检索结果-内蒙古大学图书馆

8th IEEE International Conference for Convergence in Technology, I2CT 2023

作者： Narmada, Nakka Pati, Peeta Basa Amrita School of Computing Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350334012

To evaluate a learner's knowledge of programming language skills, assessments are given. Grading of these is usually done manually which not only is tedious but prone to error due to repetition and fatigue. In this work, we employ pre-trained language models to perform automated grading of "C"programming language. Embeddings from different transformers on pre-assessed codes are used as feature vectors to train a wide range of regressors for the scoring task. Root-mean-square error (RMSE) is the metric utilized to compare the scores of these regressors. It's observed that embeddings from T5-model with CatBoost regressor gives the least error around 15%. © 2023 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Addressing Imbalance in Health Datasets: A New Method NR-Clustering SMOTE and Distance Metric Modification

引用

computers, Materials & Continua 2025年第2期82卷 2931-2949页

作者： Hairani Hairani Triyanna Widiyaningtyas Didik Dwi Prasetya Afrig Aminuddin Department of Electrical Engineering and Informatics Faculty of EngineeringUniversitas Negeri MalangMalang65145Indonesia Department of Computer Science Universitas BumigoraMataram83127Indonesia Department of Computer Graphic and Multimedia Faculty of ComputingCollege of Computing and Applied SciencesUniversiti Malaysia Pahang Al-Sultan AbdullahPekan26600Malaysia

An imbalanced dataset often challenges machine learning, particularly classification methods. Underrepresented minority classes can result in biased and inaccurate models. The Synthetic Minority Over-Sampling Technique (SMOTE) was developed to address the problem of imbalanced data. Over time, several weaknesses of the SMOTE method have been identified in generating synthetic minority class data, such as overlapping, noise, and small disjuncts. However, these studies generally focus on only one of SMOTE’s weaknesses: noise or overlapping. Therefore, this study addresses both issues simultaneously by tackling noise and overlapping in SMOTE-generated data. This study proposes a combined approach of filtering, clustering, and distance modification to reduce noise and overlapping produced by SMOTE. Filtering removes minority class data (noise) located in majority class regions, with the k-nn method applied for filtering. The use of Noise Reduction (NR), which removes data that is considered noise before applying SMOTE, has a positive impact in overcoming data imbalance. Clustering establishes decision boundaries by partitioning data into clusters, allowing SMOTE with modified distance metrics to generate minority class data within each cluster. This SMOTE clustering and distance modification approach aims to minimize overlap in synthetic minority data that could introduce noise. The proposed method is called “NR-Clustering SMOTE,” which has several stages in balancing data: (1) filtering by removing minority classes close to majority classes (data noise) using the k-nn method;(2) clustering data using K-means aims to establish decision boundaries by partitioning data into several clusters;(3) applying SMOTE oversampling with Manhattan distance within each cluster. Test results indicate that the proposed NR-Clustering SMOTE method achieves the best performance across all evaluation metrics for classification methods such as Random Forest, SVM, and Naїve Bayes, compared t

关键词： SMOTE modification Clustering-SMOTE manhattan distance

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Approaches for Myers-Briggs Personality Prediction 7

Machine Learning Approaches for Myers-Briggs Personality Pre...

引用

7th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2023

作者： Santhosh, Sethulakshmi Meenakshi, M. Avani, F. Abhishek, S. Anjali, T. Amrita School of Computing Department of Computer Science and Engineering Amritapuri India

ISBN: (纸本)9798350340600

In order to predict Myers-Briggs personality types from text input, this research article compares the abilities of Stochastic Gradient Descent (SGD), Naive Bayes, k-Nearest Neighbours (KNN), and Logistic Regression models. The Myers-Briggs Type Indicator(MBTI) captures distinctive patterns of behaviour, cognition, and preferences of human personality. It divides people into one of sixteen personality types. This study assesses the accuracy, support, recall, precision, and F1-score for the chosen models using a dataset made up of text inputs and matching Myers-Briggs types. The project attempts to determine the most successful model among the evaluated ways for precisely predicting Myers-Briggs personality types through extensive experimentation and review. The findings of this study have applications in building accurate and reliable models for personality prediction utilizing natural language processing methods. © 2023 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Multi-feature Fusion Deep Network for Skin Disease Diagnosis

引用

Multimedia Tools and Applications 2025年第1期84卷 419-444页

作者： Gairola, Ajay Krishan Kumar, Vidit Sahoo, Ashok Kumar Diwakar, Manoj Singh, Prabhishek Garg, Deepak Department of Computer Science and Engineering Graphic Era Hill University Dehradun India Department of Computer Science and Engineering Graphic Era deemed to be university Dehradun India School of Computer Science Engineering and Technology Bennett University Greater Noida India School of Computer Science and Artificial Intelligence SR University Warangal Telangana Warangal506371 India

The skin acts as an important barrier between the body and the external environment, playing a vital role as an organ. The application of deep learning in the medical field to solve various health problems has generated increasing interest. The objective of this research is to create a new model using a deep network with multi-feature fusion that enables accurate identification of various skin diseases. This paper proposes a fully fused network (FFN), which includes an improved single block (ISB) and an improved fusion block (IFB) to achieve optimal performance. To implement this, a convolutional neural network-based model for multi-class recognition of skin images has been developed, in which ISB is used to segment diseases in skin images. The IFB module is designed to enhance the effectiveness of the fused network. The model is built and evaluated using our proprietary dataset (Skin_disease_v1) along with publicly available datasets, namely ISIC2016, ISIC2017, and HAM10000. The highest accuracy achieved in experiments was 86% for ISB, 90% for IFB, and 92% for FFN using HAM10000 (for ResNet101V2), HAM10000 (for Resnet50 + ResNet101V2), and HAM10000 (for Resnet50 + ResNet101V2). This shows an accuracy improvement of 9.2%, 13.2%, and 15.2% compared to the state-of-the-art ISB, IFB, and FFN approaches, respectively. Our network outperforms existing networks in terms of performance. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Learning Model with Data Augmentation for Arabic Aspect-Based Sentiment Analysis

引用

computers, Materials & Continua 2023年第5期75卷 4419-4444页

作者： Arwa Saif Fadel Osama Ahmed Abulnaja Mostafa Elsayed Saleh Department of Computer Science Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Computer Science Faculty of Computer Sciences and EngineeringHodeidah UniversityYemen

Aspect-based sentiment analysis(ABSA)is a fine-grained *** fundamental subtasks are aspect termextraction(ATE)and aspect polarity classification(APC),and these subtasks are dependent and closely ***,most existing works on Arabic ABSA content separately address them,assume that aspect terms are preidentified,or use a pipeline *** solutions design different models for each task,and the output from the ATE model is used as the input to the APC model,which may result in error propagation among different steps because APC is affected by ATE *** methods are impractical for real-world scenarios where the ATE task is the base task for APC,and its result impacts the accuracy of ***,in this study,we focused on a multi-task learning model for Arabic ATE and APC in which the model is jointly trained on two subtasks simultaneously in a *** paper integrates themulti-task model,namely Local Cotext Foucse-Aspect Term Extraction and Polarity classification(LCF-ATEPC)and Arabic Bidirectional Encoder Representation from Transformers(AraBERT)as a shred layer for Arabic contextual text *** LCF-ATEPC model is based on a multi-head selfattention and local context focus mechanism(LCF)to capture the interactive information between an aspect and its ***,data augmentation techniques are proposed based on state-of-the-art augmentation techniques(word embedding substitution with constraints and contextual embedding(AraBERT))to increase the diversity of the training *** paper examined the effect of data augmentation on the multi-task model for Arabic *** experiments were conducted on the original and combined datasets(merging the original and augmented datasets).Experimental results demonstrate that the proposed Multi-task model outperformed existing APC *** results were obtained by AraBERT and LCF-ATEPC with fusion layer(AR-LCF-ATEPC-Fusion)and the proposed data augmentation

关键词： Arabic aspect extraction arabic sentiment classification AraBERT multi-task learning data augmentation

来源：评论

学校读者我要写书评

暂无评论

Deep learning based approaches for accurate automated nuclei segmentation of Pap smear images 14

Deep learning based approaches for accurate automated nuclei...

引用

14th International Conference on computing Communication and Networking Technologies, ICCCNT 2023

作者： Hridya Nair, S. Nair, Kasthuri A. S. Padmanabhan, Niharika Ratnakaran, Riya Vinitha Panicker, J. Amrita School of Computing Department of Computer Science and Engineering Amritapuri India

ISBN: (纸本)9798350335095

Cervical cancer is a type of cancer that occurs among women. The cancerous cells are developed in the cells of the cervix which is the lower part of the uterus. The human papillomavirus (HPV) is responsible for the vast majority of cervical cancer cases. A Papanicolaou test (pap smear test) is the most reliable screening method for identifying cancerous cells. Pathologists visually examine the slide after performing the test to look for malignancy. But this is a time-consuming and challenging task, often limited by the availability of certified professionals. Additionally, the diagnostic efficacy of visual screening is compromised by the increased workload of pathologists, leading to decreased diagnostic accuracy. Thus, a computer-aided diagnosis system is essential to enhance the quality of the Pap test results and enable early diagnosis. Nuclei segmentation is a crucial step in automated cervical cancer detection, as the nucleus carries essential information about the alterations occurring during the disease's progression. Thus, automated segmentation of nuclei can significantly and ultimately influence the diagnostic results. Recent surveys found that neural networks outperformed various traditional segmentation methods. We conducted experiments on the Herlev dataset using U-Net with ResNet and EfficientNet encoders, PAN (Pyramid Attention Network), and LinkNet with a ResNet encoder. For each of these models, our results showed IOU scores of 0.76, 0.938, 0.79, and 0.69, respectively. © 2023 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Deep Convolutional Neural Networks for Automated Screening and Diagnosis of Ophthalmic Diseases 3

Deep Convolutional Neural Networks for Automated Screening a...

引用

3rd International Conference for Advancement in Technology, ICONAT 2024

作者： Babu, Tina Naik, Pramod Kumar Nair, Rekha R Janhavi, P.G. Alliance University Alliance School of Advanced Computing Department of Computer Science and Engineering Bengaluru India Dayananda Sagar University Department of Computer Science Engineering Bengaluru India

ISBN: (纸本)9798350354171

This project focuses on developing a deep learning algorithm to classify eye diseases from images. The dataset comprises images depicting various eye conditions, including glaucoma, cataracts, normal eyes, and diabetic retinopathy. We adopt a comprehensive approach by utilizing pre-trained architectures such as ResNet-18, GoogleNet, AlexNet, VGG19, and ResNet-50 as the backbone of our models, fine-tuning each on our dataset. During the training process, we employed data augmentation techniques to enhance the dataset, improving the models' generalization ability across diverse eye conditions. The evaluation of the models involves a combination of cross-entropy loss and accuracy metrics to assess performance. Notably, the individually trained models exhibited varying accuracies, with ResNet-18 achieving the highest accuracy of 92.7% on the validation set. Additionally, we conducted an analysis of model performance using metrics such as precision, recall, and F1-score, further enhancing our understanding of the models' capabilities. The visualization of results is facilitated through the presentation of confusion matrices, providing insights into the models' classification behavior across different eye diseases. This study opens up a promising new path for improving ophthalmology screening and diagnosis by demonstrating the prospective benefits of deep learning in automating the classification of eye diseases. © 2024 IEEE.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Health and Environment Monitoring System for Viral Respiratory Diseases 14

Health and Environment Monitoring System for Viral Respirato...

引用

14th International Conference on computing Communication and Networking Technologies, ICCCNT 2023

作者： Shwetha, S. Nithuna, N. Oviya, B. Swetha, J. Harini, N. Amrita School of Computing Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350335095

The proposed system in this work is a contactless health and environment monitoring system designed after conducting a literature review on the most recent research on viral respiratory diseases and their impact on businesses, risk factors of a location, and surveillance of people for various safety measures and causes leading to its spread. The proposed system takes the form of an Android Mobile Application, designed to function as a safety entry checkpoint for various organizations, including businesses and educational institutions. It aims to detect viral respiratory diseases by leveraging the capabilities of a smartphone camera without requiring any additional external hardware specifications. Furthermore, the system incorporates users' vaccination information, enabling a comprehensive assessment of health and safety. The key algorithms presented in this work focus on measuring critical body vital signs, including heart rate, temperature, and oxygen saturation (Oxygen saturation (SpO2)) levels. By utilizing advanced techniques such as mask detection and social distance monitoring, the system ensures the recognition of disease indicators and triggers appropriate actions to minimize the risk of transmission. To assess the safety of an area or environment, the proposed system employs the Euclidean distance metric and MobileNetV2, a state-of-the-art deep learning model. This combination enables real-time evaluation and analysis of the surroundings, providing crucial information for making informed decisions regarding the level of safety in a given location. © 2023 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Community detection of trajectory data for location-based facility recommendation system

引用

International Journal of Information and Communication Technology 2024年第2期25卷 101-117页

作者： Sabarish, B.A. Karthi, R. Kumar, T. Gireesh Department of Computer Science and Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Coimbatore India

Trajectory contains spatial-data generated from traces of moving objects like people, animals, etc. Community generated from trajectories portrays common behaviour. Trajectory clustering based on community-detection involves region-graph generation and community-detection. In region-graph generation, trajectories are projected to spatial grid to transform GPS representation into string representation. Sequential graph is generated from string representation. Edge-based similarity is calculated between trajectories to create an adjacency matrix representing relationship and represent entire region. In community-detection phase, region-graph is divided into communities using various algorithms and validated using modularity values. Based on analysis, Louvain, fast-greedy, leading-eigenvector, and edge-betweenness algorithms provide the optimum modularity value for better community detection. Analysing the community can be used as a pre-processing step in identifying location for location-based services (LBS), including hotspots, delay-tolerant-networks, and mobile antenna placements for better coverage. Design and capacity planning of the network based on the size and pattern of the community improves quality of LBS. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Dynamic Configurable Datapath Architecture for IoT Devices

引用

Journal of Communications and Information Networks 2024年第3期9卷 251-261页

作者： Ruizhe Zhang Junhui Liu Han Wang Li Lu Laboratory of Intelligent Collaborative Computing University of Electronic Science and Technology of ChinaChengdu 611731China School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu 611731China

This paper introduces a novel RISC-V processor architecture designed for ultra-low-power and energy-efficient applications,particularly for Internet of things(IoT)*** architecture enables runtime dynamic reconfiguration of the datapath,allowing efficient balancing between computational performance and power *** is achieved through interchangeable components and clock gating mechanisms,which help the processor adapt to varying workloads.A prototype of the architecture was implemented on a Xilinx Artix 7 field programmable gate array(FPGA).Experimental results show significant improvements in power efficiency and *** mini configuration achieves an impressive reduction in power consumption,using only 36%of the baseline ***,the full configuration boosts performance by 8%over the *** flexible and adaptable nature of this architecture makes it highly suitable for a wide range of low-power IoT applications,providing an effective solution to meet the growing demands for energy efficiency in modern IoT devices.

关键词： dynamic reconfiguration Internet of things(IoT) power efficiency RISC-V

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：