检索结果-内蒙古大学图书馆

5th International Conference on Advances in AI for Biomedical Instrumentation, Electronics and Computing, ICABEC 2023

作者： Asha, P. Babu, Bhavya Mary, S. Prince Ankayarkanni, B. Praveena, M.D. Anto Christy, A. Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India

ISBN: (纸本)9781032642987

Nowadays, digital withdrawals mostly rely on cards. Days have come where people don’t have to carry cash in their pockets and just a small card is enough to make all the withdrawals. Problems with cards will lead to passwords being hacked and easily lead to fraud. Credit card fraud can be identified using Hidden Markov Model (HMM) and Formula Based Authentication. In the Existing system, card withdrawals are very routine among the people and the frauds corresponding to the improvement of security are increasing. In the proposed system, ML algorithms have been applied to detect MasterCard deception in a disproportionate dataset. In the modification process, an application is developed for a banking sector particularly for a credit or ATM card. Users can create an account and get the ATM card along with a unique formula which should be used during suspicious transactions. The user behavior of every transaction is tracked by Hidden Markov Model and if there are any occurrences of suspicious transactions, then a message is sent to the user with the keys that are required to complete the formula. After the user applies the keys to the formula the solution must be entered as the password in order to complete the transaction. © 2024 The Author(s).

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Cyberbullying Predictive Analysis on X Data with Multi Model Supervised Technique 3

Cyberbullying Predictive Analysis on X Data with Multi Model...

引用

3rd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2024

作者： Samsun, S. Basil Xavier, S. Karunya Institute of Technology and Science Coimbatore Computer Science and Engineering India

ISBN: (纸本)9798350375190

This research introduces a multi-model supervised predictive analytic method for X cyberbullying detection. The overarching goal of this study is to find a way to effectively detect and categorize cyberbullying incidents on social media sites before they get out of hand. This study has gathered, cleaned, and turned a dataset of cyberbully-ingrelated tweets in X platform into numerical attributes. In order to forecast if tweets included cyberbullying, three ML models - Support Vector Machines (SVM), Random Forest (RF), and Deep Neural Networks (DNN) - were used. Accuracy, precision, recall, and F1-score were all highly achieved, proving that the suggested method was beneficial. To further explore how various feature engineering strategies affected model results, more tests were carried out. Cyberbullying detection tasks should take into account a variety of language and context-based indicators, according to the research. In conclusion, this research adds to the continuing endeavors to create preventative steps to fight cyberbullying by offering new perspectives and possible ways to keep an eye on and handle this common problem. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A combinatorial algorithm for finding straight skeleton of a digital object

引用

Multimedia Tools and Applications 2025年 1-21页

作者： Maity, Anukul Dutt, Mousumi Biswas, Arindam Department of Computer Science and Engineering Narula Institute of Technology 81 Nilgunj Road Agarpara West Bengal Kolkata700109 India Department of Computer Science and Engineering St. Thomas’ College of Engineering and Technology 4 Diamond Harbour Road Kidderpore West Bengal Kolkata700023 India Department of Information Technology Indian Institute of Engineering Science and Technology Botanical Garden Road Shibpur West Bengal Howrah711103 India

The paper presents a combinatorial algorithm to find the straight skeleton of the inner isothetic cover of a digital object imposed on a uniform background grid. The isothetic polygon (orthogonal polygon) tightly inscribes the given digital object. The algorithm stated here finds the straight skeleton of any isothetic polygon (simple or non-simple) in O(nglogng) time in a single traversal by applying combinatorial rules, where n is the number of pixels on the boundary of the digital object and g is the grid size on which the digital object is imposed. To find the straight skeleton of non-simple orthogonal polygon, the polygon is divided into sub-parts which are a set of simple orthogonal polygons. The straight skeleton is generated for each of the sub-parts and the corresponding results are merged. The orthogonal polygon containing holes is cut at each holes and the polygon becomes hole-free. The algorithm to obtain the straight skeleton is applied on it. The disconnected hole parts are rejoined and the result is merged. The straight skeleton is useful shape descriptor of digital object. This algorithm stated here has applications in shape analysis. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

The Face Sync - Smart Attendance System 4

The Face Sync - Smart Attendance System

引用

4th International Conference on Expert Clouds and Applications, ICOECA 2024

作者： Asha, P. Bekkem, Chakradhar Reddy Priya, Y Soni Mathivanan, G. Grace, L. K. Joshila Srinivasan, N. Sathyabama Institute of Science and Technology Computer Science and Engineering Chennai India

ISBN: (纸本)9798350385793

The existing attendance marking in various institutions, including schools and offices, is fraught with various challenges. Traditional methods, such as manual data collection through individual calls, are time-consuming and prone to errors. However, advancements in technology offer automated solutions that streamline the process and ensure accurate record-keeping. In this context, this study proposes the implementation of 'The Face Sync-Smart Attendance Marking System, ' which leverages cutting-edge technologies for face identification and analysis. Developed using deep learning algorithms, this system effectively recognizes faces by analyzing gathered data. The recorded attendance data is then transmitted to the host via email for further processing. The proposed system is implemented using Python programming language and utilizes libraries such as CV2, Face Recognition, and Smtplib to achieve its functionality. This innovative approach promises to revolutionize attendance management, enhancing efficiency and reliability across various organizational settings. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Interactive Learning with AlphAR: A Symbol-Recognition Aid for Dyslexic Children Through Augmented Reality

Interactive Learning with AlphAR: A Symbol-Recognition Aid f...

引用

2024 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication, IConSCEPT 2024

作者： Shilbi, Susan Chhirolya, Vaidik Basha, Niha Kamal Surendiran, B. School of Computer Science and Engineering Vellore Institute of Technology Vellore India National Institute of Technology Puducherry Department of Computer Science and Engineering Karikal India

ISBN: (纸本)9798331540685

Dyslexia is a neurological condition that affects a person's ability to read, write, and spell. It is characterized by difficulties in processing phonological information, leading to challenges in acquiring fluent and accurate reading skills. Early assistance fosters a positive learning trajectory, enhancing the overall well-being and confidence of dyslexic individuals. AlphAR is an innovative augmented reality (AR) web system specifically tailored to address the challenges of symbol recognition in dyslexic children, developed using cutting-edge A-Frame and *** technologies. It harnesses marker-based AR to create an immersive learning environment. The novelty lies in its seamless integration of marker patterns with corresponding 3D models, facilitating interactive learning experiences for children aged 5 to 10. Through intuitive user interface elements and audio cues, AlphAR enhances engagement and promotes auditory learning. Ethical design principles ensure inclusivity and user-friendliness, prioritizing participant comfort and engagement. Users interact with the system through intuitive gestures, such as flipping down and left, further enhancing skill development. The iterative nature of AlphAR allows for adaptability to individual learning paces, fostering a positive and inclusive experimental environment. To validate AlphAR's effectiveness, we will benchmark it against established AR interventions like LitAR, AHA System and many others. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A top-down character segmentation approach for Assamese and Telugu handwritten documents

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第9期15卷 3275-3287页

作者： Dutta, Prarthana Muppalaneni, Naresh Babu Department of Computer Science and Engineering National Institute of Technology Assam Silchar786003 India Department of Computer Science and Engineering The Assam Kaziranga University Assam Jorhat785006 India Indian Institute of Information Technology Design and Manufacturing Kurnool Andhra Pradesh Kurnool India

Digitization offers a solution to the challenges associated with managing and retrieving paper-based documents. However, these paper-based documents must be converted into a format that digital machines can comprehend, as they primarily understand alphanumeric text. This transformation is achieved through Optical Character Recognition (OCR), a technology that converts scanned image documents into a format that machines can process. A novel top-down character segmentation approach has been proposed in this work, involving multiple stages. Our approach began by isolating lines from handwritten documents and using these lines to segment words and characters. To further enhance the character segmentation, a Raster Scanning object detection technique is employed to isolate individual characters within words. Thus, the character segmentation results are integrated from the results of the vertical projection and raster scanning. Recognizing the significance of advancing digitization of handwritten documents, we have chosen to focus on the regional languages of Assam and Andhra Pradesh due to their historical and cultural importance in India’s linguistic diversity. So, we have collected datasets of handwritten texts in Assamese and Telugu languages due to their unavailability in the desired form. Our approach achieved an average segmentation accuracy of 93.61%, 85.96%, and 88.74% for lines, words, and characters for both languages. The key motivation behind opting for a top-down approach is two-fold: firstly, it enhances the accuracy of character recognition, and secondly, it holds the potential for future use in language/script identification through the utilization of segmented lines and words. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Efficient Mental Health Therapist Chatbot Assisted by Artificial Intelligence 10

Efficient Mental Health Therapist Chatbot Assisted by Artifi...

引用

10th International Conference on Advanced Computing and Communication Systems, ICACCS 2024

作者： Asha, P. Adhithya, B. Hariharan, R.S. Srinivasan, N. Joshila Grace, L.K. Ronald Doni, A. Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India

ISBN: (数字)9798350384369

ISBN: (纸本)9798350384369

This work suggests developing an AI-based chat bot that may serve as a mental health therapist in order to address the expanding need for readily available mental health care. This chat bot provides users with a safe and understanding space to discuss their emotions and concerns. It is built on Natural Language Processing (NLP) along with Machine Learning principles. The chat bot's operations are based on the fundamental concepts of Sentiment Analysis, Emotion Recognition, and Natural Language Understanding. Employing these techniques supports the chat bot to efficiently evaluate and categorize user input, thereby aids in effective understanding of the user's emotional state and intent. The chat bot delivers user support by recognizing emotions, offering tailored advice, and directing users to relevant mental health resources. It prioritizes user privacy, ensuring a secure space for open discussions, while continuous learning enables ongoing improvements in providing meaningful assistance. © 2024 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Trust management in online computing environment: a complete review

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第1期15卷 491-545页

作者： Singh, Ashish Chatterjee, Kakali School of Computer Engineering KIIT Deemed to be University Odisha Bhubaneswar751024 India Department of Computer Science and Engineering National Institute of Technology Bihar Patna800005 India

Nowadays, trust management plays a significant role in different applications like commercial applications, Internet of Things (IoT) based applications, social networking applications, cloud computing-based applications, sensor networks, online services, and many more. Thus, it is an important research area for industry and engineering research communities. The concept of trust is mainly derived from long-term sociological and psychological human behaviour. It is used for decision-making purposes in different contexts and perspectives. Many growing research studies address the development of trust computation models using different approaches in different areas, such as cloud computing, P2P networks, online social network, etc. Still, most of the prior work does not provide a comprehensive systematic review of different trust management systems nor provide sufficient details about the computation process. In this paper, we have discussed a systematic review of the existing trust management systems by indicating the limitation of previous works. A systematic review started with research question identification, followed by searching and filtration of relevant works, and ended with a comparison and final report. A detailed comparative study of trust computational models will help understand the security and privacy aspects of trust. This survey provides a detailed study of each trust taxonomy and computation model in different online computing environments. The survey result finds several trust computation techniques. The results also say that trust in the online computing environment provides greater security and protection against several threats and attacks. Despite the potential benefits of trust, the results also included challenges and open research issues that are still opportunities for new researchers. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Bone Fracture Detection using YOLOv8 and OpenCV 2

Bone Fracture Detection using YOLOv8 and OpenCV

引用

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Brikila, J. Praneeth Varma, I.V.S. Anand, Abhilakshay SRM Institute of Science and Technology Computer Science and Engineering Chennai India

ISBN: (纸本)9798331534950

This study introduces a deep learning method for automatically detecting bone fractures with the YOLOv8 object detection model, developed to aid radiologists in accurately and efficiently interpreting X-ray images. The model was developed using a carefully selected dataset of categorized X-ray pictures, utilizing convolutional neural networks (CNNs) to capture important spatial characteristics for fracture detection. The main parts of the experimental setup involved splitting the dataset, fine-tuning model settings, and assessing performance with precision, recall, F1-score, and mean Average Precision (mAP) metrics. The findings showed a high level of accuracy in classifying fractures, with the model successfully identifying and categorizing them while also striking a balance between precision and recall. Sample detections were displayed for qualitative evaluation, and error analysis identified areas for model improvement, specifically in detecting minor fractures. The results show that the YOLOv8 detection model is a promising method for quickly identifying bone fractures, which could improve accuracy in diagnosis and aid in medical imaging decision- making. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Advanced Computational Techniques In Stroke Prediction: Analyzing Cardiac And Vascular Bio-Signals

Advanced Computational Techniques In Stroke Prediction: Anal...

引用

2024 International Conference on Recent Innovation in Smart and Sustainable technology, ICRISST 2024

作者： Kathiravan, M. Raju, Boya Vengata Thirupathi Rao, K. Hindustan Institute of Technology and Science Computer Science and Engineering Chennai India

ISBN: (纸本)9798350309140

Stroke is a potentially fatal or disabling condition, making it crucial to promptly identify the early warning signs. Ischemic and hemorrhagic strokes are clinically differentiated, necessitating immediate management with thrombolytic or coagulant medication. Initially, it is imperative to identify the prompt indicators of a stroke, which may differ across individuals and necessitate the involvement of a specialist and admission to a hospital. Previous research has primarily focused on post-stroke treatment rather than stroke prevention. Recent research has shown a growing dependence on image processing, specifically MRI and CT scans, to identify and forecast prognostic indicators in individuals who have suffered from strokes. Identifying such processes in real time poses difficulties, and assessing these processes incurs costs and time constraints. This work introduces a multi-modal bio-alert system that utilizes photoplethysmography (PPG) and electrocardiogram (ECG) data to diagnose and evaluate cognitive stroke prognostic indicators in older individuals. We have created a stroke prediction gadget that uses a combination of regression algorithms to accurately estimate the occurrence of stroke infections in real-time, even when the user is walking outdoors. Elderly individuals can conveniently transport bio-signal sensing devices due to the meticulous apparatus that captures bio-indicators while walking at a sample rate of 1,000 Hz, either from the three conductors of the ECG or the forefinger for PPG. The performance and efficiency of the accurate prediction were proven through the real-time study of stroke patients in the senior age group. © 2024 IEEE.

关键词： Photoplethysmography

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：