检索结果-内蒙古大学图书馆

Ambient Intelligence, Knowledge Informatics and Industrial electronics (AIKIIE), International Conference on

作者： Shashidhar R Dhanush Balivada Shalini D N Krutthika Hirebasur Krishnappa Roopa M Department of Electronics and Communication Engineering JSS Science and Technology University Mysuru India Department of Computer Science Sothern University and A&M College Baton Rouge Lousiana Department of Electronics and Communication Engineering Dayananda Sagar College of Engineering Bengaluru India

Music emotion recognition is a challenging task that has been getting increasing kindness in the field of artificial intelligence. We propose a unique lD Convolutional Neural Network (lD CNN) method for music emotion recognition. Our proposed approach combines the advantages of convolutional neural networks with the lD temporal structure of music signals. Evaluate our model on two publicly available datasets and demonstrate its effectiveness in accurately recognizing different emotions from music signals. Our method presents a novel approach to abstracting raw audio signals into meaningful representations. It utilizes multiple lD convolutional and pooling layers to extract features from the raw audio signals, which can then be used for further analysis. We demonstrate the effectiveness of our approach by providing examples of applications that can benefit from this abstraction process, such as sound recognition and speech recognition. Additionally, we discuss the potential of this method to be applied in other areas such as natural language processing and music generation. We compare the performance of our model with traditional machine learning (ML) methods and demonstrate that our lD CNN outperforms these traditional ML methods in terms of accuracy. We also discuss potential use cases for this technology and its implications for future research in audio signal processing. We show that our model achieves superior results in terms of accuracy and computational efficiency, making it a promising solution for music emotion recognition tasks. Our results suggest that the lD CNN approach is an effective tool for recognizing musical emotions with high accuracy

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pomegranate Quality Analysis and Classification Using Feature Extraction and Machine Learning 6

Pomegranate Quality Analysis and Classification Using Featur...

引用

6th International Conference on electronics, communication and Aerospace Technology, ICECA 2022

作者： Kumar, Pullela S.V.V.S.R. Sudha, S. Das, Pranjit Pradeep, D. Isaac, J. Samson Vijaipriya, K. Aditya College of Engineering Department of Computer Science and Engineering Andhra Pradesh Surampalem533437 India Asian College of Engineering and Technology Department of Biomedical Engineering Tamil Nadu Coimbatore641110 India Department of Computer Science Engineering Andhra Pradesh Vaddeswaram522302 India M. Kumarasamy College of Engineering Department of Computer Science Engineering Tamil Nadu Karur639113 India Karunya Institute of Technology and Sciences Department of Biomedical Engineering Coimbatore641114 India Sri SaiRanganathan Engineering College Department of Electronics and Communication Enginneering Tamil Nadu Coimbatore641109 India

ISBN: (纸本)9781665482714

Fruits are an excellent source of nutrients and minerals. They have a high concentration of antioxidants and flavonoids, which are beneficial to one's health. Pomegranates have a high potential in preventing cell damage, boosting our immunity, helping with smooth digestion, fighting type-2 diabetes, keeping vital parameters in check and are seen to be effective inthe prevention of cancers. India is considered the largest producer of excellent varieties of pomegranates and thus the quality analysis in the export operation of pomegranates is highly concerned. Grading of pomegranates is very necessary for post-harvest management and is performed based on the external appearance like attractive colours, texture, size and shape which decides the standard of the fruit. Manual grading can be done which requires human operation and consumes more time. Hence quality assessment of pomegranates can be done using Machine Learning(ML) which is highly efficient. The process of feature extraction yields accurate results and can be done quickly. ML technology improves accuracy and efficiency and has improved user experience. The review paper proposes an efficient ML approach for pomegranate quality analysis using Histogram of Oriented Gradients (HOG) and Local Binary Pattern (LBP) feature extraction methods. K-Nearest Neighbour (KNN) and Naive Bayes (NB) algorithms are implemented in the designed model using both sets of feature extractors and the result illustrates that the LBP + NB model performs with better efficiency and greater accuracy. © 2022 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Speech Recognition Paradigms: A Comparative Evaluation of SpeechBrain, Whisper and Wav2Vec2 Models

Speech Recognition Paradigms: A Comparative Evaluation of Sp...

引用

International Conference for Convergence of Technology (I2CT)

作者： Dhanvanth Reddy Yerramreddy Jayasurya Marasani Ponnuru Sathwik Venkata Gowtham Guduru Harshit Anjali Dept. of Computer Science and Engineering Amrita School Of Computing Amrita Vishwa Vidyapeetham Amritapuri India Dept. of Electronics & Communication Engineering School of Engineering Amrita Vishwa Vidyapeetham Amritapuri India

ISBN: (数字)9798350394474

ISBN: (纸本)9798350394481

Speech recognition plays a pivotal role in the realm of natural language processing that deals in converting the language into the written text, providing human-computer interaction and enables us to use it widely for applications starting with voice assistants and delving upto the transcription services. Due to the complexity present in performing the task of speech recognition has led to the development of various models to enhance accuracy and efficiency. Our project mainly delves into three prominent speech recognition models that are Whisper, Wav2Vec2 and Speechbrain each of them representing distinct approaches of transcribing spoken language. The significance of the models used lies in their potential to perform better for realtime applications by improving the accuracy and reliability of speech recognition. To evaluate the best model that performs effectively, an array of metrics are used including levenshtein distance and it’s similarity percentage, jaccard similarity along with semantic similarity that provides an additional layer of evaluation describing the model’s understanding of contextual meaning in spoken language. Out of the three models, Speech Brain model outperformed all the other models through the calculation of Word Error Rate (WER), Character Error rate (CER) and BLEU score. The results have shown the model’s efficiency in converting spoken language(audio files) into precise and contextually relevant text. The results shows that these models contribute to the field of speech recognition highlighting the strengths of each approach and among them considering speechbrain as an ideal solution for accurate and meaningful transcription.

关键词： Measurement Human computer interaction Adaptation models Technological innovation Error analysis Semantics Speech recognition

来源：评论

学校读者我要写书评

暂无评论

SVM Based DDoS Attack Detection in IoT Using Iot-23 Botnet Dataset 3

SVM Based DDoS Attack Detection in IoT Using Iot-23 Botnet D...

引用

3rd IEEE International Virtual Conference on Innovations in Power and Advanced Computing Technologies, i-PACT 2021

作者： Nanthiya, D. Keerthika, P. Gopal, S.B. Kayalvizhi, S.B. Raja, T. Priya, R. Snega Kongu Engineering College Department of Computer Technology-UG Erode India Kongu Engineering College Department of Computer Science and Engineering Erode India Kongu Engineering College Department of Electronics and Communication Engineering Erode India Vivekanandha College of Engineering Department of Electrical and Electronics Engineering Namakkal India Vivekanandha College of Engineering Department of Electronics and Communication Engineering Namakkal India

ISBN: (纸本)9781665426916

Network security is one of the most important challenges in Smart cities networks. A distributed denial of service (DDoS) attack is a cyberattack that attempts to distribute the normal traffic of a targeted server, service or network sending flood of Internet traffic. In this paper, Machine learning algorithms such as Support Vector Machine, Decision Tree and Random Forest are trained and tested to classify the DDoS attacked packets. Principal Component Analysis (PCA) is a dimensionality reduction technique that helps to improve the performance of the algorithms. So, in this paper, the efficiency of the PCA is compared with the without PCA results. Initially, the dataset is passed to PCA (Principal Component Analysis) for feature selection and then implemented in different Machine Learning algorithms. The results of all the algorithms are evaluated using the parameters accuracy, precision, F1 score, and Recall. Again, the same dataset is tested and trained in all same ML algorithms using without PCA dataset. Then the results of PCA and without PCA are compared. This experimental analysis shows that by using PCA, the execution time of the algorithm reduces significantly with a smaller number of features and yields same result as that of without PCA. More over the Decision tree and Random Forest algorithms classifies the DDoS packets very accurately compared to SVM. The results are presented as graph using Matplotlib. The dataset taken for our experimental analysis is IoT-23 dataset. © 2021 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Utilizing flexible, robust optimization for the integration of renewable energy sources and electric cars in a large-scale Vehicle-to-Grid (V2G) network

Utilizing flexible, robust optimization for the integration ...

引用

2023 International Conference for Technological engineering and its Applications in Sustainable Development, ICTEASD 2023

作者： Ramalakshmi, R. Ameen, J. Noorul Srinivasa Rao, Gundala Gandhi, Rajiv Bansal, Saloni Sapaev, J.B. Alsalami, Zaid Ritwika, S. Ramco Institute of Technology Electronics and Communication Engineering Rajapalayam626117 India E.G.S. Pillay Engineering College Department of Computer Science and Engineering Tamilnadu Nagapattinam India CMR College of Engineering & Technology Department of EEE Hyderabad India CIVIL Prince Shri Venkateshwara Padmavathy Engineering College Chennai127 India GLA University Department of Computer Engineering and Applications Mathura India National Research University Tashkent Institute of Irrigation and Agricultural Mechanization Engineers Tashkent Uzbekistan The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq GRIET Telangana Hyderabad India

ISBN: (纸本)9798350336474

The development of electric Vehicle-To-Grid (V2G) interaction has the potential to enhance renewable energy consumption and maintain the relationship with the grid. Simultaneously, renewable energy can be harnessed for an adjacent microgrid or integrated into a larger grid to successfully reduce the unpredictability of Renewable Energy Sources (RES). This study presents a method to enhance the security and economics of microgrid systems, considering the growing presence of Electric Vehicles (EVs) and the unpredictable nature of RES. The uncertainty around wind power and the State Of Charge (SOC) of EVs is represented by predicted uncertainties. In the event of the most unfavorable circumstances, this suggested approach can enhance the utilization rate of sustainable energy sources. It does this by effectively managing the charging and discharging of EVs during periods of high demand and low demand, resulting in reduced operational expenses within the limitations of real-world conditions. This work proposes the introduction of a dispatch interval factor to address the issue of excessive caution in robust optimization. This coefficient allows for adjusting the level of caution while enhancing microgrid systems' economic efficiency. The statistical case studies provide evidence of the effectiveness and practicality of the suggested optimisation technique. © 2023 IEEE.

关键词： Vehicle-to-grid

来源：评论

学校读者我要写书评

暂无评论

Memristor-Based Counters Circuits for Real-Time Petrol Bunk Applications

Memristor-Based Counters Circuits for Real-Time Petrol Bunk ...

引用

Intelligent Cyber Physical Systems and Internet of Things (ICoICI), International Conference on

作者： Panati S Sreenivas Reddy P Michael Preetam Raj Sravan K. Vittapu K. Senthil Kumar Dept. of Electronics and Communication Engineering Dr MGR Educational and Research Institute Chennai India Department of Computer Science and Engineering MLR Institute of Technology Hyderabad India Department of Electronics and Communication Engineering Nalla Narasimha Reddy Education Society's Group of Institutions Hyderabad India

ISBN: (数字)9798331540661

ISBN: (纸本)9798331540678

At present researchers have been widely employing memristor for numerous electronic applications as it has several advantages when compared to the widely employed transistor-based technology. Electronic counters have been widely used for a huge number of real-life applications. To overcome the drawbacks of transistor-based counters, in this work, memristor-based counters are proposed. Both up-counter and down-counter circuits are simulated. Based on these circuits an electronic circuit that delivers the exact amount of fuel requested by the user is proposed. One can perceive that the amount of fuel vended is directly proportional to the ON duration of the fuel pump. Based on this idea a memristor-based fuel dispenser is developed. The proposed circuits outperform their existing counterparts regarding computational speed, power dissipation, and circuit complexity. These circuits pave the way for futuristic automatic fuel vending systems.

关键词： Power demand Circuits Memristors Real-time systems Complexity theory Power dissipation Fuels Fuel pumps Electronic circuits Petroleum

来源：评论

学校读者我要写书评

暂无评论

An Automated Sleep Stage Classification for Healthcare Monitoring by using Single Channel EEG Signal

An Automated Sleep Stage Classification for Healthcare Monit...

引用

Integrated Circuits and communication Systems (ICICACS), IEEE International Conference on

作者： Sasi Kumar Gurumoorthy D T Chethana M Ramesh B.P Upendra Roy C Sapna Kumari Department of Computer Science and Engineering J.J.College of Engineering and Technology Trichy India Department of Computer Science & Engineering GITAM School of Technology GITAM University India Department of Computer Science & Engineering K L University Vadeeshwaram Vijayawada India Department of Electronics and Communication Engineering Channabasaveshwara Institute of Technology Tumkur India Department of Electronics and Communication Engineering Nitte Meenakshi Institute of Technology Bengaluru India

It is well-established that biomedical signals convey crucial data regarding the functioning of living systems. The physiological and clinical information included in these signals can be improved with adequate processing. Modern qualitative and quantitative analyses of physiological systems and events rely on digital signal processing and pattern recognition methods. Analysis and interpretation of a medical practitioner's signal carry the weight of the analyst's knowledge and expertise, yet such analysis is inherently subjective. If done logically, computer analysis of biomedical information might provide credibility to the expert's interpretation by providing an objective second opinion. Furthermore, it allows for enhanced diagnosis and online monitoring of critically ill patients. The current research intends to develop effective methods for utilizing sleep-monitoring health gadgets. When it comes to handling complex classification or pattern recognition issues, the Support Vector Machine (SVM) is the instrument of choice. In this article, we focus on using support vector machines (SVMs) to identify and categorize apnea. When compared to other methods of categorization, such as sophisticated statistical approaches, SVM performed better. Both an adaptive classification model and a novel approach to merging the decisions of ensemble-based classification models are proposed in the work. The current method relies on an ensemble classifier system and a huge number of features, making it both effective and trustworthy.

关键词： Support vector machines Adaptation models Time-frequency analysis Sleep Statistical analysis Feature extraction Brain modeling

来源：评论

学校读者我要写书评

暂无评论

Optimal Scheduling and Sizing of Energy Storage System using Hybrid Algorithm for Electric Vehicles

Optimal Scheduling and Sizing of Energy Storage System using...

引用

2022 International Virtual Conference on Power engineering Computing and Control: Developments in Electric Vehicles and Energy Sector for Sustainable Future, PECCON 2022

作者： Dhivya, S. Arul, R. Maheswari, S. Kanimozhi, R. Karthik, N. School of Electrical Engineering Vellore Institute of Technology Tamilnadu Chennai India School of Computer Science and Engineering Vellore Institute of Technology Tamil nadu Chennai India FEAT Annamalai University Dept. of Electronics and Communication Engineering Tamil nadu Chidambaram India Hindustan Institute of Technology and Science Dept. of Electrical and Electronics Engineering Tamil nadu Chennai India

ISBN: (数字)9781665485920

ISBN: (纸本)9781665485920

The rapid exhaustion of fossils shaded concern about environmental problems which enforce researchers to embed this renewable distribution generation into power system networks. Electric vehicles are increasing threat to reliability of power grid by overloaded equipment and disturbed stability in voltage. However, it is important that electric vehicles must provide support to grids through vehicle to grid optimized V2G scheduling to minimize load variances. The purpose of this study is to employ a hybrid approach to improve energy storage system scheduling and sizing for electric vehicles. The hybrid version of Flower Pollination and golden section search is used. This research considers peak shaving, valley filling and priority charging mode of Energy Storage System for effective load management. Results indicated that optimized and scheduled energy storage system can fulfill the proper load allocation at grid. © 2022 IEEE.

关键词： Energy storage

来源：评论

学校读者我要写书评

暂无评论

A robust digital ECG signal watermarking and compression using biorthogonal wavelet transform

引用

Research on Biomedical engineering 2021年第1期37卷 79-85页

作者： Kumar, Ashish Ranganatham, Ramana Singh, Samayveer Komaragiri, Rama Kumar, Manjeet School of Electronics Engineering Vellore Institute of Technology ChennaiTamil Nadu India Department of Electronics and Communication Engineering Bennett University Greater NoidaU.P. India Department of Computer Science and Engineering National Institute of Technology JalandharPunjab India Delhi India

Purpose: With the advent of the technological era, the complexity of data security and privacy has gained utmost importance. People are becoming more conscious about the security and confidentiality of their crucial information. Methods: The present study is first of its kind effort in for safeguarding an individual’s electrocardiogram (ECG) data. ECG data not only does hold medical significance but also is of crucial and critical importance for purposes related to biometric information. Hence, a deciding factor for recognizing and validating personal information. The study progresses and proposes a new technique in ECG watermarking compression. Results: This method ensures high reliability of data and information with confidentiality. The efficiency of the proposed research is evaluated in terms of compression ratio (CR), compressed signal-to-noise-ratio (CSNR), root-mean-square error (RMSE), maximum absolute error, percentage root-mean-square difference (PRD), and quality score. Conclusion: After a comprehensive evaluation, the final results show that the proposed work is robust and feasible. © 2020, Sociedade Brasileira de Engenharia Biomedica.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Hybrid Vision Transformer and CNN for Detection of Overripe Coffee Berry Disease (OCBD) in Coffee Plantation

Hybrid Vision Transformer and CNN for Detection of Overripe ...

引用

Emerging Research in Computational science (ICERCS), International Conference on

作者： Raveena Selvanarayanan Surendran R Gomathi T Kartheesan L Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Science Chennai India Department of Electronics and Communication Engineering Sathyabama Institute of Science and Technology Chennai India Department of Computer Science and Engineering Vel Tech Rangarajan Dr.Sangunthala R&D Institute of Science and Technology Chennai India

ISBN: (数字)9798331534967

ISBN: (纸本)9798331534974

The article proposes an innovative Hybrid Vision Transformer and CNN architecture for the precise identification of Overripe Coffee Berry Disease (OCBD) in coffee farms. The suggested model adeptly integrates the advantages of Vision Transformers and CNNs, allowing it to capture both the global and local characteristics of coffee berries. Experimental findings indicate that the Hybrid model outperforms conventional CNN-based methods, with an impressive accuracy of 96.7% on a varied dataset. The model's resilience to fluctuating illumination conditions and obstructions makes it a viable alternative for practical applications in coffee plantation management.

关键词： computer vision Accuracy Scientific computing Computational modeling Plantations Lighting Transformers Reliability Diseases Resilience

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：