检索结果-内蒙古大学图书馆

Content recommendation based on recognised Emotion

Content recommendation based on recognised Emotion

2023 International Conference on Recent Advances in Electrical, Electronics, Ubiquitous Communication, and Computational Intelligence, RAEEUCCI 2023

作者： Challa, Sireesha Gowri, Manohari V. Roobini, M.S. Nandhini, P. Daphine Desona Clemency, A.C. Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350337426

E-commerce, video websites, and social networking sites are just a few examples of where recommendation algorithms are currently being used. As the amount and variety of data used in recommendation systems grows, more and more of it will be unstructured multimodal data, including text, images, and videos. Yet, it is difficult to employ unstructured multimodal data to enhance the effectiveness of recommendation schemes because of the illustration gap between different modalities. In this paper, we present a new multimodal framework for user-driven ensemble modelling based on the recommendation of mood descriptions. In contrast to standard approaches, our video reference formulation makes use of not just the audio stream but also the face (emotion) and textual modalities that together make up a video document's elementary data. Audio data is used as input by algorithms like Gaussian Naïve Bayes (GNB), Logistic Regression (LR), and Convolutional Neural Network (CNN), whereas text data is used by methods like, LR, Long-short Term Memory (LSTM), and Naive Bayes. The user's current disposition is used to inform recommendations for appropriate music, quotes, etc. generated by these ensemble models. Comprehensive experiments on real-world datasets demonstrate that, across a wide range of assessment measures, the proposed ensemble model greatly outperforms the state-of-the-art baselines. © 2023 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

CVS-FLN: a novel IoT-IDS model based on metaheuristic feature selection and neural network classification model

引用

Multimedia Tools and Applications 2024年第39期83卷 86557-86591页

作者： Geetha, R. Jegatheesan, A. Dhanaraj, Rajesh Kumar Vijayalakshmi, K. Nayyar, Anand Arulkumar, V. Velmurugan, J. Thavasimuthu, Rajendran Department of Computing Technologies SRM Institute of Science and Technology Kattankulathur Campus Chengalpattu Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamil Nadu Chennai India Pune India Department of Computer Science and Engineering Ramco Institute of Technology Tamil Nadu Rajapalayam India Graduate School Faculty of Information Technology Duy Tan University Da Nang550000 Viet Nam School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore India

The Internet of Things (IoT) is one of the technologies that will be used all over the world in the future, and its security and privacy features are the primary concerns. However, the most critical limitation to overcome before the IoT's widespread use is addressing its security concerns. One of the most critical tasks to address the security problems posed by the IoT is the detection of network intrusions. Intrusion Detection Systems (IDS) for the IoT face substantial challenges because of the functional and physical diversity of the devices. In the rapidly growing IoT industry, the use of IDS is essential for ensuring security since many devices communicate efficiently. IDS are crucial for continual monitoring and responding to any security risks, ensuring the integrity and reliability of interconnected IoT networks. The primary objective of this research is to develop a feature-selection-based intrusion classification model. Therefore, we develop an IoT-IDS feature selection-based classification model to detect intrusions. We propose a metaheuristic algorithm, the Chaotic Vortex Search (CVS) algorithm, for feature selection. The Fast-Learning Network (FLN), an artificial neural network (ANN) model, is additionally proposed for classification. We use the IDS datasets, such as CIC IDS-2017 and BoT-IoT, to evaluate our research model. To test and validate the proposed model, extensive experiments were performed, and the outcomes stated that the CVS-FLN model achieved 99.77% accuracy, 99.92% specificity, 99.60% precision, 99.81% detection rate, and a 99.72% F1-score in the CIC IDS dataset, and 99.68% accuracy, 99.30% precision, 99.83% specificity, 99.11% detection rate, and a 99.21% F1-score in evaluating the BoT-IoT dataset. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Predicting Lung Cancer Disease Using Optimized Weighting-Based Enhanced Neural Network Classification 3

Predicting Lung Cancer Disease Using Optimized Weighting-Bas...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Chitra, T. Hemanth, S.V. Karthikeyan, S. Reddy, Vallem Ranadheer Banupriya, K.M. Amirthayogam, G. Christian College of Engineering and Technology Department of Electronics and Communication Engineering Tamilnadu Oddanchatram624619 India Hyderabad Institute of Technology and Management Department of Computer Science and Engineering Telangana Hyderabad501401 India PSNA College of Engineering and Technology Department of Electronics and Communication Engineering Tamil Nadu Dindigul624622 India Vaagdevi Engineering College Department of Computer Science and Engineering Telangana Bollikunta506005 India Arunai Engineering College Department of Computer Science and Engineering Tamil Nadu Tiruvannamalai606603 India Department of Information Technology Tamilnadu Chennai603103 India

ISBN: (纸本)9798350372120

Lung cancer is a highly lethal disease, claiming the lives of approximately 1 million individuals annually. Cancer is characterized by abnormal and rapid cell growth, making it difficult to control, though early diagnosis through Computed Tomography (CT) scan images can significantly improve chances of survival. However, detecting lung cancer early is challenging and can increase the risk of complications such as infection, inflammation, and tumor growth in the lungs. Moreover, the current methods for analyzing lung cancer prognosis have low accuracy. To solve this problem, we proposed an Optimized Weighting-Based Enhanced Neural Network (OWENN) method to classify patients based on attributes accurately. Furthermore, they utilize the Adaptive Median Filter (AMF) technique during image pre-processing to calculate the mean value of each pixel and remove noise. Moreover, Improved Particle Swarm Optimization (IPSO) can be implemented to extract tumors from lung images efficiently. Finally, the OWENN method improves the accuracy of cancer or non-cancer detection by classifying patients based on their selected attributes. Afterward, the experimental results indicate that the suggested OWENN approach can attain lung cancer prediction by evaluating sensitivity, precision, accuracy, and time delay. © 2024 IEEE.

关键词： Median filters

来源：评论

学校读者我要写书评

暂无评论

Robust Prediction of Alcoholism from EEG Signals Using Auto-Encoder 14

Robust Prediction of Alcoholism from EEG Signals Using Auto-...

引用

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

作者： Aarthi, B. Kulkarni, Raj Sanjay Chandra Kiran, K. Vinod, S. SRM Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350335095

The diagnosis of alcoholism (substance abuse) is crucial due to its impact on individuals, society, and healthcare systems worldwide. Electroencephalography (EEG) signals have been shown to contain valuable information about the effects of alcoholism on the brain, and can potentially be used as a non-invasive tool for early detection and monitoring. In this study, we proposed an auto-encoder model for predicting alcoholism from EEG signals, which achieved robust and accurate performance even in the presence of noise and variability in the data. We evaluated the model using multiple classification algorithms, including Logistic Regression, Random Forest Classifier, AdaBoost Classifier, and AutoEncoders. The auto-encoder model (consisting of Bi-LSTMs and ReLU, Sigmoid activation for Dense and output layers respectively) outperformed the other algorithms, achieving an accuracy of 65.5% on the test set, while Logistic Regression achieved an accuracy of 55%, Random Forest Classifier achieved 58%, and AdaBoost Classifier achieved 58.4%. These results demonstrate the effectiveness of auto-encoder models for biomedical signal processing and provide a promising avenue for future research in this area, including the investigation of more complex architectures and feature engineering techniques, and the use of larger and more diverse datasets for training and evaluation. This research contributes to the fields of biomedical signal processing, neurophysiology, and neuroimaging, offering insights into brain activity related to alcoholism and highlighting the importance of non-invasive diagnosis and early detection in tackling alcoholism disorders and their societal impact. © 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

Sorted Range Selection and Range Minima Queries 2nd

Sorted Range Selection and Range Minima Queries

引用

2nd International Conference on Applied Algorithms, ICAA 2025

作者： Akram, Waseem Saxena, Sanjeev Department of Computer Science and Engineering Indian Institute of Technology Kanpur208016 India

ISBN: (纸本)9783031845420

Given an array A[1 : n] of n elements drawn from an ordered set, the sorted range selection problem is to build a data structure that can be used to answer following queries: Given a pair of indices i, j(1≤i≤j≤n), and a positive integer k, report the k smallest elements from the sub-array A[i : j] in sorted order. Brodal et al. (Brodal, G. S., Fagerberg, R., Greve, M., and López-Ortiz, A., Online sorted range reporting. Algorithms and Computation (2009) pp. 173–182) introduced the problem and gave a solution that can answer a query in O(k) time. The preprocessing takes O(nlogn) time and O(n) space. In this paper, we propose the only other possible optimal trade-off for the problem. After preprocessing using O(n) time and space, we can answer a range selection query in O(klogk) time. Moreover, the proposed algorithm reports the output elements individually in non-decreasing order. Our solution is simple and practical. We also study the problem in a dynamic setting. We also describe an extremely simple method for the range minima queries (most of whose parts are known), which takes almost (but not exactly) linear time. We believe that this method may be, in practice, faster and easier to implement in most cases. Moreover, we also give a simple dynamic solution to the range minimum problem. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

IoT-Deep Learning Based Activity Recommendation System

引用

computer Systems science & engineering 2023年第5期45卷 2001-2016页

作者： Sharmilee Kannan R.U.Anitha M.Divayapushpalakshmi K.S.Kalaivani Department of Electronics and Communication Engineering Nandha Engineering CollegePerundurai638052TamilnaduIndia Department of Computer Science Sona College of Arts and ScienceSalem636005TamilnaduIndia Department of Artificial Intelligence and Machine Learning Engineering Gokaraju Rangaraju Institute of Engineering and TechnologyHyderabad500090TelanganaIndia Department of Computer Science and Engineering Kongu Engineering CollegePerundurai638060TamilnaduIndia

The rising use of mobile technology and smart gadgets in the field of health has had a significant impact on the global *** professionals are increasingly making use of the benefits of these technologies,resulting in a major improvement in health care both in and out of clinical *** Internet of Things(IoT)is a new internet revolution that is a rising research area,particularly in health *** Monitoring Systems(HMS)have progressed rapidly as the usage of Wearable Sensors(WS)and smartphones have *** existing framework of conventional telemedicine’s store-and-forward method has some issues,including the need for a nearby health centre with dedicated employees and medical devices to prepare patient ***’health can be continuously monitored using advanced WS that can be fitted or embedded in their *** research proposes an innovative and smart HMS,which is built using recent technologies such as the IoT and Machine Learning(ML).In this study,we present an innovative and intelligent HMS based on cutting-edge technologies such as the IoT and Deep Learning(DL)+Restricted Boltzmann Machine(RBM).This DL+RBM model is clever enough to detect and process a patient’s data using a medical Decision Support System(DSS)to determine whether the patient is suffering from a major health problem and treat it *** recommended system’s behavior is increasingly investigated using a cross-validation test that determines various demographically relevant standard *** a healthcare DSS,this framework is clever enough to detect and analyze a patient’s *** results further reveal that the proposed system is efficient and clever enough to deliver health *** data reported in this study demonstrate the *** device is a low-cost solution for people living in distant places;anyone can use it to determine if they have a major health problem and seek treatment by contacting nearby hospitals.

关键词： Deep learning IoT healthcare system activity recommender system body sensors

来源：评论

学校读者我要写书评

暂无评论

Bengali Music Genre Classification Using WaveNet 26

Bengali Music Genre Classification Using WaveNet

引用

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

作者： Khan, Md. Nabil Rahman Tuli, Khandaker Iffat Jahan Salsabil, Most. Sadia Reza, S.M. Raiyan Shah, Faisal Muhammad Joy, Sajib Kumar Saha Ahsanullah University of Science and Technology Department of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350359015

Music genre classification plays a crucial role in music recommendation and information retrieval. While there have been numerous studies on classifying genres of English music using various machine learning approaches, there is a noticeable absence of similar work for Bangla music classification. Bangla music encompasses a wide range of types and styles that can be classified into different genres. In this research, we focus on six distinct Bangla music genres, including 'Bangla Adhunik,' 'Bangla Hip-Hop,' 'Bangla Band Music,' 'Nazrulgeeti,' 'Palligeeti,' and 'Rabindra Sangeet.' Our dataset consists of 250-300 songs (***3 format) for each genre. By comparing the performances of different models, we demonstrate that our proposed model, using a combination of Principal Component Analysis and K-Fold on the model WaveNet, achieves high accuracy in the multiclass classification of Bangla music genres by comparing with other machine learning and deep learning. This work contributes to the advancement of music genre classification specifically for Bangla music and paves the way for enhanced music recommendation systems and information retrieval in this rich musical tradition. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bengali Cyberbullying Text Detection: A Comprehensive Study 26

Bengali Cyberbullying Text Detection: A Comprehensive Study

引用

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

作者： Hamza, Golam Ibna Muthaki, Tahsina Masuk, Safwan Ibne Mushfiqur Rahman, Mohammad Saha Joy, Sajib Kumar Muhammad Shah, Faisal Ahsanullah University of Science & Technology Department of Computer Science & Engineering Dhaka Bangladesh

ISBN: (纸本)9798350359015

Cyberbullying is a serious online problem that involves harassment and harm via digital communication systems. It can have serious effects on people's mental health and well-being. This research aims to address cyberbullying in Bengali, a low-resource language that has gotten little attention. Previous machine learning approaches for Bengali cyberbullying detection relied on feature extraction techniques that failed to accurately capture word meanings. To address this restriction, this study suggests using word embedding, which portrays words as multidimensional vectors that capture their semantic interactions. The research will compare several machine learning algorithms and feature extraction techniques in order to give a thorough analysis of their accuracy and performance measures. This study intends to contribute to the development of a sophisticated cyberbullying detection model for Bengali. The results demonstrate that one of the ensemble-based models outperforms individual models, achieving a higher accuracy of 0.796, recall of 0.796, and precision of 0.804. The findings of this study promise to make a substantial contribution against cyberbullying in Bengali. This study aims to establish the framework for future breakthroughs in the field of linguistic cybersecurity through its insightful results and methodological approach. © 2023 IEEE.

关键词： Bengali cyberbullying toxicity

来源：评论

学校读者我要写书评

暂无评论

Enhancing Human Action Recognition through advanced Motion Descriptors and Machine Learning 1

Enhancing Human Action Recognition through advanced Motion D...

引用

1st International Conference on Optimization Techniques for Learning, ICOTL 2023

作者： Ramalingam, Vijay Saravanan, D. Vignesh, S. Rahin Batcha, R. Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350328042

Understanding human activities from videos presents a formidable challenge in computer Vision. Intelligent video systems primarily specialize in automatically recognizing human actions within video sequences and annotating them accordingly;human action identification involves recognizing actions associated with one or more objects based on analysis of their activities and context. As technology has proliferated rapidly, huge amounts of human-centric video data have accumulated;it has become an obstacle in contemporary video processing systems due to identifying all these actions efficiently. Complex backgrounds compound these challenges, creating error margins that severely hamper many object detection algorithms and creating error margins that compromise performance - particularly with regard to occlusion and distortion issues. This work addresses these obstacles using Apache Spark with in-memory computing and distributed environment for improved recognition of human actions;specifically, a Local Motion Descriptor is employed for feature extraction that calculates intensities between frames that include both motion and appearance elements. Spark MLlib employs random forest to effectively recognize human behavior. Experimental studies are performed to evaluate its activity recognition capabilities and results are benchmarked against popular supervised classification techniques like Decision Trees;results demonstrate that our proposed model outshone other classification techniques, confirming its efficacy in activity recognition. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Clustered Wireless Sensor Network in Precision Agriculture via Graph Theory

引用

Intelligent Automation & Soft Computing 2023年第5期36卷 1435-1449页

作者： L.R.Bindu P.Titus D.Dhanya Department of Science and Humanities Mar Ephraem College of Engineering and TechnologyTamil Nadu629171India. Department of Science and Humanities University College of Engineering NagercoilAnna University Constituent CollegeKonamNagercoil629004India Department of Computer Science and Engineering Mar Ephraem College of Engineering and TechnologyTamil Nadu629171India

Food security and sustainable development is making a mandatory move in the entire human *** attainment of this goal requires man to strive for a highly advanced state in theﬁeld of agriculture so that he can produce crops with a minimum amount of water and *** though our agricultural methodol-ogies have undergone a series of metamorphoses in the process of a present smart-agricultural system,a long way is ahead to attain a system that is precise and accurate for the optimum yield and proﬁ*** such a futuristic method of cultivation,this paper proposes a novel method for monitoring the efﬁcientﬂow of a small quantity of water through the conventional irrigation system in cultiva-tion using Clustered Wireless Sensor Networks(CWSN).The performance measure is simulated the creation of edge-ﬁxed geodetic clusters using Mat lab’s Cup-carbon tool in order to evaluate the suggested irrigation process model’s ***ﬁndings of blocks 1 and 2 are *** signal takes just a little amount of energy to communicate,according to the *** is feasible to save energy while maintaining uninterrupted communication between nodes and cluster ***,the need for proper placement of a dynamic control station in WSN still exists for maintaining connectivity and for improving the lifetime fault tolerance of *** on the minimum edgeﬁxed geodetic sets of the connected graph,this paper offers an innovative method for optimizing the placement of control *** edge-ﬁxed geodetic cluster makes the network fast,efﬁcient and ***,it also solves routing and congestion problems.

关键词： Wireless sensor networks edgeﬁxed geodetic set agriculture cluster control station precision agriculture

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：