检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Bandyopadhyay, Dibyanayan Bhattacharjee, Soham Ekbal, Asif Department of Computer Science and Engineering IIT Patna India School of AI and Data Science IIT Jodhpur India

Large Language Models (LLMs) are highly proficient in language-based tasks. Their language capabilities have positioned them at the forefront of the future AGI (Artificial General Intelligence) race. However, on closer inspection, Valmeekam et al. (2024);Zečević et al. (2023);Wu et al. (2024) highlight a significant gap between their language proficiency and reasoning abilities. Reasoning in LLMs and Vision Language Models (VLMs) aims to bridge this gap by enabling these models to think and re-evaluate their actions and responses. Reasoning is an essential capability for complex problem-solving and a necessary step toward establishing trust in Artificial Intelligence (ai). This will make ai suitable for deployment in sensitive domains, such as healthcare, banking, law, defense, security etc. In recent times, with the advent of powerful reasoning models like Openai O1 and DeepSeek R1, reasoning endowment has become a critical research topic in LLMs. In this paper, we provide a detailed overview and comparison of existing reasoning techniques and present a systematic survey of reasoning-imbued language models. We also study current challenges and present our findings. © 2025, CC BY.

关键词： Problem solving

来源：评论

学校读者我要写书评

暂无评论

Segmentation of Retinal Blood Vessels in Fundus Images Using Fully Convolutional Networks

Segmentation of Retinal Blood Vessels in Fundus Images Using...

引用

2024 IEEE International Conference on Communication, Computing and Signal Processing, IICCCS 2024

作者： Vijayalakshmi, G. Al-Farouni, Mohammed Sourav Sravani, Ch Satya Kumar Singh, Rajesh Saiharsha, R. Prince Shri Venkateshwara Padmavathy Engineering College Chennai India The Islamic University College Of Technical Engineering Department Of Computers Techniques Engineering Najaf Iraq The Islamic University Of Al Diwaniyah College Of Technical Engineering Department Of Computers Techniques Engineering Al Diwaniyah Iraq Chandigarh Group of Colleges Chandigarh Engineering College Department of Computer Application Punjab Jhanjeri Mohali140307 India Aditya Engineering College Department of Computer Science & Engineering Surampalem India Ies University Ies Institute of Technology and Management Department of Computer Science & Engineering M.P. Bhopal India Saveetha Institute of Medical and Technical Sciences Department of CSE-AI Tamilnadu Chennai India

ISBN: (纸本)9798350390759

Segmentation is mandatory to analyze retinal blood vessel indication for diagnosis of various ophthalmic and systemic disorders. This paper takes a look at this problem, specifically, the application of Fully Convolutional Networks (FCNs) in this whole process, with a primary focus on the U-Net architecture. In this work, the authors conduct the experiments on three datasets, namely DRIVE, STARE and CHASE_DB1, and prepare the images for modeling through normalization, resizing, and data augmentation. Due to the binary structure of the task, the loss function of the proposed method is binary cross-entropy along with the Dice coefficient, and the model is trained with the Adam optimizer. The improvement scores that was obtained shows that the proposed model has a high accuracy, precision, recall and F1 score on all the datasets used and has proven to be better than other existing methods. The study establishes the usefulness of FCNs in segmenting the tree structure of the retinal blood vessel structures in uniterrupted manner, and presented promising improvement for early diagnosis and treatment in the clinical application. it emphasizes on the necessity of utilizing far improved deep learning architectures and more holistic training mechanisms in striving to create more accurate diagnosis support systems in medical image analysis. © 2024 IEEE.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

IoT - Healthcare Based Model for Heart Diseases Classification 1

IoT - Healthcare Based Model for Heart Diseases Classificati...

引用

1st IEEE International Conference on Applied Intelligence and Sustainable Computing, ICaiSC 2023

作者： Pareek, Piyush Kumar Deepak, R. Hemalatha, K.L. Sengupta, Jewel Rajashekarappa Nitte Meenakshi Institute of Technology Department of AI & ML Bengaluru India BGS Institute of Technology Department of ECE Mandya India Sri Krishna Institute of Technology Department of Information Science and Engineering Bangalore India Kaunas University of Technology K. Donelaičio g. 73 Kaunas44249 Lithuania SDM College of Engineering and Technology Department of Information Science & Engineering Dharwad India

ISBN: (纸本)9798350323795

The rising prevalence of cardiovascular disorders has led to a substantial improvement in their diagnosis. Despite the fact that several techniques have been created for illness classification and privacy protection for safe data transfer, most of these techniques still have problems with precise decision making. In the field of clinical data investigation, the expectation of cardiovascular activity is a fundamental test. Artificial intelligence (ai) has matured into a useful tool for sifting through the mountain of data produced by medical professionals and health organisations to make informed decisions and forecasts. Machine learning techniques are helping doctors better predict heart attacks, and this has led many people to alter their behaviour in the future to avoid a similar fate. This study looks at two data sets, one from UCI and one from Kaggle, to make predictions about cardiovascular illness. The results obtained by applying the suggested model to these two datasets are competitive with current approaches. The heart disease prediction model presented here makes use of a Dual path network with recurrent convolutional cascades. Both the individual channel and the inter-channel connection are taken into account when employing LSTM. Then, layers that are completely interconnected occur. For this reason, the proposed system outperforms preexisting smart heart disease prediction systems by a wide margin, with an accuracy of 91.7% and 93.7%, respectively, when tested on the UCI and Kaggle datasets, respectively. © 2023 IEEE.

关键词： Data transfer

来源：评论

学校读者我要写书评

暂无评论

Integrating Recurrent Neural Networks in Virtual Reality-Based Learning Environments for Dynamic Educational Content Generation 13

Integrating Recurrent Neural Networks in Virtual Reality-Bas...

引用

13th IEEE International Conference on Communication Systems and Network Technologies, CSNT 2024

作者： Paliwal, Sachit Bhadauria, Shraddha Sasikala, P. Ramya, M. Bala, Kiran B. Amity University Online Uttar Pradesh Noida India Gla University Online Uttar Pradesh Mathura India Department of Computer Science Bangalore India Panimalar Engineering College Department of It Chennai India K. Ramakrishnan College of Engineering Department of Ai & Ds Trichy India

ISBN: (纸本)9798350305463

The integration of Recurrent Neural Networks (RNNs) in virtual reality (VR)-based learning environments represents a cutting-edge approach to revolutionizing educational content generation The study begins by establishing the need for personalized and responsive educational content in the context of evolving learning paradigms. RNNs, known for their ability to capture sequential dependencies and patterns, are introduced as a powerful tool for modeling dynamic aspects of educational content. The integration of RNNs in VR environments is motivated by the desire to create interactive and evolving learning scenarios that adapt to individual learner preferences and progress. The research methodology involves the development of a prototype VR-based learning environment that incorporates RNNs for real-time content generation. The RNNs are trained on diverse datasets, allowing the system to learn and adapt to the varying needs and learning styles of users. The VR setting provides an immersive and engaging platform for learners, fostering a deeper understanding of complex concepts through interactive experiences. Key outcomes of the study include insights into the effectiveness of RNNs in dynamically generating educational content. The accuracy of the proposed model is 98.32% which is higher than existing methods like CNN (Convolutional Neural Network), CNN-LSTM (Long shirt Term Memory, GRU (Gated Recurrent Units). © 2024 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Integrated Energy-Efficient Distributed Link Stability Algorithm for UAV Networks

引用

computers, Materials & Continua 2024年第11期81卷 2357-2394页

作者： Altaf Hussain Shuaiyong Li Tariq Hussain Razaz Waheeb Attar Farman Ali Ahmed Alhomoud Babar Shah School of Computer Science and Technology Chongqing University of Posts and TelecommunicationsChongqing400065China Key Laboratory of Industrial Internet of Things and Networked Control Ministry of EducationChongqing University of Posts and TelecommunicationsChongqing400065China School of Computer Science and Information Engineering Zhejiang Gongshang UniversityHangzhou310018China Management Department College of Business AdministrationPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Applied AI School of ConvergenceCollege of Computing and InformaticsSungkyunkwan UniversitySeoul03063Republic of Korea Department of Computer Science College of ScienceNorthern Border UniversityArar91431Saudi Arabia College of Technological Innovation Zayed UniversityDubai19282United Arab Emirates

Ad hoc networks offer promising applications due to their ease of use,installation,and deployment,as they do not require a centralized control *** these networks,nodes function as senders,receivers,and *** such network is the Flying Ad hoc Network(FANET),where nodes operate in three dimensions(3D)using Unmanned Aerial Vehicles(UAVs)that are remotely *** the integration of the Internet of Things(IoT),these nodes form an IoT-enabled network called the Internet of UAVs(IoU).However,the airborne nodes in FANET consume high energy due to their payloads and low-power *** optimal routing approach for communication is essential to address the problem of energy consumption and ensure energy-efficient data transmission in *** paper proposes a novel energy-efficient routing protocol named the Integrated Energy-Efficient Distributed Link Stability Algorithm(IEE-DLSA),featuring a relay mechanism to provide optimal routing with energy efficiency in *** energy efficiency of IEE-DLSA is enhanced using the Red-Black(R-B)tree to ensure the fairness of advanced energy-efficient *** link stability,transmission loss avoidance,delay awareness with defined threshold metrics,and improving the overall performance of the proposed protocol are the core functionalities of *** simulations demonstrate that the proposed protocol performs well compared to traditional FANET routing *** evaluation metrics considered in this study include network delay,packet delivery ratio,network throughput,transmission loss,network stability,and energy consumption.

关键词： FANET UAV internet of UAVs relay mechanism energy consumption routing IEE-DLSA

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Diagnostic System using Deep Learning for Early Prediction of Pancreatic Cancer

An Enhanced Diagnostic System using Deep Learning for Early ...

引用

International Conference on Electrical Energy Systems (ICEES)

作者： Kumbham Bhargavi M Lakshmi Prasad Arun G Pundru Chandra Shaker Reddy S Yuvalatha M Naga Triveni Department of CSE (AI & ML) Keshav Memorial Institute of Technology Hyderabad Telangana India Computer Science and Engineering Institute of Aeronautical Engineering Hyderabad Telangana India Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India School of Computer Science and Artificial Intelligence SR University Warangal Telangana India Computer Science and Business Systems Anna University Bannari Amman Institute of Technology Tamil Nadu India Department of CSE (AI&ML) St. Martin's Engineering College Hyderabad Telangana India

ISBN: (数字)9798350353778

ISBN: (纸本)9798350353785

With a dismal 5-year survival-rate of approximately 7%, pancreatic-cancer(PC) remains one of the world's most lethal tumors. In order to improve patient survival rates, early detection of PC is essential. computerized-tomography(CT), MRI combined with MRCP, or a biopsy is necessary for the diagnosis of PC. The steps involved in the suggested CAD design process are as follows: picture preprocessing, segmentation, feature-extraction & classificatiion. Color conversion and the isotropic diffusion filter method are utilized for preprocessing. The next step is the segmentation processes' usage of the suggested Fuzzy K-NN Equality code. A classification tool that makes use of Deep Learning is feature extraction. Using the characteristics gathered from the pancreatic sample, tumor cells are categorized. The image classification criterion includes both the train values and the testing datasets. To identify pancreatic cancer, an algorithm called DCNN_DBN is employed, which combines Deep-Convolutional Neural-Networks with Deep-Belief-Networks. The results of the experiments show that the present CAD system has great promise and is safe for the automated diagnosis of benign & malignant tumors, with an accuracy rate of 99.8 percent. The use of this classifier greatly reduces the computational complexity. More anomalies in pancreatic cancer cells could be detected with an improved version of the proposed method.

关键词： Deep learning Image segmentation Accuracy Sensitivity Image color analysis Databases Roads Pancreatic cancer Classification algorithms Testing

来源：评论

学校读者我要写书评

暂无评论

Automated Word Prediction in Telugu Language Using Statistical Approach

Automated Word Prediction in Telugu Language Using Statistic...

引用

2023 International Conference on computer Communication and Informatics, ICCCI 2023

作者： Lakshmi, L. Devi, K.Dhana Sree Kalyani, A.Naga Ravisankar, M. Rani, K. Pushpa Deaprtment of DS & AI Faculty of Science and Technology Hyderabad501203 India Department of CSE Hyderabad India BVRIT HYDERABAD College of Engineering for Women Department of CSE Hyderabad India MLR Institute of Technology Dundigal Department of Computer Science and Engineering Hyderabad500043 India

ISBN: (纸本)9798350348217

Automated word prediction commonly called as language modeling is the task of predicting the next Word. Word completion and word prediction phenomenally benefit the disabled users who use physical keyboard or virtual keyboards in desktops and handheld systems. The objective of this paper is to predict the next word prediction and sequence of words prediction in Telugu language sentences with stochastic approach. The N-gram linguistic models such as uni-gram, bigram, tri-gram, maximum likely hood estimation, Laplace and add1 smoothing have used for automatic completion of a sentence with the prediction of appropriate word to save time, keystrokes and misspelling. We have used large data corpus of Telugu language from Telugu Wiki pages, which has words from different domains to predict correct word. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Automated Health Monitoring: Integrating ai and IoT for Continuous Patient Observation

Automated Health Monitoring: Integrating AI and IoT for Cont...

引用

IoT Based Control Networks and Intelligent Systems (ICICNIS), International Conference on

作者： E V N Jyothi Sighakolli Sailaja M. SriRama Lakshmi Reddy T. Sunitha Department of CSE (AI&ML) CMR College of Engineering & Technology Hyderabad Telangana India Department of Computer Science and Engineering Rise krishna sai prakasam group of institutions Ongole A.P India Department of Computer Science and Engineering CMR Institute of Technology Hyderabad Telangana India Department of Computer Science and Engineering (Data Science) Marri Laxman Reddy Institute of Technology and Management Hyderabad Telangana India

ISBN: (数字)9798331518097

ISBN: (纸本)9798331518103

Integrating Artificial Intelligence (ai) with the Internet of Things (IoT) has recently become more advantageous for various complex fields like innovative health, intrusion detection in various devices, and continuous monitoring of crops yielding in various farming lands. From the health point of view, it is essential to monitor multiple patients' health according to their abnormal health conditions. The proposed Integrated Health Monitoring System (IHMS) is developed in this work by combining ai-based models such as Recurrent Neural Networks (RNNs) and advanced IoT sensors. The IHMS is mainly used in health care applications such as heart care analysis and other abnormal health conditions like blood pressure, levels of oxygen, and glucose readings, and it transmits this information to ai-powered systems. The IHMS mainly analyzes abnormal patterns, detects anomalies, and provides timely analytical analysis of patient data. Finally, the proposed approach IHMS analyzes several datasets and shows the performance in terms of classification.

关键词： Recurrent neural networks Medical services Sepsis Real-time systems Blood pressure Sensor systems Internet of Things Biomedical monitoring Monitoring Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Leveraging Machine Learning for Pattern-Based Detection of Respiratory Illnesses

Leveraging Machine Learning for Pattern-Based Detection of R...

引用

Artificial Intelligence and Data engineering (aiDE), International Conference on

作者： Anusha Prashanth Shetty Deepthi L Raksha Puthran Surendra Shetty Pavan Hegde Shravan Kumar Department of Master of Computer Applications NMAM Insitute of Technology NITTE (Deemed to be University) Nitte Karkala India Department of Computer Science and Engineering (AI&ML) Sahyadri College of Engineering and Management Mangalore India Department of Paediatrics Father Muller Medical College and Hospital Mangalore India

ISBN: (数字)9798331527518

ISBN: (纸本)9798331527525

Lung sound analysis presents a promising, noninvasive, and potentially cost-effective approach for detecting respiratory diseases. This research aims to assess the feasibility of using lung sounds for pattern recognition and detection of various respiratory disorders, specifically by conducting an analysis of cough sounds. We review a range of recent studies that explore the use of deep learning models, machine learning algorithms, and feature extraction techniques in this context. These studies are categorized based on their methodologies, and their performance in accurately classifying lung sounds is discussed. Research findings highlight the significant diagnostic potential of lung sound analysis, demonstrating improved classification accuracies across various disease types. However, challenges such as data inconsistency, noise interference, and limited model generalizability remain. It captures the current state of lung sound analysis research in respiratory disease detection, offering insights that could drive future advancements in this critical field.

关键词： Machine learning algorithms Accuracy Tuberculosis Lungs Pulmonary diseases Medical services User interfaces Data models Convolutional neural networks Mel frequency cepstral coefficient

来源：评论

学校读者我要写书评

暂无评论

Enhancing Privacy in Real-Time Stream Processing: Federated Transfer Learning Approaches

Enhancing Privacy in Real-Time Stream Processing: Federated ...

引用

Metrology for Living Environment (MetroLivEn), IEEE International Workshop on

作者： Shwetha Jog Damodharan Palaniappan M. A. Jabbar Department of Computer Engineering Marwadi University Rajkot India Department of Information Technology Marwadi University Rajkot India Department of CSE-AI&ML Vardhaman College of Engineering Hyderabad India

ISBN: (数字)9798350385014

ISBN: (纸本)9798350385021

In the era of data ubiquity, safeguarding privacy while harnessing the power of real-time streaming presents a critical challenge. This study delves into the intersection of privacy preservation, real-time streaming, and federated transfer learning to devise robust solutions. First, we elucidate the essence of data privacy, real-time streaming, and federated transfer learning. Subsequently, we propose an innovative approach that seamlessly integrates privacy considerations into the fabric of real-time streaming analytics through federated learning models. Leveraging this framework, we ascertain the optimal model selection process tailored to the specific data characteristics and user requirements. Our analysis encompasses a comparative evaluation of five prominent models: Differential Privacy, Secure Multi-party Computation, Homomorphic Encryption, Federated Learning with User-level Differential Privacy, and Decentralized Federated Learning. Through empirical examination, we discern the most suitable model for preserving privacy in real-time streaming contexts, thereby advancing the discourse on privacy-preserving machine learning paradigms.

关键词： Privacy Differential privacy Analytical models Federated learning Computational modeling Transfer learning Metrology

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：