct code. The question is: what kinds of contracts would provide the most help to API users? We are especially interested in what kinds of contracts help API users catch errors at earlier stages in the ML pipeline. We describe an empirical study of posts on Stack Overflow of the four most often-discussed ML libraries: TensorFlow, Scikit-learn, Keras, and PyTorch. For these libraries, our study extracted 413 informal (English) API specifications. We used these specifications to understand the following questions. What are the root causes and effects behind ML contract violations? Are there common patterns of ML contract violations? When does understanding ML contracts require an advanced level of ML software expertise? Could checking contracts at the API level help detect the violations in early ML pipeline stages? Our key findings are that the most © 2023, CC BY.

关键词： Machine learning

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：