检索结果-内蒙古大学图书馆

2024 International Conference on Communication, computer sciences and engineering, IC3SE 2024

作者： Sriprasadh, K. Palit, Shamik Pravallika, B. Manjunatha Lenka, Reena Singla, Atul Srm Institute Of Science And Technology Faculty Of Science And Humanities Department Of Computer Science And Applications Chennai Vadapalani India University Of Stirling Rak Campus Department Of Computing Science And Software Engineering United Arab Emirates Institute Of Aeronautical Engineering Dundigal Hyderabad India New Horizon College Of Engineering Department Of Mechanical Engineering Bangalore India University Pune India Lovely Professional University Phagwara India

ISBN: (纸本)9798350366846

A machine learning-based e-commerce personalised recommendation system helps address the issue of information overload that inevitably arises when consumers have more and more options in e-commerce, leading to an increasingly complex structure. Customer segmentation is a crucial component of contemporary marketing strategy since it enables companies to effectively adjust their advertising campaigns and customise their communications with customers. Through the analysis of enormous quantities of consumer behaviour data and the discovery of trends that can be utilised for dividing customers into segments, ML algorithms provide a potent tool for automating the procedure of customer segmentation. We report our research and results for identifying a customer's segment. In order to perform machine learning, we integrate the Python Tensorflow library with Pandas for manipulating data frames. To address any discrepancies or gaps in the collected client data, it is refined. Key features are found, and to find hidden patterns and relationships, an exploratory analysis of the data is done. After that, we decide on a suitable machine learning technique to divide the clientele into various groups. We also experiment with several clustering models, including conventional machine learning techniques. © 2024 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Subjective Answers Using Machine Learning 3

Evaluation of Subjective Answers Using Machine Learning

引用

3rd International Conference on Issues and Challenges in Intelligent Computing Techniques, ICICT 2022

作者： Sneha, G. Shreya Shree, G. Babu, Tina Nair, Rekha R. School of Engineering Dayananda Sagar University Department of Computer Science and Engineering Bengaluru India School of Engineering Dayananda Sagar University Department of Computer Applications Bengaluru India

ISBN: (纸本)9781665482684

Negative methods are currently used to evaluate subjective writing. The evaluation of the subjective responses is an essential responsibility. When a human analyses anything, the evaluation's quality can change depending on the person's emotions. All outcomes in machine learning are solely dependent upon the user's input data. To address this issue, our suggested method combines machine learning (ML) and natural language processing (NLP). To analyse the subjective response, our algorithm performs tasks including tokenizing words and phrases, classifying parts of speech, chunking and chinking, lemmatizing words, and word netting. Our suggested approach also offers the context's semantic meaning. There are two modules in our system. Extracting data from scanned photos is the initial step. Then arranging it properly, and the second is using ML and NLP to analyse the text obtained in the previous phase and assigning grades to it. © 2022 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Joint aspect-opinion extraction and sentiment orientation detection in university reviews

引用

International Journal of Information Technology (Singapore) 2022年第6期14卷 3213-3225页

作者： M, Devi Sri Nandhini Gurunathan, Pradeep Department of Computer Science and Engineering A.V.C. College of Engineering Mannampandal Tamilnadu Mayiladuthurai India Department of Computer Applications A.V.C. College of Engineering Mannampandal Tamilnadu Mayiladuthurai India

With the exponential growth of the Internet and the various forms of social media, the number of people using such platforms to share their views and experiences is also greatly increased. The reviews posted by people regarding a service or entity serve as valuable sources for decision making. However, acquiring valuable insights from the abundantly available unstructured information is not so straightforward. There is a need for more effective methodologies to carry out aspect-based sentiment analysis in a fine-grained manner. The proposed work performs joint aspect-opinion extraction and sentiment orientation detection (JAESOD) using an integrated approach of complex dependency rule-based extraction and proper treatment of various forms of adjectives that contribute to the effective extraction of subjective sentiment-bearing terms. The objective of the proposed work is three-fold: to extract aspect-sentiment word pairs, to detect implicit aspects, and to perform sentiment orientation detection at the aspect level along with sentiment scoring. In this paper, we propose a novel methodology to classify the sentiment orientation on a fine-tuned nine-point scale in contrast to the existing three to five-point scale found in the literature works. Concerning the task of sentiment detection, the goal of the proposed work is to achieve optimality in sentiment classification by giving due weightage to the modifies or intensifiers based on their degree of intensification and fair treatment of crucial factors such as double intensification, extended forms of adjectives, negations, sentiments expressed in numerical forms that play a vital role in fine-tuning the sentiment orientation detection. © 2022, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer applications and Management.

关键词： Appositive adjectives Aspect-based sentiment analysis Aspect-sentiment word extraction Degree of intensification Implicit aspect extraction Nonary scale of sentiment strength Sentiment orientation detection

来源：评论

学校读者我要写书评

暂无评论

Enhanced Image Concealment: Leveraging LSB and Brotli Compression 3

Enhanced Image Concealment: Leveraging LSB and Brotli Compre...

引用

3rd International Conference for Advancement in Technology, ICONAT 2024

作者： Yacoob, Shaik Sabnis, Vikrant Jain, Jay Kumar Mansarovar Global University MP Bhopal India Mansarovar Global University Faculty of Engineering and Technology Department of Computer Science MP Bhopal India Maulana Azad National Institute of Technology Department of Mathematics Bioinformatics and Computer Applications MP Bhopal India

ISBN: (纸本)9798350354171

Steganography a cryptographic technique enables the concealment of confidential data within multimedia files like images and videos. This method facilitates the exchange of encrypted information through unconventional means, ensuring that only intended recipients can decipher the hidden message. The LSB technique has attracted significant attention in the literature due to its capability to conceal secret message bits within the least significant parts of image pixels. Although LSB has performed well in image steganography, there is some way to go in terms of its development, especially in the ways in which messages are dealt with. This paper presents a new technique of image steganography basing on the LSB method and the BROTLI algorithm. It uses the compression algorithm to compress message text. After that, to scramble the text, one LSB embedding technique is then used to hide the compressed text in the cover image. Applying the methods of data analysis on the benchmark images, the new approach developed outperforms the standard methods that exist at the present stage. This supports the idea of performing BROTLI on data with a view of compressing the data to be embedded in LSBs. © 2024 IEEE.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Human Activity Recognition in Smart Homes using Deep Learning and Edge Computing for Real-Time Processing 5

Privacy-Preserving Human Activity Recognition in Smart Homes...

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Mariappan, K. Gopal, Baskar Parthasarathy, J. Sreekanth, G.R. Nanmaran, R. Jegajothi, B. SRM Institute of Science and Technology Department of Computer Science and Applications Chennai India College of Engineering University of Technology & Applied Science Nizwa Oman Computer Science & Engineering Jayalakshmi Institute Of Technology Dharmapuri India Information Technology Nandha Engineering College Erode52 India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Electronics and Communication Engineering Chennai India SRS Tech Solutions Chennai India

ISBN: (纸本)9798331530013

The rapid advancement of smart home technologies necessitates efficient human activity recognition (HAR) systems while ensuring user privacy. This research presents a novel architecture that integrates deep learning and edge computing for real-time HAR, emphasizing privacy protection. By employing differential privacy methods and federated learning, the approach minimizes personal data exposure risks. Using the UCI HAR dataset, the model achieves an accuracy of 96.50%, with precision, recall, and Fl-score metrics of 95.75%, 96.20%, and 95.97%, respectively. The results indicate high accuracy and adaptability to varying smart home environments, while edge computing ensures minimal latency. This work highlights the importance of balancing performance and privacy in HAR systems, paving the way for secure smart home applications. Additionally, it points to the potential of deep learning in medical diagnostics, suggesting future research could enhance diagnostic capabilities across various medical imaging modalities, including CT scans and MRIs, to improve healthcare outcomes. © 2024 IEEE.

关键词： Smart homes

来源：评论

学校读者我要写书评

暂无评论

Sentiment classification of reviews using combination of Firefly Algorithm and ANN 21

Sentiment classification of reviews using combination of Fir...

引用

21st OITS International Conference on Information Technology, OCIT 2023

作者： Tripathy, Abinash De, Utpal Chandra Dash, Bibhuti Bhusan Patra, Sudhansu Shekhar Rao, Ch. Chakradhara Pandey, Trilok Nath KIIT Deemed to Be University School of Computer Applications Odisha Bhubaneswar India Raghu Engineering College Department of Computer Sc. & Engg AP Viskahapatnam India Vellore Institute of Technology School of Computer Science & Engineering Chennai India

ISBN: (纸本)9798350358230

With the availability of many social media sites, the reviews and comments by the customers are freely available for analysis. Most of these reviews are textual as per the content ***, proper processing need to be done for future use of the reviews. As reviews are in text, the amount of words need to be processed for any analysis work is very large in amount. So, an approach needs to be adopted to minimize the amount of word without affecting the result of the analysis. Thus, in this paper the Firefly algorithm is used to select the words / features that can act as a representative of the whole set of words. The output of Firefly algorithm i.e., selected features act as input of ANN. In this paper, a hybridization of Firefly algorithm and ANN is carried out for better accuracy result. The result of the proposed approach is analyzed by using confusion matrix and various evaluation parameters. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Ad Service Detection - A Comparative Study Using Machine Learning Techniques 13

Ad Service Detection - A Comparative Study Using Machine Lea...

引用

13th International Conference on Computing Communication and Networking Technologies, ICCCNT 2022

作者： Yadhu Krishna, M. Sanjana, S. Thushara, M.G. Amrita Vishwa Vidyapeetham Amrita School of Engineering Department of Computer Science and Engineering Amritapuri India Amrita Vishwa Vidyapeetham Amrita School of Engineering Department of Computer Science and Applications Amritapuri India

ISBN: (数字)9781665452625

ISBN: (纸本)9781665452625

The use of web-based services has been soaring since the internet has come up. Hence, traditional forms of advertisements have moved on to the web, leading to a rising number of ad services and trackers affecting user privacy. Ad blockers were developed in order to prevent these. However, the currently available ad blockers are purely based on a predefined set of blacklist domains. This study proposes a machine learning-based approach to detect web-based ad services and trackers. In order to help us explore the area using machine learning techniques, a dataset was created. The developed dataset contained 74,000 entries comprising both domains that served advertisements and normal domains. In addition, we have also compared the scores that were obtained by various supervised machine learning models, and the best model was identified. The best model offered up to 88% accuracy in classifying ad services and normal websites. The model contributed by this paper could be further developed into a machine learning-based advertisement blocker system. © 2022 IEEE.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Insect Classification Framework based on a Novel Fusion of High-level and Shallow Features

Insect Classification Framework based on a Novel Fusion of H...

引用

2022 International Conference on Machine Learning and Data engineering, ICMLDE 2022

作者： Haarika, Raye Babu, Tina Nair, Rekha R. Department of Computer Science and Engineering Dayananda Sagar University School of Engineering Bengaluru India Department of Computer Applications Dayananda Sagar University School of Engineering Bengaluru India

The largest and most diversified group of organisms are insects. Since insects play a crucial role in many ecosystems, it must be precisely identified for efficient management. However, it is difficult and labor-intensive to identify insect species. Due to advancements in deep learning, computer vision, and sensor technologies, there is rising interest in image-based systems for quick, accurate identification. This study investigates a novel hybrid feature set of shallow features from the tiger beetle dataset, such as texture and wavelet features and high-level features from SqueezeNet. The tiger beetle insect is classified into the cicindelini and collyridini classes with a random forest classifier with 97.65 percent accuracy using this hybrid feature set, which considers the texture and structural characteristics of the insect. Thus the technique provides insight into various features and indicates promising future directions for image-based insect identification and species classification relevant to computer science, Agriculture, and Ecology research. © 2022 Elsevier B.V.. All rights reserved.

关键词： Ecology

来源：评论

学校读者我要写书评

暂无评论

Sentiment analysis of reviews using Nature Inspired PSO and ANN

Sentiment analysis of reviews using Nature Inspired PSO and ...

引用

2023 IEEE Global Conference on Information Technologies and Communications, GCITC 2023

作者： Tripathy, Abinash De, Utpal Chandra Dash, Bibhuti Bhusan Patra, Sudhansu Shekhar Rao, Ch. Chakradhara Pandey, Trilok Nath Kiit Deemed to Be University School of Computer Applications Odisha Bhubaneswar India Raghu Engineering College Department of Computer Sc. & Engg AP Viskahapatnam India Vellore Institute of Technology School of Computer Science & Engineering Chennai India

ISBN: (纸本)9798350308167

Social media now plays an important role is sharing the views or comments about a topic. These comments are available to the users for their processing and future decision making process. As the reviews contains mostly text or emojis, thus, processing is required to obtained the required information. Nature is always a source for inspiration and *** activities of the nature can act as a source for optimization and classification. In this paper, two nature inspired algorithms are considered for analysis. Firstly, Particle Swarm Optimization (PSO) act as an optimization technique for feature selection i.e., best features are selected and these best features act as input to Artificial Neural Network (ANN) for further classification purpose. The reviews are processed using the proposed algorithms and finally, the confusion matrix is generated, which helps to generate the evaluation parameters to evaluate the results. © 2023 IEEE.

关键词： Artificial Neural Network (ANN) Confusion matrix Particle Swarm Optimization(PSO) Performance evaluation parameter Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

A Smart Approach to Coconut Leaf Spot Disease Classification using computer Vision and Deep Learning Technique

A Smart Approach to Coconut Leaf Spot Disease Classification...

引用

2023 IEEE World Conference on Communication and Computing, WCONF 2023

作者： Brar, Simrat Kaur Sharma, Rishabh Vats, Satvik Kukreja, Vinay Chandigarh Group of Colleges Department of Computer Applications Landran India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Graphic Era Hill University Computer Science and Engineering Dehradun India

ISBN: (纸本)9798350311204

Coconut leaf spot (CLS) disease is a major threat to coconut production and can cause severe economic losses. In this study, we propose a deep learning (DL)-based ResNext50 model for automated detection and severity classification of CLS disease. Our model leverages a ResNext50 mode;and is trained and tested on a dataset of coconut leaf images with six severity levels, ranging from healthy leaves to critical severity. The proposed approach achieves high accuracy in detecting and classifying the severity levels of the disease. Our findings suggest that the proposed method is successful in properly identifying and categorizing the illness severity levels, with an accuracy rate of 91.77% overall. The strategy that has been presented has the possibility to significantly improve the efficiency and accuracy of CLS disease detection and monitoring, ultimately leading to better management strategies and increased productivity in the coconut industry. © 2023 IEEE.

关键词： computer vision

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：