检索结果-内蒙古大学图书馆

2023 7th International Conference On Computing, Communication, Control And Automation, ICCUBEA 2023

作者： Moharana, Bhimasen Biswal, Bhramara Bar Dey, Snehasis Rath, Manas Kumar Banerjee, Shobhan Lovely Professional University Department of Computer Science and Engineering Punjab India College of Engineering P.G. Department of Computer Science & Applications Bhubaneswar India College of Engineering Electronics & Telecommunication Engineering Bhubaneswar India Maharaja Sriram Chandra Bhanja Deo University Department of Computer Application Baripada India Birla Institute of Technology and Science Department of Engineering Technology Pilani India

ISBN: (纸本)9798350304268

Each app available in the App Store or Play Store has various aspects linked to it such as its version, category, number of installations, genre, etc. which makes it unique, robust & popular. The reviews and ratings given by end users play an important role for both the developers and other users for the performance and survival of the app in the marketplace. Reviews are just a description for justification of the rating given by a user & the rating plays an important role in the first look. In this paper, we have used the Play Store Analysis Dataset to descriptively analyze the various attributes present in it and create models that predict the rating of an app, given its specifications. The models have been compared based on a common accuracy metric based on which their reliability can be judged and used in real-time rating predictions for a new application in the store for which a certain amount of data is available over some period. © 2023 IEEE.

关键词： Descriptive Statistics ML Classification Models Model Comparison Play Store App Analysis Rating Prediction

来源：评论

学校读者我要写书评

暂无评论

An IoT-Based Deep Learning Approach for Online Fault Detection Against Cyber-Attacks

引用

SN computer science 2023年第4期4卷 393页

作者： Rajkumar, Sujatha Sheeba, S. Lilly Sivakami, R. Prabu, S. Selvarani, A. Department of Embedded Technology School of Electronics Engineering Vellore Institute of Technology Tamil Nadu Vellore 632014 India Department of Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Tamil Nadu Chennai India Department of Computer Science and Engineering Sona College of Technology Tamil Nadu Salem India Department of ECE Mahendra Institute of Technology Tamil Nadu Namakkal India Department of ECE Panimalar Engineering College Tamil Nadu Chennai India

Trustworthy has been included as proof of the passed-in quality, which is safety, security, and privacy, and is not time limited. A real-time system operates according to a set of expected behaviors and conditions. Internet of Things (IoT) systems and applications are essential industrial investments expected to be of critical importance. Maintaining the reliability ofq7 such systems and networks is expensive, time-consuming and costly. A reliable IoT system considers the system operation’s security features and IoT reliability. These difficulties incorporate information breaks, phishing and spam crusades, and dispersed refusal of administration (DRoA) assaults, and malevolent exercises, for example, security breaks focusing on IoT gadgets. Deep learning (DL) strategies have been proposed to recognize pernicious traffic information, especially for malignant assaults against IoT gadgets. The proposed layered, profound learning strategy is stacked long short-term memory (SLSTM) coordinated with pre-prepared deep learning (DL) to gain proficiency with the attributes of dubious exercises inside and out and recognize them from ordinary traffic. Each pre-prepared DL model comprises the remaining blocks. We have utilized two huge datasets to evaluate the presentation of our discovery technique. Mixed IoT conditions guarantee that this approach can be applied to any IoT climate. Our proposed method, SLSTM, can recognize most IoT assaults by identifying harmless and malignant traffic information. The train results demonstrate that the proposed layered, profound learning technique can give a higher continuous location rate than existing grouping strategies. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Cyber-attack Deep learning (DL) Internet of Things (IoT) Malicious Neural networks Security Stacked long short-term memory (SLSTM)

来源：评论

学校读者我要写书评

暂无评论

An Empirical Method For Chronic Kidney Disease Prediction 15

An Empirical Method For Chronic Kidney Disease Prediction

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Ravi Kumar, R. Mudepalli, Srinivas Sujay, V. Lande, Jayapal Mohmmad, Sallauddin Sr University School of Computer Science and Artificaial Intelligence Telangana Warangal506371 India Telangana Hyderabad India Krishna University College of Engineering and Technology Department of Computer Science and Engineering Machilipatnam Andhra Pradesh Krishna District India

ISBN: (纸本)9798350370249

This study introduced a systematic approach to predicting chronic kidney disease using machine learning models. The dataset was sourced from Kaggle and underwent comprehensive preprocessing to address null values, feature encoding, and class imbalance. Several machine learning algorithms were implemented and fine-tuned, including KNN, SVM, Random Forest, XGBoost, and ANN. The performance of each model was evaluated based on accuracy, precision, recall, and F1-score. Ensemble methods, particularly Random Forest and XGBoost, consistently outperformed other models, demonstrating robustness across different proportions of training data. The accuracy of Random Forest reached 98.2%, and XGBoost achieved 96.7% accuracy. Furthermore, Accurate Positive and False Negative analysis and Receiver Operating Characteristic curves provided insights into the models' effectiveness and discriminatory power. The findings contribute valuable insights into developing reliable predictive models for chronic kidney disease. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Deep Learning for User-Centric Car Recommendations

Multi-Modal Deep Learning for User-Centric Car Recommendatio...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Karthikeyan, M. Saravana Blessie, A. Alice Raj, J. Relin Francis Krishnan, R. Santhana Haribabu, K. Balamurugan, S. Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Avadi Chennai India Government College of Engineering Department of Electronics and Communication Engineering Tirunelveli India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Electronics and Communication Engineering Chennai India Scad College of Engineering and Technology Department of Electronics and Communication Engineering Cheranmahadevi India Scad College of Engineering and Technology Department of Mechanical Engineering Cheranmahadevi India Velammal College of Engineering and Technology Department of Mathematics Madurai India

ISBN: (纸本)9798331509828

This paper presents a Multi-Modal Deep Learning framework for User-Centric Car Recommendations, aimed at transforming the car selection process through advanced artificial intelligence techniques. The proposed system integrates a wide range of data sources, including search history, showroom visits, car performance metrics, and social media engagements, to deliver highly personalized, accurate, and timely car recommendations that align with individual preferences, budgets, and lifestyles. The framework leverages multi-modal data processing to optimize car selection by analyzing both qualitative and quantitative user inputs, ensuring precise and context-aware recommendations. By addressing challenges such as choice overload and decision fatigue, the system enhances user decision-making capabilities. Real-time processing ensures that users receive up-to-date and relevant suggestions, improving engagement and overall satisfaction. The inclusion of a feedback loop further refines the system, enabling continuous improvement and adaptation to evolving user needs and market trends. This innovative framework represents a significant advancement in car recommendation systems by combining data diversity, state-of-the-art deep learning models, and real-time analytics. Its ability to provide dynamic, personalized, and actionable insights empowers users to make confident, well-informed decisions during their car-buying journey. With its robust and scalable design, this framework offers a transformative approach to modern automotive recommendation systems, setting a new standard for user-centric experiences. © 2025 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Classification of Musical Genres Using Audio Spectrograms 5

Classification of Musical Genres Using Audio Spectrograms

引用

5th IEEE International Conference on Advances in Computing, Communication Control and Networking, ICAC3N 2023

作者： Abbas, Mohammad Kazim Gupta, Kunal Mudassir, Mohammad Jain, Rishabh Galgotias College Of Engineering And Technology Dept. Of Computer Science And Engineering Greater Noida India Kiet Group Of Institutions Dept. Of Computer Science Delhi-NCR Ghaziabad India

ISBN: (纸本)9798350330861

The classification of music into distinct genres is a valuable undertaking in the realm of multimedia study, as it enables artists, albums, and songs to be categorized based on shared musical characteristics. This study aims to contribute to the field of music genre categorization by proposing an approach that can more accurately classify musical genres compared to existing methodologies. Our approach leverages the attributes extracted from the MK2 audio dataset, which is a compilation of musical genre data that has been collected and processed to facilitate the prediction of song genres. The proposed method employs convolutional neural networks (CNN) and utilizes audio spectrograms as input features. Additionally, this study presents a comparative analysis of our proposed approach with previous research papers, providing insights into the effectiveness of our proposed model. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Robust Tweets Classification Using Arithmetic Optimization with Deep Learning for Sustainable Urban Living

引用

SN computer science 2024年第5期5卷 549页

作者： Hamza, Manar Ahmed Hashim, Aisha Hassan Abdalla Motwakel, Abdelwahed Elhameed, Elmouez Samir Abd Osman, Mohammed Kumar, Arun Singla, Chinu Munjal, Muskaan Department of Electrical and Computer Engineering International Islamic University Malaysia Kuala Lumpur 53100 Malaysia Department of Computer and Self Development Preparatory Year Deanship Prince Sattam bin Abdulaziz University AlKharj Saudi Arabia Department of Management Information Systems College of Business Administration in Hawtat bani Tamim Prince Sattam bin Abdulaziz University AlKharj Saudi Arabia Department of Computer Science College of Post-Graduated Studies University of Science and Technology Omdurman Sudan Department of Information System Faculty of Computer Science and Information Technology Omdurman Islamic University Omdurman Sudan Department of Electronics and Communication Engineering New Horizon College of engineering Bengaluru India Computer Engineering Thapar Institute of Engineering and Technology Punjab Patiala India

Natural Language Processing (NLP) with Deep Learning (DL) for Tweets Classification includes use of advanced neural network designs to analyse and classify Twitter messages. DL techniques like recurrent neural network (RNN) or transformer-based frameworks like BERT are used to mechanically learn difficult linguistic patterns and contextual info from tweet data. These techniques able to capture subtleties of language with sarcasm, sentiment, and context-specific meanings and making them suitable for tasks like sentiment analysis or topic classification in realm of social media. Leveraging deep symbols learned from great amounts of textual data, these NLP techniques permit precise and nuanced classification of tweets, donating to enhanced information retrieval, sentiment tracking, and trend analysis in dynamic and fast-paced world of social media communication. In this view, this research develops an arithmetic optimization algorithm with deep learning based tweets classification (AOADL-TC) approach for sustainable living. The goal of the AOADL-TC technique is to identify and discriminate different kinds of sentiments that exist in the tweet data. At the initial stage, the AOADL-TC model pre-processes tweet data to convert uniform data into a useful format. For sentiment detection, the AOADL-TC technique applies a parallel bidirectional gated recurrent unit (BiGRU) model. At last, tuning of parameters related to parallel BiGRU model performed by AOA. An wide set of tests carried out to illustrate better performance of AOADL-TC model. The experimental outcomes portrayed that AOADL-TC technique demonstrates the supremacy of the AOADL-TC technique in terms of different evaluation metrics. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Deep learning Machine learning Natural language processing Sentiment analysis Social media

来源：评论

学校读者我要写书评

暂无评论

Enhancing Non-Destructive Examining of Composite Materials Using Lightweight Structures And Machine Learning

Enhancing Non-Destructive Examining of Composite Materials U...

引用

2023 International Conference on Advances in Computation, Communication and Information technology, ICAICCIT 2023

作者： Gangwar, Prashant Kumar Pattanaik, Balachandra Madiajagan, M. Sohail, Mohammed Ali Babu, M. Dinesh Sarala, B. Woldia University Department of Construction Technology & Management Amhara Region Ethiopia Wollega University College of Engineering and Technology Department of Electrical and Computer Engineering Nekemte Ethiopia Vellore Institute of Technology School of Computer Science and Engineering Tamil Nadu Vellore India Jazan University College of Computer Science & Information Technology Department of Computer & Network Engineering Jazan Saudi Arabia Rajalakshmi Institute of Technology Department of Mechanical Engineering Chembarabakkam Chennai India R.M.K Engineering College Department of Electronics and Communication Engineering Chennai India

ISBN: (纸本)9798350344387

Composite materials and structures are becoming more efficient and cost-effective, and new special features are being developed to improve their specific properties. Their use in a variety of applications such as wind turbines, aeronautical, medical equipment, transportation, and other load-bearing structures is becoming increasingly important. It is necessary for non-destructive composite examining to be robust and trustworthy in order to limit the risk of damage as well as the cost of maintenance. In order to ensure the product quality throughout its life cycle, many non-destructive examining procedures based on a wide range of concepts have been created. In this paper, nondestructive examining was used to obtain vibration measurements of composites in high-frequency regimes, which were then analysed. Both end-to-end classifications of the data and classifications of data acquired by feature engineering with modal analysis employ Support Vector Machine (SVM) to carry out damage localization in their respective applications. Finally, the findings display a large number of plates made of various materials and with defects of varying magnitudes. © 2023 IEEE.

关键词： Composite Localization Machine Learning Nondestructive Examining

来源：评论

学校读者我要写书评

暂无评论

Designing an Intelligent Model that Employs Advanced Machine Learning Techniques to Optimize Disease Prediction and Classification in Humans 1

Designing an Intelligent Model that Employs Advanced Machine...

引用

1st International Conference on Trends in engineering Systems and Technologies, ICTEST 2024

作者： Kumari, Sudesh Lekshmi, V. Arathi Chandran, R.I. Shankar, Jaya Vishnu Priya, P.M. Bps Women University Department of Electronics and Communication Engineering Sonipat India Christ Nagar College Department of Computer Science and Applications Kerala Maranalloor India Sree Narayana Institute of Technology Department of Computer Science and Engineering Kerala Adoor India Department of Computer Science Karnataka Bengaluru India

ISBN: (纸本)9798350307795

Machine learning (ML) has emerged as a powerful tool with applications across diverse fields, including clinical diagnostics. With the growing prevalence of heart and liver diseases worldwide, early detection is paramount for saving lives. This study presents a hybrid ML model that combines the support vector machine (SVM) approach with a modified particle swarm optimization (PSO) model for the classification of heart and liver disease data. Utilizing datasets from the UCI ML repository, we evaluate the model's performance using various metrics, including categorization accuracy, error rates, correctness, recall, and the F1 score. Comparative analyses with traditional SVM and other hybrid algorithms such as the PSOSVM and Crazy PSO-SVM (CPSOSVM) are conducted. The experiments encompass the prediction of cardiac and liver illness. Results demonstrate that the designed Cauchy Crazy PSOSVM (CCPSOSVM) algorithm outperforms other approaches, achieving the greatest accuracy rate and least error rate. While this study focuses on cardiac and hepatic illness prediction, the CCPSOSVM algorithm holds promise for the extension of disease prediction across various medical domains. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Point Cloud Part Segmentation Combined with Adaptive Sampling and Channel Attention Mechanism 3

Point Cloud Part Segmentation Combined with Adaptive Samplin...

引用

3rd International Conference on Signal Image Processing and Communication, ICSIPC 2023

作者： Zhu, Lingyun Zhao, Yueying Wang, Chenyu College of Computer Science and Engineering Chongqing University of Technology Chongqing400054 China Liangjiang International College Chongqing University of Technology Chongqing401135 China

ISBN: (纸本)9781510670945

To address the problem that the geometric connection of the channels was ignored and the segmentation accuracy was not enough in existing point cloud part segmentation, a point cloud part segmentation model based on channel attention mechanism was proposed. First, adaptive furthest point sampling was used to determine the sampling points so that the determined local area is better representative, so that the local area could be represented better. In order to suppress the interference of useless information and capture more useful local feature details, three kinds of channel compression operators were used to perform attention pooling in the local area, so as to calculate the attention distribution of channel features. At the sametime, feature interpolation was used to classify each point to achieve the purpose of overall point cloud segmentation. Finally, the ability of the experimental model to capture channel geometric features was verified by comparing the segmentation results of two point cloud datasets with different channel dimensions. The results show that the proposed model can effectively improve the segmentation accuracy of 3D point cloud classes and parts. It can maintain the robustness of the segmentation effect in the case of different number of channels. © 2023 SPIE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Handling Class Imbalance in Online Transaction Fraud Detection

引用

computers, Materials & Continua 2022年第2期70卷 2861-2877页

作者： Kanika Jimmy Singla Ali Kashif Bashir Yunyoung Nam Najam UI Hasan Usman Tariq School of Computer Science and Engineering Lovely Professional UniversityPunjabIndia Department of Computing and Mathematics ManchesterMetropolitan UniversityUK&School of Electrical Engineering and Computer ScienceNational University of Science and TechnologyIslamabadPakistan Department of Computer Science and Engineering Soonchunhyang UniversityAsan31538Korea Department of Electrical and Computer Engineering Dhofar UniversitySalalahOman College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia

With the rise of internet facilities,a greater number of people have started doing online transactions at an exponential rate in recent years as the online transaction system has eliminated the need of going to the bank physically for every ***,the fraud cases have also increased causing the loss of money to the ***,an effective fraud detection system is the need of the hour which can detect fraudulent transactions automatically in ***,the genuine transactions are large in number than the fraudulent transactions which leads to the class imbalance *** this research work,an online transaction fraud detection system using deep learning has been proposed which can handle class imbalance problem by applying algorithm-level methods which modify the learning of the model to focus more on the minority class i.e.,fraud transactions.A novel loss function named Weighted Hard-Reduced Focal Loss(WH-RFL)has been proposed which has achieved maximum fraud detection rate i.e.,True PositiveRate(TPR)at the cost of misclassification of few genuine transactions as high TPR is preferred over a high True Negative Rate(TNR)in fraud detection system and same has been demonstrated using three publicly available imbalanced transactional ***,Thresholding has been applied to optimize the decision threshold using cross-validation to detect maximum number of frauds and it has been demonstrated by the experimental results that the selection of the right thresholding method with deep learning yields better results.

关键词： Class imbalance deep learning fraud detection loss function thresholding

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：