检索结果-内蒙古大学图书馆

2023 International Conference on Next-Generation Computing, IoT and Machine Learning, NCIM 2023

作者： Hasan, Md. Nahid Hossain, Md. Ali Rajshahi University of Engineering and Technology Dept. of Computer Science and Engineering Bangladesh

ISBN: (纸本)9798350316001

Cataract is a common eye condition that causes clouding of the eye's natural lens, resulting in blurry vision and it is very common in older ages people. However, it can also occur in younger aged people due to various genetical effects, diabetes, smoking, and prolonged exposure to sunlight. Cataracts can be treated through surgery to remove the clouded lens and replaced by an artificial one, which can significantly improve the vision. This problem can be reduced through early detection, regular eye examinations etc. In this research, a Contrast Limited Histogram Equalization (CLAHE) of retinal fundus images is applied for a better presentation of the above cataract effects. These improved images are fed to a machine learning-based model for effective detection. Finally, the ensembling of the proposed machine learning-based classifiers is performed for the accurate detection of cataracts. The proposed model was tested experimentally on a real dataset and achieves excellent performance with accuracy, precision, and recall scores of 99.67%, 100%, and 99.25%, respectively which outperform the baseline methods. The robustness of the proposed ensemble model is evaluated through 5-fold cross-validation and achieved an average accuracy of 99.6%. The implementation code can be accessed from the GitHub repository: https://***/nahid-tech/cataract-detection. © 2023 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Efficiency Measurement of k-Partitioning of Mobile WSN 4

Efficiency Measurement of k-Partitioning of Mobile WSN

引用

4th IEEE International Conference on Computing, Communication, and Intelligent Systems, ICCCIS 2023

作者： Hossain, Azad Rehena, Zeenat Murshidabad Institute of Technology Lecturer in Computer Science and Technology Berhampore India Aliah University Dept. of Computer Science and Engineering Kolkata India

ISBN: (纸本)9798350306118

Network partitioning improves the energy efficiency of the network. In this work, the algorithm (KP-MWSN) can determine the no. of partitions (k) required based on the delay tolerance limit of each node of MWSN. It can be fruitful for the events where a small amount of delay can be accepted but efficiency has not been calculated in respect of a metric. So, we have measured the efficiency of KP-MWSN algorithm and the results are compared with the Topology Partitioning Scheme (TPS). The simulation result shows that in every randomly created event the efficiency of KP-MWSN is always better than other related state-of-The-Art work. © 2023 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Identification of Malignant Cells Using Convolutional Neural Network 1

Identification of Malignant Cells Using Convolutional Neural...

引用

1st International Conference on Circuits, Power, and Intelligent Systems, CCPIS 2023

作者： Sahu, Rekha Dash, Akshaya Kumar Silicon Institute of Technology Dept. of Computer Science and Engineering Bhubaneswar India

ISBN: (纸本)9798350315769

Breast cancer has a high impact as a leading cause of death. Doctors face problems with the quick diagnosis of malignant tumors, which would help in the prevention of cancer at an early stage. Automatic detection of malignant cells is a life-saving boon. The deep learning approach extensively manipulates the data non-linearly to obtain suitable information. In this study, a one-dimensional convolutional neural network is implemented on a tumor dataset to detect malignant and benign tumors. The deep learning approach has achieved 99.9% classification accuracy with 45 epochs and 98.8% ROC-AUC. More experiments are needed on new tumor datasets to study the performance of the one-dimensional convolutional neural network approach in identifying malignant cells. © 2023 IEEE.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Blockchain and IoT-Based Medical Care Utilizing Secure and Protection Safeguarding Watermark

Blockchain and IoT-Based Medical Care Utilizing Secure and P...

引用

2023 International Conference on Smart Systems for Applications in Electrical Sciences, ICSSES 2023

作者： Shruthi, K. Poornima, A.S. Siddaganga Institute of Technology Dept. of Computer Science and Engineering Tumakuru India

ISBN: (纸本)9798350347296

Patient clinical information is critical information for a well-being application. Clinical information regularly assumes a significant part in illness examination and is ensnared in persuading values for instructing symptomatic techniques and altering analytic outcomes. Privacy of patient well-being reports is more significant, furthermore, subsequently, specialists have considered numerous safety efforts, counting access control, classification, and uprightness of these records. To take care of the security issue, this paper presents a high-level arrangement in light of changing over clinical information into minimized size, as a watermark before being sent on Blockchain. Along these lines, difficult tasks will be securely performed off-chain, like gathering and preprocessing patient information, while accommodation of this information is finished on an hourly premise chain. We suggest an information stream design that consolidates the IoT with blockchain using the Ethereum platform, utilizing brilliant agreements to access and store information against many assaults. The proposed model is successful in sharing and overseeing patient electronic well-being information. The tests need to be carried out on Ethereum chain arrangements on laptops, and desktops. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Operating System Command Execution Using Voice Command 3

Operating System Command Execution Using Voice Command

引用

3rd IEEE Asian Conference on Innovation in technology, ASIANCON 2023

作者： Singh, Paras Nath Navaneetha, M. Tijare, Poonam Vijay Cmr Institute of Technology Dept. of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350302288

Recent years have seen a considerable increase in the use of voice commands as a result of the growing popularity of smart gadgets, virtual assistants, and other related technologies. In this study, we investigate the viability of voice commands for operating system commands. In this paper a system is proposed and demonstrated that enables voice commands to be recognized by the operating system and executed according to parameters. This way it is offering a fresh and more usable voice assistant to carry out typical computer chores. Python tools are used to go over how the system is put into practice, including how speech recognition and natural language processing are used, and how well it executes in terms of accuracy, speed, and usefulness. The main impact factor of this paper is to provide voice assistance to disadvantageous people whose hands and fingers are not working well. © 2023 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Convolutional Neural Network Object Detection Algorithms for Image Processing

Comparative Study of Convolutional Neural Network Object Det...

引用

2023 IEEE International Conference on Electrical, computer and Energy Technologies, ICECET 2023

作者： Reddy, Saieshan Pillay, Nelendran Singh, Navin University of Technology Dept. of Electronic & Computer Engineering Durban South Africa

ISBN: (纸本)9798350327816

This paper presents a comparative study on three Convolutional Neural Network (CNN) object detection algorithms to find the best detector based on the combination of speed and accuracy on a personal computer. The MATLAB® development environment is used to evaluate three different object detector algorithms, namely Faster Region-Based Convolutional Network (R-CNN), Single Shot Detector (SSD) and You Only Look Once (YOLO). These algorithms are trained, and their performance metrics are tested on a small sample dataset. The results show that the SSD object detector algorithm performs best when considering both performance and processing speeds. Faster R-CNN detected objects at an average speed of 4.838 seconds and achieved a mean average precision of 0.76 with an average loss of 0.429. SSD detected objects at an average speed of 0.377 seconds and achieved a mean average precision of 0.92 with an average loss of 1.754. YOLO v3 detected objects at an average speed of 1.004 seconds and achieved a mean average precision of 0.81 with an average loss of 2.739. © 2023 IEEE.

关键词： computer Vision Convolutional Neural Network Image Processing MATLAB Object Detection

来源：评论

学校读者我要写书评

暂无评论

Enhanced Autonomous Mobile Robot Navigation Using a Hybrid BFO/PSO Algorithm for Dynamic Obstacle Avoidance

Informatica (Slovenia)

引用

Informatica (Slovenia) 2024年第17期48卷 209-222页

作者： Makhlouf, Amina Benmachiche, Abdelmadjid Boutabia, Ines LIMA Laboratory Dept. of Computer Science Faculty of science and technology House of Artificial Intelligence Chadli Bendjedid University El-Tarf PB 73 Algeria36000 Algeria

Determining path planning for mobile robots has received a lot of attention over the last three decades, with the goal of identifying safe and effective paths between starting points and destinations. The investigation of diverse navigation methodologies exhibits potential in expanding the range of uses for autonomous mobile robots. This research introduces a novel navigation strategy by combining the Particle Swarm Optimization (PSO) method with the Bacteria Foraging Optimization Algorithm (BFO). Utilizing the benefits of PSO, this bio-inspired method is used to optimize paths for mobile robots, drawing inspiration from the foraging behavior of bacteria, namely E. coli. The principal aim of this study is to design routes that are practical and safe. The proposed model features a robot that emulates bacterial foraging behavior to determine the most optimal path through environments densely populated with obstacles, effectively linking a starting point to a specified destination. This strategy has been implemented and rigorously evaluated across a variety of scenarios. Experimental results reveal that the hybrid BFO-PSO algorithm achieves a success rate exceeding 90% in navigating dynamic environments. Furthermore, the algorithm significantly outperforms traditional methods, offering approximately 50% less computational speed, efficiency, and superior security metrics, confirming its effectiveness and potential for real-world applications. © 2024 Slovene Society Informatika. All rights reserved.

关键词： Escherichia coli

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Driven Packet Loss Classification via TCP Jersey and Multi-Layer Perceptron

Machine Learning-Driven Packet Loss Classification via TCP J...

引用

2023 International Conference on Computational Intelligence, Networks and Security, ICCINS 2023

作者： Kiruthiga, R. Nithya, B. National Institute of Technology Dept. of Computer Science and Engineering Tiruchirapalli India

ISBN: (纸本)9798350313796

With the huge increase in the amount of data that is transferred every second, congestion in the network becomes unavoidable. There is always a need for algorithms to control the congestion in the network when the data flow increases drastically. The traditional Transmission Control Protocol (TCP) uses a slow start and congestion avoidance mechanism that is not capable of differentiating the cause of packet loss. In a heterogeneous network, the packet loss could result either from congestion in the wired network or a transmission error in the wireless network. In this paper, we propose a machine learning based improvement over TCP-Jersey, a variant of TCP that can distinguish the cause of packet loss and handle it appropriately. TCP-Jersey contains two key components, the Available Bandwidth Estimation (ABE) algorithm and Congestion Warning (CW) router configuration. Our machine learning model learns to distinguish wireless packet loss from congestion packet loss using Multi-Layer Perceptron (MLP). It predicts the cause of the packet loss and handles the congestion using bandwidth estimation algorithm. The simulation results show that our algorithm outperforms TCP-Jersey, TCP-Reno, TCP-Tahoe and TCP-Vegas in terms of throughput, goodput, fairness index and friendliness index. © 2023 IEEE.

关键词： Packet loss

来源：评论

学校读者我要写书评

暂无评论

'Hastabhashya'-Interpretation of Indian Sign Language using SqueezeNet and YoloV3

'Hastabhashya'-Interpretation of Indian Sign Language using ...

引用

2023 International Conference on Emerging Trends in Networks and computer Communications, ETNCC 2023

作者： Anbazhagan, Adithya Deeksha, D.V. Kumar Reddy, Ambavaram Tharun Singh, Paras Nath Cmr Institute of Technology Dept. of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350314878

The primary means of communication for persons who are hearing and voice-impaired is sign language, which is sadly not understood by a significant section of the public. To solve this problem, a naïve method is offered that converts sign language symbols into comparable plain text alphabets almost instantly using image processing and deep learning principles. Beyond providing healthcare for the deaf and dumb community, this technology has the potential to evolve into a general-purpose symbol-to-text converter with a variety of uses. The difficulties with character classification for Indian Sign Language (ISL) is tried to solve in this paper and work. Even though American Sign Language (ASL) has been the subject of much research, this cannot be said of Indian Sign Language (ISL) due to the absence of standardized datasets, obscured aspects, and regional variances in the language. ISL research has been hampered by these issues, but our initiative aims to fix them. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Based Music Streaming Services: A Novel Approach to Transparent Artist Control 3

Blockchain-Based Music Streaming Services: A Novel Approach ...

引用

3rd IEEE International Conference on Blockchain and Distributed Systems Security, ICBDS 2024

作者： Ashtagi, Rashmi Deshmukh, Tanmay Jadhav, Swati Bidwe, Ranjeet Akkalkot, Afsha Buchade, Amar Uke, Nilesh Banerjee, Sudipta Vishwakarma Institute of Technology Dept. of Computer Engineering Pune India Symbiosis Institute of Technology Dept. of Cse Pune India Coep Technological University Dept. Name of Computer Engineering Pune India Data Science Vishwakarma Institute Technology Dept. of Artificial Intelligence Pune India Indira College of Engineering and Management Pune India Symbiosis Institute of Technology Pune India

ISBN: (纸本)9798350354348

Artists have historically used music as a form of personal expression. However, due to the centralized nature of music streaming services, artists receive only a small percentage of the revenue generated and have no control over their content produced. To address these issues, a revolutionary technique is needed that provides artists with greater control and transparency over their output. This paper focuses on a decentralized strategy that utilizes blockchain technology to facilitate direct interaction between artists and users, enabling artists to upload their music, sell songs, and receive royalties. The implementation of blockchain technology could potentially revolutionize the music industry by ensuring that rightful owners receive payment for their music while reducing the waste of paying intermediaries. Without intermediaries involved in the distribution process, the music industry could pay out more royalties to rights holders automatically and instantaneously. The proposed solution also addresses piracy concerns through the use of encryption and watermarking techniques. Blockchains provide security, confidentiality, tamper-proofing, traceability, control, and oversight over information. By developing a secure, self-installing, cross-platform reader positioned on the header of the digital content file, The research empowers data owners to manage the flow of information even after it has been made available. The suggested approach enables content owners to control their digital content and monitor its most popular components after distribution. The blockchain-based system also benefits from token distribution among the content's owner, distributor, and consumer. The simulation results demonstrate that our approach is capable of overcoming the flaws of the existing system. © 2024 IEEE.

关键词： Blockchain

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：