检索结果-内蒙古大学图书馆

Automatic hate speech detection in audio using machine learning algorithms

International Journal of Speech technology 2024年第2期27卷 447-469页

作者： Imbwaga, Joan L. Chittaragi, Nagatatna B. Koolagudi, Shashidhar G. Computer Science and Engineering National Institute of Technology Karnataka Karnataka Surathkal575025 India Information Science and Engineering Siddaganga Institute of Technology Karnataka Tumkur572103 India

Even though every individual is entitled to freedom of speech, some limitations exist when this freedom is used to target and harm another individual or a group of people, as it translates to hate speech. In this study, the proposed research deals with detection of hate speech for English and Kiswahili languages from audio. The dataset used in this work was collected manually from YouTube videos and then converted to audio. Audio-based features namely spectral, temporal, prosodic and excitation source features were extracted and used to train various machine learning classifiers. Initial experiments were conducted for English language and later on for Kiswahili language. However, it is observed from literature that research activities on Kiswahili language is comparatively lesser. The scores calculated for accuracy, recall, precision, auc and f1 score in detecting hate speech, suggest that Random Forest classifier performed better for English language while the Extreme Gradient Boosting classifier performed better for Kiswahili language. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Stationary wavelet transform and SpinalNet trained light spectrum Tasmanian devil optimization enabled DR detection using fundus images

引用

Multimedia Tools and Applications 2025年第4期84卷 1597-1626页

作者： Tamboli, Mubin Shoukat Dhumane, Amol Prasad, Rajesh Prasad, Jayashree Rajesh Ranjan, Nihar M. Computer Engineering Pimpri Chinchwad College of Engineering Pradhikaran Maharashtra Pune411044 India Computer Science and Engineering Symbiosis Institute of Technology Maharashtra Pune India Computer Science and Engineering School of Computing MIT Art Design and Technology University Loni Kalbhor Maharashtra Pune412201 India Information Technology JSPM’s Rajarshi Shahu College of Engineering Tathawade Maharashtra Pune411033 India

Diabetes is a common disease that causes complications in the eyes known as Diabetic Retinopathy (DR). It aids in discovering the DR and tends to be the main cause behind people’s blindness amidst the previous decades. For prevent the complications of DR and to control the level of blood Glucose, the timely and crucial diagnosis is essential. A model is provided for detecting the DR. Here, Light Spectrum Tasmanian Devil Optimization (LSTDO) is utilized with SpinalNet for DR detection. The method undergoes an adaptive median filter and Region of interest mining process to generate a pre-processed image. The Sparse Fuzzy C-Means (FCM) is adapted for segmenting the optic disks followed by feature extraction. Then, the Hough line transformation with Tyler Coye algorithm (HLTCA) is used for blood vessel segmentation. Concurrently, the Stationary Wavelet Transform (SWT) is adapted to input image to overwhelm the deficiency of translation-invariance issue and then the feature mining is done. The feature vector is generated by unifying the outputs of the three-feature extraction phases and is employed to detect DR. The accuracy, sensitivity, and specificity obtained by the LSTDO-based SpinalNet are 91.6%, 89.9% and 92.1%, respectively. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Symptom Analysis: Enabling Early Disease Prediction Through Chatbot Interaction 3rd

AI-Driven Symptom Analysis: Enabling Early Disease Predictio...

引用

3rd International Conference on Intelligent Systems and Sustainable Computing, ICISSC 2023

作者： Prasannakumar, P. Paul, Jaydev Vani, V. Karthik, N. Department of Computer Science and Engineering National Institute of Technology Puducherry Karaikal609609 India

ISBN: (纸本)9789819783540

Given the current environment, in which the appearance of fresh diseases has become a regular occurrence and human immunity seems to be declining, it is critical that basic healthcare services be made available to everyone on the planet. In order to provide health care to individuals, this work offers a novel model that makes creative use of an AI-driven chatbot. The prediction model that powers the chatbot’s functioning is based on historical data about different diseases, the symptoms that go along with them, and how serious these illnesses are. Through the integration of historical data and user-provided real-time symptom data, the chatbot functions as a potent instrument for very accurate disease prediction. Its unique strength lies in its capacity to merge medical records from the past with current data, providing customers with the most precise and trustworthy illness prediction. This research further investigates the concept of AI-Driven Symptom Analysis, a novel method that enables early disease prediction via conversational interactions with the chatbot. In an era marked by changing health threats and weakened human immune systems, this two-pronged approach, which incorporates both historical data and current health information, represents a major advancement in our quest to improve access to healthcare and proactively tackle emerging health challenges. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Optimizing Crop Health: Evaluating CNN Performance in Plant Disease Detection 5th

Optimizing Crop Health: Evaluating CNN Performance in Plant ...

引用

5th EAI International Conference on Cognitive Computing and Cyber Physical Systems, IC4S 2024

作者： Charan Tejas, Parimi Murali Sriram Ganapathi, Marnala Mahesh Babu, Parepalli Surya Sai, Kosuru Amulya, Godi Bonthu, Sridevi Department of Computer Science and Engineering Vishnu Institute of Technology Andhra Pradesh Bhimavaram India

ISBN: (纸本)9783031770807

Plant diseases represent a significant challenge in agriculture, significantly impacting crop yield. Addressing this issue is imperative to ensure agricultural productivity. Convolutional Neural Networks (CNNs) have emerged as a promising solution for image-based disease detection. Detecting diseases in their early stages using CNN models can potentially enhance crop yield for farmers. Given the multi-class nature of most plant diseases, we conducted a comprehensive comparative study of CNNs to assess their effectiveness. Our study compared three CNN models: AlexNet, VGG-19, and ResNet18. ResNet18 demonstrated superior performance, achieving a validation accuracy of 95.68%. Furthermore, we developed a web application to enable farmers to utilize the trained model effectively. © ICST institute for computer Sciences, Social Informatics and Telecommunications engineering 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

VR theatre-A virtual reality based seat selection system 1st

VR theatre-A virtual reality based seat selection system

引用

1st International Conference on Applications of AI in 5G and IOT, ICAAI5GI 2024

作者： Kanyal, Hoshiyar Singh Mansi Singh, Mayank Kumar Koranga, Nandika Department of Computer Science & Engineering ABES Institute of Technology Uttar Pradesh Ghaziabad India

ISBN: (纸本)9781032874036

Traditional movie ticket booking relies on static 2D seat maps, limiting user’s ability to visualize their chosen seat. This project explores the potential of virtual reality (VR) to revolutionize the movie-going experience by introducing VR seat selection. We designed a VR theatre environment where users can navigate and virtually "sit" in different seats, experiencing the view from each location. This immersive experience empowers users to make informed decisions about seat selection, considering factors like screen proximity, and overall viewing angle. User testing will compare VR seat selection with traditional methods, evaluating its impact on user confidence and satisfaction. This project investigates the potential of VR technology to enhance user engagement and decision-making in the movie ticket booking process. © 2025 the Author(s).

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Decentralized face verification attendance system using ERC20 token 1st

Decentralized face verification attendance system using ERC2...

引用

1st International Conference on Applications of AI in 5G and IOT, ICAAI5GI 2024

作者： Tiwari, Avdhesh Kumar Ratan, Gyan Verma, Himanshu Department of Computer Science & Engineering ABES Institute of Technology Uttar Pradesh Ghaziabad India

ISBN: (纸本)9781032874036

The proposed attendance management system integrates biometric authentication to replace manual methods, enhancing accuracy and preventing issues like proxy attendance. Employing facial recognition on a blockchain, it secures attendance tracking by distributing data across a network, making tampering difficult. Stored on a blockchain for data integrity, entries are timestamped and encrypted, forming an immutable, auditable chain. This comprehensive solution combines facial recognition with blockchain technology, ensuring tamper-proof, reliable attendance records. Easily integrable into existing infrastructure, it offers heightened security, accuracy, and transparency. Additionally, a rewards mechanism using blockchain-based tokenization incentivizes meeting attendance criteria through automated and transparent smart contracts, promoting fairness. © 2025 the Author(s).

关键词： Data integrity

来源：评论

学校读者我要写书评

暂无评论

Maximizing Weighted Dominance in the Plane 21st

Maximizing Weighted Dominance in the Plane

引用

21st International Colloquium on Theoretical Aspects of Computing, ICTAC 2024

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

ISBN: (纸本)9783031770180

Let P be a set of n weighted points, Q be a set of m unweighted points in the plane, and k a non-negative integer. We study the k-maxDominance problem, where the objective is to find a subset Q′⊆Q with size at most k such that the sum of the weights of the points in P dominated by at least one point in Q′ is maximized. A point q in the plane dominates another point p if and only if x(q)≥x(p) and y(q)≥y(p), and at least one inequality is strict. An algorithm for the k-maxDominance problem can be used to solve problems previously examined in scheduling, graph optimization, and database systems. We present a simple algorithm solving the problem in O(km2+nlogm) time and O(n+m) space. The algorithm is faster than the existing one when m=o(n). Additionally, we provide another solution to the problem with O(kmin{n+m,nk+m2}logm) time and O(n+m) space. These bounds are the same or better than those of the existing solution (the bounds are better when m=o(n)). The expected number of skyline points is θ(logn), a term much less than n. To obtain the second solution, we design a general technique that can be used to reduce the number of points n in P to min{n,m2} in any algorithm for the k-maxDominance problem. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

The Multi-Way Path Over the Blockchain: The Development of the Security Algorithm RB-24-1 6

The Multi-Way Path Over the Blockchain: The Development of t...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Rajaprakash, S. Bagath Basha, C. Rathish Babu, T.K.S. Karthik, S. Subapriya, V. Kavitha, S. Department of Computer Science & Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Tamil Nadu Chennai India Department of Computer Science & Engineering Kommuri Pratap Reddy Institute of Technology Telagana Hyderabad India Department of Computer Science & Engineering SRM Institute of Science and Technology Ramapuram Tamil Nadu Chennai India Department of Computer Science & Engineering Aarupadai Veedu Institute of Technology Vinayaka Missions Research Foundation Tamil Nadu Chennai India Department of Computer Science & Engineering Sathyabama Institute of Science and Technology Tamil Nadu Chennai India

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522667

In the current world, a lot of new technologies are becoming famous. The Block Chain is one of these technologies. A very high amount of safety is offered by the technology in question;it is extremely robust. Users are not privy to a great deal of information regarding Block Chain;however, Protecting the data that is sent in multiple ways is what its security features are for. The "SalSa and RBJ25 algorithms" were still being used by this person. We are going to talk about the new "security mechanism" we have named RB-24-1. This method is comprised of these four different techniques. The procedure begins with the "Latin Alphabet code" being assigned to T. This is the first step in the process. To proceed to the next step, use Equation (1) to perform four times the multiplication of the number by itself. "Exchanging the values of the cells" is what the third step does., and it is carried out with the help of encrypted data. Putting the "SalSa" algorithm into action within the matrix constitutes the fourth step throughout the process. Finally, the plain text is converted into the encrypted text format. This has been a long time coming. There is a higher level of security offered by the method that has been suggested in compare and contrast with the method that is being used at the moment. © 2025 IEEE.

关键词： Encryption algorithms

来源：评论

学校读者我要写书评

暂无评论

WENSA: WhatsApp Emotion and Sentiment Analyzer Using LSTM and BI-LSTM 3rd

WENSA: WhatsApp Emotion and Sentiment Analyzer Using LSTM an...

引用

3rd International Conference on Intelligent Systems and Sustainable Computing, ICISSC 2023

作者： Kumar, N. A. Abhinav Sanjay, R.V. Vani, V. Karthik, N. Department of Computer Science and Engineering National Institute of Technology Puducherry Karaikal609609 India

ISBN: (纸本)9789819783540

WhatsApp is a widely popular messaging app used for communication. This study focuses on analyzing WhatsApp group chats, aiming to assess member activity and engagement. It seeks to determine the most active day, the highest number of messages sent on that day, the most active user, active group members, the total user count, individual message contributions, and the most frequently used phrase. Additionally, it conducts daily, monthly, and annual analyses of the top 15 members’ messages. Furthermore, the study aims to predict emotions within the text, such as joy, sadness, and anger, using a deep learning algorithm known as LSTM. The model's performance is evaluated using a dataset from Kaggle comprising 16,000 English language records with various emotions, with validation accuracy as the key metric for emotion analysis. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Active learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Load Balancing for Distributed Multi-Controller SDNs through Switch Migration Strategy 17

Adaptive Load Balancing for Distributed Multi-Controller SDN...

引用

17th International Conference on COMmunication Systems and NETworkS, COMSNETS 2025

作者： Rao, Allu Sudharshan Khanal, Bipal Alam Ansari, Md. Sarfaraj National Institute of Technology Sikkim Department of Computer Science and Engineering Sikkim Ravangla India

ISBN: (纸本)9798331531195

Software-defined networking (SDN) is a transformative technology that systematically centralises and manages network resources. This paradigm shift allows for greater flexibility, agility, and efficiency in network management. In the ever-evolving landscape of distributed software-defined networks, the escalating demand for cloud services and data traffic underscores the critical need for a sophisticated load-balancing scheme. This paper addresses the pivotal challenge of optimising resource utilisation in SDN controllers to mitigate bottlenecks, enhance responsiveness, and ensure efficient network operations. This paper proposes a switch migration algorithm for efficient load balancing in distributed multi-controller topology. The proposed framework uses resource utilisation, load balancing rate, and re-association time for performance measurement. The proposed algorithm considers the switch to controller distance and remaining processing capacity to select an immigration controller. It also minimizes re-association time in the process of switch migration. The proposed algorithms are compared with benchmark algorithms like 'Closest Switch Migration' and 'Maximum Utilization Switch Migration' using various performance metrics. It has shown promising results and outperforms the benchmark algorithms. © 2025 IEEE.

关键词： Benchmarking

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：