检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Chen, Tinghui Li, Shuai College of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China University of Oulu Faculty of Information Technology and Electrical Engineering Oulu90570 Finland Technology Research Center of Finland Finland

ISBN: (纸本)9781665410205

Within the context of intelligent manufacturing, industrial robots have a pivotal function. Nonetheless, extended operational periods cause a decline in their absolute positioning accuracy, preventing them from meeting high precision. To address this issue, this paper presents a novel robot algorithm that combines an adaptive and momental bound algorithm with decoupled weight decay (AdaModW), which has three-fold ideas: a) adopting an adaptive moment estimation (Adam) algorithm to achieve a high convergence rate, b) introducing a hyperparameter into the Adam algorithm to define the length of memory, effectively addressing the issue of the abnormal learning rate, and c) interpolating a weight decay coefficient to improve its generalization. Numerous experiments on an HRS-JR680 industrial robot show that the presented algorithm significantly outperforms state-of-the-art algorithms in robot calibration performance. Thus, in light of its reliability, this algorithm provides an efficient way to address robot calibration concerns. © 2024 IEEE.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

LayOut Loud: An AI-Powered Augmented Reality and Mobile Application for Room Interior Design and Layout Optimization 4

LayOut Loud: An AI-Powered Augmented Reality and Mobile Appl...

引用

4th International Conference on Intelligent Cybernetics technology and Applications, ICICyTA 2024

作者： Cuevas, John Raphael G. Rili, John Kenneth R. Santillan, Anny Neolicia G. Agustin, Vivien A. Gonzales, Mary Grace N. Centeno, Criselle J. Regala, Richard C. College of Information Systems and Technology Management Pamantasan ng Lungsod ng Maynila Department of Information Technology Manila Philippines College of Information Systems and Technology Management Pamantasan ng Lungsod ng Maynila Department of Computer Science Manila Philippines Pamantasan ng Lungsod ng Maynila Faculty of College of Engineering and Technology Department of Information Technology Manila Philippines College of Information Systems and Technology Management Pamantasan ng Lungsod ng Maynila Department of Information Technology Manila Philippines Pamantasan ng Lungsod ng Maynila College of Engineering and Technology Department of Computer Science Manila Philippines

ISBN: (纸本)9798331506490

LayOut Loud is an AI-powered augmented reality (AR) and mobile application designed to revolutionize room interior design by offering tailored, real-time solutions for layout optimization. The primary objective of this tool is to design AI-powered features that analyze user-provided room dimensions, furniture types, and style preferences. By leveraging advanced algorithms, LayOut Loud generates personalized design suggestions that cater to the individual needs and aesthetic tastes of users, ensuring that each interior design experience is customized and unique. A key goal of the application is to enhance user experience and decision-making through a clustering algorithm. This algorithm categorizes furniture pieces based on their suitability and appearance in living spaces, streamlining the selection process for users. By enabling the visualization of these items in a 3D model, users can make informed decisions about their interior design choices, ensuring that each piece contributes to the overall aesthetic and functional harmony of the space. Additionally, LayOut Loud focuses on improving its AR capabilities by allowing users to capture their room layouts and view virtual furniture arrangements in real time. This feature provides practical, interactive design solutions, empowering users to experiment with different configurations and instantly see how potential changes would appear in their actual living environments. Ultimately, LayOut Loud offers a user-friendly, immersive platform that transforms the way individuals approach interior design. © 2024 IEEE.

关键词： Architectural design

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Classification Algorithms for Accurate Breast Cancer Diagnosis 3

Machine Learning Classification Algorithms for Accurate Brea...

引用

3rd International Conference on Emerging Smart Technologies and Applications, eSmarTA 2023

作者： Alzboon, Mowafaq Salem Qawasmeh, Sami Alqaraleh, Muhyeeddin Abuashour, Ahmad Bader, Ahmad Fuad Al-Batah, Mohammad Jadara University Faculty of Science and Information Technology Irbid Jordan Arab Open University Faculty of Computer Studies Farwanya Kuwait Jadara University Faculty of Engineering Irbid Jordan

ISBN: (纸本)9798350305333

The introduction of algorithms based on machine learning (ML) has revolutionized computer science by allowing machines to learn without explicit programming. These algorithms automate operations, like categorization and clustering, that formerly required human interaction. In the medical field, classification algorithms based on machine learning have been used extensively to diagnose various diseases, including breast cancer, which remains one of the leading causes of death among women. This study describes an experiment that analyzes the effectiveness of machine learning-based algorithms for breast cancer diagnosis. Among the techniques evaluated are Logistic Regression, Decision Tree, Neural Network, Naive Bayes, The kNN, support vector machines (SVM), AdaBoost, Stochastic gradient descent (SGD), CN2 rule inducer, Constant, and Random Forest. The investigation used the renowned Wisconsin Diagnosis Breast Cancer dataset (WDBC). The primary objective of this experiment is to evaluate the Precision and accuracy of these algorithms in discriminating between malignant and benign tumors. The SVM model has the best accuracy at 0.975%, suggesting that Random Forest is a viable breast cancer diagnostic tool. These findings indicate that algorithms based on machine learning can potentially increase the accuracy and speed of breast cancer diagnosis. This research can inform the development of more precise and influential breast cancer diagnostic tools, enabling physicians to administer quick and appropriate therapy to patients. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Continuous Wavelet Transform Spectral Image Based Epileptic Episode Classification 25

Continuous Wavelet Transform Spectral Image Based Epileptic ...

引用

25th International Arab Conference on information technology, ACIT 2024

作者： Nuhi-Alamin, Md. Sarkar, Ajay Krishno Talukder, Md. Simul Hasan Aljaidi, Mohammad Swapnil, Safkat Shahrier Rajshahi University of Engineering & Technology Department of Electrical and Electronic Engineering Rajshahi Bangladesh Dhaka University of Engineering & Technology Department of Electrical and Electronic Engineering Gazipur Bangladesh Zarqa University Faculty of Information Technology Department of Computer Science Zarqa Jordan University of Business and Technology College of Engineering Jeddah21448 Saudi Arabia

ISBN: (纸本)9798331540012

Numerous individuals globally, regardless of age, have the neurological condition epilepsy. Recurrent seizures compromised motor and sensory abilities, and a hindered normal lifestyle are all signs of epilepsy. By seeing or manually examining electroencephalogram (EEG) data, neurologists can make the diagnosis of epileptic seizures. In this paper, a continuous wavelet transform spectral image-based epileptic episode classification technique is proposed. The EEG signal was first converted into 227x227 RGB images using CWT. Then these images were used to create an image dataset, and classification was performed using the proposed deep ensemble epileptic seizure classifier (DE-ESC). DE-ESC ensembled Dense-net-169, Dense-net-201, and Inception-V3. This proposed method obtained 100% accuracy (Ac), precision (Pr), recall, and F1 Score, respectively. © 2024 IEEE.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

A Survey on Object Instance Segmentation

引用

SN computer Science 2022年第6期3卷 499页

作者： Sharma, Rabi Saqib, Muhammad Lin, C.T. Blumenstein, Michael Faculty of Engineering and Information Technology School of Computer Science University of Technology Sydney Broadway Sydney 2007 NSW Australia

In recent years, instance segmentation has become a key research area in computer vision. This technology has been applied in varied applications such as robotics, healthcare and intelligent driving. Instance segmentation technology not only detects the location of the object but also marks edges for each single instance, which can solve both object detection and semantic segmentation concurrently. Our survey will give a detail introduction to the instance segmentation technology based on deep learning, reinforcement learning and transformers. Further, we will discuss about its development in this field along with the most common datasets used. We will also focus on different challenges and future development scope for instance segmentation. This technology will provide a strong reference for future researchers in our survey paper. © 2022, The Author(s).

关键词： Convolutional neural network Deep learning Instance segmentation Reinforcement learning Transformers

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of LoRa 923 MHz for the Internet of Things 10

Performance Evaluation of LoRa 923 MHz for the Internet of T...

引用

10th IEEE information technology International Seminar, ITIS 2024

作者： Juledi, Angga Putra Huda, Moh. Khoridatul Dwi Putra, Muhammad Taufik Delsi Samsumar, Lalu Prasetyo Adi, Puput Dani Nurdiansyah, Yanuar Universitas Labuhanbatu Faculty of Science and Technology Department of Information Technology Labuhanbatu City Indonesia Malang East Java Malang Indonesia Universitas Pendidikan Indonesia Department of Computer Engineering Bandung Indonesia Universitas Teknologi Mataram Department of Information Technology Mataram City Indonesia Research Center for Telecommunication Bandung Indonesia University of Jember Faculty of Computer Science Indonesia

ISBN: (纸本)9798331521295

This research focuses on enhancing the performance of data transmission in the Internet of Things (IoT) by leveraging LoRa technology. Specifically, it utilizes the LILYGO 923 MHz LoRa32 board, which integrates the ESP32 microcontroller with a LoRa module and additional devices like a 0.96-inch OLED display. This board also features a serial converter interface, simplifying the programming process, and uses a micro USB connection for both power and uploading code. One of the goals of this research is to enable the transmission of images using LoRa, though currently, only image conversion during transmission is implemented. The study includes reliability testing of the LoRa module over a distance of 10 km. The results show that the Packet Delivery Ratio (PDR) for Spreading Factor (SF) 7 is 50%, while for SF 12, it improves to 85%. Additionally, the Received Signal Strength Indicator (RSSI) measurements at a distance of 1000 meters with 3 Non-Line-of-Sight (NLoS) conditions yielded values of -120 dBm, -90 dBm, and -78 dBm. These results highlight the potential of LoRa technology in improving IoT data transmission, especially for long-range applications. © 2024 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Tomato Plant Disease Detection using Deep Learning Based Techniques: A Comparative study 2

Tomato Plant Disease Detection using Deep Learning Based Tec...

引用

2nd International Conference on Electrical, Electronics, information and Communication Technologies, ICEEICT 2023

作者： Deepika, P. Arthi, B. SRM Institute of Science and Technology Chennai India Easwari Engineering College Department of Information Technology TN Chennai India College of Engineering and Technology Faculty of Engineering and Technology SRM Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350397635

Tomato is most widely used and important crop in India. It plays a significant role in agriculture. Tomato plant grows in short period of time yields more tomatoes. Tomato is good in both nutrition and income. It can be grown in any soil condition and temperature. There are various diseases that affect tomato. To increase the production of tomato early detection of disease is important. There are various diseases in tomato plant like bacterial wilt, early blight, Late blight, Leaf, septorial leaf spot, leaf mold, bacterial spot etc. Deep Learning technologies provides better result in disease identification and detection. Deep learning architectures AlexNet, ResNet50, DenseNet121, EfficientNetB5, Inception-Resnet-V2, InceptionV3, MobileNet, VGG16 and VGG19 are tested against tomato plant diseases. The implementation is done by taking the tomato leaf images from real environment. The nine architectures are compared and in which DenseNet121 and MobileNet provides better accuracy than other deep learning architectures. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Preserving Performance and Reducing Energy Consumption: A Two-Phase Scheduling Approach in Cloud Computing Environments 9

Preserving Performance and Reducing Energy Consumption: A Tw...

引用

Joint 9th International Conference on Digital Arts, Media and technology with 7th ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications engineering, ECTI DAMT and NCON 2024

作者： Thanavanich, Thanawut Kantawong, Krittika Yaibuates, Mayoon Duangtang, Pumipong Siri, Atikhom Sriwanna, Kittakorn Chiang Rai Rajabhat University Faculty of Digital Technology Department of Computer Engineering Chiang Rai Thailand University of Phayao School of Information and Communication Technology Department of Digital Business Phayao Thailand

ISBN: (纸本)9798350318241

Cloud computing has evolved significantly, transitioning from traditional on-demand architectures to decentralized, multi-provider models. This shift is pivotal for enhancing connectivity in the Internet of Things and data-intensive computing. While accessing shared online resources, effective task scheduling is crucial for optimal service performance. However, the challenge persists in balancing resource optimization with potential issues like energy wastage or service performance degradation. This study proposes a two-phase scheduling approach in distributed computing, addressing the balance between performance preservation and energy reduction. The method seamlessly integrates with existing algorithms, employing a prescheduling phase followed by a model to estimate processors, minimizing underutilization. Experimental results highlight its contribution to energy-efficient scheduling, emphasizing a nuanced balance between performance and energy consumption. The approach employs a mathematical model to determine suitable processors, providing versatile options for computational resource providers, aiming for energy-conscious and performance-oriented solutions. © 2024 IEEE.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Ensemble Based Detection Model for DDoS Attacks in SDNs Using Advanced Feature Selection 17

Ensemble Based Detection Model for DDoS Attacks in SDNs Usin...

引用

17th International Conference on Signal Processing and Communication Systems, ICSPCS 2024

作者： Alashhab, Abdussalam Ahmed Edrah, Aisha Mohd Zahid, Mohd Soperi Siddikur Rahman, Md. Department of Computer and Information Sciences Universiti Teknologi Petronas Seri Iskandar Malaysia Faculty of Information Technology Alasmarya Islamic University Zliten Libya Western University Faculty of Engineering Department of Electrical and Computer Engineering LondonONN6A 5B9 Canada Universiti Teknologi Petronas Department of Electrical and Electronics Engineering Seri Iskandar Malaysia

ISBN: (纸本)9798350389630

Software-Defined Networking (SDN) enhances flexibility, scalability, and innovation by decoupling the control plane from the data plane, managed through streamlined controller operations. However, Distributed Denial of Service (DDoS) attacks pose significant cybersecurity threats to SDNs, disrupting services by flooding targeted systems with traffic from multiple sources. Real-time detection of these attacks remains challenging, as traditional methods often lack the ability to accurately identify complex attack patterns due to limited feature sets. To address this, we propose an ensemble-based model that combines three classifiers (SGD, EBM, and MLP) for effective DDoS attack detection and mitigation in SDNs. Our approach integrates a reliable feature selection methodology, leveraging Principal Component Analysis (PCA) to identify the most informative features for attack detection. This enhancement significantly improves the accuracy and efficiency of the ensemble model. Evaluated using the CIC-DDoS2019 and InSDN datasets, our model demonstrates substantial improvements in detection rates and computational efficiency. Results show that the proposed approach achieves 99% accuracy, underscoring its potential as a resilient solution for DDoS attack detection in SDNs. © 2024 IEEE.

关键词： Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

The Evaluation Result Based on the SURE Model: Case of Samarkand Branch of TUIT 13

The Evaluation Result Based on the SURE Model: Case of Samar...

引用

13th International Symposium on computer Science and Educational technology, ISCSET 2024

作者： Boynazarov, Ilkhom Tudevdagva, Uranchimeg Safarova, Gulnoza Raxmonova, Robiya Samarkand Branch of Tashkent University of Information Technologies Samarkand Uzbekistan Graduate School of Engineering Mongolian University of Sceicnce and Technology Computer Science Faculty Mongolia Chemnitz University of Technology Chemnitz Germany

ISBN: (纸本)9798350390803

This paper describes self-evaluation of several distance and e-Iearning courses of Samarkand branch of Tashkent University of information Technologies (TUIT) in Uzbekistan. Teaching from distance and use of e-Iearning is one of key issue of the TUIT. Teaching learning from distance is the complex process which requires different kind of actors with own interests. The success of the distance and e-Iearning process depends on cooperation and collaboration of those actors. Therefore, e-Iearning needs to scientific evaluation method to measure success of teaching and learning. The evaluation process which describes in this paper is the first self-evaluation for distance and e-Iearning courses in the Samarkand branch of the TUIT. The structure-oriented evaluation (SURE) model is selected for basic evaluation model for this self-evaluation. The SURE model is originally developed for measure a success of e-Iearning. The data for evaluation is collected by volunteer-based contribution from students in cases of three selected courses. The collected data is processed by online tool of the SURE model. Final evaluation SURE score of the three courses were bigger than 0.80. However, this result has no comparison with other similar evaluation due to the lack of self-evaluation at the university. This confirms that self-evaluation of selected courses and further courses should continue in next studies. © 2024 IEEE.

关键词： Contrastive 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：