检索结果-内蒙古大学图书馆

Hyper Spectral Spatial Image Segmentation Using Machine Learning Algorithms 1

Hyper Spectral Spatial Image Segmentation Using Machine Lear...

1st International Conference on Intelligent Technologies for Sustainable Electric and Communications Systems, iTech SECOM 2023

作者： Saravanan, G. Suresh, A. Jagannathan, J. Thanga Mariappan, L. Majeeth, Najeem Dheen Abdul Kumar, Nithish Veltech Rangarajan Dr.Sagunthala R and D Institute of Science and Technology Department of Computer Science and Engineering Tamilnadu India Vellore Institute of Technology School of Computer Science and Engineering Tamilnadu Vellore India Vellore Institute of Technology School of Computer Science Engineering and Information Systems Tamilnadu Vellore India Saveetha Engineering College Department of Artificial Intelligence and Machine Learning Tamilnadu India

ISBN: (纸本)9798350371185

In recent years, there has been a notable surge in the development of methods dedicated to classifying hyper spectral image samples. However, the inherent high dimensionality of hyper spectral data presents significant challenges for traditional supervised classification algorithms. Prior studies have attempted to address these challenges by incorporating active learning methods for hyper spectral data segmentation. Nevertheless, a crucial drawback of active learning lies in its dependence on labeled data samples, leading to less improved classification results for unlabeled data samples. In response to this limitation, our work introduces Supervised Active Learning (SAL) techniques that harness both spectral and spatial information. The key innovation of our research lies in the introduction of a novel hyper spectral image segmentation approach based on the k-dependence Bayesian (KDB) model. We estimate the maximizer of the posterior marginal using Symmetric Iterative Proportional Fitting (SIPF) within this KDB model. By implementing the KDB model for hyper spectral image segmentation, our goal is to enhance the classification accuracy of our SAL classifiers. The SAL framework integrates shape prior probability estimation, class density results from Improved Multi-Level Logistic (IMLL) methods, and the maximization of the posterior marginal estimated through Symmetric Iterative Proportional Fitting (SIPF). We evaluate the accuracy of our proposed MPM-SIPF-SAL system using the real ROSIS Hyper Spectral Dataset, demonstrating that our system outperforms existing methods in terms of classification accuracy. © 2023 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Traffic Prediction Using GPS Based Cloud Data Through RNN-LSTM-CNN Models: Addressing Road Congestion, Safety, and Sustainability in Smart Cities

引用

SN computer science 2025年第2期6卷 1-18页

作者： Selvan, C. Senthil Kumar, R. Iwin Thanakumar Joseph, S. Malin Bruntha, P. Amanullah, M. Arulkumar, V. School of CSE REVA University Karnataka Bangalore India Department of Computer Science and Engineering (AIML) Faculty of Engineering and Technology Jain (Deemed-to-be) University Bangalore India Department of CSE Koneru Lakshmaiah Education Foundation Andhrapradesh Vaddeswaram India Department of ECE Karunya Institute of Technology and Sciences Coimbatore India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai India School of Computer Science and Engineering Vellore Institute of Technology Tamilnadu Vellore India

Smart cities that use technology and data for efficiency optimization, sustainability, and well-being of citizens face a lot of challenges. Because all of the aforementioned challenges share a common characteristic of complexity, achieving success will need careful preparation and coordinated effort. This research presents a novel approach utilizing deep learning models to address issues about road congestion, specifically by offering secure routes for pedestrians and cyclists. The Global Positioning System (GPS) data stored in the cloud is used as input for the proposed work. In the proposed work, the flow of vehicles, their speed, and the occupancy have been predicted. The need for deep learning to resolve the traffic problem is that deep learning methods are highly efficient when compared to statistical techniques as they provide more than 90% of accuracy in forecasting. The novel approaches used in this paper are integrated Recurring Neural Networks (RNN)-Long Short Term Memory (LSTM)- Convolutional Neural Networks (CNN) to form RLC (RNN-LSTM-CNN) models. The system encompasses appropriate methods for improving the transportation system’s efficiency by mitigating environmental impacts. The implementation of Recurrent Neural Networks (RNN) along with Long Short-Term Memory (LSTM) are used to analyze historical traffic flow data by predicting future traffic conditions by optimizing traffic signal timings, traffic flow, and public transportation schedules to reduce idling time and fuel consumption, leading to lower emissions by predicting Electric Vehicle (EV) charging demand patterns, optimize charging stations’ locations and driver routes, and manage energy distribution more efficiently. The proposed Deep Learning-based models perform better when compared to the other methods and hold the potential to transform urban mobility, making it more efficient, safer, and environmentally friendly in the smart cities of the future as it provides higher forecasting accuracy

关键词： CNN LSTM Occupancy RNN Speed Traffic flow prediction

来源：评论

学校读者我要写书评

暂无评论

Imbalanced Classification in Diabetics Using Ensembled Machine Learning

引用

computers, Materials & Continua 2022年第9期72卷 4397-4409页

作者： M.Sandeep Kumar Mohammad Zubair Khan Sukumar Rajendran Ayman Noor A.Stephen Dass J.Prabhu School of Information Technology and Engineering Vellore Institute of TechnologyVelloreTamil Nadu632014India Department of Computer Science and Information Taibah UniversityMedinaSaudi Arabia College of Computer Science and Engineering Taibah UniversityMedinaSaudi Arabia

Diabetics is one of the world’s most common diseases which are caused by continued high levels of blood *** risk of diabetics can be lowered if the diabetic is found at the early *** recent days,several machine learning models were developed to predict the diabetic presence at an early *** this paper,we propose an embedded-based machine learning model that combines the split-vote method and instance duplication to leverage an imbalanced dataset called PIMA Indian to increase the prediction of *** proposed method uses both the concept of over-sampling and under-sampling along with model weighting to increase the performance of *** measures such as Accuracy,Precision,Recall,and F1-Score are used to evaluate the *** results we obtained using K-Nearest Neighbor(kNN),Naïve Bayes(NB),Support Vector Machines(SVM),Random Forest(RF),Logistic Regression(LR),and Decision Trees(DT)were 89.32%,91.44%,95.78%,89.3%,81.76%,and 80.38%*** SVM model is more efficient than other models which are 21.38%more than exiting machine learning-based works.

关键词： Diabetics classification imbalanced data split-vote instance duplication

来源：评论

学校读者我要写书评

暂无评论

A Multi-channel Convolutional Neural Network for Multilabel Sentiment Classification Using Abilify Oral User Reviews

引用

Informatica (Slovenia) 2023年第1期47卷 109-114页

作者： Trueman, Tina Esther Jayaraman, Ashok Kumar Jasmine, S. Ananthakrishnan, Gayathri Narayanasamy, P. Department of Computer Science University of the People Pasadena United States Department of Information Science and Technology Anna University Chennai India Department of Information Technology Vellore Institute of Technology Vellore India Department of Electrical and Electronics Engineering PSG College of Technology Coimbatore India

Nowadays, patients and caregivers have become very active in social media. They are sharing a lot of information about their medication and drugs in terms of posts or comments. Therefore, sentiment analysis plays an active role to compute those posts or comments. However, each post is associated with multilabel such as ease of use, effectiveness, and satisfaction. To solve this kind of problem, we propose a multichannel convolution neural network for multilabel sentiment classification using Abilify oral user comments. The multichannel represents the multiple versions of the standard model with different strides. Specifically, we use the pre-trained model to generate word vectors. The proposed model is evaluated with multilabel metrics. The results indicate that the proposed multichannel convolutional network model outperforms the traditional machine learning algorithms. © 2023 Slovene Society Informatika. All rights reserved.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Motion Detection in Real-Time Surveillance Using Two Frame Differencing 1

引用

8th International Conference on Information and Communication technology for Competitive Strategies, ICTCS 2023

作者： Biswas, Tamal Bhattacharya, Diptendu Rudrapal, Dwijen Roy, Srijan Mandal, Gouranga National Institute of Technology Agartala Department of Computer Science and Engineering Tripura Agartala India National Institute of Technology Agartala Department of Computer Science and Engineering Tripura Agartala India National Institute of Technology Agartala Department of Computer Science and Engineering Tripura Agartala India National Institute of Technology Agartala Department of Computer Science and Engineering Tripura Agartala India Vellore Institute of Technology Andhra Pradesh India

ISBN: (数字)9789819702107

ISBN: (纸本)9789819702091

This research article delves into the creation of a real-time system for detecting motion, particularly for surveillance purposes. The proposed approach relies on computer vision algorithms to analyze live video streams captured by a camera. By scrutinizing these feeds, the algorithms can discern alterations within the scene, specifically identifying objects in motion. The primary aim is to ensure that this system functions in real time, thereby furnishing instantaneous insights to security personnel. The paper expounds on the different steps integral to motion detection, encompassing procedures like background subtraction, foreground segmentation, and object tracking. To validate the system’s effectiveness, an evaluation is conducted using a collection of actual surveillance videos. The findings underscore the system’s capability to accurately detect moving objects across diverse scenarios. The article concludes by contemplating the system’s potential applications, which span security setups, traffic supervision, and ecological monitoring. The focal technique utilized in this study is Frame Differencing, a means of detecting object motion. This approach is adept at distinguishing moving objects within a given environment. In conjunction with this method, the paper emphasizes the viability of background subtraction to further enhance Frame Differencing, thereby augmenting its precision and efficacy. Upon applying this method to a camera, it is discerned that luminosity has a significant impact on the minimal value. Notably, a minimal value of 35 is identified as the most favorable choice. Here, threshold value 35 is selected because we have seen in our experiment that 35 gives the optimal result with our algorithm. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

A Deep Convolutional Neural Network for Breast Cancer Detection in Mammograms 3rd

A Deep Convolutional Neural Network for Breast Cancer Detect...

引用

3rd International Conference on computer Vision, High Performance Computing, Smart Devices, and Networks, CHSN 2022

作者： Naga Jagadesh, B. Kanya Kumari, L. Murthy, Akella V. S. N. School of Computer Science and Engineering Vellore Institute of Technology-Andhra Pradesh Andhra Pradesh Amaravathi India Department of Information Technology Andhra Loyola Institute of Engineering and Technology Andhra Pradesh Vijayawada India Department of Mathematics SAS Vellore Institute of Technology Tamil Nadu Vellore India

ISBN: (纸本)9789819966899

Breast cancer is the most prevalent ailment among women worldwide. The screening for detecting breast cancer is mammograms. The anticipated methodology uses preprocessing, feature extraction and classification. The main objective is early detection of the diseases so that the lifetime can be increased. A popular deep convolutional neural network (DCNN) model is used for mammogram classification that classifies into normal or abnormal. Initially, the mammograms are preprocessed using contrast limited adaptive histogram equalization (CLAHE). These images are fed to the DCNN model which contains five convolutional layers that use rectified linear unit (ReLU) as the activation function, and max-pooling is used to select the best features. The fully connected layer uses softmax as the activation function and classifies the selected features, and these are done with several optimizers, namely stochastic gradient descent (SGD), RMSprop, and Adam. The experiments are done on two benchmark datasets, namely the Mammographic Image Analysis Society (MIAS) and Digital Database for Screening Mammography (DDSM), and performance is measured with sensitivity, specificity, and accuracy. The results show that DCNN with SGD optimizer gives better results compared to the traditional methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Optimizing Gene Expression Analysis Using Clustering Algorithms 1

引用

5th International Conference on computer and Communication Technologies, IC3T 2023

作者： Bikku, Thulasi Ramu, J. Sekhar, J. Chandra Pratap, V. Krishna Pujari, Jeevana Jyothi Computer Science and Engineering Amrita School of Computing Amaravati Amrita Vishwa Vidyapeetham Andhra Pradesh Amaravati522503 India Department of Computer Science and Engineering NRI Institute of Technology Andhra Pradesh Guntur India Department of Database Systems School of Computer Science and Engineering Vellore Institute of Technology Tamilnadu Vellore632014 India

ISBN: (数字)9789819997077

ISBN: (纸本)9789819997060

Gene expression analysis plays a crucial role in understanding biological processes and diseases. However, the high-dimensional nature of gene expression data poses challenges for its analysis and interpretation. Clustering algorithms have been widely used for identifying patterns in gene expression data, but their effectiveness is limited by the choice of algorithm and parameters used. In this study, we propose an approach for optimizing gene expression analysis using clustering algorithms. Initially, a range of clustering techniques were assessed, encompassing K-means, hierarchical clustering, and DBSCAN. This assessment was conducted using gene expression information sourced from a publicly accessible database. Subsequently, various techniques for feature selection were employed. These techniques encompassed principal component analysis (PCA) as well as correlation-based feature selection (CFS). Their objective was twofold: to decrease the data's dimensionality and to enhance the effectiveness of the clustering process. From the study, we came to know that the combination of K-means clustering with PCA feature selection outperformed other methods in terms of clustering accuracy and stability. We also identified a set of genes that were consistently associated with different clusters, providing insights into the underlying biological processes. Overall, our study demonstrates the importance of careful algorithm and parameter selection for gene expression analysis and highlights the potential of clustering algorithms for identifying meaningful patterns in gene expression data. The suggested methodology entails merging DBSCAN with K-means clustering, which could be extended to diverse high-dimensional datasets for the enhancement of their analysis and comprehension. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Multiple moving object classification and tracking using DenCNN classifier

引用

Journal of Intelligent and Fuzzy Systems 2024年第5-6期46卷 11311-11329页

作者： Premanand, V. Arulalan, V. Kumar, Dhananjay School of Computer Science and Engineering Vellore Institute of Technology Chennai Campus Tamil Nadu India Department of Computing Technologies SRM Institute of Science and Technology Chengalpattu District Tamil Nadu Kattankulathur India Department of Information Technology Anna University Madras Institute of Technology Campus Tamil Nadu Chennai India

A Multiple moving object detection, tracking, and counting algorithm is mainly designed exclusively suitable for congested areas. The counting system can alleviate the betrayal performance in the crowded areas. Most of the existing methods developed for tracking and counting face serious challenges in detection due to high densities of the target. This condition urged the researchers to update the existing systems. The present methodology was designed to address such issues. In the present methodology, the contrast was initially enhanced between the objects and their backgrounds using a Double Plateau Histogram Equalization (DPHE). Then, the motion was estimated for the contrast-enhanced image to identify the moment of the object using the modified Adaptive Distance Covariance Rood Pattern Search (ADCRPS) algorithm. After that, the morphological operation was deployed to sharpen the images by removing all the unwanted things. Then, the features were extracted and important features were selected using the modified Chaotic Tent Shuffled Shepherd Optimization (CTSSO) Algorithm. With the selected features object, detection was done using the proposed Scaled Non-Monotonic Cauchy Dense Convolutional Neural Network (SNMC-DenCNN). The detected object was then tracked with the aid of Channel and Spatial Reliability Tracker (CSRT). Finally, the objects were counted by intersection over union (IOU) by explicitly computing the association between detected and tracked objects. Also, the experimental results showed the effectiveness and efficiency of the proposed system with enhanced accuracy. © 2024 - IOS Press. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Improved water shower model for greener data centers

引用

Materials Today: Proceedings 2022年 62卷 4677-4684页

作者： Anusooya, G. Kumar, R. School of Computer Science and Engineering Vellore Institute of Technology University Tamil Nadu Chennai India

The ecological threat is produced by IT industries that are the critical frontrunners of the universal greenhouse gasses with a massive increase in hazardous carbon emission that accumulates gradually due to the computing device usage and its equivalent electricity consumption. The state of being significant in reducing carbon emission with the reduced/appropriate use of power consumption is sloping upwards, which should not be focused only on the hardware design it should also be firmed with appropriate software design and resource allocation. This originates the evolution of proficient algorithms and effective resource provisioning by allocating the loads evenly based on requests like read-only or read-write for the new or existing workloads to improve the performance in a virtualized data center. This paper proposes an improved water shower model, which can effectively manage the resources in data centers, in order to address this challenge. Different with the traditional Water Shower Model which uses the mode of operation to distribute the load among the resources, the proposed improved Trigger - Water Shower Model uses the mode of operation as well as the identification of the heavily loaded and lightly loaded resources, and thus distributes the loan eventually to obtain a reduced carbon emission. The proposed approach is validated by examining the reduction of carbon emission led by the proposed algorithm. The experimental results show more effective utilization of resources with improved average response time as 64 ms with 1.28 mgco2 reduced carbon emission by the proposed approach, compared to the traditional water shower model. © 2022

关键词： Virtual machine

来源：评论

学校读者我要写书评

暂无评论

Detecting Uteropelvic Junction Obstruction at an Early Stage using Ultrasound Images through an Interplanetary File System 5

Detecting Uteropelvic Junction Obstruction at an Early Stage...

引用

5th International Conference on Data Intelligence and Cognitive Informatics, ICDICI 2024

作者： Kaviya, R. Prasad, Mridula Pavithra, S. Kapali, B. Suresh Chander Vellore Institute of Technology School of Computer Science and Engineering Chennai India Easwari Engineering College Department of Biomedical Engineering Chennai India

ISBN: (纸本)9798350389609

Ureteropelvic junction obstruction (UPJO) is a medical condition characterized by a blockage at the junction between the ureter and the kidney, leading to impaired urine flow and increased fluid pressure. If left untreated, UPJO can progress to hydronephrosis and potentially result in irreversible kidney damage. This paper presents a novel system for the early detection and severity grading of UPJO using Deep Learning computer-Aided Diagnosis (DL-CAD) techniques. The proposed approach leverages ultrasound imaging as a primary diagnostic tool, noted for its cost-effectiveness, absence of radiation, and non-invasive nature. To enhance the security and integrity of medical data transmission, we integrate blockchain technology into our framework. Our solution combines a DL- CAD model featuring an attention-based pyramid semantic segmentation network with a discrete wavelet transformation- processed residual classification network. An IoT device is employed to detect patient abnormalities and transmit this data to the diagnosis model via an InterPlanetary File System (IPFS). This decentralized storage solution facilitates secure data management across a peer-to-peer network. Ultimately, the proposed framework not only identifies the presence of UPJO but also assesses its severity, ensuring that patient data remains protected throughout the diagnostic process. © 2024 IEEE.

关键词： Semantic Segmentation

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：