检索结果-内蒙古大学图书馆

Emerging smart Computing and Informatics (EsCI), Conference on

作者： Tushar b T Umang Goel varun Urs Ms vinay Kulkarni Kavitha sooda Department of Computer Science and Engineering B.M.S. College of Engineering Bengaluru India

Dysgraphia, a learning disability impacts hand-writing fluency and legibility, which significantly hinder's a child's academic progress and self-esteem. The proposed work utilizes pattern recognition techniques, employing preprocessing techniques like Canny Edge Detection, Watershed segmentation and various image enhancement techniques to analyze written characters and extract relevant features using character-wise bounding boxes. This detailed analysis allows the system to capture subtle variations in letter formation and spacing that are often indicative of dysgraphia. Furthermore, A MobileNet architecture has been proposed to assess the system's performance and classify dysgraphia risk levels into three categories: below Average(bA), Average(Av) and Above Average(AA). This categorization system provides valuable insights for educators and parents, enabling early intervention and tailored support for students struggling with dysgraphia. The model was trained using a data set of 940 images of handwriting samples from students studying in grades one to seven. students were asked to write 20 words through dictation and another 20 words copied from the board. The proposed system aims to demonstrate immediate results, highlighting its potential for early detection and intervention.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Improved speech Enhancement:Parameter Optimization in the scalart Wiener Filter Method

Towards Improved Speech Enhancement:Parameter Optimization i...

引用

Recent Trends in Microelectronics, Automation, Computing and Communications systems (ICMACC), International Conference on

作者： Prathvi P Puthran samhitha D siri Prahlad spoorthi Udupa Kavitha sooda Department of Computer Science and Engineering B.M.S College of Engineering Bengaluru India

ISBN: (数字)9798350366570

ISBN: (纸本)9798350366587

Communication in noisy environments demands efficient noise suppression techniques due to reduced intelligibility and listener fatigue. This research optimizes the Decision-Directed Wiener filter for speech enhancement by meticulously adjusting the smoothing factor (alpha) and noise updating parameter (NoiseLength), crucial for adaptive performance across diverse acoustic settings. Using the Noizeus dataset, a thorough evaluation was conducted to assess how varying these parameters impacts speech enhancement quality. The proposed adjustments were rigorously evaluated using objective metrics such as Perpetual Evaluation of speech Quality(PEsQ), Normalized Cross-correlation Metric (NCM), and signal-to-Noise Ratio (sNR), offering a comprehensive assessment of speech enhancement quality. These metrics collectively offer insights into speech enhancement quality. Findings show that fine-tuning alpha and NoiseLength parameters significantly improve speech quality, underscoring their critical role in optimizing the Decision-Directed Wiener filter. With the optimal settings, the enhancements led to an average increase of 19.72% in Perpetual Evaluation of speech Quality (PEsQ), 17.68% in Normalized Cross-correlation Metric (NCM), and 59.35% in signal-to-Noise Ratio (sNR), demonstrating the effectiveness of the parameter adjustments.

关键词： Measurement Wiener filters smoothing methods speech enhancement Market research Acoustics Microelectronics Noise measurement Optimization signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Leveraging Online social Content for Early Detection of suicidal Ideation: A Multi-Modal Deep Learning Approach

Leveraging Online Social Content for Early Detection of Suic...

引用

Emerging Technologies in computer science for Interdisciplinary Applications (ICETCs), International Conference on

作者： Nikita Paras Toliya N Nagarathna Computer Science and Engineering Department B.M.S. College of Engineering Bangalore India

ISBN: (数字)9798350372502

ISBN: (纸本)9798350372519

The contemporary society is grappling with the alarming rise in suicide rates, exacerbated by factors such as prolonged exposure to negative emotions and challenging life events. Detecting early signs of suicidal ideation holds significant promise in addressing this crisis. In the digital age, online communication platforms have become outlets for individuals to express distress, presenting an opportunity for timely intervention. This study aims to explore online social content for the early identification of suicidal ideation, with a focus on user- generated text that contains valuable insights into people’s mental states. The research begins with a thorough content analysis to extract knowledge from suicide-related text, establishing a benchmark for binary classification of suicidal ideation using various classifiers, including feature-based and deep neural networks. The urgency of early detection for prevention underscores the importance of this research. by integrating content analysis, feature engineering, and advanced deep learning methodologies, such as deep neural networks and attentive relation networks, this study aims to contribute to suicide prevention efforts. This paper advocates for the application of multi-modal deep learning techniques to identify early signs of suicidal ideation from online social content. The integration of machine learning and mental health intervention is crucial in addressing the escalating concern of suicide rates, especially among vulnerable populations like youths. Through our research, we aim to provide a valuable tool for promoting mental well-being and ultimately saving lives.

关键词： Deep learning Technological innovation Refining sociology Mental health Artificial neural networks streaming media

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Model for Email Fraud Detection Using Naïve bayes and svM 1

Hierarchical Model for Email Fraud Detection Using Naïve Ba...

引用

1st International Conference for Women in Computing, InCoWoCo 2024

作者： vasudevan, I. Nasurudeen, M.Mohamed Kumar, M.senthil Charaan, R.M.Dilip Kumar, s.Ashok Jenefa, Leena Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology CSE Chennai India V.S.B.Engineering College CSE Karur India Erode Sengunthar Engineering College AIDS Erode India Hindustan Institute of Technology and Science MBA Chennai India

ISBN: (纸本)9798331518943

Email fraud detection is one of the major problems in our society with the quick rise of internet frauds and spam nowadays. some people were using it for illegal and evil purposes like phishing and fraud. The spammers are pretending like a genuine person in the spam emails for creating a fake profile and fake account. In this paper, we propose a method for email fraud detection that combines the strengths of the Naive bayes algorithm and support vector Machine (svM) in machine learning. The Naive bayes algorithm is one of the most popular and effective in handling large datasets, and this can be used to model their relationships between words in emails and their properties of being spam or ham. Meanwhile, svM is able to separate classes in high-dimensional spaces, and it is also used for the accuracy classification. by integrating these two approaches, the proposed method aims to improve the detection of spam emails by using the advantages of both algorithms. This mixed-breed model offers a strong solution to the challenge of distinguishing between spam and not spam emails. Most of the existing methods have less accuracy in detecting spam. The proposed Naïve bayes and svM algorithms achieve higher accuracy of 97.49% for email fraud detection and fast processing speed compared to other proposed methods. © 2024 IEEE.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

Particle swarm Optimization for Efficient brain Tumor Classification Using Inceptionv3 Deep Learning Model 9

Particle Swarm Optimization for Efficient Brain Tumor Classi...

引用

9th International Conference on Communication and Electronics systems, ICCEs 2024

作者： Akhila, P. Prabaharan, G. Pandiiyan, K. swarna, s.L. Hussain, A. sakthivelu, U. B V Raju Institute of Technology Department of Artificial Intelligence and Machine Learning Telangana Narsapur India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Avadi Chennai India Srm Arts and Science College Department of Computer Science with Artificial Intelligence Kattankulathur Chengalpattu India Sona College of Technology Department of Computer Science Science and Engineering Junction Main Road Tamil Nadu Salem India College of Engineering and Technology Srm Institute of Science and Technology Department of Networking and Communications Tamil Nadu Kattankulathur India

ISBN: (纸本)9798350377972

This research proposes a novel framework for brain tumor classification utilizing a combination of deep learning and optimization techniques. The framework employs an autoencoder network for image preprocessing, followed by segNet for accurate tumor segmentation. The core classification is performed using the Inceptionv3 model, further optimized through Particle swarm Optimization (PsO) to enhance predictive performance. The proposed system achieved a classification accuracy of 98.75% on a dataset of 7,023 MRI images, demonstrating its effectiveness in accurately classifying brain tumors. This research contributes to the advancement of medical image analysis and provides a valuable tool for supporting clinicians in the early diagnosis and treatment of brain tumors. © 2024 IEEE.

关键词： Particle swarm optimization (PsO)

来源：评论

学校读者我要写书评

暂无评论

Transforming Hospital visitor screening with Cloud-Powered Deep Learning for safety and security

Transforming Hospital Visitor Screening with Cloud-Powered D...

引用

2025 IEEE International students' Conference on Electrical, Electronics and computer science, sCEECs 2025

作者： Joseph Rajan, D. Antony sivanesan, T.M. Mohankumar, N. srinivasan, M. sivaraman, Audithan velmurugan, s. Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Tamil Nadu Chennai India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Symbiosis Institute of Technology Pune India P. S. v College of Engineering and Technology Department of Information Technology Tamilnadu Krishnagiri India Department of Information Technology Jafferpur New Delhi110073 India T.J.S. Engineering College Department of Electronics and Communication Engineering Tamil Nadu India

ISBN: (纸本)9798331529833

This research describes a novel approach to hospital visitor screening utilizing cloud-powered deep learning using convolutional neural networks (CNNs). Our proposed approach will fill this need by improving threat detection accuracy and decreasing false positives. Our system can successfully detect possible dangers among visitors by using CNNs, renowned for their ability to perform image recognition tasks. Integrating cloud computing also makes scalability, real-time processing, and centralized administration possible across several hospital locations. This rigorous testing and evaluation technique improves hospital security requirements reliably and resiliently. It presents novel methods to transform visitor screening fundamentally, solving the challenge of keeping patients, staff, and facilities secure from evolving dangers. The proposed method greatly improves hospital security since it might increase safety and reduce dangers. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Healthcare billing Fraud Detection Through Machine Learning And Using Homographic Encryption Technique For Prevention 4

Healthcare Billing Fraud Detection Through Machine Learning ...

引用

4th International Conference on Recent Trends in computer science and Technology, ICRTCsT 2021

作者： Alam, Md shoaib Tiwari, Rajesh Kr Pandey, vijay Jharkhand University Of Technology Computer Science And Engineering Jharkhand Ranchi India R.V.S College Of Engg & Tech Computer Science And Engineering Jharkhand Jamshedpur India

ISBN: (纸本)9781665466332

Fraud on health care costs has become dangerous. The healthcare industry has focused on detecting and preventing fraud and increasing its focus on safety and security. Although much research has been done to resolve this issue, no standard solution has been adopted. Now the day app used to detect fraud is riddled with misconceptions and very false ideas. Machine learning allows the app to view locations based on data. The basis of previous self-awareness algorithms can be designed that allow the model to apply what it has learned from previous experiences. Machine learning tools are used to analyze fraudulent situations. Another important area we face in our project is the detection of fraud in real-time. We purpose to design a fraudulent detection model in this paper that provides us a large amount of efficiency, working with the kaggle fraud database. This novel idea is useful for predicting fraud less than 300 times, the current method will be phased with an accuracy of 99.62%, which can prevent many health billing security problems thus making the model more secure. © 2022 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

study and design of decision-making models for education system using artificial intelligence 4

Study and design of decision-making models for education sys...

引用

4th International Conference on Recent Trends in computer science and Technology, ICRTCsT 2021

作者： Kujur, Abhay Gyan P. Kr Tiwari, Rajesh Department Of Computer Science And Engineering Jharkhand Dhanbad828123 India R.V.S College Of Engg & Tech Department Of Computer Science And Engineering Jharkhand Jamshedpur India

ISBN: (纸本)9781665466332

In today's changing educational scenario as it transitioned to more and more dynamism demanding flexibility in terms of Learning pedagogy, Curriculum restructuring, monitoring the performance of students at every level of learning. As students are being an important component of this entire process of the educational ecosystem, their performance monitoring and acting on performance reports with an appropriate decision-making model holds prime importance. The term "big Data"is gaining currency along with machine learning when it comes to Decision making in the education system involves handling an array of *** assisted curriculum restructuring and record-keeping at all levels of the education ecosystem has proven with substantial benefits. AI-assisted decision-making models extract data from various levels and domains of the education system and do a comparative analysis to make the entire decision-making model more reliable and expedite. This study aims to study and design different models of AI-assisted decision-making models for education systems with a comparative study with the traditional models. © 2022 IEEE.

关键词： big data

来源：评论

学校读者我要写书评

暂无评论

Autonomous Mobility: A smart Wheelchair Ecosystem by Iaas Cloud Model using AWs 4

Autonomous Mobility: A Smart Wheelchair Ecosystem by IaaS Cl...

引用

4th International Conference on Innovative Practices in Technology and Management, ICIPTM 2024

作者： saravanan, s.K. Praveen, More Aghalya, s. shadaksharappa, b. Mohankumar, N. Nandagopal, v. Saveetha University Saveetha Institute of Medical and Technical Sciences Tamil Nadu Chennai India Sreenidhi Institute of Science and Technology Telangana Hyderabad India St. Joseph's College of Engineering Tamil Nadu Chennai India Sri Sairam College of Engineering Department of Computer Science and Engineering Karnataka Bengaluru India B.V. Raju Institute of Technology Telangana India Mohan Babu University Andrapradesh Tirupathi India

ISBN: (纸本)9798350307757

A cutting-edge smart wheelchair ecosystem is proposed in this paper which is driven by Infrastructure as a service (Iaas), with the primary emphasis being placed on Amazon Web services (AWs). Through the use of Raspberry Pi, other advanced sensors, and AI algorithms, the system is able to accomplish extraordinary levels of autonomous movement, obstacle avoidance, and individualized user support. Iaas design and AWs makes dynamic scalability, fast data processing and seamless integration of cloud-based services much easier to achieve. The use of virtual computers, cloud storage, and the AWs Internet of Things service provide a solid basis for real-time communication and decision-making. AWs offers a variety of security measures and monitoring tools to guarantee the dependability of the system and the integrity of user data. This sophisticated combination of hardware and AWs Infrastructure as a service not only establishes a new benchmark for intelligent wheelchair technology but also highlights the potential for adaptive, cloud-enabled assistive devices to greatly improve persons with restricted mobility and their quality of life. © 2024 IEEE.

关键词： Infrastructure as a service (Iaas)

来源：评论

学校读者我要写书评

暂无评论

Toward Personalization of User Preferences in Partially Observable smart Home Environments

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第3期4卷 549-561页

作者： suman, shashi Rivest, Francois Etemad, Ali Queen's University Department of Electrical and Computer Engineering KingstonONK7L 3N6 Canada Royal Military College Department of Mathematics and Computer Science KingstonONK7K 7B4 Canada

The technologies used in smart homes have recently improved to learn the user preferences from feedback in order to enhance the user convenience and quality of experience. Most smart homes learn a uniform model to represent the thermal preferences of users, which generally fails when the pool of occupants includes people with different sensitivities to temperature, for instance, due to age and physiological factors. Thus, a smart home with a single optimal policy may fail to provide comfort when a new user with a different preference is integrated into the home. In this article, we propose a bayesian reinforcement learning framework that can approximate the current occupant state in a partially observable smart home environment using its thermal preference and, then, identify the occupant as a new user or someone who is already known to the system. Our proposed framework can be used to identify users based on the temperature and humidity preferences of the occupant when performing different activities to enable personalization and improve comfort. We then compare the proposed framework with a baseline long short-term memory learner that learns the thermal preference of the user from the sequence of actions that it takes. We perform these experiments with up to five simulated human models each based on hierarchical reinforcement learning. The results show that our framework can approximate the belief state of the current user just by its temperature and humidity preferences across different activities with a high degree of accuracy. © 2020 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：