检索结果-内蒙古大学图书馆

2nd IEEE Mysore Sub Section International Conference, MysuruCon 2022

作者： Sutagundar, A.V. Halakarnimath, B.S. Bhajantri, Lokesh B. Nalini, N. Basaveshwar Engineering College Electronics & Communication Engineering Karnataka Bagalkot India S. G. Balekundri Institute of Technology Computer Science & Engineering Karnataka Belagavi India Basaveshwar Engineering College Department of Information Science and Engineering Karnataka Bagalkot India Nitte Meenakshi Institute of Technology Professor & Dean Student's Welfare Department of Computer Science & Engineering Bengaluru India

ISBN: (数字)9781665497909

ISBN: (纸本)9781665497909

The wide spectrum of marine applications has drawn the research community to discuss the several issues of UASNs. Acoustic communication is the most relevant channel for communicating information among sensor nodes that utilize more energy to avoid network failure and render continuous connectivity. The Energy-efficient Topology Control (ETC) is proposed to discuss this issue for UASNs to overcome the coverage and connectivity by improving their lifetime. The proposed approach is divided into the topology construction and topology maintenance phase. In the construction phase, initially, each node recognizes the neighbor nodes and records the range and orientation in an internal database. After that, each node drops some nodes by applying specific conditions and forms the candidate neighbor nodes. Finally, the minimum number of sensor nodes is added to the Topology Member Set (TMS) based on the nodes' orientation, range, energy levels, and topology of the network are created. The topology's maintenance is initiated by the sink node periodically, or any sensor node can send a request message to the sink node at particular conditions. The proposed scheme's performance shows the necessity for minimal sensor nodes for seamless connection and improves coverage area. © 2022 IEEE.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Deep Learning and Sentiment Analysis Improve E-commerce Sales Prediction

Deep Learning and Sentiment Analysis Improve E-commerce Sale...

引用

2023 International Conference on Data science and Network Security, ICDSNS 2023

作者： Geetha, K. Swarnalatha, K. Ananda Babu, J. Sudha, Poranki V. L. R. N. Sai Ramachandra, A.C. Gst Gitam University Bengaluru Campus Dept. of Cse Bengaluru India Thandavapura Mysore Dept of Ai and Ds Mit India Malnad College of Engineering Hassan Department of Information Science and Engineering India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Andhra Pradesh India Nitte Meenakshi Institute of Technology Bengaluru Department of Electronics and Communication Engineering India

ISBN: (纸本)9798350301595

The dataset labelled 'Amazon and Yelp Reviews' is a useful resource for sentiment analysis and opinion mining. It has roughly 1.5 million reviews from Amazon and Yelp for a wide range of products and services, as well as the relevant information for each review, which includes product ratings, review dates, and review titles. The dataset's size and diversity make it a good choice for training large-scale deep learning models to handle sentiment analysis tasks. The recommended approach for undertaking sentiment analysis using the 'Amazon and Yelp Reviews' dataset includes three steps: collecting data on a daily basis, preparing user comments, and applying a BiLSTM model for sentiment analysis. Assessing consumer sentiment entails evaluating comments, goods, and businesses to develop predictions about how people feel about various products and services. Some of the measures used in the model evaluation process include accuracy, precision, recall, and F1-score. The proposed method achieves an average accuracy of 87.3%, which is comparable to existing deep learning methods such as character-level convolutional neural networks (CNNs)- LSTM and deep transfer learning. The model's errors may be evaluated to discover where it can be improved, and additional assessment metrics such as AUC- ROC, AUC-PR, G-mean, and MCC can be used to determine how well the model is doing. The dataset and methods presented have the potential to be useful for a wide range of applications, including customer feedback analysis, product and service development, and online reputation management. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

MUNPE:Multi-view Uncorrelated Neighborhood Preserving Embedding for unsupervised feature extraction

TechRxiv

引用

TechRxiv 2023年

作者： Jayashree ShivaPrakash, T. Venugopal, K.R. The Department of Computer Science and Engineering Nitte Meenakshi Intitute of Technology Bangalore and Research Scholar Vijaya Vittala Institute of Technology VTU Belgaum Bangalore India The Department of Computer Science and Engineering Vijaya Vittala Institute of Technology VTU Belgaum Bangalore India Bangalore University India Department of Computer Science and Engineering University Visvesraraya College of Enginering VTU Belgaum Bangalore India

In order to identify the shared subspace between two views, in Canonical Correlation Analysis (CCA), a popular multi-view dimension reduction technique tries to maximize correlation between the views. Although, there are frequently more than two views in many actual applications, it can only process data with two views. In prior studies, data with more than two viewpoints were managed using either linear correlation or higher degree polynomial correlation. The link between multiview data viewed from diverse perspectives is established by these two types of correlation, that is linear correlation and high order correlation, each of which has a different effect on view consistency. In this paper, we propose a Multi-view Uncorrelated Neighborhood Preserving Embedding (MUNPE), which simultaneously considers two distinct types of correlation to give flexible view consistency. While keeping the local structures of each perspective, the MUNPE also takes into account the complementaries of numerous viewpoints. The MUNPE makes the characteristics gathered by numerous projections for each view uncorrelated in order to get many projections and reduce the duplication of low-dimensional data. Iterative methods are used to resolve the MUNPE, and the algorithm’s convergence has been demonstrated. The testing on the Multiple Feature and other synthetic data sets were successful for MUNPE. It is observed that performance is better than MLPP[1], MSE[2], MLLE[3], GCCA[4], MCCA[5] algorithms. © 2023, CC BY.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approach for Automated Skin Disease Diagnosis

Deep Learning Approach for Automated Skin Disease Diagnosis

引用

Innovations in Communications, Electrical and computer engineering (ICICEC), International Conference on

作者： Prashanth B S Puneeth B H Manoj Kumar M V Bhavana RK K Arshitha Santhosh S Puneeth S P Sneha H R Department of Information Science & Engineering Nitte Meenakshi Institute of Technology Bangalore Karnataka India Department of Computer Science and Business Systems Bapuji Institute of Engineering and Technology Davanagere Karnataka India Department of Information Science and Engineering Bapuji Institute of Engineering and Technology Davanagere Karnataka India

ISBN: (数字)9798350376517

ISBN: (纸本)9798350376524

Skin diseases has been a significant challenge in healthcare, necessitating accurate and timely diagnosis for effective treatment. This paper presents research on the use of Convolutional Neural Networks (CNNs) for the categorization of skin illnesses. CNNs are a viable tool for automated skin disease detection since they successfully leverage the deep learning capabilities in image-based tasks. The research begins with a detailed review of existing methodologies and datasets in the domain of skin disease classification. Subsequently, we propose a novel CNN architecture tailored to address the unique challenges posed by dermatological images, such as variability in lesion size, color, and texture. The proposed model is trained and evaluated on a diverse and extensive dataset, ensuring its robustness and generalization capabilities across various skin conditions. The study delves into the interpretability of the CNN model, providing insights into the features learned during the training process. This analysis contributes to the understanding of how deep learning models make decisions in the context of dermatological diagnosis, enhancing the trustworthiness and acceptance of such automated systems in clinical settings. Furthermore, the paper investigates the impact of data augmentation techniques on model performance, addressing the scarcity of labeled dermatological datasets. By increasing the training data, we explore strategies to improve the model’s ability to generalize to unseen cases, thereby enhancing its practical utility. Experimental results are presented and compared with state-of-the-art approaches, proving the viability of the suggested CNN architecture.

关键词： Deep learning Training Technological innovation Training data computer architecture Skin Data models Robustness Convolutional neural networks Diseases

来源：评论

学校读者我要写书评

暂无评论

Whale Optimization Algorithm with Convolutional Neural Network for Object Detection

Whale Optimization Algorithm with Convolutional Neural Netwo...

引用

2023 International Conference on Integrated Intelligence and Communication Systems, ICIICS 2023

作者： Yamsani, Nagendar Al-Jawahry, Hassan M. Karunakara Rai, B. Goud, Bollipelly PruthviRaj Ramadan, Ghazi Mohamad SR University School of Computer Science and Artificial Intelligence Warangal India The Islamic University Najaf Iraq Nitte Meenakshi Institute of Technology Department of Electronics and Communication Engineering Bengaluru India Anurag University Hyderabad India Ahl Al Bayt University College of Mlt Karbala Iraq

ISBN: (纸本)9798350315455

The Object detection is method of computer vision for locate instances of objects in videos or images. Algorithms for object detection generally control Machine (ML) or Deep Learning (DL) for producing results. Several ML methods are used for detecting objects from image acquired through video. Huge incoming volume information is high for ML methods to manage. DL methods are used for recognizing objects and individuals from videos in accordance with handle high quantity of information as input. Several DL methods are used like Convolutional Neural Network (CNN), Recurrent Neural Network (RNN) and etc., to handle huge quantity of input data and also human and object recognition. Thus, Hybrid Whale optimization Algorithm (WOA) and Convolutional Neural Network (CNN) is proposed to detect object from video frames. WOA is used to enhance the method parameter of CNN architecture. Initially, the pre-processing technique is used to delete noise in image and quality of image is improved. Gaussian filter is utilized to subtract background in images. The proposed method improved accuracy of object detection and identifies the small targets in videos. The proposed algorithm attained high accuracy of 98.23%, precision of 96.78%, recall of 96.02% and f1-score of 96.45% which is higher than other existing methods. © 2023 IEEE.

关键词： Convolutional Neural Network Gaussian filter Object recognition Video frames and Whale optimization Algorithm

来源：评论

学校读者我要写书评

暂无评论

IoT enabled Vehicle Tracking and Monitoring System

IoT enabled Vehicle Tracking and Monitoring System

引用

North Karnataka Subsection Flagship International Conference (NKCon), IEEE

作者： Deepthi Shetty Prateek G Onkar Bharatesh Kakamari Sarojadevi H Devidas Mitul Jain Computer Science & Engineering Department Nitte Meenakshi Institute of Technology Bangalore India Information Science & Engineering Department NMAM Institute of Technology Nitte India

As we all know, the fact that the population increase in the last decade has given rise to increased automobile usage. Along with this, society is facing unethical actions such as robbery, accidents, growth in crime rate, etc. in turn affecting the smooth functioning of society. Vehicle security can be enhanced thanks to recent technological advancements in the field of IoT. Road accidents are increasing by the day, many times the severity of the accidents is high which needs an instant response and if not present could lead to loss of life. With the use of advanced technology such as GPS, IoT, etc., the fatality of these accidents can be significantly reduced. The main concept of this paper is to propose a system that helps reduce the time taken to respond to such road accidents and provide/increase vehicle security by adopting cutting-edge technology. The components that are used for the system are cost-effective as well as efficient such as GPS, GSM, NODEMCU-ESP8266, and Microcontroller.

关键词： Temperature measurement Temperature sensors Road accidents Pulse measurements Hospitals Pressure measurement Security

来源：评论

学校读者我要写书评

暂无评论

Early Cervical Cancer Diagnostics Detection Based on RMSE and Extreme Learning Machine

Early Cervical Cancer Diagnostics Detection Based on RMSE an...

引用

2023 International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2023

作者： Singh Pundir, Aditya Kumar Nayak, Ullal Akshatha Gayathri, D. Sucharitha, M. Jamalpur, Bhavana Rastogi, Ravi Arya College of Engineering and Information Technology Department of Electronics and Communication Engineering Rajasthan Jaipur India Nitte Meenakshi Institute of Technology Department of Information Science and Engineering Karnataka Bangalore India Psna College of Engineering and Technology Department of Ece Tamilnadu Dindigul India School of Electronics Engineering VIT-AP University Andhra Pradesh Amaravati India School of Computer Science and Artificial Intelligence Sr University Telangana Warangal India Nielit Gorakhpur Electronics Department Uttar Pradesh India

ISBN: (纸本)9798350300857

Among Indian women, cervical cancer continues to be the most prevalent form of the disease. The death and incidence rates from cervical cancer are dramatically higher in India than in any other country. Cervical cancer is unique among malignancies in that it can be prevented through screening by detecting and treating precancerous lesions at any point in the disease's lengthy natural history. Women can be screened for cervical precancers and malignancies using a number of different procedures, both older and more cutting-edge technologies. Given the limitations of any given screening tool, selecting the appropriate tool for a given situation is essential. Cervical precancers can be treated in a number of ways;the one chosen will rely on a number of factors, including the patient's preferences, the available budget, the quality of the biopsy specimens, etc. Cervical cancer screening guidelines for Indian women are examined. The proposed method consists of three main stages: preprocessing, feature extraction, and model training. In the preprocessing phase, image processing techniques like HE and sharpening and smoothing are applied. The Fourier Transform is used for feature extraction in GLCM. The RMSE-ELM technique is utilized for model evaluation. Better results are achieved with the proposed technique than with CNN or ELM. © 2023 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Transformer Neural Network for Throughput Improvement in Non-Terrestrial Networks

Transformer Neural Network for Throughput Improvement in Non...

引用

2023 IEEE International Conference on Network, Multimedia and Information technology, NMITCON 2023

作者： Giuliano, Romeo Innocenti, Eros Mazzenga, Franco Vizzarri, Alessandro Di Nunzio, Luca Divakarachari, Parameshachari Bidare Habib, Ibrahim Guglielmo Marconi University Department of Engineering Science Via Plinio 44 Rome00128 Italy University of Rome Tor Vergata viale del policlinico 1 Rome Italy Nitte Meenakshi Institute of Technology Department of Electronics and Communication Engineering 6429 Nitte College Rd Bengaluru India The City College of New York Department of Computer Engineering 160 Convent Avenue New York CityNY United States

ISBN: (纸本)9798350300826

The integration of Non-Terrestrial Networks (NTNs) within the 6G framework provides full connectivity worldwide but some system procedures can be ineffective and should be modified for example in the timer thresholds, which may expire in NTN. Moreover, some procedures may also be affected by the different timeline of terrestrial networks and NTN. For example, the aging of the Channel State Information (CSI) collected by the User Equipment (UE) and sent to the gNode B (gNB) for the scheduler activities may affect its behavior reducing the user throughput, due to the high propagation latency in NTN and outdated data. In this paper we propose a strategy to overcome this problem by using a Transformer Neural Network (TNN) to predict the experienced Signal-to-Interference plus Noise Ratio (SINR) of a generic UE to the transmitting gNB. We assume a period in which the gNB receives frequently CSI/SINR reports by a given UE in order to train the TNN model. Next, the gNB uses data provided by the trained TNN to predict the UE channel behavior and then to properly select the best Modulation and Coding Scheme (MCS) for that UE, avoiding to transmit any CSI data. Results show that the throughput obtained with the TNN trained model is close to the highest CSI update rate (1 ms), while it is higher than the throughput obtained with a CSI update rate of 200 ms of about 5 Mbit/s in Sub-Urban environment for both always LOS and variable LOS/NLOS channel conditions, which corresponds to about a gain of 10 %. © 2023 IEEE.

关键词： Channel state information

来源：评论

学校读者我要写书评

暂无评论

Trustworthy Decision-Making Model for Autonomous Vehicles using Graph Neural Networks and Proximal Policy Optimization

Trustworthy Decision-Making Model for Autonomous Vehicles us...

引用

Distributed Computing and Electrical Circuits and Electronics (ICDCECE), IEEE International Conference on

作者： K M Monica Mohammed Ihsan Sowmya M R. Manikandan Mamatha Talakoti School of Computer Science and Engineering VIT Chennai India Department of Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq Department of AI & DS Nitte Meenakshi Institute of Technology Bengaluru India Department of Computer Science and Engineering Nandha Engineering College (Autonomous) Erode India Department of Computer Science and Engineering Sreenidhi Institute of Science and Technology Hyderabad India

ISBN: (数字)9798331533663

ISBN: (纸本)9798331533670

In recent decades, autonomous vehicles mostly use advanced systems and Machine Learning (ML) algorithms to make accurate decisions, without involvement of humans. Even though many researchers have developed robust model to enhance the robustness of the system with safety and reliability of autonomous vehicles still there are challenges in handling the events which are unpredictable. Therefore, this research proposes a model namely Graph Neural Networks and Proximal Policy Optimization (GNN-PPO) for decision making of autonomous vehicles. Firstly, the data is collected from Performance Measurement System - Bay Area (PEMS-BAY) dataset. Then, the data collected is preprocessed using Kalman Filter (KF) and min-max scaling for handling noise and normalization. Further, the preprocessed data is embedded into Mutual Information (MI) for optimal selection of features. Finally, the proposed GNN-PPO is incorporated to train with spatial dependencies between traffic sensors and adaptive decision making respectively. The proposed GNN-PPO acquired greater results with low level density return of (198.76 ± 1.06) and high-level density return of (165.30 ± 19.35) respectively when compared to the existing Observation Adversarial Reinforcement Learning (OARL) model.

关键词： Solid modeling Decision making Noise Graph neural networks Data models Sensors Kalman filters Autonomous vehicles Optimization Mutual information

来源：评论

学校读者我要写书评

暂无评论

Enhancing Fairness and Performance: Scalable Hybrid Solutions for Class Imbalance in Big Data Analytics

Enhancing Fairness and Performance: Scalable Hybrid Solution...

引用

3rd International Conference on Machine Learning and Data engineering, ICMLDE 2024

作者： Puneetha, B.H. Kumar, Manoj M.V. Prashanth, B.S. Kumara, Ajay M.A. Department of Computer Science and Business Systems Bapuji Institute of Engineering and Technology Karnataka Davanagere India Department of Information Science and Engg Nitte Meenakshi Institute of Technology Karnataka Bangalore560064 India Department of Computer Science University of North Carolina Wilmington United States

Recent advancements in handling class imbalance include hybrid approaches that combine data-level and algorithmic-level techniques. However, challenges such as computational efficiency and adaptability to dynamic datasets remain to be prominently addredssed. This research paper introduces novel hybrid techniques that combine both data-level and algorithmic-level approaches to address class imbalance in large datasets. These techniques are designed to improve class distribution and processing efficiency while enhancing prediction accuracy, particularly for minority classes. The proposed model applies K-means SMOTE for over-sampling the minority class and centroid-based undersampling for the majority class, followed by Classification using XGBoost. Evaluations on multiple datasets demonstrate significant improvements in precision, recall, AUC-ROC, and F1-score compared to traditional methods. In addition to enhancing robustness and fairness, the approach effectively addresses challenges related to scalability, data diversity, and dynamic data sources in big data analytics. The hybrid technique achieved a 10-20% improvement in key performance metrics, including precision, recall, F1-score, and AUC-ROC, across various UCI datasets such as Diabetes, Hepatitis, and German Credit, confirming the model's superiority in handling class imbalance and improving overall Classification performance. © 2025 The Author(s).

关键词： Large datasets

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：