检索结果-内蒙古大学图书馆

10th International Conference on Advanced Computing and Communication Systems, ICACCS 2024

作者： Sujaykumar Reddy, M. Thota, Phanitha Sri Vellore Institute of Technology School of Computer Science Engineering Vellore India

ISBN: (纸本)9798350384369

The escalating prevalence of Android malware poses a substantial threat to online security, necessitating innovative approaches to combat this growing menace. Identifying novel and intricate malware variants remains a formidable challenge in the realm of software security. Existing malware detection methods primarily relying on static features often prove inadequate in countering sophisticated modern malware. While dynamic detection methods hold promise, they frequently fail to leverage the full spectrum of malware characteristics. This paper proposes a novel malware classification framework utilizing semi-supervised learning methods utilizing both unsupervised and supervised learning algorithms. We use the CCCS-CIC-AndMal-2020 dataset encompassing 13 prominent malware categories and 191 eminent malware families. Our results suggested that PCA+XGBoost accomplished by reducing the original dimensionality from 142 features to a more compact set of 48 features. The utilization of PCA in conjunction with the XGBoost model not only enhances the computational efficiency but also preserves the essential information required for classification. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Privacy-Protected Data Mining and CNN for E-Healthcare Systems 5

Privacy-Protected Data Mining and CNN for E-Healthcare Syste...

引用

5th IEEE Global Conference for Advancement in technology, GCAT 2024

作者： Nevatia, Isha Chaudhary, Vraj Pandian, M. Thurai Vellore Institute of Technology School of Computer Science and Engineering Vellore India

ISBN: (纸本)9798350376685

The E-Health care system is crucial in modern health care. These systems are designed to secure medical data repositories. The main goal of this study is to ensure both security and privacy by enhancing fully homomorphic data collection. It also aims to improve classification accuracy in disease detection. The existing method of Privacy-Preserving Data Mining (PPDM) is utilized to maintain privacy in healthcare, and the new method using a Convolutional Neural Network (CNN) algorithm is employed to identify diseases more accurately. This new approach enhances performance by achieving higher accuracy, recall, and reducing time complexity. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Gesture-based mouse control system based on MPU6050 and Kalman filter technique

引用

International Journal of Intelligent Systems Technologies and Applications 2023年第1期21卷 56-71页

作者： Prasanth, Narayanan Shrivastava, Kaustubh Sharma, Abhishek Basu, Aritri Sinha, Ritwik A. Raja, S.P. School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore632 014 India

The recognition of gestures with accuracy is still a widespread challenge which leads to prevention in the usage of wearable gesture recognition systems. In this paper, we proposed a gesture-based mouse, a smart glove based system for gesture recognition and remote control. To reduce the dependency of the gesture recognition system on external conditions like light and network connection, we eliminate the need of a camera and use a glove fitted with the MPU6050 sensor to detect motion accurately with minimal latency. The elimination of the camera component also reduced the overall component cost significantly. In this paper, we discuss the algorithm followed to map hand motion to cursor movement on the screen via the pseudocode and flowchart. Using this methodology, basic functionalities of the mouse and its operations were implemented with less expense and to more effectiveness. © 2023 Inderscience Enterprises Ltd.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

A Novel RoPE-Enhanced Informer Approach for Accurate Remaining Useful Life Prediction of Lithium-Ion Batteries

A Novel RoPE-Enhanced Informer Approach for Accurate Remaini...

引用

2024 IEEE Conference on engineering Informatics, ICEI 2024

作者： Nair, Aayush Bhatnagar, Shashwat Srinivasan, Kathiravan Manoov, R. Vellore Institute of Technology School of Computer Science and Engineering Vellore India

ISBN: (纸本)9798331505776

Lithium-ion batteries are integral to various systems, including electric vehicles and warehouses, where estimating their operational lifespan is critical. This lifespan, known as Remaining Useful Life (RUL), helps in optimizing performance and maintenance. Accurate RUL prediction helps avoid unexpected breakdowns and lowers maintenance costs, making these systems more reliable. This paper introduces a novel approach using a Rotary Positional Embedding (RoPE) Enhanced Informer model to address challenges in long-term time series forecasting for RUL prediction. By integrating RoPE into the Informer, the model efficiently preserves positional information and leverages sparse attention mechanisms to reduce computational complexity, enabling it to handle longer sequences with minimal memory usage. The proposed model was tested on benchmark datasets, where it outperformed peer level approaches in terms of Mean Absolute Error and Root Mean Squared Error. The results show a significant reduction in validation errors, indicating the model's superior generalization ability and its robustness against overfitting. This approach offers a scalable solution suitable for real-time predictive maintenance, particularly in resource-constrained environments. The combination of advanced positional encoding with the Informer architecture demonstrates the potential for this method to enhance battery management and improve the accuracy of RUL prediction across various industrial applications. © 2024 IEEE.

关键词： Lithium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

A Scalable Framework for Precision-Boosted Healthcare Predictions with Advanced Algorithms 4

A Scalable Framework for Precision-Boosted Healthcare Predic...

引用

4th International Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2024

作者： Subaraksha, R.T. Nithin Pranav, S. Uthish Shiva Kaarthik, R. Ragavan, K. Kalyanaraman, P. School of Computer Science and Engineering Vellore Institute of Technology Vellore India

ISBN: (数字)9798331529635

ISBN: (纸本)9798331529635

Healthcare data continues to grow in size and complexity. Hence, there's a rising need for more scalable and accurate prediction models. This study presents a framework that combines big data processing with advanced machine learning techniques to improve healthcare predictions, with diabetes mellitus as the primary use case. Apache Spark is used for data preprocessing, which distributes the large dataset to its worker nodes and completes the tasks at faster rate. This approach significantly reduces processing time when handling with millions of records. Most of the healthcare data often suffers from class imbalance, which is addressed with Synthetic Minority Over-sampling Technique (SMOTE) to develop a well-learned model. A StackingClassifier is built with three powerful boosting algorithms: XGBoost, CatBoost, and LightGBM. These models are combined to capture the strength of each algorithm and then enhanced by an AdaBoost meta-learner to boost precision. Further, doing cross validation and tuning the model with hyperparameters showed impressive results. SHAP and LIME is used for explaining the model's predictions. Evaluating the model with standard metrics like accuracy, precision, recall, and AUC-ROC shows up 98% accuracy and precision. This high precision indicates fewer false positives, making the model especially useful for real-world healthcare applications. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Unveiling the Multidimensional Risk Landscape of Human Trafficking in India: A K-Means Approach 1

Unveiling the Multidimensional Risk Landscape of Human Traff...

引用

1st IEEE International Conference on Smart Power Control and Renewable Energy, ICSPCRE 2024

作者： Rajan, Nitya Dasararaju, Shalini School of Computer Science and Engineering Vellore Institute of Technology Vellore India

ISBN: (纸本)9798350377002

Human trafficking, a modern form a slavery, causes extreme pain and trauma by depriving victims of their basic right and dignity. Within South Asia, India emerges as a significant focal point of human trafficking activities. Our research provides a multidimensional risk analysis on a state level by analyzing Human Trafficking Data using 5 categories: Total Number of Cases, Cases per Lakh Population, Child Trafficking, Trafficking for Forced Labor, and Sex Trafficking. Using the K-Means algorithm, we classify states into 3 risk levels: High, Medium and Low Risk. Our research shows that risk distribution varies significantly based on the type of Human Trafficking, showing different prevalence in different states and calls for a more nuanced analysis and intervention to combat Human Trafficking. Furthermore, it highlights the importance of analyzing the data using population normalized metrics, showing smaller states can have high prevalence of trafficking cases with respect to their population but lower numbers overall. Finally, we provide a ranked list of the most vulnerable states to Human Trafficking based on a multidimensional analysis over all categories, the top 5 states being Orissa, Delhi, Telangana, Rajasthan and Bihar. © 2024 IEEE.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Enabled Fair Profit and Transparent Supply Chain Platform for Small-Scale Farmers: A Case for Agricultural Transformation 4

Blockchain-Enabled Fair Profit and Transparent Supply Chain ...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Bhuvaneswari, M. Pal, Srija Kumar, Aman School of Computer Science and Engineering Vellore Institute of Technology Vellore India

ISBN: (纸本)9798331540364

India's agricultural sector is the backbone of the country, yet there are inefficiencies, a lack of transparency, and unequal farmer prices in its supply chain. Issues including inadequate market accessibility, inadequate infrastructure, and insufficient value addition exacerbate these challenges, especially for small and marginal farmers. Stakeholder collaboration is occasionally lacking in traditional supply chain systems, which leads to uneven farmer compensation and inefficient product delivery to consumers. Information and communication technologies (ICT) have been used to solve these problems in the past, but scalability, data security, and cost-effectiveness have all been shown to be lacking. With its core characteristics of automation, security, and transparency, blockchain technology presents a viable substitute. Blockchain technology can be used in the agricultural supply chain, but there are a number of obstacles to overcome, such as high implementation costs, complicated technology, and a need for major stakeholder engagement. This study investigates how blockchain technology could resolve these problems and transform India's agricultural supply chain. The goal is to create a system that leverages smart contracts to improve product traceability, increase trust, and automate procedures. Additionally, the study looks at certain blockchain applications including payment automation and farm-to-customer monitoring that make use of ***, Ganache, Truffle, and MetaMask technologies. This paper offers a thorough evaluation of earlier studies and offers a method for building an agricultural ecosystem that is more open, effective, and sustainable and that benefits supply chain participants, farmers, and consumers. The development of a blockchain-based software program is the main objective of this project, which attempts to increase the efficiency and transparency of the agricultural supply chain. No direct model comparisons have been done because the effort fo

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

Collision Avoidance System using YOLO-based Object Detection and Distance Estimation 3

Collision Avoidance System using YOLO-based Object Detection...

引用

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

作者： Raj, Shiv Akash Dhinakar Singh, Ashita Shekhawat, Tarakshraj Singh Manav Muthanna, M. Sivasankaran, K. School of Electronics Engineering Vellore Institute of Technology Vellore India School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore India

ISBN: (纸本)9798331527549

Road accidents are a significant global issue, with human error causing a substantial number of collisions. This emphasizes the need for advanced collision avoidance systems to improve road safety. In response, this study integrates object detection and distance estimation techniques to enhance vehicle safety. Utilizing recent iterations of the YOLO architecture—YOLOv6n, YOLOv8n, YOLOv9t, and YOLOv10n—the models were trained and evaluated on the KITTI dataset, a benchmark suite for driving applications. This research study provides a comparative analysis of these models, focusing on performance metrics such as precision, mean average precision, recall, and F1 score. A novel single-camera distance estimation method was also implemented to assess object proximity accurately. Among the evaluated models, YOLOv8n achieved the best results, with a F1 score of 0.74 and a mAP@0.5 of 0.782, demonstrating superior detection accuracy and reliability. Its swift convergence and low training losses make it well-suited for real-world use cases. While YOLOv9t and YOLOv10n also performed well, they were slightly less effective. The system enhances its capabilities by accurately estimating distances, which improves collision avoidance and road safety applications. Overall, YOLOv8n is the most efficient and reliable option for developing advanced safety features in vehicle systems. © 2025 IEEE.

关键词： Vehicle safety

来源：评论

学校读者我要写书评

暂无评论

Music Emotion Classification using Harris Hawk Optimization based LightGBM Classifier 10

Music Emotion Classification using Harris Hawk Optimization ...

引用

10th International Conference on Biosignals, Images and Instrumentation, ICBSII 2024

作者： Patil, Hemprasad Yashwant Bhagwan Patil, Priyanka Balasubramaniam, Anishkaa Shanmugasundaram, Lackesh Vellore Institute of Technology School of Electronics Engineering Vellore India Vellore Institute of Technology School of Computer Science and Engineering Vellore India

ISBN: (纸本)9798350350951

This research investigates the relationship between music and human emotions, focusing on emotion classification in Turkish music and the role of acoustics in music emotion recognition (MER). Leveraging a unique dataset stored in the UCI-MLR, the study employs machine learning techniques, including Linear Discriminant Analysis and Gradient Boost Classifier, to build a robust model. The accuracy enhancement is primarily driven by the feature selection process, which is powered by the Harris Hawks optimizer. This optimizer, when used with the LightGBM model, enables a more precise selection of features, thereby significantly improving the model's accuracy. The research achieves notable accuracies - 81.25% for Linear Discriminant Analysis and 83.75% for the Gradient Boosting Classifier - surpassing previous records. The paper discusses findings in the context of affective computing, emphasizing potential applications in music recommendation systems and therapy, concludes with a comprehensive analysis, and outlines future possibilities. This research contributes to advancing MER, laying the groundwork for innovations in diverse domains, including the potential integration with IoT-based intelligent systems for real-time emotion analysis and personalized music experiences based on camera frames. © 2024 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Text News Classification using Bi-directional LSTM Model 3

Deep Learning-based Text News Classification using Bi-direct...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Anand, Shreyas Prakasam, P. Vellore Institute of Technology School of Computer Science and Engineering Vellore India Vellore Institute of Technology School of Electronics Engineering Vellore India

ISBN: (纸本)9798350372120

The advancement of technology has resulted in increased news consumption through various online platforms and social media channels. Hence, there is a requirement for intelligent systems that may categorize the news that exists on the social media/online platform. Hence, this paper explores creating a news classifier utilizing a Bidirectional Long ShortTerm Memory (Bi-LSTM) deep learning model, which is a type of recurrent neural network (RNN) specifically designed to overcome the challenge of vanishing gradient often faced in deep learning. The machine learning was performed on a Kaggle dataset with over 400,000 records of news stories from various publishers. Natural language processing techniques such as stemming, one-hot encoding, vectorization, and embedding are used to prepare the data for machine learning. The multiclass classification is achieved and the performance of the model is analyzed. © 2024 IEEE.

关键词： Classification (of information)

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：