检索结果-内蒙古大学图书馆

HybridNet: Integrating Multiple Approaches for Aerial Semantic Segmentation

SN computer science 2024年第1期5卷 1-14页

作者： Chouhan, Avinash Sur, Arijit Chutia, Dibyajyoti Aggarwal, Shiv Prasad North Eastern Space Applications Centre Meghalaya Umiam 793103 India Department of Computer Science and Engineering Indian Institute of Technology Assam Guwahati 781039 India

In recent times, semantic segmentation for VHR aerial images has become an emerging research topic due to its widespread applications in disaster management, environmental monitoring, natural resource mapping, etc. The problem of semantic segmentation can be modeled as an image-to-image mapping problem where pixel-level classification is required. Pixel level classification is challenging for the high-resolution aerial image due to the presence of the tiny objects in low-frequency and more information details for such tiny objects required for dense semantic labeling. In general, encoder–decoder based architecture for semantic segmentation suffers from information loss due to the up and downsampling process. To handle this, we extend a high-resolution network with dense connection integration to preserve the original resolution and better parameter sharing. We also incorporate a lightweight self-attention module for positional attention, which results in better segmentation maps. Additionally, we use a generalized Hough transform based deep voting module for pixel dependencies extraction. Experimental results reveal that the proposed model achieves the best mean intersection over union and overall accuracy in local and benchmark evaluation on the Vaihingen and Potsdam datasets. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： High-resolution connection Hough voting Semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Evaluating 10Gbps Wireless Optical Communication Using NRZ Modulation: Analyzing BER, Signal Quality, and System Performance 7

Evaluating 10Gbps Wireless Optical Communication Using NRZ M...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Khant, Shailesh Makwana, Mayur Patel, Atul Faculty of Computer Science and Applications Charusat Changa Anand India Dept. Electronics and Communication Engineering Charusat Changa Anand India

ISBN: (纸本)9798350350067

Free space optical (FSO) communication is a fast and wireless data transfer technique that serves as a viable alternative to traditional fiber-optic systems. This study illustrates how FSO can effectively address the growing demand for rapid data transmission and suggests its potential applicability in various scenarios. FSO can be employed to establish connections between buildings within a corporate campus without the need for physical wiring, or it can provide high-speed internet access in locations where installing cables is challenging. We used Optsim software to assess critical parameters such as Bit Error Rate (BER), eye diagrams, power, and signal quality. The results offer valuable insights into enhancing the efficiency and reliability of FSO systems. FSO can find applications in cellular networks to interconnect network equipment, as well as in high-definition video surveillance. These findings highlight the areas in which FSO can advance communication technology and provide valuable insights for future developments. © 2024 IEEE.

关键词： Bit error rate

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Model for Predicting Internet Addiction in Teenage and Young Students 3

A Machine Learning Model for Predicting Internet Addiction i...

引用

3rd IEEE World Conference on Applied Intelligence and Computing, AIC 2024

作者： Johar, Geetika Patel, Ravindra University Institute of Technology Rgpv Dept. of Computer Science & Engineering Bhopal India University Institute of Technology Rgpv Dept. of Computer Applications Bhopal India

ISBN: (纸本)9798350384598

Internet addiction is becoming one of the critical issues among teenagers and young university students. This habit not only negatively impacts the student's learning performance, but also affects the student's physical and mental health. This paper is focusing on designing a Machine Learning (ML) model for accurately identifying internet addiction. The model incorporates data preprocessing and feature selection techniques for reducing the computational complexity. Next, five different ML algorithms have been implemented and compared to identify appropriate ML algorithms. The identified ML model has been trained using the behavioral features of the students for predicting internet addiction. The experiments have been carried out and the performance of the models has been measured. The results demonstrate that a random forest classifier provides 83% accurate detection for university students and 96% accurate results are provided by an SVM-based classifier for teenager internet addiction detection. Therefore, by using the entire observation of experiments it is found that the proposed model can successfully identify internet addiction in students by analyzing the student's behavioral features. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Exploring Missing Value Handling Techniques for Optimized KNN Heart Disease Prediction

Exploring Missing Value Handling Techniques for Optimized KN...

引用

2024 IEEE International Conference on Signal Processing, Informatics, Communication and Energy Systems, SPICES 2024

作者： Joseph, Jeena Kartheeban, K. Kalasalingam Academy of Research and Education Department of Computer Applications Tamilnadu Krishnankoil India Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Tamilnadu Krishnankoil India

ISBN: (数字)9798350376135

ISBN: (纸本)9798350376135

Heart disease prediction stands at the forefront of contemporary medical research, with machine learning models such as K-Nearest Neighbors (KNN) being increasingly employed for this purpose. A critical factor influencing the performance of these models is the presence of missing data, which, if not addressed appropriately, can severely hinder predictive accuracy. This study provides a comparative analysis of different missing value handling techniques and explores the impact of each method in predicting heart disease by applying the KNN model. Several imputation methods were employed in the existing literature and techniques such as mean imputation, median imputation, mode imputation, KNN imputation, list-wise deletion, and replacement with a constant value were scrutinized. The popular Framingham heart disease dataset is selected for the study and the missing values are addressed using the techniques mentioned. Subsequently, the KNN method is used to ascertain the predictive accuracy and this highlights the deviations in the results depending upon the chosen imputation method. Remarkably, the method of replacing missing values with a predefined constant value of zero achieved a more accurate result. The study focuses on the distinct characteristics, performance, suitable data type and limitations of each missing value handing technique and it provides valuable information for practitioners and researchers who aim to maximize the effectiveness of machine learning algorithms in cardiovascular disease prediction. © 2024 IEEE.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Extractive Summarization on Twi Language Using Text-Rank and Fuzzy Clustering Algorithm 1

Extractive Summarization on Twi Language Using Text-Rank and...

引用

1st International Conference on Circuits, Power, and Intelligent Systems, CCPIS 2023

作者： Dhole, Sayak Sagnika, Santwana Dominic, Ampofo Mishra, Bhabani Shankar Prasad Fernando, Aloka Dash, Satya Ranjan School of Computer Engineering Kiit Deemed to Be University India School of Computer Applications Kiit Deemed to Be University India University of Moratuwa Department of Computer Science and Engineering Sri Lanka

ISBN: (纸本)9798350315769

Twi is a dialect of the Akan language spoken in southern and central Ghana by several million people. About 80% of the Ghanaian population speaks Twi as a first or second language. Summarization is a basic natural language processing task, that is a step to further more advance tasks as well as an aid in reviewing information. This paper tackles the problem of summarizing Twi texts. Three extractive summarization techniques - TF-IDF, Text-Rank and Fuzzy C-means Clustering are implemented. We find that Text Rank performs best, while TF-IDF despite being fairly simple performs comparably well to Text Rank. Our work suggests that embedding based approaches are potent and further work should employ their use. © 2023 IEEE.

关键词： Fuzzy clustering

来源：评论

学校读者我要写书评

暂无评论

NLP Based Sentiment Analysis Using Particle Swarm Optimization with Logistic Regression for Digital Education 6

NLP Based Sentiment Analysis Using Particle Swarm Optimizati...

引用

6th International Conference on Cybernetics, Cognition and Machine Learning applications, ICCCMLA 2024

作者： Priyadharshini, G. Clara Barathi Balaji, Prasanalakshmi Chaurasia, Mousmi Ajay Das, Subhranginee Dutta, Sushama Rani Karpagam Academy of Higher Education Department of Computer Applications Coimbatore India King Khalid University Department of Computer Science Abha Saudi Arabia Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Hyderabad India

ISBN: (纸本)9798331505790

Identification and categorization of user sentiments from a text passage is known as sentiment analysis into several sentiments. For example, using feelings like happiness, sadness, anger, or positive, negative, or neutral to gauge how the user feels about a certain topic or item. These days, a variety of websites and applications collectively referred to as online educational platforms allow users to obtain a higher degree of education across a range of areas. For this reason, digital education provides a platform for the dissemination of knowledge. Among the most active areas within NLP, web mining, and text mining research is sentiment analysis. It is significant in a variety of subjects, including as the social sciences and management sciences, where evaluating the efficacy of learning technology depends heavily on student input. Due to the proliferation of educational institutions, many students have become enthralled with online learning portals that provide cost-free courses. Every year, a huge number of students enrol in these expansive online courses and then revisit their opinions regarding the course material and level of instruction. Additionally, share ideas on blogs on how to raise the standard of instruction by expressing both good and negative opinions. However, an assortment of ML techniques are available to assess these ratings and ascertain which virtual education platform is the most user-friendly and optimal. This study examined natural language processing (NLP)-based sentiment analysis and social media evaluations that were manually gathered from educational applications. To categorise the reviewer's comment for digital education, Particle Swarm Optimisation with Logistic Regression (PSOLR) outperformed all other existing Naïve Bayes, Decision Tree, and Logistic Regression algorithms in terms of accuracy (93.75%). © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Moving Target Defense - Challenges, Problems and Suitability for Internet of Things 4

Moving Target Defense - Challenges, Problems and Suitability...

引用

4th International Conference on Computing and Communication Systems, I3CS 2023

作者： Gurung, Dipendra Gurung, Sandeep Pradhan, Mohan Pratap Sikkim Manipal Institute of Technology Department of Computer Applications Majitar India Sikkim Manipal Institute of Technology Department of Computer Science and Engineering Majitar India Sikkim University Department of Computer Applications Gangtok India

ISBN: (纸本)9798350323771

Traditionally cyber attackers have always had an upper hand over defenders as the latter can only react in the event of an attack. Moving Target Defense (MTD) has emerged as a potential game changer by reversing the advantage from attackers to defenders. Together with traditional defenses, MTD is expected to take cyber security up a notch. MTD solutions have been proposed for various levels, namely operating system, network, runtime platform, etc. However, improvement of existing solutions and development of new solutions are required. This paper presents an overview of MTD, the various MTD approaches, attacks mitigated, open research problems in MTD and MTD for the Internet of Things (IoT). © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Smart question answering system using vectorization approach and statistical scoring method

引用

Materials Today: Proceedings 2023年 80卷 3719-3725页

作者： Manjunath, T.N. Yogish, Deepa Mahalakshmi, S. Yogish, H.K. Information Science & Engineering B M S Institute of Technology &Management Karnataka Bangalore560064 India K S School of Engineering & Management Computer Science & Engineering Affiliated to Visvesvaraya Technological University Karnataka Belagavi India Department of Master of Computer Applications M S Ramaiah Institute of Technology Karnataka Bangalore560054 India

In this digital era, internet users are increasing day by day to extract information related to various fields such as health, economic, educational, politics and daily needs from Information Retrieval Systems (IRS) such as Google, Ask, Yahoo etc. Information Retrieval (IR) is a conventional method which depends on metadata searching method that is searching of adocuments for information within documents and information about documents. Lot of research in the IR area improves accessing the quality of information. Most of the search engines such as Google, Yahoo, Ask Jeeves depends on keyword based query processing mechanism internally which can't handle natural language questions which results in returning long list of documents for a query. The task of users is to manually explore each document to retrieve correct answer which is a time consuming process. To overcome the problems of conventional search engines, smart question answering system comes to play. The objective of Smart Automated Answering system is to impart accurate and valid answers to user question in natural language rather than set of full documents. The Smart Question answering system which accepts user question in Natural language in specific domain and provide short and precise answer using Natural language processing technique, used for pre-processing, normalized term weighting-TF-IDF with cosine similarity approach for document retrieval and enhanced BM25 ranking function to extract answer. The main focus is on decreasing the response time, designing ranking function and giving the pertinent responses to the users’ intent. The system achieved an overall Precision of 93.2%, Recall of 84.3% and F-measure of 88.5% with 80% of Accuracy. © 2021

关键词： Information retrieval

来源：评论

学校读者我要写书评

暂无评论

Apply Deep Learning-based CNN and LSTM for Visual Image Caption Generator 3

Apply Deep Learning-based CNN and LSTM for Visual Image Capt...

引用

3rd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2023

作者： Indumathi, N. Divyalakshmi, R.J. Stalin, J. Ramachandran, V. Rajaram, P. Srm Institute of Science and Technology Computer Science and Applications Chennai India Sethu Institute of Technology Computer Science and Business Systems Virudhunagar India Computer Science and Engineering Gitam School of Computing Bengaluru India

ISBN: (纸本)9798350399264

Implemented Image captioning is becoming a need. Deep neural network models enable integrated applications to generate and caption images. Image captioning describes an image. It requires identifying an image's main objects, properties, and relationships. It produces correct sentences. The creation of image caption generators, which examine the content of an image and offer pertinent descriptions, makes use of deep learning and computer vision techniques. One element of this method involves classifying objects in the image using English keywords derived from training datasets. The caption generator was created by combining LSTM and CNN. In this paper, we propose a deep-learning model that uses computer vision and machine translation to characterize images and generate captions. The model successfully recognizes and labels visual items and their relationships. Transfer Learning will be used to demonstrate the suggested experiment, coupled with the Flickr8k dataset and the Python3 programming language. This study will also look into the functions and construction of neural networks. The proposed model achieves a BELU Score of 69.8. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study in Image Fusion Using Orthogonal and Biorthogonal Wavelet 12th

A Comparative Study in Image Fusion Using Orthogonal and Bio...

引用

12th International Conference on Soft Computing for Problem Solving, SocProS 2023

作者： Pandy, Saroj Kumar Kumar, Ankit Kumar, Gaurav Singh, Kamred Udham Singh, Teekam Srivastava, Sandeep Choudhury, Tanupriya Department of Computer Engineering and Applications GLA University UP Mathura India School of Computing Graphic Era Hill University Dehradun India Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India Department of Computer Science and Engineering Galgotias University Greater Noida India Department of Computer Science and Engineering University of Petroleum and Energy Studies Dehradun India

ISBN: (纸本)9789819732913

A method called picture fusion is largely concerned with improving photographs to enhance scene visualization. In order to produce a composite image that is more significant and instructive, it attempts to maintain the key elements from each image. This method has been used in a number of industries, including robots, satellite images, and medicine. Researcher decision-making and the success of scientific endeavors are greatly influenced by the quality of the fused image. In this article, a comparison of the wavelets Haar and Bior 2.2 is made. In order to compare the two wavelets, different photos are employed. Based on metrics like the Peak Signal-to-Noise Ratio (PSNR), Signal-to-Noise Ratio (SNR), Mean Squared Error (MSE), Structural Similarity Index (SSIM), and Standard Deviation (SD), the performance of the wavelets is assessed. Based on the results, it can be said that Bior 2.2 performs somewhat better than Haar in terms of picture fusion quality. We use orthogonal and biological wavelets to compare how well image fusion works. To fuse pictures, we utilize the Discrete Wavelet Transform (DWT) and the maximum selection criteria. The performance of the fused pictures is assessed using a number of factors, such as visual quality measurements. The advantages of biorthogonal wavelets over orthogonal wavelets for image fusion tasks are highlighted in this research, especially when working with numerous sensors. It emphasizes how important the decomposition level is for producing high-quality fused pictures. The results help advance image fusion methodologies and offer insightful information to academics and industry professionals involved in picture processing and analysis. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Discrete wavelet transforms

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：