检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICml 2024

作者： Ringel, Liran Cohen, Regev Freedman, Daniel Elad, Michael Romano, Yaniv Department of Computer Science Technion—Israel Institute of Technology Haifa Israel Verily AI Israel Department of Electrical and Computer Engineering Technion—Israel Institute of Technology Haifa Israel

Early time classification algorithms aim to label a stream of features without processing the full input stream, while maintaining accuracy comparable to that achieved by applying the classifier to the entire input. In this paper, we introduce a statistical framework that can be applied to any sequential classifier, formulating a calibrated stopping rule. This data-driven rule attains finite-sample, distribution-free control of the accuracy gap between full and early-time classification. We start by presenting a novel method that builds on the Learn-then-Test calibration framework to control this gap marginally, on average over i.i.d. instances. As this algorithm tends to yield an excessively high accuracy gap for early halt times, our main contribution is the proposal of a framework that controls a stronger notion of error, where the accuracy gap is controlled conditionally on the accumulated halt times. Numerical experiments demonstrate the effectiveness, applicability, and usefulness of our method. We show that our proposed early stopping mechanism reduces up to 94% of timesteps used for classification while achieving rigorous accuracy gap control. Copyright 2024 by the author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning and Artificial Intelligence-Driven Advanced Methods for Acute Lymphoblastic Leukemia Identification and Classification: A Systematic Review

引用

computer Modeling in engineering & sciences 2025年第2期142卷 1199-1231页

作者： Syed Ijaz Ur Rahman Naveed Abbas Sikandar Ali Muhammad Salman Ahmed Alkhayat Jawad Khan Dildar Hussain Yeong Hyeon Gu Department of Computer Science Islamia CollegePeshawar25120Pakistan Department of Information Technology The University of HaripurHaripur22620Pakistan College of Technical Engineering The Islamic UniversityNajaf100986Iraq School of Computing Gachon UniversitySeongnam13120Republic of Korea Department of AI and Data Science Sejong UniversitySeoul05006Republic of Korea

Automatic detection of Leukemia or blood cancer is one of the most challenging tasks that need to be addressed in the healthcare *** of white blood cells(WBCs)in the blood or bone marrow microscopic slide images play a crucial part in early identification to facilitate medical *** Acute Lymphocytic Leukemia(ALL),the most preferred part of the blood or marrow is to be analyzed by the experts before it spreads in the whole body and the condition becomes *** researchers have done a lot of work in this field,to demonstrate a comprehensive analysis few literature reviews have been published focusing on various artificial intelligence-based techniques like machine and deep learning detection of *** systematic review has been done in this article under the PRISMA guidelines which presents the most recent advancements in this *** image segmentation techniques were broadly studied and categorized from various online databases like Google Scholar,science Direct,and PubMed as image processing-based,traditional machine and deep learning-based,and advanced deep learning-based models were *** Neural Networks(CNN)based on traditional models and then the recent advancements in CNN used for the classification of ALL into its subtypes.A critical analysis of the existing methods is provided to offer clarity on the current state of the ***,the paper concludes with insights and suggestions for future research,aiming to guide new researchers in the development of advanced automated systems for detecting life-threatening diseases.

关键词： Acute lymphoblastic bone marrow segmentation classification machine learning deep learning convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Exploring Geospatial Mapping through Speech Commands

Exploring Geospatial Mapping through Speech Commands

引用

International Conference on computer, Electrical & Communication engineering (ICCECE)

作者： Danish Jamil Dev JyotiPatra Pradhuman Kumar Sourodip Kar Papri Ghosh Subhram Das Md Ashifuddin Mondal Computer Science and Engineering (AI&ML) Narula Institute Of Technology Kolkata India Computer Science and Engineering Narula Institute Of Technology Kolkata India

ISBN: (数字)9798331513894

ISBN: (纸本)9798331513900

The integration of voice assistant technology into geospatial data visualization and processing platforms enhances accessibility and user interactivity. Traditional GIS tools often present challenges for non-technical users due to complex interfaces and terminologies. This study addresses these limitations by developing a voice-enabled web-based application capable of understanding domain-specific commands for seamless geospatial data interaction. The proposed system processes voice inputs for tasks such as navigating to specific coordinates, toggling WMS layers, and overlaying geospatial data. A custom Natural Language Processing (NLP) model was designed to interpret geospatial terminologies like “LULC” and “AWiFS”, using curated datasets sourced from platforms such as Bhuvan, Bhoonidhi, and open-access WMS services. The prototype was built using open-source technologies, including Flask for backend processing, OpenLayers for map visualization, and the Web Speech API for voice recognition. Testing on real-world queries achieved $\mathbf{9 3 \%}$ accuracy in converting voice commands into actionable outputs like layer management and map navigation. The results demonstrate the system’s ability to reduce cognitive load while enabling natural interaction with geospatial data. This research provides a scalable solution for enhancing GIS usability, paving the way for more intuitive, accessible, and interactive geospatial tools.

关键词： Technological innovation Navigation Terminology Urban planning Data visualization Transforms Natural language processing Geospatial analysis Usability Testing

来源：评论

学校读者我要写书评

暂无评论

Rural Ecosystem Monitoring in Food Security Analysis Based on Sustainable Agriculture: Artificial Intelligence Application

引用

Remote Sensing in Earth Systems sciences 2024年第1期8卷 56-64页

作者： M, Mohideen AbdulKader Kumaran, M. Senthil Keerthika, Vijay Reddy, Polu Srinivasa Rajendra, Alla R, Subbulakshmi Department of Computing Technologies School of Computing SRM Institute of Science and Technology Tamil Nadu Kattankulathur India Electrical and Electronics Engineering Sri Sivasubramaniya Nadar College of Engineering Tamil Nadu Chennai India Department of Artificial Intelligence and Machine Learning (AI & amp ML) MLR Institute of Technology Dundigal Hyderabad 500043 India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Bowrampet Telangana Hyderabad 500043 India Department of Civil Engineering Aditya University Andhra Pradesh Surampalem India Department of Computer Science and Engineering Karpagam Institute of Technology Coimbatore 641105 India

The ecological security patterns (ESPs) in the Qinling Mountains are facing significant challenges due to the worldwide issues of harsh climate and urbanization. Achieving sustainable development in China requires an understanding of the features of ESPs in the Qinling Mountains, an important ecological barrier. With a Yangxian focus, this work makes use of techniques like geographic information systems (GISs), remote sensing, and machine learning (ml). This research proposed a novel technique in rural region ecosystem monitoring-based food security based on sustainable agriculture using machine learning in artificial intelligence application. Here, input is collected as food security analysis for rural region ecosystem monitoring as well as processed for noise removal and normalization. Then, this data features are extracted and classified using reinforcement radial Gaussian encoder with adversarial Boltzmann temporal neural networks. Experimental analysis is carried out for parameters like training accuracy, random precision, sensitivity, AUC, and F-1 score. The proposed method obtained 98% of training accuracy, 96% of sensitivity, 95% of F-1 score, 97% of AUC, and 93% of random precision. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Artificial intelligence application Ecosystem monitoring Food security Machine learning Rural region Sustainable agriculture

来源：评论

学校读者我要写书评

暂无评论

Optimizing Healthcare Delivery through CloudBased Clinical Decision Support Systems

Optimizing Healthcare Delivery through CloudBased Clinical D...

引用

2024 OPJU International Technology Conference on Smart Computing for Innovation and Advancement in Industry 4.0, OTCON 2024

作者： Ebenezar, U. Samson Jenila Vennila, G. Balakrishnan, T. Suresh Krishnan, Prabhakar Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India Care College of Engineering Department of Computer Science and Engineering Tamil Nadu Trichy India Mohan Babu University School of Computing Department of Ai & Ml Andhra Pradesh Tirupati India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Computer Science and Engineering Chennai India Amrita Vishwa Vidyapeetham Center for Cyber Security Systems and Networks Amritapuri-campus India

ISBN: (纸本)9798350373783

The experiment aims at evaluating how four machine learning algorithms work: Decision Tree, Random Forest, SVM, and Neural Network, in a task, of binary classification. Models were evaluated using comprehensive metrics such as accuracy, precision, recall, F-score and AUC that revealed a good diagnostic performance. Models selected for the experiment and parameters tested on real datasets show steady changes in performance. The Neural Network model remained on top, achieving accuracy, precision, recall, F-score and AUC-ROC of 91.8%, 92.1%, 91.3%, 91.7% and 0.93 respectively. Random Forest displayed a competitive accordance along with the accuracy of 88.6%, precision of 89.2%, recall of 88.7%, and the F-score of 89.0%, and the AUC of 0.91. From the results, Support Vector Machine and Decision Tree models posted lower accuracy, recall, and fscores compared to the Neural Network and Random Forest models in most cases. These reveal the need for the improvement of the suitable machine learning model that comes from specific task needs as well as the consideration of each one of factors including accuracy, interpretability, and computational efficiency. Extensive and development of the model may result in more comprehensive understanding of how the model leads classifying of real-world applications such as medical diagnoses, fraud detection and target marketing. © 2024 IEEE.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

Dynamic Radial Movement Optimization for Throughout Maximization in Energy Harvesting Cognitive Radio Network

Dynamic Radial Movement Optimization for Throughout Maximiza...

引用

2024 International Conference on Distributed Systems, computer Networks and Cybersecurity, ICDSCNC 2024

作者： Vasantha, B. Kumar, Komuravelly Sudheer Husain, Saif O. Naveen, I.G. Kalpana, Kasapogu Maisammaguda Hyderabad India Sr University School of Computer Science & Artificial Intelligence Warangal India The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq Nitte Meenakshi Institute of Technology Department of Ece Bengaluru India Gokaraju Rangaraju Institute of Engineering and Technology Department of Ai&ml Hyderabad India

ISBN: (纸本)9798350375442

The Energy Harvesting (EH) and corrperative communication technique and information accessibility of Energy Harvesting Cognitive Radio Network (EH-CRN). However, minimized throughput in EH, leading to longer EH periods where nodes are inactive and multi-use CRN secondary user interfere with each other transmissions overlap in time due to require maximum energy. In this paper, proposed Dynamic Inertia Weight with Radial Movement Optimization (DRMO) approach provides a framework for dynamic management of both energy and spectrum resources, allowing the network to adapt to changing conditions and maintain high throughput. The DRMO improves the utilization of under used spectrum bands by allowing secondary users to opportunistically transmit data while minimizing interference with primary user. The RMO adapts to changing environmental factors such as variations in harvested energy and spectrum access opportunities making it minimized energy for using dynamic wireless network. The DRMO method exhibits superior performance compared to existing method such as Whale Colony Optimization algorithm (WCO) and Particle Swarm Optimization (PSO). The proposed DRMO method achieving maximum throughput of 0.45, energy of 0.25mJ and time of 0.2, respectively. © 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

Optimizing IoT Threat Mitigation with Artificial Intelligence in Banking: A Multi-Objective Approach 2

Optimizing IoT Threat Mitigation with Artificial Intelligenc...

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Pratap Singh Chauhan, Rudra Sonker, Sanjav Kumar Kaur, Manpreet Sharma, Chhaya Singh, Robin Singh, Ramendra Shri Shankracharya Institute of Professionals Management and Technology Department of CSE-AI and Ai Ml Raipur India Ajay Kumar Garg Engineering College Department of Information Technology Ghaziabad India Institute of Computing Chandigarh University Gharuan Mohali India Raj Kumar Goel Institute of Technology Department of Computer Science & Engineering Ghaziabad India Graphic Era Hill University Dehradun India Ghaziabad India

ISBN: (纸本)9798350371055

This research introduces a novel ai-based mechanism for optimizing threat mitigation in IoT banking systems, addressing the growing vulnerabilities in this critical sector. The proposed mechanism, characterized by a precision of 0.88 and a balanced recall of 0.79, offers a robust defense against cyber threats. Leveraging a Deep Neural Architecture known as Pointer Networks, the mechanism adapts dynamically, ensuring high accuracy in threat identification (precision) while comprehensively covering potential threats (recall), resulting in a harmonious F1 score of 0.83. Through extensive threat-specific evaluations, the mechanism proves versatile, exhibiting high performance in scenarios involving malware (precision: 0.89, recall: 0.82, F1 score: 0.85), denial of service (DoS) attacks (precision: 0.87, recall: 0.78, F1 score: 0.82), and unauthorized access attempts (precision: 0.90, recall: 0.81, F1 score: 0.85). Scalability testing further validates its practical applicability, maintaining precision and F1 score values across varying sizes of IoT ecosystems. This research establishes the proposed mechanism as a potent and adaptable cybersecurity tool, poised to fortify the resilience of IoT banking systems against the dynamic landscape of cyber threats. © 2024 IEEE.

关键词： Artificial Intelligence Banking Cybersecurity IoT Threat Mitigation

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning for Dynamic Compliance Management in Blockchain Supply Chains: An LSTM Perspective 2

Deep Reinforcement Learning for Dynamic Compliance Managemen...

引用

2nd IEEE International Conference on IoT, Communication and Automation Technology, ICICAT 2024

作者： Ranjith, Jinugu Al-Farouni, Mohammed Anitha, R. Poornima, Ediga Sharma, Kamal Kumar, Neelam Sanjeev CMR College of Engineering & Technology Department of CSE India The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq New Prince Shri Bhavani College of Engineering and Technology Department of IT Tamil Nadu Chennai600073 India GRIET Bachupally Department of AI&ML Telangana Hyderabad India GLA University Department of Mechanical Engineering Mathura India SRM Institute of Science & Technology Vadapalani Department of Computer Science & Engineering Chennai26 India

ISBN: (纸本)9798350368109

Supply chain management is one of the industries that benefit greatly from implementing blockchain technology since it supplies chains with a high level of transparency, security, and traceability. Nonetheless, keeping up to date with different regulatory requirements or specifications that change frequently and still meeting contract requirements still pose a major problem. In this paper, we introduce a new method in the dynamic compliance management of blockchain implemented supply chain system by the use of deep reinforcement learning (DRL) and Long Short-Term Memory (LSTM) networks. Through DRL, supply chains can obtain real-time insights in learning from the environment and apply the knowledge effectively to satisfy regulatory standards as well as contractual terms. The inclusion of the LSTM component allows the system to capture sequential dependency and long-horizon effects within the supply-chain data. To prove the efficiency of our strategy, we provide simulation results as well as the analysis of real-world applications that discuss the positive shift in percentages and potential increase in productivity. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Integrating DCCS-Net for High-Fidelity Watermarking and Tampering Detection in Brain Scan Images 6

Integrating DCCS-Net for High-Fidelity Watermarking and Tamp...

引用

6th International Conference on Cybernetics, Cognition and Machine Learning Applications, ICCCmlA 2024

作者： Ahamed, Bsh. Shayeez Baskar, Radhika Nalinipriya, G. Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Computer Science & Engineering Chennai India Madanapalle Institute of Technology & Science Department of CSE-AI&ML Madanapalle India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Electronics and Communication Engineering Chennai India Saveetha Engineering College Department of Information Technology Tamilnadu Chennai India

ISBN: (纸本)9798331505790

This study presents a new approach that combines the Deep Cascade Compressed Sensing Network (DCCS-Net) with a watermarking and tampering detection framework to improve the accuracy and quality of medical images. The system analyzes brain scan images by incorporating watermarks and identifying any tampering, thereby guaranteeing a high level of accuracy and maintaining the structural resemblance to the original images. The essential steps involve preprocessing the image using Discrete Cosine Transform (DCT), employing compressed sensing for efficient data management, and embedding watermarks using binary quantified reference values. The evaluation metrics, namely Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM), indicate that the watermarked images exhibit a PSNR of 41.906 and SSIM of 0.98458. These values suggest that there is minimal degradation in the quality of the images. The tampering detection process achieves a precision of 0.94531, effectively identifying tampered blocks. The reconstructed images exhibit minimal degradation in quality, as evidenced by a PSNR of 36.21 and SSIM of 0.9789. The results highlight the ability of DCCS-Net to effectively manage noise, minimize artifacts, and maintain intricate details, thereby improving the accuracy and reliability of diagnostics. The graphical depiction of metrics provides additional evidence to support the strength and reliability of the methodology in preserving image quality and reconstructing manipulated images, thus ensuring the trustworthiness and reliability of medical image analysis. © 2024 IEEE.

关键词： Discrete cosine transforms

来源：评论

学校读者我要写书评

暂无评论

Application of Multilingual OCR Algorithm for Converting Text from Images and PDFs 5th

Application of Multilingual OCR Algorithm for Converting Tex...

引用

5th International Conference on Data science, Machine Learning and Applications, ICDSmlA 2023

作者： Venkatesh, Maganti Chiranjeevi, S.V. Kumar, M. Siva Alam, S. Shiek Davanam, Ganesh Malchi, Sunil Kumar Department of AI & ML Aditya Engineering College Surampalem India Department of CSE N.B.K.R Institute of Science and Technology Vidyanagar AP Nellore India TN Chennai India AP Tirupati India

ISBN: (纸本)9789819780426

Multilingual OCR with audio output is an innovative approach that aims to convert text from imagesand PDFs into audio representations in multiple languages. This method leverages advancedtechniques in OCR, language identification, text-to-speech (TTS), and graph analysis to provide accurate and comprehensive results. The process begins with preprocessing the input images or PDFsto enhance their quality and remove any noise or distortions. Next, sophisticated OCR algorithms andmachine learning techniques are employed to extract text from the documents. This step involves character recognition, word segmentation, and sentence parsing to ensure precise and reliable text extraction. Language identification models are then utilized to determine the languages present in the extracted text, enabling multilingual support. The method also incorporates computer vision techniques and pattern recognition algorithms for graph analysis. Graphsand charts within the documents are identified and their components, such as labels, axes, and datapoints, are analyzed and interpreted. The textual and graphical information is combined to generate the final audio representation. By integrating cutting-edge OCR algorithms, language identification, language-specific TTS models, and graph analysis techniques, this novel method facilitates accurate multilingual OCR with audio output. It enhances accessibility and comprehension of textual and graphical information, catering to a diverse range of users with different language needs. This technology has the potential to benefit various domains, including education, accessibility services, and information dissemination in multilingual contexts. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Deep 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：