检索结果-内蒙古大学图书馆

Drone-Based Public Surveillance Using 3D Point Clouds and Neuro-Fuzzy Classifier

computers, Materials & Continua 2025年第3期82卷 4759-4776页

作者： Yawar Abbas Aisha Ahmed Alarfaj Ebtisam Abdullah Alabdulqader Asaad Algarni Ahmad Jalal Hui Liu Faculty of Computing and AI Air UniversityIslamabad44000Pakistan Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Information Technology College of Computer and Information SciencesKing Saud UniversityRiyadh12372Saudi Arabia Department of Computer Sciences Faculty of Computing and Information TechnologyNorthern Border UniversityRafha91911Saudi Arabia Department of Computer Science and Engineering College of InformaticsKorea UniversitySeoul02841Republic of Korea Cognitive Systems Lab University of BremenBremen28359Germany

Human Activity Recognition(HAR)in drone-captured videos has become popular because of the interest in various fields such as video surveillance,sports analysis,and human-robot ***,recognizing actions from such videos poses the following challenges:variations of human motion,the complexity of backdrops,motion blurs,occlusions,and restricted camera *** research presents a human activity recognition system to address these challenges by working with drones’red-green-blue(RGB)*** first step in the proposed system involves partitioning videos into frames and then using bilateral filtering to improve the quality of object foregrounds while reducing background interference before converting from RGB to grayscale *** YOLO(You Only Look Once)algorithm detects and extracts humans from each frame,obtaining their skeletons for further *** joint angles,displacement and velocity,histogram of oriented gradients(HOG),3D points,and geodesic Distance are *** features are optimized using Quadratic Discriminant Analysis(QDA)and utilized in a Neuro-Fuzzy Classifier(NFC)for activity ***-world evaluations on the Drone-Action,Unmanned Aerial Vehicle(UAV)-Gesture,and Okutama-Action datasets substantiate the proposed system’s superiority in accuracy rates over existing *** particular,the system obtains recognition rates of 93%for drone action,97%for UAV gestures,and 81%for Okutama-action,demonstrating the system’s reliability and ability to learn human activity from drone videos.

关键词： Activity recognition geodesic distance pattern recognition neuro fuzzy classifier

来源：评论

学校读者我要写书评

暂无评论

Determinants of success and failure of knowledge transfer in information systems offshoring: a ranking-type Delphi study

引用

International Journal of Information Technology and Management 2023年第1-2期22卷 32-56页

作者： Strasser, Artur Strahringer, Susanne Westner, Markus Business Information Systems Faculty of Business and Economics Technische Universität Dresden Helmholtzstr. 10 Dresden01069 Germany Faculty of Computer Sciences and Mathematics OTH Regensburg Galgenbergstr. 32 Regensburg93053 Germany

The transfer of knowledge from client to service provider poses major challenges in information systems (IS) offshoring projects. Knowledge transfer directly affects IS offshoring success. Therefore, associated challenges must be overcome. Our study examines the determinants of success and failure of knowledge transfer in IS offshoring projects based on a ranking-type Delphi study. We questioned 32 experts from Germany, each with more than ten years of experience in near- or offshore initiatives to seek a consensus among them. We identified 19 success and 20 failure determinants. These determinants are ranked in order of importance using best-worst scaling. Aspects of closer cooperation are critical for effective knowledge transfer. This includes regular collaboration, willingness to help and support, and mutual trust. In contrast, critical determinants of failure are concerned with fears and fluctuation of human resources. Hidden ambiguities or knowledge gaps, an unwillingness and disability to share knowledge, and high fluctuation of human resources negatively impact knowledge transfer. Copyright © 2023 Inderscience Enterprises Ltd.

关键词： Information systems

来源：评论

学校读者我要写书评

暂无评论

Classification Driver Emotion with Deep Learning Method for Driver Safety Detection 8

Classification Driver Emotion with Deep Learning Method for ...

引用

8th International Conference on Informatics and Computing, ICIC 2023

作者： Jaya, Kurniawan Indra Bachtiar, Fitra Abdurrachman Universitas Brawijaya Intelligent Systems Laboratory Faculty of Computer Science Malang Indonesia

ISBN: (纸本)9798350342604

The main thing that car drivers care about is driving safety. At present, deaths and material losses due to car driving accidents commonly happen. According to several studies, human emotions also influence the level of risky driver behavior, for example, angry emotions show more frequent risky driving behavior more often. Based on this problem, researchers propose the classification of driver's emotions using deep learning methods. By using deep learning methods, drivers can understand their emotions and help to obtain information of driver's emotion state. The emotion detection is usually used for driving safety systems as one of the module to detect human factors in driving. In this study, KMU-FED dataset used for the emotion classification process. In addition, preprocessing step is conducted to prepare the dataset. The dataset image is resized to $48 \times 48$. Two deep learning model used for driver emotion classification. In this study, researchers applied the GhostNet and GhostNetV2 methods to find out the results in the classification of emotions in drivers. Hyperparameter tunning is conducted to get the best predictive model performance. Training and testing steps involved dataset split of 80% and 20% for training set and testing set, respectively. Model evaluation conducted to compare between GhostNet and GhostNetV2 architectures. Furthermore, the results also compared to similar previous studies. The classification results obtained using the KMU-FED dataset achieved a maximum accuracy of 99.10% on the GhostNetV2 architecture. Other methods such as SquezeeNet with Transfer Learning yield in maximum accuracy of 95.83%. This results indicates that GhostNetV2 architecture has good performance compared to the benchmark results of previous research. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Reading Technology for Blind People Using OCR and Neura Machine Learning Method 6

Reading Technology for Blind People Using OCR and Neura Mach...

引用

6th International Conference on Recent Trends in Advance Computing, ICRTAC 2023

作者： Preethi, C. Haripriya, K. Hammed, S. Shahul Pavalarajan, S. Priyadharshini, S. Varshambigai Achithra, B.R. Psna College of Engineering and Technology Department of Computer Science and Business Systems Dindigul India

ISBN: (纸本)9798350394702

This study focuses on the creation of a Neura Smart Book Reader that can help people who have visual impairments, especially those who are blind or have low vision and do not know Braille. The project uses IoT technology, which includes hardware, infrastructure, and services within the Internet of Things framework. The project primarily uses the energy-efficient Raspberry Pi device, which has machine-learning capabilities, making it adaptable. The Raspberry Pi computer is small and portable and operates on minimal power, showcasing advanced computing and Machine Learning algorithms. The system has a camera for capturing book pages, and the software performs Optical Character Recognition (OCR), combined with Machine Learning-driven character recognition. This improves the system's proficiency with each use. Once the image is recognized, the Neura Smart Book Reader converts it into audible text, allowing users to listen without tactile interaction. This proves how Machine Learning can improve accessibility. The device also offers online text-to-voice conversion via WiFi and 4G services and uses Machine Learning-based algorithms for enhanced linguistic articulation. This ensures a seamless reading experience for users across digital and hardcopy books. This amalgamation of IoT, Raspberry Pi, and Machine Learning technologies highlights the latest accessible reading solutions for visually impaired individuals,proving how Machine Learning can improve accessibility technology. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Forecasting Unemployment Recession Rates: A Logistic Regression Approach Utilizing Comprehensive Economic Indicators

Forecasting Unemployment Recession Rates: A Logistic Regress...

引用

2023 IEEE International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication Engineering, RMKMATE 2023

作者： Skandarsini, R.R. Lakshmi Narayanaa, T. Jhansi Ida, S. Dept. of Computer Science and Business Systems RMK ENGINEERING COLLEGE Thiruvallur India

ISBN: (纸本)9798350305708

This paper presents a predictive model using logistic regression to forecast unemployment recession rates, utilizing a range of variables such as GDP, inflation rates, employment rates, and trade activities. The model aims to provide accurate predictions of recession occurrence, utilizing historical data and rigorous cross-validation techniques. The model's significance lies in its potential applications in financial prudence and risk management, enabling job seekers to plan their personal finances and career trajectories, while companies can integrate these insights into strategic planning and supply chain optimization. The model's interpretability provides actionable insights by highlighting the significance and direction of each variable's impact on the predicted recession rate. The paper contributes to a deeper understanding of economic recessions and empowers stakeholders to navigate challenges with resilience and confidence. The model's deployment offers a practical tool for individuals and organizations to make informed choices during economic uncertainties, ultimately fostering prudent and sustainable economic strategies. © 2023 IEEE.

关键词： Economic recession Economic uncertainties Financial prudence GDP Machine learning Predictive model Recession

来源：评论

学校读者我要写书评

暂无评论

Vendor-to-Retailer Vegetables and Fruits Ordering Application Using Time Series Algorithm 2

Vendor-to-Retailer Vegetables and Fruits Ordering Applicatio...

引用

2nd IEEE International Conference on Futuristic Technologies, INCOFT 2023

作者： Sathya, T. Prabhu, D. Dhanush, Prabhu K Harithaa, S. Luckysha, M. Venkat, Ram S Sri Sairam Engineering College Computer Science & Business Systems Tamilnadu Chennai India

ISBN: (纸本)9798350308846

In this paper, we propose a vendor-to-retailers vegetable and fruit ordering application that streamlines the supply chain process. The application provides a platform for vendors and retailers to interact and conduct business transactions in a seamless and efficient manner. Vendors can use the application to upload their available inventory, pricing, and delivery schedules, while retailers can use the application to place orders, track deliveries, and make payments. The application is built on a user-friendly interface that allows vendors and retailers to easily navigate and manage their accounts. The system also employs a time series algorithm to predict future demand and optimize the allocation of vegetables and fruits to different retailers. The algorithm uses historical sales data and other relevant factors, such as seasonality and weather patterns, to provide accurate and timely forecasts. This can help vendors to make informed decisions about inventory management, production planning, and pricing strategies. It also improves the efficiency and enhance customer satisfaction by ensuring that fresh produce is available when and where it is needed. © 2023 IEEE.

关键词： demand forecasting inventory management supply chain time series algorithm vegetable and fruit ordering application Vendor-to-retailer

来源：评论

学校读者我要写书评

暂无评论

Scrap Management using E-com Online Machine Learning Iscrap Algorithm

Scrap Management using E-com Online Machine Learning Iscrap ...

引用

2023 International Conference on Sustainable Computing and Smart systems, ICSCSS 2023

作者： Shahul Hammed, S. Karthikeyan, M.P. Raj, R.Pranesh Preethi, C. Haripriya, K. Kathiravan, A. Psna College of Engineering and Technology Department of Computer Science and Business Systems Dindigul India

ISBN: (纸本)9798350333602

The scrap recycler app is an online application where users can sell the scrap materials that are available in the house. Scrap materials are referred to as waste, unused products like broken items, plastics, waste metals, papers, glass etc. Scrap is defined as a material that has no economic value only the basic materials that are available in that scrap can be recovered and *** application serves as a bridge to sell those waste scraps online. The main motto is to create an application that will be used to sell waste scraps and reduce the scraps that are available in the house and increase the recycling process and develop a sustainable environment. By using this application users can directly post the scrap materials online and vendors can be able to see the available scrap materials to be purchased and it is send to recycling stations. This application helps the vendors to easily make profit and it collects the scraps efficiently from the users, by this transportation costs can be managed. Only verified vendors can buy the scrap from the customers so that customer trust is developed and the vendors can mainly focus on customer satisfaction. This study provides a new perspective on selling those available scraps that are available in houses and small organizations using machine learning. The main objective of creating this algorithm is to reduce the usage of waste and reduce the land pollution. The algorithm is going to encounter challenges in sorting scraps and segregating waste, as well as disposing of waste. The machine learning is also used to detect the scraps so that the app will able to detect the scraps and indicate to the vendors. As a consequence, the algorithm is capable of resolving it. The software application is free and is available on the android platform. The application is user-friendly with a basic structure and easily able to sell scraps online. This software application is developed using MYSQL, android studio, and kotlin. © 2023 IEE

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Gender and Age Classification Using Caffe Network 6

Gender and Age Classification Using Caffe Network

引用

6th International Conference on Contemporary Computing and Informatics, IC3I 2023

作者： Arunkumar, S. Thirisha, R. Subarna Kiruthiga, A. Lilian, J. Felicia Malini, A. Thiagarajar College of Engineering Department of Computer Science and Business Systems Tamilnadu Madurai India

ISBN: (纸本)9798350304480

The availability of labelled data at scale has contributed to the rapid expansion of Deep Learning. This results show that training deep-cnn learning representations can lead to huge increases in performance on specific tasks. The caffe net model surpasses existing modernization approaches for gender and age approximation when tested against the Adience benchmark. It is suggested convolutional net architecture is simple and accurate to 95%. © 2023 IEEE.

关键词： computer Vision Deep Learning OpenCv'CNN

来源：评论

学校读者我要写书评

暂无评论

IBS: Secured Healthcare Data Management over Cloud Environment using Integrated BlockChain Strategy 1

IBS: Secured Healthcare Data Management over Cloud Environme...

引用

1st IEEE International Conference on Emerging Research in Computational science, ICERCS 2023

作者： Haripriya, K. Preethi, C. Hammed, S. Shahul Pavalarajan, S. Meenambika, A. Psna College of Engineering and Technology Department of Computer Science and Business Systems Dindigul India

ISBN: (纸本)9798350359756

Healthcare needs better diagnosis and disease analysis methods to simplify the *** address these concerns, a novel approach called Integrated Blockchain Strategy (IBS) has been developed, combining various cutting-edge technologies, including Blockchain, and Cloud-based Data *** aims to enhance healthcare disease prediction and secure data management. It leverages the logical Blockchain and secured cipher strategy, with a focus on the Advanced Encryption Standard (AES) algorithm for data security. A unique aspect of this approach is the Attribute-Based Secret Key Generation Logic (ASKGL), which modifies the key generation process by incorporating user authorization attributes and concatenating them with a random key to create a new cipher key. By integrating these elements, the proposed approach ensures data security on the server end and facilitates disease prediction analysis with improved accuracy. Artificial Intelligence (AI) plays a vital role in handling complex healthcare-assisted data management tasks, simplifying the overall process. The result provides compelling evidence to support the efficiency of the proposed approach. It demonstrates reduced time consumption constraints, enhanced prediction accuracy, and other relevant benefits. In conclusion, the suggested approach offers a comprehensive and effective solution for healthcare data management, addressing the challenges faced in the healthcare domain with clarity and precision. © 2023 IEEE.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Radioactive Metal Detection in Dustbin using Metaheuristic with Augmented Reality for Enhanced Safety and Security 6

Radioactive Metal Detection in Dustbin using Metaheuristic w...

引用

6th International Conference on Recent Trends in Advance Computing, ICRTAC 2023

作者： Preethi, C. Hammed, S. Shahul Haripriya, K. Pavalarajan, S. Saran, V. S.Shree Meikannan, R. Pranesh Raj Psna College of Engineering and Technology Department of Computer Science and Business Systems Dindigul India

ISBN: (纸本)9798350394702

Enabling everyday objects to collect, exchange, and analyze data, the Internet of Things (IoT) is a technology paradigm that has the potential to revolutionize industries through data-driven decision-making, automation, and efficiency. IoT's fundamental principles and applications are succinctly summarized in this abstract, with emphasis on its role as a catalyst for the Fourth Industrial Revolution. Its ubiquity in various domains, such as smart homes and industrial automation, highlights its importance in shaping our interconnected world. With this in mind, we are encouraged to explore the vast opportunities and challenges presented by the IoT ecosystem. In industrial, medical, and research environments utilizing radioactive materials, ensuring radiation safety and security is essential. An important measure in preventing harm to staff and surroundings is identifying and segregating radioactive metal objects. Introducing an innovative camera-based approach for augmenting the detection of such objects is the aim of this *** order to develop a reliable and real-time detection system, our suggested Radioactive Metal Detection Bin (RMDB) integrates cutting-edge camera systems with powerful image processing *** acquire pictures of items moving across the detecting region, the RMDB system places high-resolution cameras strategically. These cameras have specific sensors and filters that are made to find gamma radiation coming from radioactive metals. © 2023 IEEE.

关键词： Automation

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：