检索结果-内蒙古大学图书馆

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Dhaarini, G. Sanjai, R. Sandosh, S. School of Computer Science and Engineering Vellore Institute Of Technology Chennai India

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509828

The rapidly changing urban landscape introduces unprecedented challenges to mobility and security, especially for the visually impaired and surveillance operators. All existing assistive technologies and monitoring systems significantly lack real-time environmental awareness, detection of obstacles, and comprehensive threats. Current approaches, mainly based on traditional mobility aids and conventional surveillance mechanisms, fail to provide adaptive and intuitive solutions that address the complex needs of navigation and safety in a modern urban environment. The Adaptive Navigation and Surveillance System is thus the innovative technological intervention that seeks to revolutionize environmental monitoring with high-performance ultrasonic sensing, multi-modal feedback mechanisms, and intelligent processing. The servo-mounted ultrasonic sensor features 180-degree scanning capability while also using sophisticated Arduino-based processing as well as a color-coded radar visualization interface, allowing it to take a transformative approach to personal mobility assistance and security infrastructure. The research will develop flexible, context-aware technological frameworks in support of enhancing situational awareness, real-time threat detection, and a more inclusive safer urban experience by bridging those critical gaps in existing assistive and surveillance technologies. Therefore, the system represents a leap forward in addressing the problems of navigation and security in increasingly intricate urban landscapes. © 2025 IEEE.

关键词： Environmental monitoring

来源：评论

学校读者我要写书评

暂无评论

Enhanced Myocardial Infraction Prediction through ECG using Multimodal Transfer Learning

Enhanced Myocardial Infraction Prediction through ECG using ...

引用

2025 AI-Driven Smart Healthcare for Society 5.0, AdSoc5.0 2025

作者： Omana, J. Sanjay Akash, R.V. Anand, Harish Sujay Sai, R. School of Computer Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (纸本)9798331536336

Myocardial infarction (MI), commonly known as a heart attack, is a leading cause of illness and death globally. The timely identification and classification of complications associated with MI are crucial for effective management and improved patient outcomes. This study proposes a novel deep learning-based approach to predict complications of MI by analyzing ECG images. A hybrid model is developed that integrates the strengths of Xception and ResNet50, two powerful convolutional neural networks, to extract diverse features from the ECG scans. These features are then processed through a series of steps, including concatenation, batch normalization, dropout, and dense layers, to refine the predictions. To prevent overfitting and enhance the model’s performance, L2 regularization is applied, and optimization methods like Adam and SGD are utilized. The model’s performance is evaluated using metrics such as accuracy, F1 score, confusion matrix, and ROC curves. Additionally, a user-friendly Streamlit web application is created to enable real-time prediction and visualization of MI complications from ECG images, improving accessibility for both clinicians and users. This approach demonstrates the potential of deep learning to enhance diagnostic accuracy and facilitate early intervention, leading to better healthcare outcomes. © 2025 IEEE.

关键词： Electrocardiography

来源：评论

学校读者我要写书评

暂无评论

Autism detection in children based on facial image data using RPY axial facial features and Dual Phase Net model

引用

Multimedia Tools and Applications 2024年第17期84卷 1-30页

作者： Attar, Nilofer Paygude, Shilpa School of Computer Engineering and Technology Dr. Vishwanath Karad MIT World Peace University Kothrud Pune India

Autism Spectrum Disorder (ASD) causing problems in social interaction and communication. Numerous studies for detecting autism in children result in a risk of losing track of the human facial element and also suffer from a severe parallax effect that increases the misclassification rate. Hence a novel autism detection technique namely, the -RPY(Roll-Pitch-Yaw) axial facial features based Dual Phase Net model" has been proposed. In the existing methods, the side facial landmarks were not accurately localized and identified. Hence, a novel Robust Facial Landmark Localization is introduced in which a Deep Arc Geo-segment NN provides localization pattern for 73 anatomical and pseudo-anatomical landmarks points. Moreover, head inclination range and eyeball configuration were not considered in previous methods for feature extraction. Hence, a Rotated RPY (Roll-Pitch-Yaw) axial with pattern wise feature extraction has been proposed for measuring head inclination range and eyeball configuration via Rotated Curvature Polynomial NN with the Haar Cascade algorithm. Besides, it is inaccurate to estimate the covariance matrix for high-dimension data. Hence, a Dual Phase Net has been proposed in which Probit Classifier performs binary classification to classify autism and non-autism in children and Multinomial track score NN classifies the autism level with demographic details. Overall the proposed model identifies autism with high accuracy and also classifies the severity level of autism in children. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Research on Personalized Recommendation Algorithms Based on Collaborative Filtering 5

Research on Personalized Recommendation Algorithms Based on ...

引用

5th International Conference on computer engineering and Intelligent Control, ICCEIC 2024

作者： Cao, Hangrui Shi, Zhan Yang, Hao School of Computer Engineering Nanjing Institute of technology Nanjing China

ISBN: (纸本)9798331507992

Traditional recommendation algorithms often suffer from issues such as data sparsity, lack of memory association, and prediction accuracy. This paper proposes a collaborative filtering recommendation algorithm that integrates memory and balance factors. When analyzing user interests and preferences, there are optimal design from multiple aspects such as memory factors and novelty of objects. This paper introduces a memory weight function to reflect the temporal characteristics of user interests, and incorporates a balance factor into user similarity calculation to reduce the impact of popular items on user similarity calculation, thus improving the accuracy of user similarity calculation. Experimental validation is conducted on the MovieLens dataset using MAE as the evaluation metric. The results demonstrate significant improvements in the experimental metrics, indicating enhanced recommendation accuracy and improved resilience to data sparsity. © 2024 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Sign Language Recognition Using Convolutional Neural Network Based on VGG-16 Deep Learning Approach 5th

Sign Language Recognition Using Convolutional Neural Network...

引用

5th International Conference on Advances in Information Communication technology and Computing, AICTC 2024

作者： Athish, M.J. Sowmya, S. Lakshaya, E. Preetha, S. Rishiya Shankar, S.U. Sendhil Kumar, K.S. School of Computer Science and Engineering Vellore Institute of Technology Vellore India

ISBN: (纸本)9789819761050

Communication is a significant part of our lives, as it facilitates interaction among individuals. Language serves as a mode of communication for all individuals for expressing their thoughts and interpretations. However, hearing-impaired individuals often face hurdles in using spoken language. The technology for recognizing sign language made a commendable effort to improve communication levels among hearing-impaired individuals. In the current era of deep learning, which is a subset of machine learning, Convolutional Neural Network models have been developed and are now in use for gesture recognition. This recognition is based on the CNN model and VGG-16 model. It is used to hone the temporal features. The dataset used here is American Sign Language Dataset (A–Z and 0–9). The focus of this work is to develop a sign language recognition system to fulfill the need for communication of impaired people in society. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cardiac Health: Machine Learning in Coronary Artery Disease Prediction 6th

Enhancing Cardiac Health: Machine Learning in Coronary Arter...

引用

6th International Conference on Computational Intelligence in Pattern Recognition, CIPR 2024

作者： Vijayaraj, Anu Ragavi Pasupathi, Subbulakshmi School of Computer Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (纸本)9789819780891

The alarming surge in cardiovascular diseases, with a particular focus on Coronary Artery Disease (CAD), is causing premature fatalities. This escalation is exacerbating the inefficiency of the diagnostic process, burdened by both time constraints and the strain on human resources, as more patients endure extended wait times for diagnosis. Addressing this pressing issue calls for the fusion of analytical decision-making with digital patient data, aiming to develop a robust and efficient predictive model for early-stage cardiac illness. Machine Learning (ML) emerges as a promising tool to bolster CAD detection and prognosis within the healthcare sector. This chapter introduces an ML-based approach for CAD prediction, leveraging the Z-Alizadeh Sani dataset sourced from the UCI repository. The classification task is tackled using three distinct ML models—Artificial Neural Network (ANN), Decision Tree (DT), and Random Forest (RF). The findings underscore the superior performance of ANN, achieving an impressive 89.01 percent accuracy in CAD diagnosis. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Cardiology

来源：评论

学校读者我要写书评

暂无评论

Improving Cancer Classification Through an Deep Learning Framework Using Transfer Learning 2

Improving Cancer Classification Through an Deep Learning Fra...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Subitha, D. Khalid, Fayyaz Kavitha, C. Abhinav, Gulisetty School of Computer Science & Engineering Vellore Institute of Technology Chennai India

ISBN: (纸本)9798331505745

The primary objective of this work is to create an AI system that offers intelligible and transparent justifications for cancer classification. When it comes to medical imaging-based cancer detection, sophisticated image analysis techniques such as deep learning models are used to assess and interpret medical pictures while offering a transparent account of its reasoning. The performance of the three state-of-art pre-trained deep models: VGG-16, and EfficientNetB0 on a dataset of eight different cancer types obtained from Kaggle is analyzed in this work. Furthermore, a novel deep learning framework is proposed using the above mentioned three pre-trained models as the backbone network using transfer learning approach for each type of cancer. Each model's effectiveness is evaluated in classifying these cancers using metrics like accuracy, precision, recall, and F1-score. This work ultimately yields the best fit model that are tuned with the hyper parameters optimized using Powell's algorithm. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Fixed-time-synchronized control: a system-dimension-categorized approach

引用

Science China(Information Sciences) 2023年第7期66卷 177-194页

作者： Wanyue JIANG Shuzhi Sam GE Dongyu LI Institute for Future & Shandong Key Laboratory of Industrial Control Technology School of Automation Qingdao University Department of Electrical and Computer Engineering National University of Singapore School of Cyber Science and Technology Beihang University Shanghai Institute of Satellite Engineering

This study addresses the fixed-time-synchronized control problem of perturbed multi-input multioutput(MIMO) systems. In the task of fixed-time-synchronized control, different dimensions of the output signal in MIMO systems are required to reach the desired value simultaneously within a fixed time *** MIMO system is categorized into two cases: the input-dimension-dominant and the state-dimensiondominant cases. The classification is defined according to the dimension of system signals and, more importantly, the capability of converging at the same time. For each kind of MIMO system, sufficient Lyapunov conditions for fixed-time-synchronized convergence are explored, and the corresponding robust sliding mode controllers are designed. Moreover, perturbations are compensated using the super-twisting technique. The brake control of the vertical takeoff and landing aircraft is considered to verify the proposed method for the input-dimension-dominant case, which shows the essential advantages of decreasing the energy consumption and the output trajectory length. Furthermore, comparative numerical simulations are performed to show the semi-time-synchronized property for the state-dimension-dominant case.

关键词： fixed-time-synchronized convergence sliding mode control perturbed MIMO systems

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection System To Counter Sybil Attacks In Underwater Wireless Sensor Networks Using Isolation Forest 5

Intrusion Detection System To Counter Sybil Attacks In Under...

引用

5th International Conference on Emerging Systems and Intelligent Computing, ESIC 2025

作者： Mandal, Anindita Chatterjee, Pinaki Sankar Kalinga Institute of Industrial Technology School of Computer Engineering Bhubaneswar India

ISBN: (纸本)9798331522100

Underwater Wireless Sensor Networks (UWSNs) are increasingly deployed in maritime and environmental monitoring, data gathering, and underwater communication. However, their unique characteristics - limited bandwidth, high latency, and energy constraints - make UWSNs highly susceptible to security threats, particularly the Sybil attack. In a Sybil attack, a malicious node forges multiple identities, compromising network integrity and leading to false data propagation and resource exhaustion. This paper proposes an Intrusion Detection System (IDS) that leverages the Isolation Forest algorithm to counter Sybil attacks in UWSNs. By analyzing node behavior, the proposed IDS identifies anomalies that correspond to Sybil nodes. The Isolation Forest algorithm is well-suited for this purpose due to its unsupervised nature and efficiency in detecting outliers, making it ideal for the constrained environment of UWSNs. Experimental results show that the proposed IDS effectively identifies Sybil nodes with high accuracy and low computational overhead, enhancing network security without compromising performance. This approach represents a significant advancement in safeguarding UWSNs against malicious intrusions, enabling more secure and reliable underwater operations. © 2025 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

IUST at ClimateActivism 2024: Towards Optimal Stance Detection: A Systematic Study of Architectural Choices and Data Cleaning Techniques 7

IUST at ClimateActivism 2024: Towards Optimal Stance Detecti...

引用

7th Workshop on Challenges and Applications of Automated Extraction of Socio-Political Events from Text, CASE 2024

作者： Mahmoudi, Ghazaleh Eetemadi, Sauleh School of Computer Engineering Iran University of Science and Technology Iran

ISBN: (纸本)9798891760707

This paper describes the IUST submission for sub-task C of the Climate Activism Shared Task at The 7th CASE workshop at EACL 2024. This work presents a systematic search of various model architecture configurations and data cleaning methods. The study evaluates the impact of data cleaning methods on the obtained results. Additionally, we demonstrate that a combination of CNN and Encoder-only models such as BERTweet outperforms FNNs. Moreover, by utilizing data augmentation, we are able to overcome the challenge of data imbalance. Our best system achieves 74.47% F1-Score on the unseen test set, outperforming the baseline by 19.97% and ranked 3th among 19 participants. © 2024 Association for Computational Linguistics.

关键词： Cleaning

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：