检索结果-内蒙古大学图书馆

2nd IEEE International Conference for Women in Innovation, Technology and Entrepreneurship, ICWITE 2024

作者： Sethi, Vikas Kumar, Rajneesh Mehla, Stuti Department of Computer Science and Engineering Ambala Mullana India Panipat Institute of Engineering and Technology Department of Computer Science and Engineering Panipat India

ISBN: (纸本)9798350383287

COVID-19 crisis expedited the spread of e-commerce, moving beyond luxury goods and services and towards new businesses, product categories and basic necessities that are important to many people. Customers can have access to a wide range of products from the comfort and security of their homes but still have trusting issues while purchasing online. Online feedback either comments or ratings given by customers, has the power to affect how consumers make purchasing decisions. This meteoric expansion of digitized information and number of users over internet brought the use of recommender systems as a significant solution by offering more proactive and individualized information services and enable users to quickly narrow their choices and make wise ***, the majority of existing recommendation models have poor accuracy issues as a result of data scarcity and cold start issues because recommender systems only have a limited amount of explicit data and this also lead to trust issue where users are fear of being taken advantage due to misleading information on the e-commerce websites. To solve this problem and provide quality recommendations, a new trust-based approach CNN with Autoencoder Attention Mechanism (CAAM) is proposed. CAAM uses static and dynamic trust combined with the user-item preferences and pass through the auto-encoder to reduce noise and make encoded features visible. After that convolution is used to combine encoded features with user and item features in latent space to provide nonlinear mapping and increase the reliability of features and to improve the recommendations which ultimately lead to improve the trust of people over *** Epinions dataset is used to evaluate the concept in a number of measures. © 2024 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Deep ensemble optimal classifier-based software defect prediction for early detection and quality assurance

Journal of Umm Al-Qura University for Engineering and Archit...

引用

Journal of Umm Al-Qura University for engineering and Architecture 2025年 1-12页

作者： Srinivas, Kalyanapu Janapati, Krishna Chaithanya Sai Kiran, Mungalched Sudheer Reddy, Davu Vinay, Thota Vamshi Yashwanth, Choula Department of Computer Science and Engineering Dhanekula Institute of Engineering and Technology Andhra Pradesh Vijayawada India Department of Electronics and Communication Engineering Vardhaman College of Engineering Telangana Hyderabad India Department of Computer Science and Engineering (Data Science) Malla Reddy Engineering College and Management Sciences Medchal Telangana Kistapur India

software Defect Prediction (SDP) is critical in identifying fault-prone modules during the software development life cycle, enhancing software quality, and reducing maintenance costs. However, existing SDP models face significant challenges, including high false positive rates and severe class imbalance between defect-prone and non-defect modules, which hinder practical model training and accurate defect detection. To overcome these challenges, this study proposes a robust and efficient SDP architecture that integrates several advanced techniques to enhance predictive accuracy and model reliability. The methodology begins with comprehensive data preprocessing, incorporating normalization to standardize feature scales and outlier detection to eliminate noise and improve data quality. To address the inherent class imbalance in the dataset, the minority oversampling by synthetic data (MOSD) technique is employed to generate synthetic samples for the minority class, thus achieving a more balanced distribution. Following this, an Adaptive sequential K-best (ASKB) feature selection strategy is implemented to identify and retain the most relevant features, effectively reducing dimensionality while preserving critical information. Finally, the weighted random forest (WRF) classifier is utilized, which assigns appropriate weights to training instances, enabling improved classification performance, especially for minority class instances. The proposed methodology achieved an accuracy of 99.119%, a precision of 99.431%, a recall of 99.122%, and an F1-score of 99.333%. © The Author(s) 2025.

关键词： Adaptive sequential K-best Class imbalance Data preprocessing Feature selection Minority oversampling Predictive modeling software defect prediction Synthetic data Weighted random forest

来源：评论

学校读者我要写书评

暂无评论

Metaheuristic-Driven Two-Stage Ensemble Deep Learning for Lung/Colon Cancer Classification

引用

computers, Materials & Continua 2024年第9期80卷 3855-3880页

作者： Pouyan Razmjouei Elaheh Moharamkhani Mohamad Hasanvand Maryam Daneshfar Mohammad Shokouhifar Department of Electrical&Computer Engineering Valie-e-Asr University of RafsanjanKerman***Iran International Academic Relations Office(IRO) Computer Science DepartmentUniversity of HalabjaHalabja46018Iraq Department of Computer Engineering University of Mohaghegh ArdabiliArdabil***Iran Department of Biomedical Engineering Islamic Azad University of MashhadMashhad***Iran Department of Electrical&Computer Engineering Shahid Beheshti UniversityTehran***Iran

This study investigates the application of deep learning,ensemble learning,metaheuristic optimization,and image processing techniques for detecting lung and colon cancers,aiming to enhance treatment efficacy and improve survival *** introduce a metaheuristic-driven two-stage ensemble deep learning model for efficient lung/colon cancer *** diagnosis of lung and colon cancers is attempted using several unique indicators by different versions of deep Convolutional Neural Networks(CNNs)in feature extraction and model constructions,and utilizing the power of various Machine Learning(ML)algorithms for final ***,we consider different scenarios consisting of two-class colon cancer,three-class lung cancer,and fiveclass combined lung/colon cancer to conduct feature extraction using four *** extracted features are then integrated to create a comprehensive feature *** the next step,the optimization of the feature selection is conducted using a metaheuristic algorithm based on the Electric Eel Foraging Optimization(EEFO).This optimized feature subset is subsequently employed in various ML algorithms to determine the most effective ones through a rigorous evaluation *** top-performing algorithms are refined using the High-Performance Filter(HPF)and integrated into an ensemble learning framework employing weighted *** findings indicate that the proposed ensemble learning model significantly surpasses existing methods in classification accuracy across all datasets,achieving accuracies of 99.85%for the two-class,98.70%for the three-class,and 98.96%for the five-class datasets.

关键词： Lung cancer colon cancer feature selection electric eel foraging optimization deep learning ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Resource scheduling in cloud environment using particle swarm search algorithm

引用

International Journal of Cloud Computing 2024年第4期13卷 330-352页

作者： Majhi, Malay Kumar Kabat, Manas Ranjan Sahoo, Satya Prakash Department of Computer Science and Engineering Veer Surendra Sai University of Technology Sambalpur India

Cloud computing has gained significant popularity as a platform for processing large-scale data analytics, offering benefits such as high availability, robustness, and cost-effectiveness. However, job scheduling in cloud systems presents a major challenge, as it directly impacts execution time and operational costs. To address these issues, this paper presents a novel multi-adaptive convergent particle swarm optimisation (MAC-PSO) algorithm designed to decrease the failure rate, minimise makespan values, and enhance resource utilisation. The round Robin scheduling method aids in task execution by determining the appropriate time-space allocation. The proposed algorithm’s performance is compared to that of the TLBO algorithm, demonstrating that MAC-PSO outperforms both TLBO and the original PSO. Moreover, a comprehensive analysis is proposed to evaluate the performance metrics within the MAC-PSO algorithm. Notably, MAC-PSO effectively increases the ratio of solutions that dominate previous algorithmic approaches and identifies a greater number of solutions that cater to user preferences. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

GWO-CNN: Trust and Intelligent Recommendation system based model to improve marketing strategies on e-commerce 2

GWO-CNN: Trust and Intelligent Recommendation system based m...

引用

2nd IEEE International Conference for Women in Innovation, Technology and Entrepreneurship, ICWITE 2024

作者： Sethi, Vikas Kumar, Rajneesh Mehla, Stuti Department of Computer Science and Engineering Mullana Ambala India Panipat Institute of Engineering and Technology Department of Computer Science and Engineering Panipat India

ISBN: (纸本)9798350383287

In 21st century, AI-based intelligent recommendation system uses rating predictions, which are frequently utilized and helps users swiftly filter down their options and make informed judgements from an abundance of material. Nevertheless, as recommender systems only contain a small number of explicit data and are subject to cold start and sparsity issues, the majority of existing recommendation models have poor accuracy. The majority of conventional algorithms used to make recommendations simply take into account the straight-forward connection among consumers and products, largely ignoring the interests, prospective employment factors, or other social aspects of the products being *** this study focus is on user preferences, as they are key to tailoring recommendations to individual needs. By combining trust values with user preferences, the system can recommend items that not only have a high trust value but also align with a user's individual tastes or needs. For this proposed model used feature matrix, Grey Wolf Optimizer (GWO) and Convolution Neural Network (CNN). GWO is an optimization algorithm used to find optimal weights or parameters for the recommendation system. Once the GWO has found optimal or near-optimal weights, they are integrated into the feature matrix. These weights can help prioritize or scale certain features to improve the recommendation quality. Then CNN will extract patterns and relationships from the feature matrix. Based on the processed feature matrix, the system predicts the top 'K' items to recommend to the user. © 2024 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Enhancing Deep Learning Models for Sentiment Analysis Integrating Texts and Emojis: A Comprehensive Survey 10

Enhancing Deep Learning Models for Sentiment Analysis Integr...

引用

10th International Conference on Communication and Signal Processing, ICCSP 2024

作者： Suresh Kumar, S. Gayathri, D. Shugavaneshwar, R. Department of Computer Science and Engineering Tamilnadu Chennai India Rajalakshmi Engineering College Department of Computer Science and Engineering Tamilnadu Chennai India

ISBN: (纸本)9798350353068

Sentiment analysis is used to get meaningful insights from data that is being retrieved from various resources or social media platforms. Sentiment analysis plays an important role in making crucial decisions that can improve the existing status significantly. This survey addresses and compares various machine learning models and deep learning models that have been recently employed for efficient sentiment analysis. In general, people use both texts and emojis to express their emotions. Considering the above fact, the proposed system addresses reviews that integrate both texts and emojis. The convolution neural network (CNN) is trained with a dataset that contains a cluster of texts and emojis. However, the texts and emojis are handled separately by processing them independently for efficient results. © 2024 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

A Predictive Model of the Stock Market Using the LSTM Algorithm with a Combination of Exponential Moving Average (EMA) and Relative Strength Index (RSI) Indicators

引用

Journal of The Institution of Engineers (India): Series B 2024年第5期105卷 1145-1157页

作者： Dhokane, Rahul Maruti Agarwal, Sohit Computer Science and Engineering Department Suresh Gyan Vihar University Rajasthan Jaipur India

This research paper has focused on the integration of promising stock market indicators such as the relative strength index (RSI) and different versions of the exponential moving average (EMA) (i.e., 50-day, 100-day, and 150-day EMA) with the long short-term memory (LSTM) machine learning algorithm for stock price prediction. LSTM is the most robust version of recurrent neural network because it can handle the "vanishing gradient" problem effectively and handle lengthy time series data. The selected dataset was taken from NSE India using Yahoo Finance. In our proposed research, we used RSI and EMA data along with basic features such as open, high, low, close, and volume (OHLCV) information. The selected technical indicators and OHLCV data act as input features for the LSTM model. The results show that the integration of technical indicators along with traditional OHLCV improves the performance of the stock closing price prediction model. The evaluation metrics used in this research are the RMSE, MAPE, and R2 score. The improvements in the R2 score and decreases in the RMSE and MAPE indicate that the proposed technique performs well in stock closing price prediction. The proposed technique helps to improve intraday trading by predicting the closing price of the stock for the next day and the trends of selected stocks in the near term. © The Institution of Engineers (India) 2024.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Efficacy of Ensemble Learning Method over Individual Classifier for Rainfall Forecasting in Eastern India

引用

Journal of The Institution of Engineers (India): Series B 2024年第4期105卷 929-939页

作者： Karmakar, Rahul Kundu, Saranagta Biswas, Saroj Kumar Tripathi, Deeksha Department of Computer Science The University of Burdwan West Bengal Bardhaman India Department of Computer Science and Engineering National Institute of Technology Assam Silchar India

Severe rainfall has seriously threatened human health and survival. Natural catastrophes such as floods, droughts, and many other natural disasters are caused by heavy rains, which people worldwide have to deal with throughout the year. Accurate rainfall forecasting is essential in nations like India where cultivation is the main occupation. Machine learning (ML) techniques are more effective than many other strategies because of the unpredictable nature of rainfall. Ensemble learning (EL) methods yield higher accuracy than ML specific classifiers. Therefore, this paper proposes an EL-based prediction model for not only a specific state of India but for the entire eastern India region, which includes ten states: West Bengal, Jharkhand, Bihar, Odisha, Assam, Tripura, Mizoram, Manipur, Nagaland and Meghalaya. We acquired the rainfall data for eastern India using NASA’s power data access view for 22 years (2000–2021). In this model, apart from classification feature selection is done using Pearson correlation and ANOVA. This study looks at the accuracy of several different classifiers, including DT, LR, and SVM. The acceptable accuracy of 96.53% for rainfall prediction in eastern India was determined using an ensemble model that includes the XGBoost ensemble technique and the classifiers DT, LR, and SVM. The findings of our experiment reveal that EL-based prediction model outperforms the individual classifiers utilized in the experiment. © The Institution of Engineers (India) 2024.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

An Initial Risk Assessment for Multimodal with LSTM-Based Trust Evaluation Framework for Autonomous Vehicle Security

引用

SN computer science 2025年第2期6卷 1-15页

作者： Renjith, P.N. Balasubramani, S. Ramesh, K. Patnala, Eswar School of Computer Science and Engineering Vellore Institute of Technology Chennai Campus Chennai India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India Department of Computer Science and Engineering Sri Krishna College of Engineering and Technology Coimbatore India

This research aims to develop a new approach to increase the safety and reliability of Autonomous Vehicle (AV) through the proposed risk assessment framework, supported by the trust evaluation approach derived from a machine learning algorithm. This work proposes a comprehensive risk assessment model with real-time sensor data, Vehicle-to-Vehicle (V2V), key communication reliability, environmental cognition, and Improved Long Short-Term Memory (I-LSTM). This framework is multidimensional compared to most conventional models, focusing primarily on assessing individual threat factors. Here, the machine learning portion is designed to evaluate and predict trust by quickly processing vast amounts of information from sensors, signals, and prior operation history. Such an approach to trust assessment enables the system to continuously evaluate the dependability of automated vehicle operation and identify threats to security with improved accuracy. The effectiveness of the performance of this method is substantiated by a number of stand-alone and live scenarios, where the model's performance is higher in perceiving possible risks, avoiding threats, and enhancing safety than the conventional approaches. The findings suggest that the safety regulations of the AVs will be improved by using a multi-dimensional risk assessment model and integrating the I-LSTM trust rating with 95.5% accuracy, 96.7% risk identification, and 180 ms response time. This will cause AV and its surrounding environment to be accepted by the public and used on the roads. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Autonomous vehicles LSTM model Machine learning Risk assessment Trust evaluation

来源：评论

学校读者我要写书评

暂无评论

Real-Time Speech Enhancement Based on Convolutional Recurrent Neural Network

引用

Intelligent Automation & Soft Computing 2023年第2期35卷 1987-2001页

作者： S.Girirajan A.Pandian Department of Computer Science and Engineering School of ComputingSRM Institute of Science and EngineeringKattankulathurTamil NaduIndia

Speech enhancement is the task of taking a noisy speech input and pro-ducing an enhanced speech *** recent years,the need for speech enhance-ment has been increased due to challenges that occurred in various applications such as hearing aids,Automatic Speech Recognition(ASR),and mobile speech communication *** of the Speech Enhancement research work has been carried out for English,Chinese,and other European *** a few research works involve speech enhancement in Indian regional *** this paper,we propose a two-fold architecture to perform speech enhancement for Tamil speech signal based on convolutional recurrent neural network(CRN)that addresses the speech enhancement in a real-time single channel or track of sound created by the *** theﬁrst stage mask based long short-term mem-ory(LSTM)is used for noise suppression along with loss function and in the sec-ond stage,Convolutional Encoder-Decoder(CED)is used for speech *** proposed model is evaluated on various speaker and noisy environments like Babble noise,car noise,and white Gaussian *** proposed CRN model improves speech quality by 0.1 points when compared with the LSTM base model and also CRN requires fewer parameters for *** performance of the pro-posed model is outstanding even in low Signal to Noise Ratio(SNR).

关键词： Speech enhancement convolutional encoder-decoder long short-term memory noise suppression speech restoration

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：