检索结果-内蒙古大学图书馆

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Sewal, Piyush Singh, Hari Computer Science & Engineering Department Jaypee University of Information Technology Solan173234 India

In the realm of big data, where datasets of immense scale pose processing challenges, distributed processing platforms like open-source Apache Spark have emerged to address these issues. Spark's internal configuration parameters exert varying impacts on execution times based on job characteristics, making manual optimization daunting. The core focus of this study lies in optimizing Spark's internal configurations, with specific attention directed towards three types of workloads: Iterative-intensive, Memory-intensive, and CPU-intensive. Employing Grid Search, Random Search, and Evolutionary Optimization algorithms yields substantial execution time reductions: 23.24% with Grid Search, 19.71% with Random Search, and 23.06% with Evolutionary Optimization. Notably, Evolutionary Optimization achieves optimal configurations approximately 29% faster than Grid Search. While Random Search and Evolutionary Optimization share similar time requirements, Random Search's execution time reduction for a given Spark workload is relatively lower. This research sheds light on algorithmic configuration tuning intricacies and its influence on Spark workload execution times, contributing to the exploration of optimizing big data processing platforms. © 2024 Elsevier B.V.. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

VISION-PF: A computer Vision Approach to Injury Prevention in Physical Fitness

VISION-PF: A Computer Vision Approach to Injury Prevention i...

引用

2024 International Telecommunications Conference, ITC-Egypt 2024

作者： Ouf, Mohamed Ashraf Amin, Rowan Mohamed Sabry, Moustafa Mamdouh Ali, Abdulrahman Hussien Hamdan, Yehia Ahmed Saleh, Sherine Nagy Arab Academy for Science Technology and Maritime Transport Computer Engineering Department Alexandria Egypt

ISBN: (纸本)9798350351408

Ensuring accurate and effective exercise performance monitoring is essential for sports-focused injury prevention. Maintaining perfect form is crucial since incorrect training increases the chance of injuries dramatically. This article focuses on the popular push-up exercise and introduces a new approach that uses a carefully curated dataset for analysis. The proposed model can accurately discriminate between correct and wrong push-up forms by employing LSTM networks and sophisticated computer vision algorithms. This improved method enables focused interventions, tailored feedback, and the detection of form deviations, providing insights into typical errors. This research aims to improve athlete safety, maximize athletic performance, and establish a framework for using the concept in other significant sports-related injury prevention initiatives. The proposed model significantly improved performance, achieving F1 scores of 0.9 and 0.85 on the training and testing sets, respectively. © 2024 IEEE.

关键词： Machine vision

来源：评论

学校读者我要写书评

暂无评论

Offline Signature Forgery Detection Based on Geometric Measures Using Tensorflow Model 2

Offline Signature Forgery Detection Based on Geometric Measu...

引用

2nd International Conference on Advancements in Smart, Secure and Intelligent Computing, ASSIC 2024

作者： Lakshmi, A. Anagha Reddy, G. Siddarth Reddy, M. Sowmya Kathirisetty, Nikhila Vardhaman College of Engineering Department of Information Technology Hyderabad India Vardhaman College of Engineering Department of Computer Science and Data Science Hyderabad India

ISBN: (纸本)9798350370188

The most popular method for identifying people from past signatures is through signatures. By using a TensorFlow model which is a deep learning algorithm, we created a new system to verify signatures on bank checks and other important documents. The main point is that a signature plays a crucial role in banking because it is necessary for money withdrawals. In banks there are no efficient systems to check if a signature is real or fake as it is the most frequently used bio-metric method to verify a person's identity. This can lead to bank fraud. The Project will make it easier to tell whether a signature is genuine or not. Online and offline verification are the two methods of verification. We're going to use various geometric measurements to accomplish offline verification. Python libraries were employed in this case. In the testing phase the model's performance is evaluated. To protect the integrity and legitimacy of handwritten signatures, signature forgery detection is an essential responsi-bility. The capacity to recognize forged signatures with accuracy has grown more important as a result of the rise in digital transactions and the growing reliance on electronic documents. The act of duplicating or copying another person's signature with the purpose to deceive or gain illegal access is known as signature forging. Manually spotting these forgeries can be difficult because expert forgers are adept at closely imitating the visual style and traits of real signatures. Therefore, there has been a lot of interest in the development of automated methods and algorithms to identify fake signatures. © 2024 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Video Anomaly Detection Based on HSOE-FAST Modified Deep Neural Network

引用

SN computer science 2024年第5期5卷 588页

作者： Gupta, Anil Kumar Sharma, Rupak Ojha, Rudra Pratap Department of Computer Science and Engineering SRM Institute of Science and Technology NCR Campus Modinagar Uttar Pradesh Ghaziabad India Department of Computer Applications SRM Institute of Science and Technology NCR Campus Modinagar Uttar Pradesh Ghaziabad India Department of Computer Science and Engineering G.L. Bajaj Institute of Technology and Management (GLBITM) (Affiliated to AKTU) Uttar Pradesh Greater Noida India

In recent times, video surveillance has become indispensable for public security, leveraging computer vision advancements to analyze and comprehend lengthy video feeds. Anomaly detection and classification stand out as crucial components of this technology. Anomaly detection's primary objective is to swiftly identify irregularities within a given timeframe. It is promising to use Deep Neural Network (DNN) approaches for anomaly detection because they combine the ideas of deep learning and reinforcement learning, enabling artificial agents to learn from and gain insights from real-world data. A modified DNN (Deep Neural Network) technique known as HSOE-FAST (Histo sigmoid of Orientation and Enthalpy with Fast Accelerated Segment Test) was proposed in this study. From the dataset, the input is obtained. Initially, the input is pre-processed using a Gaussian filter followed by the feature extraction using the HSOE-FAST method and finally classification is done using the modified DNN approach. Compared to other approaches, our suggested solution achieves an accuracy of almost 99% while overcoming the shortcomings of the existing methodologies. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： DNN Enthalpy Fast Accelerated Segment Test Histo sigmoid of Orientation Video anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Power Flow Estimation for MVDC Distribution Systems Based on Physics-Embedded FCN

引用

IEEE Transactions on Smart Grid 2025年第4期16卷 2816-2829页

作者： Sun, Pingyang Wu, Rongcheng Shen, Zhiwei Wang, Hongyi Li, Gen Khalid, Muhammad Konstantinou, Georgios School of Electrical Engineering and Telecommunications UNSW Sydney Australia University of Technology Sydney Data Science Institute Australia Aalborg University Department of AAU energy Denmark Energy Technology and Computer Science Section Department of Engineering Technology Ballerup2750 Denmark King Fahd University of Petroleum and Minerals Electrical Engineering Department Interdisciplinary Research Center for Sustainable Energy Systems Dhahran31261 Saudi Arabia

Maintaining high prediction accuracy with varying grid topologies poses a significant challenge to adopting neural network (NN)-based approaches for power flow (PF) estimation in medium-voltage direct current (MVDC) distribution systems. This paper proposes a physics-embedded fully convolutional network (PEFCN) to improve the accuracy. Physics-embedded techniques are incorporated in the proposed PEFCN through 1) architecture reconstruction, and 2) loss function reformulation. Architecture is reconstructed by input channel conversion calculation in a new physics operation layer. This process offers physical connections among the three input matrix channels (voltage, current, and line conductance). Three new physics loss terms are included in the loss function to restrict the outliers violating the limits of converter power ratings and terminal MVDC voltages. The two operations enable the FCN to achieve improved prediction accuracy and strong generalization capabilities. Five MVDC distribution systems, characterized by different dc voltage levels and topology configurations, serve to validate the superiority of the proposed PEFCN over other NNs in the PF estimation for scenarios involving both fixed and varying system structures. Moreover, a modified IEEE 69-bus distribution system is further used to demonstrate the applicability of the proposed PEFCN for larger systems. © 2010-2012 IEEE.

关键词： DC distribution systems

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Study on Quantum Key Distribution Protocols 15

A Comprehensive Study on Quantum Key Distribution Protocols

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Mummadi, Swathi Fathima, Sabiha B V Raju Institute of Technology Telangana Department of Computer Science and Engineering India

ISBN: (纸本)9798350370249

Quantum Key Distribution (QKD) represents a revolutionary mechanism ensuring secure communication amidst the quantum computing era. With the evolving threat landscape due to quantum computing advancements, there's an urgent need for a comprehensive review and assessment of existing QKD protocols and implementations. This paper systematically explores the QKD landscape, focusing on protocols, security models, practical implementations, and recent progress. We commence by elucidating the foundational principles of QKD and its pivotal role in establishing verifiably secure communication channels. Based on their underlying principles, we then categorize and scrutinize various QKD protocols, like BB84, BBM92, CV-QKD, etc. We delve into the security models utilized in QKD protocols, evaluating their strengths and limitations. Additionally, we evaluate practical QKD system implementations encompassing both fibre-based and free-space setups. We shed light on crucial technological challenges, advancements, and recent developments in quantum repeaters, memories, and network architectures aiming to enhance the reach and scalability of QKD systems. This systematic review provides insights into the current state of QKD technology, identifies research gaps, and discusses potential pathways for future progress. Our analysis is a vital resource for researchers and practitioners who are engaged in quantum cryptography and secure communication protocols. © 2024 IEEE.

关键词： Quantum entanglement

来源：评论

学校读者我要写书评

暂无评论

A Framework on Positioning of Medical Sensors in Healthcare Domain

A Framework on Positioning of Medical Sensors in Healthcare ...

引用

2024 International Conference on Communication, computer sciences and engineering, IC3SE 2024

作者： Rajput, Anuj Singh Prabha, S. Khare, Mayank Deep Tula's Institute Department Of Computer Science And Engineering Dehradun India Department Of Computer Science And Information Technology Bangalore India Noida Institute Of Engineering And Technology Department Of Internet Of Things Uttar Pradesh Greater Noida India

ISBN: (纸本)9798350366846

In the last several years, the incorporation of sensor technology into our everyday routines has resulted in improved comfort, convenience, and overall wellbeing. The size and cost of medical sensors have decreased as a consequence of technical improvements that have improved their use. Medical sensors make 'remote health monitoring, surgical procedures, therapy, and rehabilitation' more efficient and practical. We provide an in-depth historical overview of medical sensors during the last fifty years, emphasising their use in clinical settings. The evaluation also examines the impact of IoT on the advancement of sensor technologies and the uses of such technologies in healthcare. We also examine the benefits and drawbacks of several integrated architectures that have been recently proposed for the smooth integration of different medical sensors with novel paradigms and technologies, including those that are located at the edge, in the cloud, in the middle (mobile cloud computing), and in the sky (fog computing) of the network. We conclude by outlining the next challenges that must be overcome in order to fully actualize the best potential and benefits of medical sensor technologies and, in the end, build a robust, scalable, reliable, and affordable healthcare system. © 2024 IEEE.

关键词： Mobile cloud computing

来源：评论

学校读者我要写书评

暂无评论

Smart Farming System Using IoT for Efficient Crop Growth 3

Smart Farming System Using IoT for Efficient Crop Growth

引用

3rd International Conference for Advancement in technology, ICONAT 2024

作者： Ganesh, Jetti Venkata Bisht, Saksham Reddy, Shashidhar Babu, A. Mohan SRM Institute of Science and Technology Ramapuram Chennai Department of Electronics and Computer Engineering India

ISBN: (纸本)9798350354171

The Shrewd Cultivating Framework utilizes a combination of sensors and IoT innovation to make a robotized checking and control framework for agrarian purposes. The utilization of sensors like ultrasonic, soil dampness, DHT11, and LDR, interfaces with a microcontroller, empowers real-time information collection on plant development, soil dampness substance, temperature, and light escalated. The system's integration with IoT encourages farther get to screen and oversee these parameters. In case of unfavorable conditions such as moo soil dampness, the framework triggers caution through a buzzer, guaranteeing incite consideration and activity to keep up ideal edit development conditions. This framework presents a arrangement to improve edit surrender by empowering productive and opportune intercession based on exact natural data. © 2024 IEEE.

关键词： Microcontrollers

来源：评论

学校读者我要写书评

暂无评论

IoT-Based Pesticide Detection in Fruits and Vegetables Using Hyperspectral Imaging and Deep Learning 4th

IoT-Based Pesticide Detection in Fruits and Vegetables Usi...

引用

4th EAI International Conference on Cognitive Computing and Cyber Physical Systems, IC4S 2023

作者： Augustin, Anju Kiliroor, Cinu C. Department of Computer Science and Engineering Indian Institute of Information Technology Kottayam Kottayam India

ISBN: (纸本)9783031488870

Fruits and vegetables contain rich nutrients and vitamins. So that they are part of our daily diet. For proper cell growth and health, we need these nutrients. Today in most crops during their growth and post-harvesting preservation different kinds of pesticides were used. Normal usage of such pesticides not that much affects health. But the actual situation is beyond our control. From soil preparation to the post-harvesting stage, pesticides are being added at alarming rates. It affects our health in a harmful way and leads to major health issues. Various studies exist to detect the pesticide levels in fruits and vegetables. This article analyses different existing methods of pesticide detection and examines their features and problems. Through this study, it is understood that Hyperspectral Imaging (HSI) is a very good method, and with it, more accurate results can be obtained by Transfer Learning (few-shot learning). This paper proposes an architecture and algorithm based on HSI and few-shot learning. Future studies are needed in this area to convert an RGB image to a spectral image because the HSI device is very expensive. © 2024, ICST Institute for computer sciences, Social Informatics and Telecommunications engineering.

关键词： Nutrients

来源：评论

学校读者我要写书评

暂无评论

A cloud service composition method using a fuzzy-based particle swarm optimization algorithm

引用

Multimedia Tools and Applications 2024年第19期83卷 56275-56302页

作者： Nazif, Habibeh Nassr, Mohammad Al-Khafaji, Hamza Mohammed Ridha Jafari Navimipour, Nima Unal, Mehmet Department of Mathematics Payame Noor University Tehran Iran Communication Technology Engineering Department Tartous University Tartus Syria Dpartment of Mathematics and Natural Sciences Gulf University for Science and Technology Mishref Campus Mubarak Al-Abdullah Kuwait Biomedical Engineering Department College of Engineering and Technologies Al-Mustaqbal University Babil Hillah51001 Iraq Department of Computer Engineering Faculty of Engineering and Natural Sciences Kadir Has University Istanbul Turkey Future Technology Research Center National Yunlin University of Science and Technology Yunlin Douliou64002 Taiwan Department of Computer Engineering Nisantasi University Istanbul Turkey

In today's dynamic business landscape, organizations heavily rely on cloud computing to leverage the power of virtualization and resource sharing. Service composition plays a vital role in cloud computing, combining multiple cloud services to fulfill complex user requests. Service composition in cloud computing presents several challenges. These include service heterogeneity, dynamic service availability, QoS (Quality of Service) constraints, and scalability issues. Traditional approaches often struggle to handle these challenges efficiently, leading to suboptimal resource utilization and poor service performance. This work presents a fuzzy-based strategy for composing cloud services to overcome these obstacles. The fact that service composition is NP-hard has prompted the use of a range of metaheuristic algorithms in numerous papers. Therefore, Particle Swarm Optimization (PSO) has been applied in this paper to solve the problem. Implementing a fuzzy-based PSO for service composition requires defining the fuzzy membership functions and rules based on the specific service domain. Once the fuzzy logic components are established, they can be integrated into the PSO algorithm. The simulation results have shown the high efficiency of the proposed method in decreasing the latency, cost, and response time. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2023.

关键词： Fuzzy logic

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：