检索结果-内蒙古大学图书馆

2024 International Conference on science, Technology, Engineering and Management, ICSTEM 2024

作者： Sri Ram, M.S. Joy, Emmanuel Shree, Leka J. Division of Data Science and Cyber Security Karunya Institute of Technology and Sciences Coimbatore India Division of Artificial Intelligence and Machine Learning Karunya Institute of Technology and Sciences Coimbatore India

ISBN: (纸本)9798350376913

Web accessibility plays a significant role in shaping our online experiences in today's ever-changing digital world. People with vision impairmentsstill have trouble using most websites. This paper introduces WebSight an innovative AI-based Image Description Generator web extension to address these challenges. By seamlessly interfacing with a Flask server, Optical Character Recognition, and a dedicated Image Description Generator model, this browser extension systematically enhances web accessibility by methodically replacing 'alt' attributes of images with meticulously generated descriptions. This approach significantly contributes to web inclusivity, providing visually impaired users with accurate and contextually rich information. The extension's commitment to inclusivity is further demonstrated through the intelligent integration of Tesseract-OCR and Text-to-Speech ensuring a novel and far-reaching impact, offering an enhanced and tailored browsing experience for users with visual impairments. © 2024 IEEE.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Enhanced Radiological Anomaly Detection using Optimized YOLO-NAS Model

Enhanced Radiological Anomaly Detection using Optimized YOLO...

引用

2024 International Conference on Advances in Modern Age Technologies for Health and Engineering science, AMATHE 2024

作者： Leka Shree, J. Joy, Emmanuel Sri Ram, M.S. Karunya Institute Of Technology And Sciences Division Of Data Science And Cyber Security Coimbatore India Division Of Artificial Intelligence And Machine Learning Karunya Institute Of Technology And Sciences Coimbatore India

ISBN: (纸本)9798350371567

Chest X-rays are commonly used to detect lung diseases. Chest radiographs often have a lot of perceptual errors. The application of image processing in diagnosing lung diseases has improved medical imaging. This has also enabled the creation of databases for classifying chest radiographs. However, current methods are not accurate enough to reliably detect anomalies. Aimed at improving the shortcomings of existing techniques, the proposed approach uses the Automated Neural Architecture Construction (AutoNAC) engine, a proprietary of Neural Architecture Search (NAS). Comparative evaluations against established models, including YOLOv3, YOLOv5, YOLOv7, and YOLOv8, showcase the superiority of YOLO-NAS in mean Average Precision (mAP@0.5), precision, and recall metrics. The originality of this study lies in introducing NAS specifically AutoNAC, to optimize neural network architectures for chest X-ray anomaly detection, marking a significant advancement in diagnostic capabilities in medical imaging. © 2024 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Understanding adversarial attacks on observations in deep reinforcement learning

引用

science China(Information sciences) 2024年第5期67卷 69-83页

作者： You QIAOBEN Chengyang YING Xinning ZHOU Hang SU Jun ZHU Bo ZHANG Department of Computer Science and Technology Beijing National Research Center for Information Science and Technology Tsinghua-Bosch Joint Center for Machine Learning Institute for Artificial Intelligence Tsinghua University Peng Cheng Laboratory

Deep reinforcement learning models are vulnerable to adversarial attacks that can decrease the cumulative expected reward of a victim by manipulating its observations. Despite the efficiency of previous optimization-based methods for generating adversarial noise in supervised learning, such methods might not achieve the lowest cumulative reward since they do not generally explore the environmental ***, a framework is provided to better understand the existing methods by reformulating the problem of adversarial attacks on reinforcement learning in the function space. The reformulation approach adopted herein generates an optimal adversary in the function space of targeted attacks, repelling them via a generic two-stage framework. In the first stage, a deceptive policy is trained by hacking the environment and discovering a set of trajectories routing to the lowest reward or the worst-case performance. Next, the adversary misleads the victim to imitate the deceptive policy by perturbing the observations. Compared to existing approaches, it is theoretically shown that our adversary is strong under an appropriate noise level. Extensive experiments demonstrate the superiority of the proposed method in terms of efficiency and effectiveness, achieving state-of-the-art performance in both Atari and MuJoCo environments.

关键词： deep learning reinforcement learning adversarial robustness adversarial attack

来源：评论

学校读者我要写书评

暂无评论

Decoding Bias in #Climatechange Tweets: A Neural Language Style Transfer Approach

Decoding Bias in #Climatechange Tweets: A Neural Language St...

引用

2024 International Conference on artificial intelligence and Quantum Computation-Based Sensor Applications, ICAIQSA 2024

作者： George, Elizabeth Leah Parthasarathy, Subashini Avinashilingam Institute for Home Science and Higher Education for Women Department of Computer Science Coimbatore India Avinashilingam Institute for Home Science and Higher Education for Women Centre for Machine Learning and Intelligence Department of Computer Science Coimbatore India

ISBN: (纸本)9798331517953

In response to the increase of biased and misleading opinions on social media regarding climate change, we present the Neural Language Style Transfer Bias (NLST Bias) framework - an AI-driven solution to identify and mitigate bias in climate-related tweets. Our approach analyses a curated dataset of climate change tweets collected from Twitter, leveraging spaCy for text pre-processing and BERT-based sentence embeddings to extract semantic features. Evaluation metrics with classifier models showed significant improvements, with CNN-LSTM achieving the highest F1 score of 78%. Most classifiers show marked improvements across accuracy, precision, recall, and F1 score with NLST, highlighting its effectiveness on this dataset. NLST Bias employs DistilBERT to classify tweets as biased or unbiased, with the Named Entity Recognition (NER) model trained on RobERTa transformers to identify word-level bias indicators. The framework's core component is a transformer-based style transfer model (e.g., GPT-2) that modifies the stylistic tone of biased text while preserving its semantic content. This transfer uses a style-specific decoder within the transformer architecture, ensuring the generated text maintains grammatical accuracy and contextual relevance. The resulting output exhibits tone, phrasing, and word choice adjustments to foster a more neutral style. Results indicate a significant reduction in bias without compromising text fluency or naturalness, verified through statistical metrics and human evaluations. Furthermore, Explainable AI techniques are integrated to enhance transparency in model decisions. Our findings underscore NLST Bias's efficacy in countering climate misinformation and promoting balanced discussions on social media, highlighting its potential as a tool for responsible AI in digital discourse. © 2024 IEEE.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Deepfake Detection: Leveraging InceptionResNetV2 and LSTM for Enhanced Accuracy

Deepfake Detection: Leveraging InceptionResNetV2 and LSTM fo...

引用

2025 International Conference on Pervasive Computational Technologies, ICPCT 2025

作者： Saini, Aradhna Attiuttama Naaz, Sheenam Shivhare, Anushka Dhuriya, Gaurav Yadav, Neha G L Bajaj Institute of Technology and Management Computer Science and Engineering Greater Noida India G L Bajaj Institute of Technology and Management Artificial Intelligence and Machine Learning Greater Noida India Sharda University Computer Science and Engineering Greater Noida India Netaji Subhas University of Technology Computer Science and Engineering Delhi India

ISBN: (纸本)9798331508685

The antique adage "seeing is believing"is simply no longer actual, which has profound implications for a ramification of sides of our lives. Deepfakes are becoming less complicated and simpler to create as technology advances. In fact, with the right software program, you can do a part of it right out of your palm. it is challenging to pick out deepfakes. The capability of the human eye to differentiate among deepfakes has reduced. however, a few academics have tried to identify deepfake. Deepfakes are media that can be generated by synthetic intelligence (AI) using algorithms. artificial intelligence algorithms are designed to understand the traits of both the supply and the target photo. Subsequently, the target image is positioned on the pinnacle of the supply photograph. Our goal is to pick out video deepfakes by way of utilizing deep getting-to-know neural networks which include InceptionResNetV2 and LSTM. With the usage of transfer learning and the pre-trained InceptionResNetV2 CNN for characteristic extraction and vector production, we were able to efficaciously assemble a deepfake detection version. The capabilities had been used to train the LSTM layer, and the confusion matrix that was produced offers us the accuracy of testing and validation. The corresponding version's accuracy for 20 and 40 epochs was 84.75% and 91.48%, respectively. © 2025 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Unveiling the Vision: A Comprehensive Review of computer Vision in AI and ML

Unveiling the Vision: A Comprehensive Review of Computer Vis...

引用

2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems, ADICS 2024

作者： Laad, Meena Maurya, Ratan Saiyed, Najeeb Symbiosis Institute Of Technology Dept. Of Applied Science Maharashtra Pune India Symbiosis Institute Of Technology Dept. Of Artificial Intelligence And Machine Learning Maharashtra Pune India

ISBN: (纸本)9798350364828

In the era of rapid technological advancement, computer Vision has emerged as a transformative force, reshaping the landscape of artificial intelligence (AI) and machine learning (ML). This comprehensive review paper aims to delve into the intricate evolution, methodologies, applications, challenges, and future trajectories of computer Vision. Moving beyond a mere exploration of technical intricacies, our objective is to present a holistic narrative that encapsulates the profound impact of computer Vision on AI and ML and its repercussions across society. The journey begins by traversing the philosophical and historical roots of computer Vision, unraveling the threads that connect human visual perception to the development of artificial vision. By exploring the historical evolution from early image processing to the current era of deep learning, we seek to elucidate the intellectual milestones that have shaped the field. Methodologically, this paper navigates through both traditional approaches and contemporary deep learning paradigms. It dissects traditional methods, emphasizing their enduring relevance and influence on modern computer Vision applications. In parallel, exploring deep learning delves into established architectures all the nuanced impact of design choices on interpretability and explain ability. Applications form a cornerstone of our review, with an enriched focus on case studies that spotlight the transformative influence of computer Vision. Beyond the traditional domains of image recognition, we delve into the healthcare renaissance, where computer Vision contributes to diagnostics, drug discovery, and personalized medicine. Furthermore, we explore its role in smart cities, extending beyond surveillance to urban planning, traffic management, and environmental monitoring. © 2024 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Smart Attendance Management using a Self-Supervised learning Approach 5

Smart Attendance Management using a Self-Supervised Learning...

引用

5th International Conference on Image Processing and Capsule Networks, ICIPCN 2024

作者： Vikram, D. Ajina, H. Gokilapriya, S. Malini, M. Rathinam Technical Campus Department of Computer Science and Engineering Coimbatore India Rathinam Technical Campus Department of Artificial Intelligence and Data Science Coimbatore India Kalingarkarunanidhi Institute of Technology Department of Artificial Intelligence and Machine Learning Coimbatore India Sri G.V.G Visalakshi College for Women Department of Information Technology Udumalpet India

ISBN: (纸本)9798350367171

Organizational efficiency is significantly influenced by automated attendance management systems, yet traditional methods often lack flexibility and reliability. This study proposes a novel approach to transform the Smart Attendance Management System (SAMS) by leveraging recent advances in Self-Supervised learning (SSL). The proposed method enhances accuracy and adaptability without explicit supervision by integrating SSL techniques at multiple stages, including feature extraction, anomaly detection, and data preparation. The proposed system learns meaningful representations from unlabeled attendance data through SSL-based data preprocessing, thereby improving the performance of downstream tasks. Feature extraction by utilizing SSL enables the proposed system to extract robust features enhancing both anomaly detection and attendance tracking. Anomaly detection models trained with SSL frameworks can effectively identify unusual attendance patterns. Additionally, SSL-based continuous learning ensures that the proposed system can adapt to the changing user behaviors and various situations. Supported by SSL, the proposed SAMS offers a more precise, efficient, and flexible solution for managing attendance, positioning it to meet the evolving demands of contemporary businesses across various industries. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Tropical Cyclone Detection and Tracking Using YOLOv8 Algorithm 1

Tropical Cyclone Detection and Tracking Using YOLOv8 Algorit...

引用

1st International Conference on Cognitive, Green and Ubiquitous Computing, IC-CGU 2024

作者： Rout, Saroja Kumar Kumar, Kottu Santosh Sahu, Ruchismita Barik, Shekharesh Pradhan, Samarendra Department of Information Technology Hyderabad India Department of Artificial Intelligence and Machine Learning Hyderabad India Templecity Institute of Technology and Engineering Department of Computer Science & Engineering Bhubaneswar India DRIEMS University Department of Computer Science & Engineering Cuttack India Data scientist Jayapur Cuttack India

ISBN: (纸本)9798350361780

Coastal areas around the world face a great threat from tropical cyclones, which makes timely and accurate identification essential for efficient disaster response. An enhanced method for detecting tropical cyclones is proposed in this work using the YOLOv8 (You Only Look Once version 8) object identification algorithm. Using the real-time object recognition capabilities of YOLOv8, the methodology is designed to tackle the challenges associated with finding cyclonic structures in satellite data. To detect crucial features typical of tropical cyclones - like cloud formations, circular symmetry, and dynamic atmospheric fluctuations - the YOLOv8 architecture is improved. To ensure its adaptability to different climatic circumstances, the model is trained using a varied dataset of labeled satellite photos. The YOLOv8-based methodology is superior to existing methods in detecting tropical cyclones with accuracy and efficiency almost in real-time, as demonstrated by the experimental results. Because of the algorithm's excellent precision, recall, and computing economy, early warning systems and catastrophe preparedness can benefit greatly from it. This research contributes to the ongoing effort to develop detection approaches for increased resilience in vulnerable coastal areas, while also utilizing YOLOv8's capabilities to address the global threat posed by tropical cyclones. This study can help clarify the necessity of improving models and conducting better observations of Tropical Cyclones. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

The Future of Driving: A Review on the Combination of artificial intelligence and Autonomous Vehicles 2

The Future of Driving: A Review on the Combination of Artifi...

引用

2nd DMIHER International Conference on artificial intelligence in Healthcare, Education and Industry, IDICAIEI 2024

作者： Zade, Nikita Gawande, Mayur Verma, Prateek Gundewar, Swapnil Faculty of Engineering and Technology Department of Artificial Intelligence and Data Science Sawangi Maharashtra Wardha442001 India Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Artificial Intelligence and Machine Learning Sawangi Maharashtra Wardha442001 India

ISBN: (纸本)9798331528713

The convergence of artificial intelligence (AI) and Autonomous Vehicles (AV) are poised to revolutionize the automotive industry, offering safer, more efficient, and sustainable transportation solutions. This review article explores the current state of AVs, role of AI in AV, challenges and hurdles, Real world applications & development, its critical technological components, and their impact on society. This paper presents a wide array of applications of AI in AV, elaborating on the way complex sensor fusion, computer vision, and machine learning (ML) algorithms makes AVs perceive their surroundings, form critical opinions, and carry out accurate motions. AI is making real time interpretations of great quantities of data which are paving the way for safer and more effective navigation under a diversity of traffic circumstances, from sensor fusion to decision-making algorithms. The next section of this paper elaborates on the role of AI in the field of AV in perceiving, planning, and navigating through real world environment, while also talking about issues of integration and ethics. This paper further identifies its social, economic, and environmental consequences, resulting from mass use of AV. This article discusses the latest developments and opportunities in the regulatory environment, gives an overview of how AV define transportation in the near future. This paper also explores the levels of autonomy of AVs as defined by the Society of Automotive Engineers (SAE) and defines the process from driver assistance to full automation. It examines the ethical and technical considerations arising at each instant and emphasizes the key role AI continues to play in providing more autonomy while preserving security and dependability. © 2024 IEEE.

关键词： Automotive industry

来源：评论

学校读者我要写书评

暂无评论

Touchless Mouse Control Via Hand Gestures Using Resnet and Mediapipe

Touchless Mouse Control Via Hand Gestures Using Resnet and M...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： Jagadeeswara Rao Palisetti Digumarthi Srilikhitha Karna Bhargava Basa Bhavana Devi Mettu Bharath Kumar Computer Science and Engineering(Artificial Intelligence and Machine Learning) Lakireddy Bali Reddy College of Engineering Mylavaram India

ISBN: (数字)9798331512248

ISBN: (纸本)9798331512255

Touchless control of systems using hand gestures is a trending technology in the field of Human-computer Interaction (HCI). One of the most common ways to interact with systems is through the mouse. In this paper, a touchless mouse is focus on, which can perform the same operations as a physical mouse using finger and hand gestures. All of these operations are carry out by the system without requiring any external devices. In the physical mouse, we hold and operate it using the index and middle fingers. Similarly, we use the same hand pose to control the touchless mouse system. Nowadays, every system has an inbuilt webcam. This system uses a low-resolution webcam as input to capture hand gestures with 21 landmarks using OpenCV and MediaPipe. Based on the movements of the landmarks in the hand, the cursor can navigate, and various actions such as right-click, left-click, double-click, zoom in and zoom out, drag and drop files, multiselect files, increase, and decrease volume, adjusting the brightness, are easily performed, ResNet18 is used to stop the cursor movement. Using different finger and hand gestures. The system has the potential to replace traditional HCI tools in the future and help optimize hu-man-computer communication.

关键词： Hands Human computer interaction Performance evaluation Webcams Tracking Navigation Hospitals Brightness Gesture recognition Indexes

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：