检索结果-内蒙古大学图书馆

2nd International Conference on Data science and Information System, ICDSIS 2024

作者： Nabi, Shaik Abdul Naick, B. Raveendra Almusawi, Muntather Shruthi, B.S. Rana Veer Samara Sihman Bharattej, R. Avn Institute Of Engineering & Technology Department Of Computer Science And Engineering Telangana Hyderabad India Tirupati India The Islamic University Department Of Computers Techniques Engineering College Of Technical Engineering Najaf Iraq Nitte Meenakshi Institute Of Technology Department Of Civil Engineering Bengaluru India Saint Leo University Department Of Computer Science FL United States

ISBN: (纸本)9798350381665

In this modern era of Industry 4.0, efficiency and safety of industrial machines are a primary concern in trade sectors and prediction of Remaining Useful Life (RUL) of an engine helps to plan effectively maintenance operation. However, the Predictive Maintenance is to acquire reliable prognostics and estimation RUL in turbofan engines is a difficult task. To solve this problem, an Empirical Mode Decomposition based Long Short-Term Memory (EMD-LSTM) for prediction of RUL in aircraft engine utilizing C-MAPSS dataset. Initially, the most relevant sensor signals are selected by Correlation analysis and filtered using Moving Median Filter (MMF). After, the signals are normalized by Z-score technique to train the prediction model and signals are fed as input to proposed EMD-LSTM approach for prediction of RUL span of the engine. The evaluation results of the proposed method using performance metrics are Root Mean Square Error (RMSE), Score, Accuracy and Precision. The presented EMD-LSTM model achieved great accuracy of 99.3%, Precision of 98.9%, RMSE of 13.02 and Score of 282.0 which is greater than the previous models like Deep Convolutional Neural Network (DCNN)-LightGBM, LSTM, Graph CN (GCN), DCNN and Denoising Online Sequential Extreme Learning Machine (DOSELM). © 2024 IEEE.

关键词： Empirical mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Attentive Implicit Relation Embedding for Event Recommendation in Event-based Social Network 23

Attentive Implicit Relation Embedding for Event Recommendati...

引用

4th International Conference on Computing, Networks and Internet of Things, CNIOT 2023

作者： Liang, Yuan School of Computer Science and Engineering North China Institute Science and Technology Hebei China

ISBN: (纸本)9798400700705

The event-based social network (EBSN) is a new type of social network that combines online and offline networks, and its primary goal is to recommend appropriate events to users. Most studies do not model event recommendations on the EBSN platform as graph representation learning, nor do they consider the implicit relationship between events, resulting in recommendations that are not accepted by users. Thus, we study graph representation learning, which integrates implicit relationships between social networks and events. First, we propose an algorithm that integrates implicit relationships between social networks and events based on a multiple attention model. Then, the user modeling and event modeling models are fused using a multiattention joint learning mechanism to capture the different impacts of social and implicit relationships on user preferences, improving the recommendation quality of the recommendation system. Finally, the effectiveness of the proposed algorithm is verified in real datasets. © 2023 ACM.

关键词： User profile

来源：评论

学校读者我要写书评

暂无评论

A Study of the Unbalanced Image Dataset for Classification Problem 12

A Study of the Unbalanced Image Dataset for Classification P...

引用

12th International Conference on System Modeling and Advancement in Research Trends, SMART 2023

作者： Sharma, Davesh Kumar Punhani, Akash Srm Institute of Science and Technology Department of Computer Science and Engineering Modinagar Ghaziabad India

ISBN: (纸本)9798350369861

In the case of experimental data it is evident that the dataset obtained is unbalanced. The main reason for the same is the probability of the occurrence of a particular event in real life. As these events have very less probabilities hence the collection of such sample data is very difficult. Therefore, various approaches have been suggested to overcome this problem. This paper compares the two approaches for handling the unbalanced data. In the first approach, the minimum class with random selection was used to balance the data and in the second approach, the maximum class with random duplicate is used to balance the data. Based on the results of the sugarcane disease detection using densenet with SVM it was evident that incorporating the maximum data available is helping the machine learning model to more effectively. © 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

Statistical Detection of Malicious iOS Apps through Ensemble and Active Learning 2023

Statistical Detection of Malicious iOS Apps through Ensemble...

引用

15th International Conference on Contemporary Computing, IC3 2023

作者： Bhatt, Arpita Jadhav Agarwal, Parul Department of Computer Science & Engineering and Information Technology Jaypee Institute of Information Technology India

ISBN: (纸本)9798400700224

iOS is one of the most broadly used mobile operating systems after Android. In today's era, smartphones are widely used to perform several tasks such as net banking, GPS tracking, ordering products, etc. One of the main features of smartphones is that their capabilities can be expanded by installing third-party apps. However, these apps pose privacy threats to the user as they contain a lot of user's personal information, which may be vulnerable to attackers. Background studies have identified that a lot of user's personal and sensitive data is stored on smartphones and thus, they have become a perfect target for privacy threats in the whole mobile ecosystem. Machine learning techniques to detect malware apps have offered promising results for the Android platform whereas nominal work has been done for the iOS platform. In this paper, we are incorporating various machine learning techniques to detect malicious iOS apps from several categories. Some of the ensemble learning techniques with different classification algorithms are inculcated to enhance the precision of classifiers. A weighted average method on active and ensemble learning has been proposed which proved to be more efficient as compared to other machine learning techniques in most of the categories. Our empirical analysis has demonstrated that the proposed technique is statistically significant than active and ensemble learning. © 2023 ACM.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Multi Head Graph Attention for Drug Response Predicton 3

Multi Head Graph Attention for Drug Response Predicton

引用

3rd International Conference on Smart Data Intelligence, ICSMDI 2023

作者： Selvi Rajendran, P. Sivannarayna, M. Computer Science and Engineering School of Computing Hindustan Institute of Technology and Science Chennai India

ISBN: (纸本)9781665464871

Precision medicine is based on curing diseases based on a patient's genetic profile, lifestyle, and environmental factors. This method improves clinical trial success rates and speed up drug regulatory approval. Predicting tumour vulnerability to specific anti-cancer therapy is critical for the successful implementation of precision medicine. Drug combinations have been shown to be very effective in cancer treatment to lower the drug resistance and improve the therapeutic effectiveness. The experiments carried out in all these therapeutic combinations have become expensive and time-consuming as a result of the increasing number of anti-cancer drugs. Large-scale drug response testing on cancer cell lines might help to understand the way drugs react with cancer cells. This study proposes a multi head graph attention network to perform drug response prediction. © 2023 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Clustering Algorithms: Scenario Based on Boston Crime Dataset 26

Comparative Study of Clustering Algorithms: Scenario Based o...

引用

26th International Conference on computer and Information technology, ICCIT 2023

作者： Jerin, Jubaida Quader Khan, Nusrat Kaniz Biswas, Swapnil Sharmin, Nusrat Military Institute of Science and Technology Department of Computer Science and Engineering Dhaka1216 Bangladesh

ISBN: (纸本)9798350359015

In the study of crime analysis, using clustering techniques to understand patterns in crime-prone areas is crucial. This research paper focuses on grouping regions with higher crime rates using various clustering methods and then thoroughly compares and evaluates the results. We have applied six different clustering methods: K-Means, K-Prototypes, Agglomerative Hierarchical Clustering, DBSCAN Clustering, Fuzzy C-Means clustering, and Gaussian Mixture Models (GMMs) to the Boston City Crime Dataset. These methods were carefully examined to understand their performance. For example, K-Means and K-Prototypes create clusters, Agglomerative Clustering organizes data hierarchically, Fuzzy C-Means extends the principles of K-Means for softer clustering, DBSCAN uses a unique approach based on graph density, and GMM effectively handles complex data structures while allowing for probabilistic *** research enhances the field by introducing inventive algorithmic applications, systematically assessing their effectiveness, rigorously evaluating their performance, and providing practical insights into their implementation for analyzing crime data on extensive datasets, along with aiming to demonstrate the effectiveness of different clustering techniques in identifying areas or clusters of higher crime rates. © 2023 IEEE.

关键词： Agglomerative Clustering Crime Zone DBSCAN Fuzzy C-Means Gaussian mixture models (GMMs) K-Means Clustering K-Prototypes Clustering

来源：评论

学校读者我要写书评

暂无评论

Image Restoration with Noise Diffusion: Recovering Lost Clarity and Details

Image Restoration with Noise Diffusion: Recovering Lost Clar...

引用

2024 Asian Conference on Intelligent Technologies, ACOIT 2024

作者： Yadav, Harsh Sisodia, Dilip Singh Department of Information Technology National Institute of Technology Raipur Raipur India Department of Computer Science and Engineering National Institute of Technology Raipur Raipur India

ISBN: (纸本)9798350374933

Image enhancement is a crucial task in various domains, including photography, medical imaging, and surveillance. However, existing methods often struggle to effectively address both noise reduction and resolution enhancement simultaneously. This paper proposes a novel approach that merges a custom-built diffusion model with the Enhanced Super-Resolution Generative Adversarial Network (ESRGAN) to achieve comprehensive image enhancement. The diffusion model is employed for efficient noise removal, while ESRGAN is utilized for high-quality super-resolution. By integrating these two powerful techniques, we create a synergistic effect that amplifies the benefits of each model, leading to superior image quality. The merged model is fine-tuned on a diverse dataset to ensure optimal performance across various scenarios. Extensive experiments demonstrate the effectiveness of our approach in enhancing image quality, outperforming in-dividual models in both noise reduction and resolution enhancement tasks. The proposed method offers versatility and can be deployed in real-time applications, which makes it a valuable tool for practitioners and researchers in the field of image processing. © 2024 IEEE.

关键词： Noise abatement

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Multi-Model and Uni-Model Approaches using Time Distributed Bidirectional LSTM for Multidata Sentiment Analysis 14

Comparative Analysis of Multi-Model and Uni-Model Approaches...

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Gupta, Krati Parmar, Mahesh Madhav Institute of Technology & Science Dept. of Computer Science and Engineering Gwalior India

ISBN: (纸本)9798350335095

The sentiment of the data contained in a text can be determined by analysis. This sentiment can be good, negative, or neutral. When carrying out this research, one may choose to employ either a uni-model or a multi-model technique. In the uni-model method, both the training and the analysis are performed using just a single model. The application of this strategy is uncomplicated and uncomplicated, but it might not be able to make sense of complicated or different facts, which would lead to wrong findings. Instead, the multi-model technique utilizes a number of different models, each of which is designed to examine a particular aspect of the data or a particular kind of attitude. This allows the multi-model strategy to produce more accurate results. The results of several different models might be combined in order to obtain a more in-depth understanding of feelings. This method is more accurate overall and captures more complex expressions of emotion, but it requires more time and money to train personnel and put into practice. The evaluation of metrics was carried out using Multimodal and mono Model with Time Distributed Bidirectional LSTM in this research. Both the loss and the accuracy. The Multi-Model achieves the highest accuracy of 99.71 percent for the train, while the validation accuracy achieves 99.32 percent, and the Multi-Model achieves the least loss of 0.010 percent. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

A Comparison of Different Learning Algorithms for Wildlife Detection and Classification in Animal Conservation Applications 3

A Comparison of Different Learning Algorithms for Wildlife D...

引用

3rd International Conference on Artificial Intelligence and Smart Energy, ICAIS 2023

作者： Mangaleswaran, M. Azhagiri, M. Srm Institute of Science and Technology Department of Computer Science and Engineering Ramapuram Chennai India

ISBN: (纸本)9781665462167

In order to track animal movement patterns, habitat use, population demographics, human-wildlife conflict, vehicle-animal collisions, snare and poaching occurrences, and epidemics, it is essential to monitor wildlife. Over time, accidents between wildlife and vehicles have increased in frequency on both rural and hilly roads and highways. Road deaths are sometimes caused by wildlife crossing the road at inopportune moments. The identification and categorization of animals from picture and video sequences is a popular area of study. Current methods for wildlife monitoring depend on image processing. This study provides a reliable method for detecting wildlife and divides it into two categories: animal-human conflict and animal-vehicle collision. Different learning approaches are employed to classify the animals with the use of datasets and a live motion sensor. Applications for wildlife have employed machine learning and deep learning extensively. This article discusses a variety of learning techniques and offers the authors' answers. There may be a chance to identify and categories wildlife when it enters a living area, an agricultural region, or a roadway. Various authors provide various classification and identification strategies based on Camera trap and Dataset. © 2023 IEEE.

关键词： Animals

来源：评论

学校读者我要写书评

暂无评论

Deploying On-Device AIGC Inference Services in 6G via Optimal MEC-Device Offloading

IEEE Networking Letters

引用

IEEE Networking Letters 2024年第4期6卷 232-236页

作者： Zhou, Changshi Liu, Weiqi Han, Tao Ansari, Nirwan New Jersey Institute of Technology Department of Electrical and Computer Engineering NewarkNJ07102 United States Auburn University at Montgomery Department of Computer Science and Computer Information Systems MontgomeryAL36117 United States

From AI-assisted art creation to large language model (LLM)-powered ChatGPT, AI-generated contents and services are becoming a transforming force. It calls for the telecom industry to embrace the prospects of AIGC services and face the unique challenges posed by incorporating generative model services into the AI-native 6G wireless network paradigm. We propose enabling AIGC inference services on mobile devices by optimizing MEC-device computing offloading, through which AIGC task latency is minimized by reinforcement learning based policy agent in a computing resource constrained and bandwidth limited wireless environment. Simulation results are presented to demonstrate the performance advantage. © 2019 IEEE.

关键词： Reinforcement learning

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：