检索结果-内蒙古大学图书馆

Distributed Computing and Optimization Techniques (ICDCOT), International Conference on

作者： P Lakshmiramana Mohammed Al-Farouni P Senthil Shashidhara K S Pramod Mutalik Computer Science and Technology Madanapalle Institute of Technology and Science Angallu Madanapalle India The Islamic university Najaf Iraq Department of Information Technology S.A. Engineering College Chennai India Dept. of ECE Nitte Meenakshi Institute of Technology Bengaluru India Software Engineer Visvesvaraya Technological University Raichur Karnataka India

The resource allocation in heterogeneous cognitive radio networks (CRN) system has been considered a key technology in wireless networks. However, the main challenge of the CRN system is resource allocation with minimized and maximum transmission in the spectrum band, enhancing optimum throughput increase, load balance and global optimization. The proposed method is hybrid optimization, comprising Ant Colony Optimization (ACO) and Artificial Bee Colony (ABC), allocating resources while considering power, throughput and equal to distributed the allocation. The load balancing technique should ensure virtual independent task scheduling approaches of the hybrid optimization and optimize scheduling and resource utilization to maximize throughput and create load balancing. Performance analysis of the proposed method was compared using resource allocation with existing load balancing and scheduling algorithms. Although the proposed ACO-ABC method exhibits high performance compared to existing methods such as Dynamic Fuzzy-based Primary User Aware Clustering (DFPC), non-orthogonal multiple access (NOMA) and Hybrid Tabu Search-based Stimulated Algorithm (HTSA), experimental results demonstrate high performance achieving a Packet Delivery Ratio (PDR) of 97%, Delay of 0.009s, Energy consumed of 0.01 (nJ), and Throughput of 2.0 (Mpbs).

关键词：

来源：评论

学校读者我要写书评

暂无评论

The YOLOv8 Edge: Harnessing Custom Datasets for Superior Real-Time Detection

The YOLOv8 Edge: Harnessing Custom Datasets for Superior Rea...

引用

International Conference on Emerging Technologies, ICET

作者： Tafreed Ahmed Ahmad Maaz Danyaal Mahmood Zain ul Abideen Usama Arshad Raja Hashim Ali Faculty of Computer Science & Engineering GIK Institute of Engg. Sciences & Technology Topi Pakistan BCMaterials Basque Center for Materials Applications & Nanostructure Leioa Basque Country Spain Dept. of Technology & Software Engineering University of Europe for Applied Sciences Berlin Germany

YOLO has become a central real-time object detection system for robotics, driverless cars, and video monitoring applications. Developing a custom object detection solution that can detect specific objects in real-time video streams has the potential to revolutionize various fields and has been the subject of extensive research. Although there have been advances in object detection, there is still a gap in the research for real-time detection of custom objects with high accuracy and speed. This research addresses this gap by training a YOLOv8 detector on a custom dataset of objects and evaluating its performance on real-time video streams which is by far the latest model and thus is faster and more accurate. Our experimental results demonstrate that our custom-trained YOLOv8 detector achieves high accuracy and real-time performance on a custom dataset of objects. The detector achieved an overall mAP50 of 0.864 and a mAP50-95 of 0.758, with individual class results ranging from 0.47 to 0.995. These findings show that custom training data and YOLOv8 are effective in real-time object detection, which has practical applications in various fields. The significance of the results and our contribution lies in demonstrating the effectiveness of custom training data for improving object detection accuracy and speed using YOLO, which has implications for a wide range of real-world applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning-Enhanced IoT Wearable Device for Monitoring and Providing Feedback on Stuttering

A Machine Learning-Enhanced IoT Wearable Device for Monitori...

引用

Computational Modelling, Simulation and Optimization (ICCMSO), International Conference on

作者： Hussain Suttarwala Ritesh Kumar Madhavi L. Deorankar Dikshendra Daulat Sarpate Pallavi Shingade Surender Kumar Sharma Vrushali More Uday Chandrakant Patkar Deepak K. Sharma Senior Software Engineer American Express Phoenix AZ USA Dept. of AI and Data Science Dr. Akhilesh Das Gupta Institute of Professional Studies New Delhi Delhi India Dept. of Electronics and Telecommunications Marathwada Mitramandal College of Engineering Pune Maharashtra India Dept. of AI and Data Science Zeal College of Engineering and Research Narhe Pune Maharashtra India Dept. of AI and Data Science D Y Patil College of Engineering Akurdi Pune India Dept. of Electrical Engineering Poornima University Jaipur India Dept. of AI and Data Science Genba Sopanrao Moze College of Engineering Balewadi Pune Maharashtra India Department of Computer Engineering Bharati Vidyapeeth’s College of Engineering Lavale Pune Dept. of AI and Data Science Savitribai Phule Pune University Pune Maharashtra India

ISBN: (数字)9798350361391

ISBN: (纸本)9798350361407

This study introduces an innovative IoT-enabled wearable device tailored for monitoring and providing feedback on stuttering, leveraging advanced machine learning algorithms to enhance precision and real-time responsiveness. The device integrates an array of hardware and software elements, including sensors, microcontrollers, and communication protocols, to accurately capture speech patterns and movements. Utilizing machine learning techniques such as Support Vector Machines (SVM) and Convolutional Neural Networks (CNN), the device performs real-time analysis to identify stuttering instances. Detailed discussions cover the criteria for selecting machine learning models, the training and testing procedures, and the metrics used for performance evaluation. The prototype underwent extensive testing and validation, showcasing high accuracy, sensitivity, and specificity in differentiating stuttered from fluent speech. User feedback emphasized the ergonomic design, user-friendly interface, and real-time feedback features, highlighting its potential to significantly enhance stuttering therapy outcomes. Comparative analysis with existing solutions revealed the device’s superior performance, indicating strong potential for clinical application. The study discusses the implications for stuttering therapy, acknowledges the limitations, outlines future research directions, and underscores the device’s contributions to personalized and effective stuttering interventions. This research advances the field of assistive technologies in speech therapy and demonstrates the promise of IoT-based wearable devices integrated with machine learning for improving the quality of life for individuals with stuttering disorders.

关键词： Performance evaluation Machine learning algorithms Accuracy Medical treatment Prototypes Machine learning Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Investigating the Use of Natural Language Processing in Electronic Medical Record

Investigating the Use of Natural Language Processing in Elec...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： Balaram Yadav Kasula Sachin C. Patil Prashamsh Takkalapally Ketan Gupta J. Logeshwaran Dept of Information Technology University Of The Cumberlands Williamsburg KY USA Senior Software Engineer USA Department of Engineering Computing and Mathematical Sciences Lewis University USA Dept. of Information Technology University of The Cumberlands Williamsburg KY USA Department of Computer Science CHRIST (Deemed to be University) Bengaluru Karnataka India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Natural language processing (NLP) implemented in digital scientific records (EMRs) can substantially enhance the nice and efficiency of affected person care. The purpose of NLP implemented in EMRs is to extract applicable facts from affected persons’ notes written in a human language together with English. This information can then be stored in a suitable structured form for further evaluation and records mining. NLP has been carried out in the clinical field for the reason that Fifties as a green approach for retrieving textual content-based data and reading interactions among affected persons and healthcare professionals. With the arrival of electronic facts, NLP has come to be extra extensively applied for the diffusion of purposes, inclusive of automatic coding, scientific choice aid, and medical doctor order access. This summary makes a of exploring the usage of NLP in EMRs. The scope of this research consists of an evaluate of present NLP technologies and their software in EMRs. It additionally outlines a number of the present-day demanding situations inside the use of NLP for clinical information and shows capability answers. Finally, the potential applications of NLP-driven EMRs are discussed, inclusive of making use of in-health practitioner order entry, scientific choice assistance, and population health control.

关键词： Electric potential Accuracy Natural language processing software Encoding Data mining Clinical diagnosis Protection Electronic medical records

来源：评论

学校读者我要写书评

暂无评论

Explaining Agent-Based Modeling Outputs Using Subgroup Discovery: A Case Study in Marketing

SSRN

引用

SSRN 2024年

作者： Romero, Elena del Jesús, Cristóbal José Carmona Cordón, Oscar del Jesus, María José Damas, Sergio Chica, Manuel Andalusian Research Institute in Data Science and Computational Intelligence DaSCI University of Granada Granada18071 Spain Dept. of Computer Science and Artificial Intelligence DECSAI University of Granada Granada18071 Spain Andalusian Research Institute in Data Science and Computational Intelligence DaSCI University of Jaen Jaen23071 Spain Leicester School of Pharmacy De Montfort University LeicesterLEI 9BH United Kingdom Dept. of Computer Science University of Jaen Jaen23071 Spain Dept. of Software Engineering University of Granada Granada18071 Spain School of Electrical Engineering and Computing The University of Newcastle CallaghanNSW2308 Australia

Agent-based modeling (ABM) is a popular tool for simulating complex systems. During the simulation, ABM generates valuable information about the agents' roadmap, but the large volume of generated data is difficult to analyze and understand. Improving the understanding of ABM outputs is a key challenge, which can also lead to increase the model understanding. However, most studies analyzing model outputs have mainly focused on model validation or identifying relationships between input and output, with limited emphasis on extracting insights about agent behavior from simulated data. We propose the application of Explainable Artificial Intelligence techniques, specifically Subgroup Discovery (SD), to improve model transparency and interpretability. We provide a methodology for applying SD to ABM for extracting useful knowledge of agents' behavior with respect to a variable of interest. We compare the performance of different SD algorithms and show the effectiveness of our methodology through a case study in the marketing area. We analyze the obtained set of rules from the point of view of a marketing expert. The results show that our methodology can provide a deeper understanding of consumer behavior and market dynamics, providing potential areas of opportunity for marketers. © 2024, The Authors. All rights reserved.

关键词： Consumer behavior

来源：评论

学校读者我要写书评

暂无评论

Optimized Crop Detection Using IoT and Deep Neural Networks

Optimized Crop Detection Using IoT and Deep Neural Networks

引用

Human-computer Interaction, Optimization and Robotic Applications (HORA), International Congress on

作者： Tanupriya Choudhury Rohini A Hussain Falih Mahdi SOCS University of Petroleum and Energy Studies (UPES) Dehradun Uttarakhnad India Graphic Era Hill University Dehradun India Dept. of Computer Science & Engg Anil Neerukonda Institute of Technology and Sciences (ANITS) Visakhapatnam India Department of Computer and Software Engineering University of Diyala Baquba Iraq

The advancement of agriculture in food production is an increasing concern. It is one of the major challenges in contemporary farming. The development methods of soil farming have increased the fabrication of crops and food. It emphasizes the vital role of sustainability in soil. Different technologies were used to grow and flourish in soil to supply the nutrition's. It buffers and delicate the plant roots from fluctuations in temperature. Hydroponically grown fruits can produce rich nutrition's like traditional grown fruits. Proposed research has focused on the IoT in Hydroponics for Growing Tomato Plants. The Nutrient Film Technique (NFT) is needed for the present farmers for monitor and managing the crop system. For managing and monitoring the crop to execute the method scientifically and take the decision about the crops in time. The integration of IoT has given the solutions to solve the contemporary problems of calcium deficiency, lack of airflow around plants and so on. This proposal has developed a smart hydroponic system with technology enabled by IoT system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Max-Min Fairness Power Allocation in Uplink RIS-Aided Cell-Free Massive MIMO

Max-Min Fairness Power Allocation in Uplink RIS-Aided Cell-F...

引用

IEEE Globecom Workshops

作者： Thong-Nhat Tran Giovanni Interdonato Daniel Benevides Da Costa Beongku An Dept. of Electronics and Computer Engineering in Graduate School Hongik University Republic of Korea Dept. of of Electrical and Information Engineering (DIEI) University of Cassino and Southern Latium Italy Digital Science Research Center Technology Innovation Institute Masdar City Abu Dhabi United Arab Emirates Dept. of Software and Communications Engineering Hongik University Republic of Korea

This paper evaluates the uplink spectral efficiency (SE) achieved by a reconfigurable intelligent surface (RIS)-aided cell-free massive MIMO system with max-min fairness (MMF) power allocation. We provide an exact closed-form expression for an achievable SE expression which assumes maximum ratio receive combining at the access points (APs) and centralized large-scale fading decoding at the central processing unit. The derived SE expression also accounts for imperfect channel estimation and spatially correlated Ricean fading channels for both direct (APs-users) and cascaded (APs-RISs-users) links. Alongside this, we provide a generalized SE expression and evaluate the performance achieved by local partial minimum mean-squared error combining. Finally, we optimally solve the RIS phase-shift selection problem in order to maximize the aggregate channel gains, and derive a closed-form solution to the MMF power allocation problem. Simulation results validate the effectiveness of the proposed framework in enhancing the unlink SE with resnect to various benchmarks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Blockchain-based Reputation System For IoT Data Ecosystem: A Utility Maximization Approach

Blockchain-based Reputation System For IoT Data Ecosystem: A...

引用

International Symposium on High Capacity Optical Networks and Enabling Technologies, HONET

作者： Seyednima Khezr Abdulsalam Yassine Rachid Benlamri Dept. of Electrical and Computer Engineering Lakehead University Thunder Bay ON Canada Dept. of Software Engineering Lakehead University Thunder Bay ON Canada Dept. of Information Technology University of Doha for Science and Technology Doha Qatar

ISBN: (纸本)9781665461986

Recently, blockchain technology has been used to build private and secure internet of things (IoT) data markets and trading systems. Reputation of the trading parties is an important attribute that affect their profitability and trading prosperity. However, current reputation systems are prone to malicious manipulation. Such an issue can be avoided by registering all reputation scores in the blockchain which guarantees trans-parency, encryption, privacy, and security. To this end, this paper proposes a blockchain-based reputation system where market players can maximize their utility while engaged in the IoT data ecosystem. We also propose an adaptive learning mechanism that allows the data providers and consumers to enhance their reputation and review credibility scores. We provide extensive experiments to ensure our system satisfies the feasibility, usability, and availability properties. These properties are essential for functional deployment in real IoT data markets.

关键词： Privacy Smart cities Profitability Ecosystems Blockchains Encryption Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Exploiting Partial Observability and Optimized Simple State Representations in Deep Q-Learning

Exploiting Partial Observability and Optimized Simple State ...

引用

Frontiers of Information Technology (FIT)

作者： Danyaal Mahmood Usama Arshad Raja Hashim Ali Zain Ul Abideen Muhammad Huzaifa Shah Talha Ali Khan Ali Zeeshan Ijaz Nisar Ali Abu Bakar Siddique Faculty of Computer Science & Engineering GIK Institute of Engg. Sciences & Technology Topi Pakistan Dept. of Technology & Software Engineering University of Europe for Applied Sciences Berlin Germany BCMaterials Basque Center for Materials Applications & Nanostructure Spain Faculty of Electronic Systems Engineering University of Regina Regina Canada

The advent of deep Q-learning has opened up new possibilities in training autonomous agents to perform intelligently in intricate settings. This research work examines the potential of deep Q-learning in the paradigmatic Snake game, which requires an agent to navigate a grid, ingest food items, and avoid collisions. We incorporated a partially observable game state, introducing a novel level of difficulty to the task. Our proposed approach utilizes a straightforward feed-forward neural network to estimate Q-values of potential actions, given the current state. The agent progressively learns to balance between exploration and exploitation, allowing it to navigate optimally in the game scenario. Most existing studies in deep Q-learning for the Snake game overlook the complexities posed by partial observability, focusing mainly on fully observable state representations. Furthermore, the majority of the investigations delve into the efficacy of complex neural network architectures, leaving a gap in the understanding of the performance of more simplistic feed-forward networks. Our study fills this gap by offering an in-depth exploration and analysis of deep Q-learning strategies, especially when applied to partially observable game states and simple neural networks. Simulations and results reveal that adopting simpler state representations can significantly boost the agent’s performance in the Snake game. A more detailed and intricate reward function is also observed to enhance the agent’s decision-making skills and overall proficiency in the game. These observations underscore the significance of optimizing state representations and reward functions for maximizing the performance of deep Q-learning agents in the Snake game.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Prediction of Polycystic Ovary Syndrome Using Genetic Algorithm-driven Feature Selection

Prediction of Polycystic Ovary Syndrome Using Genetic Algori...

引用

IT and Industrial Technologies (ICIT), International Conference on

作者： Fatima Faridoon Raja Hashim Ali Zain Ul Abideen Nazia Shahzadi Ali Zeeshan Ijaz Usama Arshad Nisar Ali Muhammad Imad Said Nabi Faculty of Computer Science & Engineering GIK Institute of Engg. Sciences & Technology Topi Pakistan Dept. of Technology & Software Engineering University of Europe for Applied Sciences Berlin Germany BCMaterials Basque Center for Materials Applications & Nanostructure Spain Faculty of Electronic Systems Engineering University of Regina Regina Canada

PolyCystic Ovary Syndrome (PCOS) is a hormonal disorder frequently found in women of reproductive age having a significant impact on the cause of infertility. It is an endocrine condition characterized by abnormalities in female hormone levels and aberrant synthesis of male hormones. This syndrome causes ovarian malfunction, increasing the risk of miscarriage and infertility. PCOS has a wide range of symptoms, making a diagnosis difficult. In this study, we proposed a feature selection method based on genetic algorithm with logistic regression to increase the accuracy of early diagnosis. A dataset containing the clinical and biochemical characteristics of 109 patients, including 36 with PCOS, is used. The genetic algorithm is used to extract the most important features from the dataset. Then, a logistic regression model is used for classification. The proposed model outperformed the baseline model that used all features, which had an accuracy of 86.2%, and produced a markedly improved accuracy of 95.4%. These results show that the proposed model effectively locates key characteristics for PCOS diagnosis.

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：