检索结果-内蒙古大学图书馆

A Machine Learning Approach to Identifying Employees at Risk of Workplace Injury 2

A Machine Learning Approach to Identifying Employees at Risk...

2nd IEEE International Conference on Interdisciplinary Approaches in technology and Management for Social Innovation, IATMSI 2024

作者： Pramanik, Bablu Modak, Santanu Brainware University Dept. of Computer Science & Engineering India Bengal College of Engineering and Technology Dept. of Information Technology India

ISBN: (纸本)9798350360523

Workplace injuries are a critical concern, with millions occurring annually, leading to substantial human and economic costs. This study focuses on a qualitative analysis based on statistics from 2013 to 2017, with a specific emphasis on fatal and non-fatal workplace accidents within the European Union (EU) and Romania. The primary objective is to assess Romania's workplace safety status in the context of the EU and to propose strategic measures for improvement. To achieve this goal, four key indicators and statistical datasets are utilized, sourced from the National Institute of Statistics (NIS) of Romania, the Eurostat database of the European Commission, and the Romanian Labor Inspection. These indicators include the rate of incidence frequency index for occupational accidents, the average duration index, the frequency index for fatal accidents, and the severity index, enabling a comprehensive evaluation of accident frequency and severity. The rate of incidence, measuring injuries per 100,000 workers, is a pivotal indicator. Additionally, the study calculates the frequency index of non-fatal accidents (injuries per 1,000 employees) and the fatal accident frequency index (injuries per 1,000 workers). Statistical findings are rigorously validated through ANOVA analysis and T-tests. Following data evaluation, the study offers strategic recommendations informed by national and European strategies, including the National Occupational Safety and Health (OSH) Strategy for 2017-2020 and the "EU Strategic Framework on Health and Safety at Work"spanning 2014 to 2020. These recommendations aim to guide efforts for workplace accident control and prevention in Romania and the broader European *** summary, this study's core objective is to comprehensively analyze workplace accidents in Romania and the EU, employing various indicators and statistical data. Its primary aim is to assess the current status and propose evidence-based strategies for improvement, aligning with

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Face Generation and Recognition in Forensic Science 11

Face Generation and Recognition in Forensic Science

引用

11th IEEE International Conference on Advances in Computing and Communications, ICACC 2024

作者： Ravi, Gayathri Joy, Heynes Jitto, Jeffin Joshy, Jocelyn Jose, Jisha Mary Rajagiri School of Engineering & Technology Dept. of Computer Science and Engineering India

ISBN: (纸本)9798350379136

Suspect identification can be challenging for forensic investigations since standard procedures are time-consuming and prone to mistakes. This calls for the creation of novel approaches utilizing developments in machine learning (ML) and artificial intelligence (AI). In order to overcome these obstacles, the proposed Face Generation and Recognition in Forensic Science will make use of sophisticated recognition algorithms and AI-based face generation models. Fully trained Stable Diffusion model is applied to generate high-quality face images from textual descriptions. Image Generation, Text Guided Image Manipulation using Denoising Diffusion Probabilistic Models (DDPMs), and Dataset Matching are the three primary components of the process. Using a stable diffusion model, Image Generation quickly creates high-resolution images from word prompts by combining an autoencoder (VAE), U-Net, and text encoder. With the introduction of an alternate noise space for DDPMs, Text Guided picture Manipulation makes it possible to do meaningful picture altering tasks in response to text prompts. VGG-16 , a convolutional neural network architecture is used in dataset matching to extract features and calculate similarity, which makes dataset alignment and comparison easier. The suggested methodology gives law enforcement authorities effective tools for identifying suspects, which represents a substantial development in forensic investigations. The project intends to increase the efficiency of criminal investigations, accelerate the matching process with large datasets, and enhance the accuracy of facial sketches by utilizing AI and ML approaches. The approach's ability to produce coherent and contextually relevant face images is validated by experimental results, which also show the approach's potential for speeding up the conclusion of criminal cases, particularly unsolved cold cases. All things considered, Face Generation and Recognition in Forensic Science is a promising step in st

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing VANET Efficiency with ACRR Technique for Improved Traffic Management and Network Scalability

Enhancing VANET Efficiency with ACRR Technique for Improved ...

引用

2024 International Conference on Science, technology, engineering and Management, ICSTEM 2024

作者： Karthick, K. Talari, Praveen Nishadevi, V. Krishna Prakash, R. Asokan, R. Velusamy, A. Dept. of Computer Science and Engineering Kongunadu College of Engineering and Technology Tamilnadu Trichy India Dept. of Computer Science and Engineering Vignan Bharathi institute of technology Telangana Hyderabad India Dept. of Computer Science and Engineering Mahendra College of Engineering Tamilnadu Salem India Dept. of Information Technology Sona College of Technology Salem India Dept. of Electronics and Communication Engineering Kongunadu College of Engineering and Technology Tamilnadu Trichy India Dept. of Information Technology Sona College of Technology Tamil Nadu Salem India

ISBN: (纸本)9798350376913

The role of Vehicular Ad Hoc Networks (VANETs) is crucial in enabling Intelligent Transportation System (ITS) technologies such as safe financial transactions, media applications, and effective traffic control. As traffic increases, the topology of vehicular networks is in constant flux, and the sparse distribution of vehicles, particularly on highways, presents challenges for network scalability. This situation makes it difficult for cars to keep consistent routes inside the network, which affects the stability of the network. To address these challenges, the developed Adaptive-ant Colony based Randomized Recommendation (ACRR) technique emerges as a unique solution for enhancing VANETs by reducing travel time. In instances of high traffic density on busy roads, the ACRR algorithm is effectively utilized to group vehicles. Leveraging data collected from these densely populated road segments, the system identifies congestion-prone areas and formulates optimal vehicle routes based on customized vehicle groupings. The framework's performance evaluation encompasses various parameters, including packet loss, message transmission rate, energy consumption, and average cluster growth. The proposed VANET framework, empowered by the ACRR algorithm, achieves an impressive message transmission rate of approximately 80%. In comparison, alternative methods like Re-RouTE exhibit a limited transmission rate of 70%, while others such as Net Run Rate (NRR), DIVERT 30, and DIVERT-60 demonstrate rates below 20%. Furthermore, the framework's parcel loss is significantly reduced to only 33% of that observed in the standard VANET framework. As a result, the ACRR algorithm integrated into the VANET framework demonstrates notable efficiency when compared to other approaches. It is crucial to recognize that, even with a refined technique, managing traffic congestion remains challenging if drivers disregard the recommended routing suggestions. Overall, this research offers insights into the p

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Assisted Intelligent Human computer Interaction for Next Generation Internet Applications

Informatica (Slovenia)

引用

Informatica (Slovenia) 2024年第2期48卷 145-146页

作者： Hasan, Al Mehedi Hwang, Yong Seok Shin, Jungpil Dept. of Computer Science and Engineering Rajshahi University of Engineering and Technology Bangladesh Kwangwoon University Seoul Korea Republic of School of Computer Science and Engineering The University of Aizu Aizuwakamatsu Japan

来源：评论

学校读者我要写书评

暂无评论

Cybersecurity Threat Detection Using Deep Learning and Anomaly Detection Techniques

Cybersecurity Threat Detection Using Deep Learning and Anoma...

引用

2024 International Conference on Knowledge engineering and Communication Systems, ICKECS 2024

作者： Rajendran, T. Mohamed Imtiaz, N. Jagadeesh, K. Sampathkumar, Balaji Rajalakshmi Institute of Technology Department of Computer Science and Engineering Chennai India Nagarjuna College of Engineering and Technology Dept. of Information Science and Engineering Bangalore India Sri Venkateswaraa College of Technology Dept. of Computer Science and Engineering Chennai India Akshaya College of Engineering and Technology Dept. of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350359688

Through the use of combined deep learning and anomaly detection approaches, this research investigates the area of cybersecurity threat detection. The study proves the framework's extraordinary success in recognizing as well as mitigating diverse cyber dangers, including insider threats and zero-day attacks, through practical testing and case studies. The framework establishes itself as a proactive cybersecurity solution adaptive to the changing threat landscape due to its high accuracy of 95%, low amount of false positives 5%, and quick reaction times. The recommendations cover user training, scalability, regulatory compliance, including cross-disciplinary collaboration. Behavioral analysis, AI explainability, IoT security, and countering quantum computing concerns should be the main areas of future research. These revelations help the cybersecurity industry become more resilient and well-prepared. In this research investigation, experiments on threat detection were conducted using deep learning algorithms, with a specific focus on Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). The findings of the study reveal that a detection accuracy of 93% was achieved by CNN, while a higher accuracy of 96% in threat detection was exhibited by RNN. © 2024 IEEE.

关键词： Zero-day attack

来源：评论

学校读者我要写书评

暂无评论

Autonomous Social Amenity, Pothole Detection and Reporting 4

Autonomous Social Amenity, Pothole Detection and Reporting

引用

4th International Multidisciplinary Information technology and engineering Conference, IMITEC 2024

作者： Mosela, David Olaifa, Moses Owolawi, Pius Malele, Vusi Tshwane University of Technology Dept. Computer Systems Engineering Tshwane South Africa Tshwane University of Technology Dept. of Computer Systems Engineering Tshwane South Africa

ISBN: (纸本)9798350387988

Challenges faced by traffic management in many developing nations across the globe is a result of the poor quality of road infrastructure. Inadequate and defective road infrastructure are major contributors to this effect. A key element that poses significant risk to road safety and that leads to increased road management cost is the increasing number of potholes and inefficient detection and reporting approach. This study provides an in-dept. exploration of the latest developments in pothole detection systems and examines various methodologies and technologies used in these systems, emphasizing the importance of real-time monitoring for proactive road maintenance. In addition, we proposed a system that addresses the persistent challenge of road infrastructure degradation by adopting cutting-edge technologies, including computer vision, machine learning, and sensor networks (such as ultrasonic and GPIO systems) that are used to identify and assess potholes on road surfaces. To achieve the aim of the study, the system adopts the use of RasberryPi 4 Model B for pothole detection and YOLOv4 for image processing. © 2024 IEEE.

关键词： Highway administration

来源：评论

学校读者我要写书评

暂无评论

A DNA-based Authentication System for Securing Cloud Data Storage and Transactions 18

A DNA-based Authentication System for Securing Cloud Data St...

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Kumar, Tarun Kumar, Prabhat Namasudra, Suyel National Institute of Technology Dept. of Computer Sc. & Engineering Patna India National Institute of Technology Dept. of Computer Sc. & Engineering Agartala India

ISBN: (纸本)9789380544519

Cloud computing has grown rapidly, but data breaches and unauthorized account access remain a persistent threat. Commonly used cryptographic authentication methods rely on mathematically complex but computationally insecure protocols. This paper suggests using new developments in deoxyribonucleic acid (DNA) computing to make the cloud safer by using biological authentication protocols that can be used by a lot of people. A DNA-based cryptographic key system is developed for leveraging synthetic DNA's dense information capacity. This approach interfaces biochemically secure DNA signatures with existing cloud architectures to provide multi-factor authentication (MFA), encrypting access to sensitive user data and transactions. The developed DNA cryptography protocols offer resilience against common attacks like password leaks, while the massive parallelism inherent in biochemical reactions allows efficient processing of authentication requests even under immense cloud workloads. This paper proposes the system's security using established threat frameworks, analyzing attack vectors related to storage, access control, data leakage, etc. This interdisciplinary approach highlights how DNA computing's advantages in encryption, steganography, and blockchain can address real-world cybersecurity needs. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Biometrics Cloud Data Security DNA Cryptography Multi-factor Authentication Synthetic Biology

来源：评论

学校读者我要写书评

暂无评论

Frequency Response Deterioration due to Surface Ridge Abrasion of Tactile Sensors 13

Frequency Response Deterioration due to Surface Ridge Abrasi...

引用

13th IEEE Global Conference on Consumer Electronic, GCCE 2024

作者： Yanwari, Muhammad Irwan Okamoto, Shogo Polines Dept. Computer Engineering Technology Japan Tokyo Metropolitan University Dept. Computer Science Tokyo Japan

ISBN: (纸本)9798350355079

Epidermal ridges are crucial for tactile sensing in both human fingers and synthetic sensors. These ridges are made of compliant materials and susceptible to abrasion damage after iterative use. This study focuses on examining the impact of sensor ridge damage on the acquired signal, which encompasses a broad range of frequency components. We compared the frequency responses of a tactile sensor scanning sandpaper with both intact and damaged sensors. The degradation of signal levels was evident across the 0-1,000 Hz range, with particularly prominent suppression of the peak frequency component. This study demonstrates the frequency-dependent influence of ridge abrasion. © 2024 IEEE.

关键词： Friction

来源：评论

学校读者我要写书评

暂无评论

Utilising Convolutional Neural Networks for the Automated Detection of Diabetic Retinopathy

Utilising Convolutional Neural Networks for the Automated De...

引用

2024 International Conference on System, Computation, Automation and Networking, ICSCAN 2024

作者： Lakshmi, R Poornima Shopika, S. Yaazhini, A. Hemalatha, M. Saraswathi, V. Ponnusamy, R. Chennai Institute of Technology Dept. of Computer Science and Engineering Tamil Nadu India Chennai Institute of Technology Dept. of Computer Science and Engineering Tamilnadu Chennai India

ISBN: (纸本)9798331510022

Diabetic retinopathy has emerged as one of the leading causes of eye diseases among people suffering from long-term diabetes. Indeed, it raises the risk of being blinded without proper detection and treatment. Conventional detection of retinal fundus images by an ophthalmologist is time-consuming and prone to mistakes owing to human intervention. This is particularly a cause for alarm in the wake of the growing incidence of diabetes globally. The need for automated, accurate detection systems for early diagnosis of diabetic retinopathy has never been more relevant. In this work, we develop a deep learning model based on CNN for classifying four stages of diabetic retinopathy, from no DR to proliferative DR. We tested the model in a public dataset to extract features from retinal images and to screen for abnormalities automatically. Our CNN model achieved 98.5% classification and detection accuracy, thus indicating the ability to make a real difference in the early detection and treatment plan, thereby preserving the vision of many diabetic patients. Practical value The present research is very relevant to clinical practice and, therefore, practically useful because of its relevance to healthcare technology. Using accuracy and loss function metrics, the proposed model performs well compared to the latest techniques in DR detection. An approach based on CNNs is expected to ease much of the workload that healthcare professionals bear in diagnosis and improve the precision, potentially resulting in a very high cutback in vision loss in diabetic patients with better patient outcomes. Our study has highlighted the practical utility of the CNN model, which has improved patient outcomes. DR is a serious condition affecting the eyes, which, in case of untimely detection and untreated in diabetic patients, can cause loss of vision. For centuries, the conventional diagnosis for this disease has been through the manual inspection of retinal fundus images taken through a camera

关键词： Clinical research

来源：评论

学校读者我要写书评

暂无评论

A Review of Disease Detection in Sugarcane Using Machine Learning and Deep Learning Techniques 15

A Review of Disease Detection in Sugarcane Using Machine Lea...

引用

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

作者： Pavan, Undavalli Chandra Pateriya, R.K. Tomar, Deepak Singh Singh, Surendra Maulana Azad National Institute of Technology Dept. of computer science & engineering Bhopal India National Institute of Technology Dept. of computer science & engineering Uttarakhand India

ISBN: (纸本)9798350370249

Agriculture has been an active source of food and economic growth, but it faces significant challenges from diseases and climate change. In Indonesia, sugarcane production is severely impacted by viral infections such as Sugarcane mosaic virus (SCMV) and Sugarcane streak mosaic virus (SCSMV). These infectious diseases pose a threat to the world's sugarcane industry, resulting in significant crop losses in nations like Brazil and India, along with other viruses like the Fiji Disease Virus (FDV), and Sugarcane Yellow Leaf Virus (SCYLV). For such diseases to be managed and performance to be maintained, early detection is essential. Disease detection is accomplished by both conventional and cutting-edge approaches, such as molecular, serological, and imaging methods. However, the advancements in Machine learning, Deep learning and computational image processing algorithms have demonstrated significant potential in the early and precise diagnosis of disease. In this study, different methods used for machine learning (ML) and deep learning (DL) for plant disease diagnosis were reviewed and it highlights the need of high-quality datasets, various pre-processing techniques, robust extraction of features, and efficient classification techniques. It also discussed the issues with data collection, symptom variability, over-fitting, and imbalances in classes, along with potential avenues for further advancement in diagnosing diseases systems. © 2024 IEEE.

关键词： challenges deep learning detection hybrid models machine learning Plant diseases

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：