检索结果-内蒙古大学图书馆

Recognition of American sign language using modified deep residual CNN with modified canny edge segmentation

Multimedia Tools and Applications 2025年 1-28页

作者： Hariharan, U. Devarajan, Devikanniga Kumar, P. Santhosh Rajkumar, K. Meena, M. Akilan, T. Department of Computer Science and Engineering Apex Institute of Technology Chandigarh University Punjab Mohali140413 India Department of Computer Science and Engineering GITAM University Karnataka Bengaluru561203 India Department of Information Technology Faculty of Engineering and technology SRM Institute of Science and Technology Ramapuram Tamil Nadu Chennai600089 India Department of Data Science and Business Systems School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamil Nadu Chennai603203 India Department of Computer Science and Engineering Sri Sairam Engineering College Tamil Nadu Tambaram602109 India Research Coordinator Dept. of IQAC Amity University Kolkata West Bengal 700135 India

American Sign Language (ASL) recognition aims to recognize hand gestures, and it is a crucial solution to communicating between the deaf community and hearing people. However, existing sign language recognition algorithms still have some drawbacks, such as difficulty recognizing hand movements and low recognition accuracy for most sign language recognition. A Modified Convolutional Neural Network (MCNN) deep residual 101 classifier-based American Sign Language identification system has been developed to address this problem. There are three main parts presents in the method. The first part is pre-processing the images to remove the noise, enhance the contrast of the picture, adjust the contrast level and smoothen the picture using various filters. The second part is the segmentation, and it’s used to partition the image using a modified canny edge detection method by removing all weak edges present in the image. Finally, classification will be done using the Modified CNN deep residual 101 classifiers. By classifying the image, the American Sign Language is accurately identified. This process is conducted through images. The outcome shows that the suggested approach has a 0.97% accuracy and a 0.05% False Positive Rate. Other CNN architectures such as resNet 50 and resNet 18 reached 0.90% and 0.80% accuracy, respectively, which is lower than our proposed method. In addition, the resNet 101 classifier effectively recognizes the difficult hand gestures through the image data. It obtains high recognition accuracy for 36 signs is 0 to 9 numbers and a to z alphabets from American Sign Language. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Secure-JobChain: Revolutionizing Job Recruitment with Blockchain technology

Secure-JobChain: Revolutionizing Job Recruitment with Blockc...

引用

2024 IEEE International Conference on Intelligent Systems and Advanced Applications, ICISAA 2024

作者： Pavithra, S. Geethanjali, S. Vidya, B. Suria, S. Rahul, B.S. Kishore, R. Computer Science and Engineering Rajiv Gandhi College of Engineering and Technology Pondicherry India SRM Institute of Science and Technology Data Science and Business Systems Kattankulathur India SRM Institute of Science and Technology Electronics and Communication Engineering Kattankulathur India

ISBN: (纸本)9798331539948

The traditional job recruitment process is time consuming and also undergoes certain difficulties such as data privacy, lack of transparency, and inefficient credential verification. These difficulties lead to mistrust and also delay the process of hiring. There is a need for improvement in this process that could benefit both the companies and the job applicants. In this paper, a decentralized recruitment platform based on blockchain technology is proposed. This proposed technique will overcome the above-mentioned difficulties by ensuring secure, transparent, and efficient connections between the recruitment companies and the prospective candidates. This solution uses the merits of blockchain i.e., immutability and automation to record job postings, applications, and hiring decisions on an immutable ledger, protecting personal data with cryptographic techniques and automating qualification verification with smart contracts. By implementing the decentralization concepts in Job recruitment, it is proven that the transparency in the interview process is improved by 9 0 and fraud risks are reduced considerably. Moreover, the efficiency of the entire job recruitment process is improved largely. Thus, the decentralized solution proposed in this paper demonstrates its potential in revolutionizing the job recruitment process by providing a secure, transparent and efficient hiring ecosystem. © 2024 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Beyond fossil:the synthetic fuel surge for a green-energy resurgence

引用

Clean Energy 2024年第5期8卷 1-18页

作者： Sreejaun Thothaathiri Janaki Dinesh Kumar Madheswaran G.Naresh Thangavelu Praveenkumar Electric Vehicle Technology Laboratory Department of Automobile EngineeringSRM Institute of Science and TechnologyKattankulathur CampusTamilnadu 603203India

This review offers a comprehensive overview of synthetic fuels as promising alternatives to conventional fossil *** carbon-neutral potential of synthetic fuels when produced using renewable energy and captured CO_(2),offering significant opportunities to mitigate CO_(2) emissions,is ***,the efficiency of synthetic fuels is presented,as they do not require dedicated agricultural land or substantial water resources,addressing concerns related to the land-use change and water scarcity associated with traditional *** economic viability of synthetic fuels is explored,highlighting the advancements in technology and decreased renewable-energy costs,coupled with their independence from food crops,mitigating concerns about potential impacts on food *** investments by industry leaders such as Porsche,Highly Innovative Fuels Global,and ExxonMobil,totalling$1 billion,aimed at achieving an annual production of 550 million litres by 2026,are covered in *** study is further extended by emphasizing the scalability of synthetic fuel production through modular processes,enabling tailored facilities to meet regional demands and contribute to a decentralized and resilient energy ***,the‘drop-in’nature of synthetic fuels that are seamlessly compatible with existing fuel storage,pipelines,and pumps,facilitating a smooth transition without requiring extensive infrastructure changes,is *** such as the current high cost of synthetic fuel production are acknow-ledged,necessitating supportive government policies and incentives for widespread ***,synthetic fuels have emerged as promising contenders in the pursuit of sustainable and adaptable energy solutions,with tangible benefits for the environment,economy,and existing energy infrastructure.

关键词： synthetic fuels biofuels carbon neutrality sustainable energy e-fuel ‘drop-in’nature

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Survey on Enhancing Digital Twin Security Systems with Explainable AI Techniques 3

A Comprehensive Survey on Enhancing Digital Twin Security Sy...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Lalithadevi, B. Krishnaveni, S. Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India Department of Computational Intelligence SRM Institute of Science and Technology Kattankulathur India

ISBN: (纸本)9798331527549

Digital Twin (DT) technology has emerged as a cornerstone in modern engineering, enabling real-time digital replication of physical assets for monitoring, diagnostics, and optimization. However, as DTs become increasingly integrated into critical infrastructure, their security has become a paramount concern. This paper presents a comprehensive survey on the integration of Explainable Artificial Intelligence (XAI) into Digital Twin security, highlighting the potential of XAI in enhancing the transparency, interpretability, and trustworthiness of AI - driven security mechanisms in DTs. We explore various XAI techniques, including model- agnostic approaches, interpretable neural networks, and rule-based systems, detailing their potential applications in bolstering the security of Digital Twins. Furthermore, we identify several key challenges in implementing XAI for DT security, such as the need for standardized metrics for interpretability, the trade-offs between model complexity and explainability, and the potential for adversarial attacks on explainable models. Through our analysis, we highlight the critical research gaps, including the security of Digital Twin (DT) systems and explores the integration of Explainable AI (XAI) to enhance transparency, interpretability, and trustworthiness. Outcomes include detailed XAI applications for DT security, identification of limitations, and a roadmap for future research. We discuss various XAI techniques, their applications, and the current challenges in implementing XAI for DT security. Our survey identifies key research gaps and offers a roadmap for future research in this emerging field. © 2025 IEEE.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Real-Time Multi Fractal Trust Evaluation Model for Efficient Intrusion Detection in Cloud

引用

Intelligent Automation & Soft Computing 2023年第8期37卷 1895-1907页

作者： S.Priya R.S.Ponmagal Department of Computer Science and Engineering School of ComputingSRM Institute of Science and TechnologyChengapattu603203Tamil NaduIndia Department of Computing Technologies School of ComputingSRM Institute of Science and TechnologyChengapattu603203Tamil NaduIndia

Handling service access in a cloud environment has been identified as a critical challenge in the modern internet world due to the increased rate of intrusion *** address such threats towards cloud services,numerous techniques exist that mitigate the service threats according to different *** rule-based approaches are unsuitable for new threats,whereas trust-based systems estimate trust value based on behavior,flow,and other ***,the methods suffer from mitigating intrusion attacks at a higher *** article presents a novel Multi Fractal Trust Evaluation Model(MFTEM)to overcome these *** method involves analyzing service growth,network growth,and quality of service *** process estimates the user’s trust in various ways and the support of the user in achieving higher service performance by calculating Trusted Service Support(TSS).Also,the user’s trust in supporting network stream by computing Trusted Network Support(TNS).Similarly,the user’s trust in achieving higher throughput is analyzed by computing Trusted QoS Support(TQS).Using all these measures,the method adds the Trust User Score(TUS)value to decide on the clearance of user *** proposed MFTEM model improves intrusion detection accuracy with higher performance.

关键词： Intrusion detection cloud systems trusted service support trusted network support trust user score trusted QoS support

来源：评论

学校读者我要写书评

暂无评论

An Experimental Analysis of Machine Learning Models for Diabetes Classification 7th

An Experimental Analysis of Machine Learning Models for Di...

引用

7th International Conference on Communication, Device and Networking, ICCDN 2024

作者： Ghosh, Subhayu Acharya, Riyan Jana, Nanda Dulal Department of Computer Science and Engineering National Institute of Technology Durgapur West Bengal Durgapur India Department of Computer Science and Engineering SRM Institute of Science and Technology Tamil Nadu Kattankulathur India

ISBN: (纸本)9789819764648

Diabetes is a chronic metabolic disorder that affects millions of people worldwide. Early detection and effective management of diabetes are crucial to prevent severe complications and improve the quality of life for affected individuals. Machine Learning (ML) techniques have shown great promise in aiding the early detection of various diseases on patient data, including diabetes. ML algorithms can analyze vast datasets, identify patterns, and make accurate predictions, helping medical professionals to diagnose diabetes at its early stages. In our work, we employed several ML models for diabetes classification using different datasets. These models include K-Nearest Neighbor (KNN), Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), Gradient-Boosted Model (GBM), eXtreme Gradient Boosting (XG-Boost), Adaptive Boosting (Ada-Boost), Support Vector Machine (SVM), and Gaussian Naive Bayes (GNB). We performed a comparative analysis of their performance on three distinct datasets using evaluation metrics like accuracy, precision, F1-score, sensitivity, specificity and Cohen’s Kappa Value. Our findings revealed that the RF algorithm is optimal for symptoms-based and primary lab report-based diabetes detection, while XG-Boost excels in classifying different types of diabetes from a multi-class dataset. Moreover, we investigated diverse symptoms and their impact on diabetes outcomes, offering insights into preventive measures and early stage monitoring for this disease classification. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

GAN-Based Federated Adversarial Learning for Enhancing Security Towards Consumer Digital Ecosystems

引用

IEEE Transactions on Consumer Electronics 2025年第1期71卷 1102-1114页

作者： Murmu, Anita Kumar, Piyush Namasudra, Suyel Reddy, M Rajasekhar National Institute of Technology Patna Department of Computer Science and Engineering Patna India Bennett University School of Computer Science Engineering and Technology India National Institute of Technology Department of Computer Science and Engineering Patna India National Institute of Technology Agartala Department of Computer Science and Engineering Tripura India Amrita Vishwa Vidyapeetham Amrita School of Computing Andhra Pradesh India

Federated Adversarial Learning (FAL) maintains the decentralization of adversarial training for data-driven innovations while allowing the collaborative training of a common model to protect privacy facilities. Before sharing with bigger global aggregation, it allows users to change settings locally over many iterations. However, a strong network against attackers in Industry 5.0 towards consumer digital ecosystems is a challenge for adversarial training methodologies. To solve this issue, a novel FAL-based Customized Inequality-Aware Federated Learning (CusIAFL) technique is proposed in this paper for classifying and securing color images. The proposed method reduces the instability brought on by the heterogeneity of the data and optimizes each data sample by understanding the client-label distribution. A unique Pix2Pix Generative Adversarial Network (GAN) algorithm is employed to generate realistic images in the presented research work, while a hybrid approach is used to guarantee consistency in the time series data. This innovative research work is evaluated on various non-medical, consumer electronic, and medical imagery. The experimental results have been evaluated using performance metrics, namely accuracy, entropy, Peak Signal-to-Noise Ratio (PSNR), Hausdorff Distance (HD95), Structural Similarity Index (SSIM), and Mean Square Error (MSE). The results show that the proposed technique outperforms the existing models in terms of security. © 1975-2011 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Multiple Disease Prediction from Retinal Images Using Deep Learning Algorithm

Multiple Disease Prediction from Retinal Images Using Deep L...

引用

2025 International Conference on Pervasive Computational Technologies, ICPCT 2025

作者： Rishikesh, B. Karthikayani, K. Srm Institute of Science and Technology Department of Computer Science and Engineering Vadapalani Campus Tamilnadu Chennai26 India

ISBN: (纸本)9798331508685

Retinal imaging serves as an essential tool for the early identification and diagnosis of numerous systemic diseases. This model framework is used for predicting multiple diseases simultaneously using retinal images. The implementation begins with the collection of annotated retinal images, enabling the identification of ailments as glaucoma, age-related macular degeneration, diabetic retinopathy, including hypertensive retinopathy. Preprocessing techniques are applied to enhance data quality and reduce noise. Feature extraction is conducted using the pretrained VGG16 convolutional neural network (CNNis essential for deep learning model training. Multi-label categorization and multi-task learning are employed to predict multiple diseases concurrently. Strict measures, including as accuracy, sensitivity, specificity, including the area under the receiver operating characteristic curve (AUC-ROC), are used to assess the system's performance. Clinical validation also evaluates its efficacy in practical settings. The incorporation of this predictive system into clinical workflows is facilitated by ensuring regulatory compliance and seamless communication with healthcare professionals. Experimental Results show that the suggested VGG16-based system accomplishes an impressive 98.7% accuracy in detecting multiple retinal diseases. The implementation underscores the transformative potential of leveraging advanced deep learning techniques in ophthalmology. Future efforts are focused on enhancing algorithm performance through larger datasets and refining models to further improve diagnostic precision, enabling timely and effective treatment strategies for retinal conditions. © 2025 IEEE.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Toxic Comment Classification Using Bi-LSTM, CNN, and TinyBERT 8th

Toxic Comment Classification Using Bi-LSTM, CNN, and TinyBER...

引用

8th International Conference on Information System Design and Intelligent Applications, ISDIA 2024

作者： Chandavarkar, Chetana A. Rayhan, Mohammed Soni, Rishabh Muthukmar, Steffina Department of Computer Science SRM Institute of Science and Technology Chennai India

ISBN: (纸本)9789819765805

Social Media is a vital aspect of daily life where individuals express their ideas and opinions, participate in social and political debates, share photos and make content on a wide range of subjects. However, social media platforms can also be a breeding ground for cyberbullying, hate speech, and harassment, which can lead to real-world harm. The toxic nature of many discussions on social media is one such negative side effect. This project aims to classify toxic comments using three machine learning models. The models used in this project are Bidirectional Long Short-Term Memory (Bi-LSTM), Convolutional Neural Networks (CNN), and Tiny Bidirectional Encoder Representations from Transformers (TinyBERT). The newly proposed model allows the user to choose the algorithm suitable for their respective platform. This model will deliver a multi-binary output where it is classified into the following labels: Toxic, Severely Toxic, obscene, Insult, Hate, and Threat. The metrics used to evaluate the performance of the models include recall, accuracy, and precision. Social media platforms can use the suggested method to automatically identify and filter toxic comments, enhancing the security and quality of online interactions. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Driver Drowsiness Detection Using OpenCV 8th

Driver Drowsiness Detection Using OpenCV

引用

8th International Conference on Information System Design and Intelligent Applications, ISDIA 2024

作者： Shreya, V. Srimathi, S. Niveditha, S. Department of Computer Science SRM Institute of Science and Technology Chennai India

ISBN: (纸本)9789819748914

The advancement of computing technology has provided the means for building intelligent vehicle systems. The driver drowsiness detection system is one of the potential applications of intelligent vehicle systems. Here we employ machine learning techniques to detect driver drowsiness. The input is given in the form of a real-time webcam video, which will be processed in real-time. The system gives an output in the form of a sound alert and also a message alert will be sent if the user is found closing their eyes. The proposed system aims to lessen the number of accidents that occur due to drivers’ drowsiness and fatigue, which will in turn increase transportation safety. The existing system leverages CNN which accounts for its low accuracy and high processing time. The proposed system leverages eye aspect ratio, mouth aspect ratio, and head tilt to detect the drowsiness. © The Author(s).

关键词： Deep 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：