检索结果-内蒙古大学图书馆

IEEE MTT-S International Microwave Bio Conference ((IMBIOC)

作者： Mao-Hsiang Huang Sen Bing Mohamed Benomar Hung Cao J.-C. Chiao Department of Electrical Engineering and Computer Science University of California Irvine Irvine CA USA Department of Electrical and Computer Engineering Southern Methodist University Dallas TX USA Department of Electrical Engineering and Computer Science Biomedical Engineering Computer Science University of California Irvine Irvine CA USA

ISBN: (数字)9798331510473

ISBN: (纸本)9798331510480

This work introduces a refined image-processing method explicitly designed to amalgamate raster-scanned images obtained with a compact planar microwave resonator. The resonator tuned for use on the skin provides a deeper field penetration into the dermis layer, compared to the skin impedance measurements. The resonance of the sensor is sensitive to the dielectric properties of the tissues underneath the skin. Healthy and abnormal tissues exhibit different dielectric characteristics. Pixelated images can leverage resonant frequencies and reflection coefficients to enhance contrasts and boundaries to identify the abnormal tissues. We proposed using analytical tools like the structural similarity index to correlate frequency shifts with reflection coefficient magnitudes precisely. Preliminary results suggested the adeptness of the technique at classifying whether the tissue depth surpasses 15 mm and detecting tumor locations with a high accuracy when the image depth does not exceed 15 mm. A compact neural network model was implemented for processing the microwave images when the tumor depth exceeded 15 mm and achieved a high Dice coefficient. The work incorporated simulations to substantiate the novel concept and demonstrated its potential for noninvasive, efficient, and cost-effective subcutaneous imaging in medical applications.

关键词： Accuracy Neural networks Imaging Resonant frequency Microwave theory and techniques Dielectrics Reflection coefficient Microwave imaging Tumors Testing

来源：评论

学校读者我要写书评

暂无评论

Single-level Discrete Two Dimensional Wavelet Transform Based Multiscale Deep Learning Framework for Two-Wheeler Helmet Classification

EAI Endorsed Transactions on Industrial Networks and Intelli...

引用

EAI Endorsed Transactions on Industrial Networks and Intelligent Systems 2025年第2期12卷 1-13页

作者： Annadurai, Amrutha Prusty, Manas Ranjan Pandey, Trilok Nath Patra, Subhra Rani School of Computer Science and Engineering Vellore Institute of Technology Chennai India Centre for Cyber Physical Systems Vellore Institute of Technology Chennai India Information Systems and Operations Management University of Texas at Arlington Texas 76019 United States

INTRODUCTION: A robust method is proposed in this paper to detect helmet usage in two-wheeler riders to enhance road safety. OBJECTIVES: This involves a custom made dataset that contains 1000 images captured under diverse real-world scenarios, including variations in helmet size, colour, and lighting conditions. This dataset has two classes namely with helmet and without helmet. METHODS: The proposed helmet classification approach utilizes the Multi-Scale Deep Convolutional Neural Network (CNN) framework cascaded with Long Short-Term Memory (LSTM) network. Initially the Multi-Scale Deep CNN extracts modes by applying Single-level Discrete 2D Wavelet Transform (dwt2) to decompose the original images. In particular, four different modes are used for segmenting a single image namely approximation, horizontal detail, vertical detail and diagonal detail. After feeding the segmented images into a Multi-Scale Deep CNN model, it is cascaded with an LSTM network. RESULTS: The proposed model achieved accuracies of 99.20% and 95.99% using both 5-Fold Cross-Validation (CV) and Hold-out CV methods, respectively. CONCLUSION: This result was better than the CNN-LSTM, dwt2-LSTM and a tailor made CNN model. © 2025 A. Annadurai et al.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Heart Disease Prediction Using Logistic Regression

Heart Disease Prediction Using Logistic Regression

引用

International Conference on computer, Electrical & Communication engineering (ICCECE)

作者： Dipanjan Saha Soham Guha Kankana Kundu Suchana Das Sajili Chatterjee Pritusna Banik Sohinee Mondal Computer Science & Technology Narula Institute of Technology Kolkata India Computer Science Engineering (Artificial Intelligence & Machine Learning) Institute of Engineering & Management Kolkata India Computer Science & Engineering Narula Institute of Technology Kolkata India

ISBN: (数字)9798331513894

ISBN: (纸本)9798331513900

Cardiovascular diseases (CVDs) are one of the leading causes of death worldwide, and early identification is crucial to improve the patient’s prognosis. Traditional diagnostic methods for heart diseases are highly dependent on clinical expertise and can be time-consuming, making machine learning an attractive alternative for improving accuracy to diagnose and support faster decision making. Previously, research has explored various machine learning algorithms, such as decision trees, support vector machines, and neural networks, to improve prediction accuracy. However, many of these models face challenges related to their interpretability and generalization to unexpected data. This paper presents a logistic regression model to predict CVDs based on a dataset of 303 samples, incorporating key demographic, clinical, and diagnostic features. The model achieved an accuracy of $85.12 \%$ in the training data and 81. $97 \%$ in the testing data, demonstrating its effectiveness for binary classification tasks. The study emphasizes the computational efficiency and interpretability of logistic regression, making it appropriate for real-time applications in clinical settings. In conclusion, the results indicate that logistic regression can serve as a reliable tool for early detection of heart disease, and future work can explore dataset expansion, advanced models, and explainable AI techniques to further improve prediction accuracy and model transparency.

关键词： Heart Logistic regression Accuracy Computational modeling Training data Predictive models Data models Computational efficiency Reliability Testing

来源：评论

学校读者我要写书评

暂无评论

Leveraging Ensemble Model and Optimized Feature Selection to Boost Prediction Accuracy in Educational Data Mining

引用

SN computer science 2025年第5期6卷 1-20页

作者： Verma, Swati Kholiya, Kuldeep Bala, Kanchan Department of Computer Science & Engineering Bipin Tripathi Kumaon Institute of Technology Dwarahat India Department of Applied Science Bipin Tripathi Kumaon Institute of Technology Dwarahat India Department of Computer Science & Engineering Gaya College of Engineering DSTTE Gaya India

In contemporary research, educational data mining (EDM) has become a captivating field for data mining and machine learning experts, focusing on identifying factors influencing students' academic performance and predicting the likelihood of students dropping out. To uncover these influential factors, feature selection methods are employed, while various machine learning models are used to predict students at risk of underperforming. Filter-based feature selection methods are commonly used in educational data mining due to their efficiency and ability to rank important features affecting academic success. However, because of their independence from classifiers and relying on a fixed threshold or predefined feature count, filter-based methods can sometimes negatively affect model performance. To address this, the present study introduces an optimized chi-square-based feature selection technique that dynamically selects the optimal features for each learning algorithm, ensuring that model performance is not compromised. The effectiveness of five classifiers—k-Nearest Neighbour (k-NN), Decision Tree (DT), Naïve Bayes (NB), Support Vector Machine (SVM), and Logistic Regression (LR)—has been evaluated using three configurations: no feature selection, traditional chi-square feature selection, and proposed optimized chi-square based feature selection. These evaluations were conducted on two distinct student datasets, one from secondary schools (DS1) and another from engineering institutions (DS2). The results demonstrated that the optimized chi-square method consistently improved prediction accuracy across all classifiers. Additionally, a bagging-based ensemble classifier, constructed using the best-performing individual classifier, further enhanced predictive performance. The highest accuracies achieved were 94.62% for DS1 and 96.36% for DS2, outperforming traditional feature selection and ensemble methods. This study presents a scalable, reliable, and stable approach to s

关键词：

来源：评论

学校读者我要写书评

暂无评论

CephTransXnet: An attention enhanced feature fusion network leveraging neighborhood rough set approach for cephalometric landmark prediction

引用

computers in Biology and Medicine 2025年 188卷 109891-109891页

作者： Neeraja, R. Anbarasi, L. Jani School of Computer Science and Engineering Vellore Institute of Technology Chennai India

The convergence of medical imaging, computer vision, and orthodontics has made automatic cephalometric landmark detection a pivotal area of research. Accurate cephalometric analysis is crucial in orthodontics, orthognathic and maxillofacial surgery for diagnosis, treatment planning, and monitoring craniofacial growth. In this research study, a multi-branch fused feature extraction network titled CephTransXnet is proposed to automatically predict landmark coordinates from cephalometric radiographs. The initial sequential branch enhances discriminative local feature learning and feature extraction through parallel feature fusion by integrating Convolved Pooled Normalized (CPNB) and Gradient Optimized Multi-Path Bottleneck (GMBB) blocks with Channel and Spatial Attention (CSATM) module. The Swin Transformer (STB) branch efficiently handles long-range dependencies and extracts global features in cephalometric radiographs. The multi-branch fused features along with features from skip connections of CPNB and GMBB blocks are concatenated using a Coordinate Attention module (CoATM) to captures the positional relationships between various landmark features. A Landmark Discriminative Deviation Factor (LDDF) is determined by applying the Neighborhood Rough Set (NRS) approach to analyse the surrounding features of each landmark by considering spatial relationships or similarity measures between the landmarks and neighboring regions. The Spatial Pyramid Pooling (SPPL) layer incorporated in the final phase of CephTransXnet model extracts multi-scale features by pooling over sub-regions of varying sizes, enabling the network to capture both local and global context for precise cephalometric landmark identification. The CephTransXnet framework achieved an average Successful Detection Rates (SDRs) of 88.71 % and 79.05 % in 2 mm using the 2015 International Symposium on Biomedical Imaging (ISBI) grand challenge dental X-ray analysis dataset. The effectiveness of the CephTransXnet mod

关键词： Dental orthoses

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-based Analyzing Impact of Remote Work Arrangements on Employee Well-Being and Productivity

Machine Learning-based Analyzing Impact of Remote Work Arran...

引用

International Conference on Electrical, computer and Communication engineering (ECCE)

作者： Md. Wafiur Rahman Israt Anjum Soad As Hamim Mahi Md Faisal Karim Abdul Ahad Md. Hasan Imam Bijoy Department of Computer Science and Engineering Daffodil International University Dhaka Bangladesh Department of Electrical Engineering and Computer Science The University of Toledo Toledo USA Department of Electrical Engineering and Computer Science North South University Dhaka Bangladesh

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

The wholly wholesale transition into remote and hybrid workspaces is characteristic of modern-day work settings. As more and more firms adopt such flexible models, it is important to note, their implications on employee wellness and productivity. This paper uses machine learning techniques in order to understand the effects of mental distancing and hybridization on various key results such as the mental state of the employees, balance between their work and private life, separation from the society, as well as productivity levels. With a sample size of 5000 employees collect from kaggle, we determine the advantages and disadvantages these work models present. In other regards, geographical larger shifts create practical benefits including greater flexibility and autonomy plus productivity. However, such dramatic shifts create higher work-related stress, greater social tension and isolation, as well as challenges with workplace culture. AI, or more precisely machine learning, uncovers concepts in relation to work models in this paper, fico that enable firms to better personate their constituents and the workforce. Reasonable conclusions could be drawn so as flexible working arrangements benefit in reducing work-life conflict however improved organizational structure within the companies is needed to have such benefits due. Mental health as one of the resources, alongside technology will assist in such transition. This paper is a step forward for HR practitioners.

关键词： Productivity Computational modeling Employment Focusing Mental health Machine learning Companies Data collection Remote working Data models

来源：评论

学校读者我要写书评

暂无评论

Plant Leaf Disease Detection Using EfficientNet Asynchronous Propagation Penalized Neural Network with Planet Optimization Algorithm 2

Plant Leaf Disease Detection Using EfficientNet Asynchronous...

引用

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

作者： Sasikala, G. Rikhari, Suneetha Sadhana, R. Gavali, V.S. Indra, G. Mamatha, N.P. SRM Valliammai Engineering College Kattankulathur Department of Mathematics Tamil Nadu Chennai603203 India Malla Reddy University Department of Computer Science and Engineering Telangana Hyderabad500100 India Sri Sairam College of Engineering Department of Computer Science and Engineering Karnataka Bengaluru562106 India New Institute of Technology Department of Artificial Intelligence and Machine Learning Maharashtra Kolhapur416005 India R M K College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Puduvoyal601206 India Brindavan College of Engineering Department of Electronics and Communication Engineering Karnataka Bangalore560063 India

ISBN: (纸本)9798331505745

Unpredictability in illumination conditions, similar illness symptoms, skewed datasets, processing expense, and the challenge of determining infections at their onset are some of the challenges in plant leaf disease diagnosis. Model accuracy, reliability, and generalization across different types of plant species are also influenced by environmental factors, occlusions, and image noise. Using PlantVillage database, this paper confirms the superiority of the EfficientNet Asynchronous Propagation Penalized Neural Network with Planet Optimization Algorithm (ENet-APPNNet-POA) in plant leaf disease detection. Image quality is initially enhanced by the Adaptive Tri-Plateau Limit Tri-Histogram Algorithm (ATP-LTH) approach. ENet-UNet (EfficientNet-based U-Net) divides the affected areas of plant leaves according to distinct regions. Asynchronous Propagation Penalized Neural Network (APPNNet) serves as the classifier responsible for extracting features before performing their category identification. The Planet Optimization Algorithm (POA) delivers improved results and accuracy in classifying plant leaf diseases by evaluating various classifications affecting different leaf areas. PlantVillage dataset is employed in the Python test script. Test results indicate that ENet-APPNNet-POA outperforms existing methods to detect plant leaf disease classes at 99.9% efficiency and 99.8% sensitivity, an indication that computerized systems are likely to supersede manual diagnosis. © 2025 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Comparing Collaborative Filtering Algorithms in AI-Powered Recommendation Systems for E-Commerce 4

Comparing Collaborative Filtering Algorithms in AI-Powered R...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Aamer, Najmuddin Mittal, Tanusha Muthusamy, Nantha Kumar Battula, R. S. S. Raju Ajith, P.S. Soudagar, ManzooreElahi M. Bharat Ratna Indira Gandhi College of Engineering Department of Computer Science and Engineering Maharashtra Solapur410003 India Graphic Era Deemed to Be University Department of Computer Science and Engineering Maharashtra Dehradun410003 India OntrailInc Dba Uprise San FranciscoCA94104 United States Aditya University Department of Computer Applications Andhra Pradesh Surampalem533432 India Brindavan College of Engineering Department of Mathematics Karnataka Bengaluru560063 India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Vlsi Microelectronics Tamil Nadu Chennai602105 India

ISBN: (纸本)9798331523923

The quick growth of e-commerce has brought attention to how important efficient recommendation systems are to enhancing user experience and accomplishing business objectives. This paper investigates the effectiveness of collaborative filtering algorithms in AI-powered recommendation systems, with a focus on user-based collaborative filtering (UBCF). A comprehensive method is employed to guarantee consistency across different rating scales, beginning with data normalisation to standardise user-item interaction matrices. To decrease dimensionality and maintain the most significant patterns of user-item interaction, Principal Component Analysis (PCA) is employed for feature selection. The classification system uses similarity measures and UBCF to predict user preferences based on historical data. The algorithms are evaluated on key metrics like precision, recall, and RMSE using publically available datasets. The outcomes demonstrate the impact of preprocessing and dimensionality reduction on UBCF's performance as well as its efficacy in providing customised recommendations. This research contributes to the improvement of collaborative filtering algorithms for e-commerce systems, which will raise customer satisfaction and enable scalability in dynamic online markets. © 2025 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Offsets Reconstruction Method for Clock Skew Measurement Over High-Jitter Communication

引用

SN computer science 2025年第5期6卷 1-14页

作者： Sastra, Nyoman Putra Saputra, Komang Oka Teng, Wei-Chung Study Program of Electrical Engineering Faculty of Engineering Udayana University Jalan Raya Kampus Bukit Jimbaran Bali Badung 80361 Indonesia Department of Computer Science and Information Engineering National Taiwan University of Science and Technology No. 43 Section 4 Keelung Rd Taipei 106 China

Measuring clock skew of devices over a network fully relies on the offsets, the differences between sending and receiving times. Offsets that shape a thick line are the most ideal one as their slope is directly the clock skew sought. When some outliers separate from the thick line due to higher delay jitter, current advanced approaches use the lower bound or the majority of offsets to derive accurate clock skew. However, outliers in offsets that shape parallel dotted lines, reduce the availability of offsets in the lower region, and scatter widely the offsets from their majority zone. These conditions drive the current skew estimation approaches to lose their accuracy. This paper then developed a new method, which reconstructs back the outliers into their origin positions, in order to provide ideal offsets for clock skew measurement. The experimental evaluations have demonstrated that the clock skew accuracy of dotted-lines offsets tampered by outliers was improved from 2.1 to 0.9 ppm by the proposed reconstruction method. For a broader purpose, the reconstruction method has been adjusted to be implemented also on non-dotted-lines offsets. The robustness of the proposed method for this case has also been exhibited by the very ideal reconstructed offsets that shape like a thick line. © The Author(s) 2025.

关键词： Clock skew Delay jitter Dotted lines Hough transform

来源：评论

学校读者我要写书评

暂无评论

A Evaluation-Based Large Model for Multi-Step Behavior Prediction in Intelligent Consumer Electronics

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Li, Jinpeng Yu, Hang Wei, Subo Shanghai University School of Computer Engineering and Science Shanghai200444 China

Behavior prediction is a fundamental task in intelligent consumer electronics. Its goal is to predict potential future behaviors based on known behaviors, playing a crucial role in understanding user intentions and optimizing device performance. However, existing methods lack effective evaluation measures, causing models to overly rely on local features, which restricts them to predicting only the next immediate behavior, thereby limiting their ability to make long-term future inferences. To address these issues, we propose an a evaluation-based large model (ELM) for multi-step behavior prediction. Our approach is to enhance the model's multi-step reasoning ability by evaluating the results it generates iteratively. Specifically, by generating sub-behaviors through a large model and constructing new sequences of behaviors, we can extend the range of future behaviors. We then designed a chain-level evaluator that iteratively assesses the chain-level representation of each generated behavior sequence using a large model to evaluate the authenticity of the behavior sequence. Additionally, to prevent the large model from getting trapped in a localized understanding of the behavior sequence, we enhanced the model's chain-level perception ability through two human-like learning strategies. Experimental results on four real-world datasets show that our approach can generate more reliable sub-behavior sequences. © 2025 IEEE.

关键词： Prediction models

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：