检索结果-内蒙古大学图书馆

IEEE Annual international Computer Software and Applications conference (COMPSAC)

作者： Michael Bidollahkhani Aasish Kumar Sharma Julian M. Kunkel Faculty of Mathematics and Informatics University of Goettingen Goettingen Germany

ISBN: (数字)9798350376968

ISBN: (纸本)9798350376975

Cloud computing clusters, especially those handling cloud workloads, require efficient job scheduling to optimize resource utilization and minimize completion time. Traditional approaches often fall short in dynamic cloud environments. We propose “HOSHMAND” (High-performance Open sourced AI-based Scheduling Handler for MAnaging Node Distribution), an AI-driven framework using a custom-tailored Recurrent Neural Network (RNN) to rapidly predict the most suitable nodes for cloud workload execution. A key feature of HOSHMAND is its accelerated scheduling capability, which significantly reduces the time required for job allocation compared to traditional methods. This is particularly crucial for cloud environments with fluctuating workloads and diverse computational requirements. A distinct capability of HOSHMAND is its proficiency in managing heterogeneous resources, ensuring optimal allocation regardless of varying computational capabilities or resource types. This adaptability is crucial for contemporary cloud computing en-vironments, which often comprise a diverse array of hardware configurations, to maintain high efficiency and resource utilization. Moreover, HOSHMAND mitigates the overhead associated with repetitive scheduling computations in similar scenarios by leveraging its historical knowledge. Upon recognizing a con-figuration of jobs analogous to previously encountered situations, it promptly enacts the most effective scheduling strategy without redundant recalculations. This predictive capability not only conserves computational resources but also accelerates job execution. Our approach, tested on cloud-based datasets, demonstrates remarkable improvements in scheduling speed and efficiency, validated by reduced time-to-schedule and enhanced overall system throughput. Through its innovative handling of heterogeneous resources and intelligent avoidance of unnecessary scheduling computations, HOSHMAND sets a new benchmark for AI -driven job scheduling in cloud

关键词： Cloud computing Adaptation models Job shop scheduling Recurrent neural networks Processor scheduling Computational modeling Dynamic scheduling

来源：评论

学校读者我要写书评

暂无评论

A Standard Cell Memory Based on 2T Gain Cell DRAM for Memory-Centric Accelerator Design

A Standard Cell Memory Based on 2T Gain Cell DRAM for Memory...

引用

IEEE international SOC conference

作者： Tai-Feng Chen Yutaka Masuda Tohru Ishihara Graduate School of Informatics Nagoya University Nagoya Japan

In contemporary System-on-a-Chip (SoC) designs, memory components typically consume a significant portion of the energy supplied to the system. To effectively reduce overall energy consumption without relying on the slowing process shrink of CMOS, energy-saving techniques that attempt to dynamically adapt to the feasible minimum voltage of the system can be adopted. Besides, near-memory and in-memory computing has also been widely adopted to reduce the significant data movement cost between the processor and the memory. However, conventional SRAMs become the bottleneck since they cannot function properly under low supply voltage. On the other hand, traditional DRAMs cannot be utilized in near-memory or in-memory scenarios due to logic incompatibility issues. One potential solution is to implement standard cell memories (SCMs) instead. SCMs can operate consistently over a wider range of voltages and are logic-compatible. However, existing SCM approaches need a large latch-based bit-cell and implement many multiplexers for word selection in the read-out circuitry, resulting in significant area overhead compared to SRAMs. In this paper, we propose a two-transistor (2T) Gain Cell DRAM based SCM for memory-centric accelerator design. The proposed SCM is fully functional under near-threshold supply voltage and maintains acceptable performance while greatly improving area cost. Gain Cells are DRAM bit cells that consist of only transistors, adopted recently in on-chip memory designs for their high-density, logic-compatible, and low-power characteristics. Our experimental results demonstrate that the proposed SCM can operate at a supply voltage as low as 0.37 V and have higher flexibility as SCM while outperforming existing SRAM and SCM in terms of area cost (1.7x to 8.2x smaller) and energy consumption (up to 27.2x).

关键词：

来源：评论

学校读者我要写书评

暂无评论

IoT Based Alcohol Detection and Vehicle Control System

IoT Based Alcohol Detection and Vehicle Control System

引用

Data Intelligence and Cognitive informatics (ICDICI), international conference on

作者： I. Sapthami V V Narasimha Raju V. Vaithianathan P. Chinnasamy G Kumaran Ramesh Kumar Ayyasamy Department of Computer Science and Engineering MLR Institute of Technology Hyderabad India Marri Laxman Reddy Institute of Technology and Management Dundigal Hyderabad Telangana India Department of Electronics and Communication Engineering Sri Sivasubramaniya Nadar College of Engineering Kalavakkam Chennai Department of Computer Science and Engineering School of Computing Kalasalingam Academy of Research and Education Srivilliputtur TamilNadu Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamilnadu India Faculty of Information and Communication Technology Universiti Tunku Abdul Rahman (UTAR) Kampar Malaysia

ISBN: (数字)9798350389609

ISBN: (纸本)9798350389616

It is of the utmost importance to be aware of safety measures when operating a motor vehicle in the contemporary world, characterized by a fast-paced and hazardous environment. It has become necessary to develop innovative technology in order to improve road safety as a result of the alarmingly high number of incidents that can be linked to drivers who are under the influence of alcohol. As a solution to this significant problem, this study uses the capabilities offered by the Internet of Things (IoT) to develop an integrated system for detecting and controlling alcohol in commercial vehicles. This study aims to reduce the dangers connected with driving under the influence of alcohol by allowing for the seamless integration of cutting-edge alcohol detection technologies with real-time vehicle control mechanisms. The system makes use of specific sensors for the detection of alcohol. It interacts with the control mechanisms of the vehicle in order to restrict its functioning when alcohol is present. To make this possible, the hardware component of the system mounted in the vehicle uses the MQ3 sensor, also known as the alcohol sensor. This sensor is responsible for monitoring the alcohol molecules in the air around the driver to determine whether or not the driver is intoxicated. A buzzer, a DC motor, an LCD, a GPS, and a GSM are all components utilized by the system for data transfer. Additionally, the gear is powered by a 12-volt battery. As soon as the system determines that there is alcohol present in the vehicle, it immediately locks the accelerator. Using the GPS, the driver can obtain their location coordinates.

关键词： Refining Control systems Sensor systems Road safety Sensors Safety Internet of Things Reliability Vehicles Global Positioning System

来源：评论

学校读者我要写书评

暂无评论

Enhancing Web Application Penetration Testing with a Static Application Security Testing (SAST) Tool

Enhancing Web Application Penetration Testing with a Static ...

引用

Recent Advances and Innovations in Engineering (ICRAIE)

作者： Mohamad Yusof Darus Muhammad Farhan Bin Bolhan Aditya Kurniawan Yohan Muliono Chrisando Ryan Pardomuan Mohsen Mohamad Hata School of Computing Sciences College of Computing Informatics and Mathematics Universiti Teknologi MARA (UiTM) Malaysia Ofisgate Sdn Bhd Lakefields Kuala Sungai Besi Malaysia School of Computer Science Bina Nusantara University Jl. Raya Kb. Indonesia

Static Application Security Testing (SAST) is a crucial methodology employed to assess the security posture of an organization's applications by scrutinizing source code for vulnerabilities susceptible to exploitation. Typically, SAST tools adopt rule-based techniques to meticulously scan source code for security shortcomings, ultimately enhancing the overall quality of applications. Notably, Java and PHP stand as two widely used languages in the development of open-source web applications, each bearing distinct security reputations. In the contemporary landscape, the sheer volume of code makes it increasingly challenging to conduct exhaustive line-by-line vulnerability assessments. This research introduces a novel SAST methodology implemented in the Python programming language. This approach is tailored to pinpoint vulnerabilities within the application layer, with a particular focus on identifying SQL injection and Cross-Site Scripting (XSS) vulnerabilities within both Java and PHP codebases. Thus, this research seeks to validate the system's efficacy in detecting these critical vulnerabilities in PHP and Java programming languages. To evaluate the system's performance, penetration testing techniques are employed to establish proof of concept. These techniques entail conducting sample tests on vulnerable web applications, such as DVWA (PHP) and WebGoat (Java). Subsequently, an in-depth analysis of the testing outcomes is conducted using confusion matrices, recall, and precision metrics. The proposed SAST methodology presents a valuable resource for software developers, facilitating the analysis of source code or compiled code versions to unearth security flaws. The testing results indicate an accuracy rate of 20.7% for the SAST, underscoring its potential to contribute significantly to the enhancement of application security. Cross-site scripting (XSS), SQL Injection, Web Vulnerability, Web Security, Static Application Security Testing (SAST)

关键词：

来源：评论

学校读者我要写书评

暂无评论

Basic Research on Machine Vision Underpinned by Image Frame Algebra (VFA) and Visual Semantic Algebra (VSA)

Basic Research on Machine Vision Underpinned by Image Frame ...

引用

international conference on Machine Vision and Information Technology (CMVIT)

作者： Yingxu Wang President International Institute of Cognitive Informatics and Cognitive Computing (I2CICC) Visiting Professor: Stanford Univ. (2008|2016) MIT (2012) UC Berkeley (2008) Oxford Univ. (1995|2018–2022) Distinguished Visiting Professor Tsinghua Univ. (2019–22) Schulich School of Engineering and Hotchkiss Brain Institute University of Calgary 2500 University Drive NW Calgary Alberta Canada

Computer vison [1], [2], [3], [4], [5] studies properties of machine vision, its semantic understanding, and general manipulations by Intelligent Mathematics (IM) [6], [7], [8], [9], [10] [11], [12], [13], [14], [15] [16], [17]. Computer vison has been studies from various aspects such as algorithmic methods, analysis methods, pattern recognitions, and neural-network-regression (AI) technologies [2], [3]. However, there is a lack of fundamental theories for enabling autonomous image recognition and processing by machines. Basic research on contemporary IM has revealed that formal manipulations of visual objects by intelligent machines may be rigorously implemented by Image Frame Algebra (IFA) [8], [18] in the front-end and Visual Semantic Algebra (VSA) [19] in the backend. IFA formally manipulates visual images as general 2D matrixes by a set of algebraic operators such as modeling, analyses, syntheses, feature elicitation, and pattern recognition [4], [5], [18]. Then, its counterpart, VSA, transforms the geographic relations of visual objects to their semantic interpretations by algebraic analyses and compositions. The coherent theory of IFA and VSA provides a formal methodology for machine-enabled image processing and comprehension. This keynote presents a theoretical framework of machine vision underpinned by IFA and VSA for the structural denotations of visual objects and functional manipulations of visual mechanisms [3], [8], [9]. It demonstrates how the persistent challenges to machine vision may be rigorously and efficiently solved by the IFA/VSA methodology. Case studies on applying IFA/VSA for rigorous visual pattern detection, recognition, analysis, and composition in real world will be demonstrated [5], [18], [20]. As two coherent paradigms of IM, among others [21], [22], [23], [24], [25] [26], [27], [28], [29], [30], IFA and VSA have been applied not only in robot visual and spatial reasoning, but also in computational intelligence and AI for rigorously

关键词：

来源：评论

学校读者我要写书评

暂无评论

Integrating Artificial Intelligence in Improving Educational System: The Mediating role of Smart Learning

Integrating Artificial Intelligence in Improving Educational...

引用

Business Analytics for Technology and Security (ICBATS), international conference on

作者： Iman A. Akour Hevron Muhammad Alshurideh Haitham M. Alzoubi Muhammad Turki Alshurideh Yasin Ahmad Antouz Department of Information Systems College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates Department of Foreign Languages Faculty of English Language and Literature The University of Jordan Amman Jordan School of Business Skyline University College Sharjah UAE Applied Science Research Center Applied Science Private University Amman Jordan Department of Management College of Business University of Sharjah Sharjah UAE Department of Marketing School of Business The University of Jordan Amman Jordan Department of Management College of Business University of Sharjah Sharjah United Arab Emirates

One of the contemporary developments in educational technology is artificial intelligence (AI) in the education. The use of AI will lead to a significant change in governance across the board for UAE institutes of learning. The potential use of AI in education includes an examination of the educational consequences, including how teachers would be enriched, how students would learn, and how fast and accurate judgements could be made in education institutions. Given this situation, AI assistance is absolutely necessary. Despite the fact that it has been around for close to 30 years, educators are still confused of how to use it pedagogically on a broader scale and how it may actually have a big impact on teaching and learning in higher education. Through an empirical review, this research aims to present an empirical analysis of the application of artificial intelligence in educational system with mediating effect of smart learning. This research carried out empirical evidence from 28 educational institutions based in UAE. The managerial and professors were approached in order to answer the online questionnaire. 195 valid responses were considered for data analysis using SmartPLS. Model assessment done on the basis of various tests, for instance, reliability, discriminant validity, PLS-SEM. The findings suggest a significant relationship between artificial intelligence and educational system, and mediating role of smart learning is predicted to be significant. Hence, the intention to use artificial intelligence with smart learning can enhance the academic learning outcomes.

关键词： Wireless communication Wireless sensor networks Technological innovation Educational technology Learning (artificial intelligence) Sensor systems Internet

来源：评论

学校读者我要写书评

暂无评论

Frequency-Domain Assisted Fundus Image Enhancement Network Based on the Mamba Model

Frequency-Domain Assisted Fundus Image Enhancement Network B...

引用

Symposium of Image, Signal Processing, and Artificial Vision (STSIVA)

作者： Bin Luo Yang Wen Jianhua Ji Wenming Cao Ping Li Guangdong Provincial Key Laboratory of Intelligent Information Processing College of Electronic and Information Engineering Shenzhen University Shenzhen China College of Electronic and Information Engineering Shenzhen University Shenzhen China Department of Computing and School of Design The Hong Kong Polytechnic University Hong Kong China

ISBN: (数字)9798350363203

ISBN: (纸本)9798350363210

Enhancing fundus images is crucial for early diagnosis and monitoring of retinal diseases. Although CNN and Transformer-based methods have made great progress, CNNs struggle with long-range dependencies, and Transformers face challenges with large model sizes and low computational efficiency. To address these issues, Selective Structured State-Space Models (SSMs) offer an efficient solution with linear complexity. However, standard Mamba models still suffer from local pixel information loss and channel redundancy, limiting their performance in fundus image enhancement. We propose MambaFE, which incorporates localized refinement and an advanced channel attention mechanism to resolve challenges such as pixel detail loss and excessive channel information. Considering that retinal structures play a vital role in fundus analysis, retaining these structures during the enhancement process is crucial. As retinal structures are predominantly located within the high-frequency components of fundus images, we introduce a frequency-guided approach to capture reliable representations of these features, ensuring improved retention of essential information during enhancement. Comprehensive experimental findings indicate that the proposed MambaFE outperforms contemporary fundus image enhancement techniques, significantly enhancing the quality of clinically low-quality and synthetically degraded fundus images, while offering robust support for real-world medical applications.

关键词： Image quality Attention mechanisms Computational modeling Redundancy Retina Transformers State-space methods Image enhancement Standards Diseases

来源：评论

学校读者我要写书评

暂无评论

Empowering decision-making in cardiovascular care: Exploratory data analysis and predictive models for heart attack risk

引用

AIP conference Proceedings 2024年第1期3123卷

作者： M. Reyasudin Basir Khan Gazi Md. Nurul Islam Poh Kiat Ng Ahmad Anwar Zainuddin Chong Peng Lean Jabbar Al-Fattah Saidatul Izyanie Kamarudin Tun Razak Graduate School Universiti Tun Abdul Razak (UNIRAZAK) Kuala Lumpur Malaysia Faculty of Engineering and Technology Multimedia University Jalan Ayer Keroh Lama Bukit Beruang Melaka Malaysia Department of Computer Science International Islamic University Malaysia (IIUM) Kuala Lumpur Malaysia Manipal International University Putra Nilai Negeri Sembilan Malaysia Fakulti Kejuruteraan Elektrik dan Elektronik Universiti Tun Hussein Onn Parit Raja Johor Malaysia College of Computing Informatics and Media Universiti Teknologi MARA (UiTM) Shah Alam Selangor Malaysia

Acute myocardial infarction, commonly referred to as a heart attack, stands as one of the most lethal medical conditions, highlighting the pressing necessity for the effective management of cardiovascular disease. This involves conducting comprehensive data analysis and extracting knowledge essential for diagnosis, regulation, and treatment. Anticipating the occurrence of heart attacks presents a formidable challenge for healthcare professionals, given the intricate nature of the condition that demands both experience and a profound understanding. In the contemporary landscape of medicine, the concealed data landscape conceals invaluable insights that can significantly shape critical decision-making processes. In this research endeavor, a dataset comprising patient records is harnessed to predict an individual’s vulnerability to heart attacks. Advanced data visualization techniques are employed to identify pivotal trends and outliers, facilitating the extraction of meaningful and actionable conclusions. This study involves the development of three classifier models for heart attack prediction: Logistic Regression, K Nearest Neighbor, and Support Vector model.

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：