检索结果-内蒙古大学图书馆

Global Conference for Advancement in Technology (GCAT)

作者： Daniel Nareshkumar. M Desidi Narsimha Reddy A. Sowmiya V. Samuthira Pandi Rayala Sateesh N. Hindumathy Department of Electronics and Communication Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences SIMATS University Chennai Tamil Nadu India Data Consultant (Data Governance Data Analytics: Enterprise Performance Management AI&ML) Soniks Consulting LLC Texas USA Department of EEE Rajalakshmi Engineering College Chennai Centre for Advanced Wireless Integrated Technology Chennai Institute of Technology Chennai Tamil Nadu India Department of ECE MLR Institute of Technology Hyderabad Department of Artificial Intelligence and Machine Learning Vel Tech Rangarajan Dr.Sagunthala R & D Institute of Science and Technology Chennai

ISBN: (数字)9798350376685

ISBN: (纸本)9798350376692

Autonomous vehicles (AVs) are a game-changer in the transportation industry; they will alter cityscapes, cut down on accidents, and reimagine how people experience mobility. This study investigates the complex relationship between autonomous vehicles and high-tech ai systems, looking at how these two technologies can influence transportation in the future. The paper highlights crucial developments in sensor fusion, machine learning algorithms, and real-time data processing that are essential for the development of fully autonomous systems by analyzing the present status of AV technology. In the first part of the study, the basic technologies that support AVs are described. These technologies include LiDAR, radar, cameras, and GPS. When taken together, they allow AVs to perceive their surroundings and locate themselves. After that, it delves into how ai is helping AVs understand sensor data, make judgments in real-time, and carry out complicated maneuvers, showcasing how advancements in deep learning, neural networks, and predictive analytics are powering these capabilities. Integrating AVs into current transportation infrastructures presents both potential and obstacles, which the paper delves into. Critical situation safety, legal frameworks, cybersecurity risks, and ai decision-making ethics are all covered. In addition to the environmental advantages of improved traffic flow and decreased emissions, the study delves into the possible socioeconomic implications, including shifts in urban design, public transit, and the labor market. The research delves into the existing deployment tactics and the path for scaling AV operations through a thorough analysis of case studies, pilot projects, and industry reports. It determines how prepared different groups are to accept this revolutionary technology, including the general public, lawmakers, and manufacturers. To sum up, the study highlights how important it is for academic institutions, business executives, and governm

关键词： Ethics Machine learning algorithms Urban planning Decision making Sensor fusion Data processing Real-time systems Safety computer security Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

SCOL: Supervised Contrastive Ordinal Loss for Abdominal Aortic Calcification Scoring on Vertebral Fracture Assessment Scans

arXiv

引用

arXiv 2023年

作者： Saleem, Afsah Ilyas, Zaid Suter, David Hassan, Ghulam Mubashar Reid, Siobhan Schousboe, John T. Prince, Richard Leslie, William D. Lewis, Joshua R. Gilani, Syed Zulqarnain Centre for AI & ML School of Science Edith Cowan University Joondalup Australia Nutrition and Health Innovation Research Institute Edith Cowan University Joondalup Australia Computer Science and Software Engineering The University of Western Australia Perth Australia Department of Electrical and Computer Engineering University of Manitoba Winnipeg Canada Park Nicollet Clinic HealthPartners Institute HealthPartners Minneapolis United States Departments of Medicine and Radiology University of Manitoba Winnipeg Canada

Abdominal Aortic Calcification (AAC) is a known marker of asymptomatic Atherosclerotic Cardiovascular Diseases (ASCVDs). AAC can be observed on Vertebral Fracture Assessment (VFA) scans acquired using Dual-Energy X-ray Absorptiometry (DXA) machines. Thus, the automatic quantification of AAC on VFA DXA scans may be used to screen for CVD risks, allowing early interventions. In this research, we formulate the quantification of AAC as an ordinal regression problem. We propose a novel Supervised Contrastive Ordinal Loss (SCOL) by incorporating a label-dependent distance metric with existing supervised contrastive loss to leverage the ordinal information inherent in discrete AAC regression labels. We develop a Dual-encoder Contrastive Ordinal Learning (DCOL) framework that learns the contrastive ordinal representation at global and local levels to improve the feature separability and class diversity in latent space among the AAC-24 genera. We evaluate the performance of the proposed framework using two clinical VFA DXA scan datasets and compare our work with state-of-the-art methods. Furthermore, for predicted AAC scores, we provide a clinical analysis to predict the future risk of a Major Acute Cardiovascular Event (MACE). Our results demonstrate that this learning enhances inter-class separability and strengthens intra-class consistency, which results in predicting the high-risk AAC classes with high sensitivity and high accuracy. © 2023, CC BY-NC-SA.

关键词： Bone

来源：评论

学校读者我要写书评

暂无评论

Wide-Deep Neural Networks with Randomized Sparse Backpropagation Simplify Demand-Side Load Event Detection

Wide-Deep Neural Networks with Randomized Sparse Backpropaga...

引用

Data science and Network Security (ICDSNS), International Conference on

作者： Manasa Adusumilli Ramesh G.P. Vijayrani Katkam Bhargavi Piyush Kumar Pareek Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaadeswaram India Department of Electronics and Communication Engineering St. Peter's Institute for Higher Education and Research Chennai India Department of E&CE Ballari Institute of Technology & Management Bellary India Department of CSE Hyderabad Institute of Technology and Management Hyderabad India Department of AI and ML Nitte Meenakshi Institute of Technology Bengaluru India

Identifying demand-side load events is a critical step in lowering energy use in a number of situations. Using wide-deep neural networks and randomised sparse backpropagation algorithms, this study presents a unique way to identify demand-side load events. To detect subtleties in the input data, we employ randomised sparse backpropagation and both shallow and deep network topologies. We also use the ReLU and sigmoid activation functions to improve the performance of our model. We use the Adam optimizer to train the proposed model, using a learning rate of 0.001 per batch and a batch size of 64. The results were compared to those of other popular technologies, such as support vector machines. According to the findings of our studies, the technique we utilised is more precise and efficient than any other option we investigated. The proposed approach combines wide-deep neural networks with randomised sparse backpropagation to simplify demand-side load event identification.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improved Sail Fish Optimizer for Energy Efficient Routing in Wireless Sensor Network

Improved Sail Fish Optimizer for Energy Efficient Routing in...

引用

Integrated Intelligence and Communication Systems (ICIICS), International Conference on

作者： Srinivas Aluvala Geetha Reddy Hassan M. Al-Jawahry Ghazi Mohamad Ramadan Piyush Kumar Pareek School of Computer Science & Artificial Intelligence SR University Warangal India CSE Malla Reddy Engineering College for Women Hyderabad India The Islamic university Najaf Iraq College of MLT Ahl Al Bayt University Karbala Iraq Department of AI and ML Nitte Meenakshi Institute of Technology Bengaluru India

A Wireless Sensor Network (WSN) is a collection of nodes fitted with small sensors and transceiver elements that are utilized for sensing, tracking, and data collection in a variety of situations. Sensor energy is considered a significant resource due to the difficulty in providing battery a backup to sensors when they are deployed in an uncontrolled or wild area. Integrating clustering & routing strategies are the optimal techniques for saving sensor node energy. In this research, the Improved Sail Fish Optimizer (ISFO) is proposed for the energy efficient routing path selection in WSN to improve the network lifetime. The ISFO algorithm is utilized to identify an accurate routing to sink node for data transmission. The performance of proposed algorithm is evaluated with performance metrics of Packet Delivery Ratio (PDR), Throughput, energy consumption and delay. The proposed algorithm attained high PDR of 96%, high throughput of 97%, less energy consumption of 0.4J and less delay of 3ms which is superior than other existing algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

VerteNet — A Multi-Context Hybrid CNN Transformer for Accurate Vertebral Landmark Localization in Lateral Spine DXA Images

arXiv

引用

arXiv 2025年

作者： Ilyas, Zaid Maqsood, Arooba Saleem, Afsah Zhang, Erchuan Suter, David Raina, Parminder Hodgson, Jonathan M. Schousboe, John T. Leslie, William D. Lewis, Joshua R. Gilani, Syed Zulqarnain Center for AI & ML School of Science Nutrition and Health Innovation Research Institute Edith Cowan University Australia Computer Science and Software Engineering The University of Western Australia Australia School of Science Sun Yat-sen University China School of Medical and Health Sciences Nutrition and Health Innovation Research Institute Edith Cowan University Australia Park Nicollet Clinic HealthPartners Institute Minneapolis United States Department of Medicine and Radiology University of Manitoba Canada Department of Health Sciences McMaster University Canada

Lateral Spine Image (LSI) analysis is important for medical diagnosis, treatment planning, and detailed spinal health assessments. Although modalities like Computed Tomography and Digital X-ray Imaging are commonly used, Dual Energy X-ray Absorptiometry (DXA) is often preferred due to lower radiation exposure, seamless capture, and cost-effectiveness. Accurate Vertebral Landmark Localization (VLL) on LSIs is important to detect spinal conditions like kyphosis and lordosis, as well as assessing Abdominal Aortic Calcification (AAC) using Inter-Vertebral Guides (IVGs). Nonetheless, few automated VLL methodologies have concentrated on DXA LSIs. We present VerteNet, a hybrid CNN-Transformer model featuring a novel dual-resolution attention mechanism in self and cross-attention domains, referred to as Dual Resolution Self-Attention (DRSA) and Dual Resolution Cross-Attention (DRCA). These mechanisms capture the diverse frequencies in DXA images by operating at two different feature map resolutions. Additionally, we design a Multi-Context Feature Fusion Block (MCFB) that efficiently integrates the features using DRSA and DRCA. We train VerteNet on 620 DXA LSIs from various machines and achieve superior results compared to existing methods. We also design an algorithm that utilizes VerteNet’s predictions in estimating the Region of Interest (ROI) to detect potential abdominal aorta cropping, where inadequate soft tissue hinders calcification assessment. Additionally, we present a small proof-of-concept study to show that IVGs generated from VLL information can improve inter-reader correlation in AAC scoring, addressing two key areas of disagreement in expert AAC-24 scoring: IVG placement and quality control for full abdominal aorta assessment. The code for this work can be found at https://***/zaidilyas89/VerteNet. © 2025, CC BY-NC-SA.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Advanced Neural Network Approach for Fetal Heart Rate Classification with Multi-Attribute Analysis

Advanced Neural Network Approach for Fetal Heart Rate Classi...

引用

International Conference on ICT in Business Industry & Government (ICTBIG)

作者： D. Rajeswari Prashant Chourasiya Sivakumar Kk Neelesh Kumar Sahu G. Gifta Jerith Pranav Singh Department of CSE MLR Institute of Technology Hyderabad India Department of Computer Science & Engineering IES Institute of Technology and Management IES University Bhopal M.P. India School of Liberal Arts and Sciences Mohan Babu University Tirupati AP India Dept of CSE-AIR Gyan Ganga Institute of Technology & Sciences Jabalpur MP India Department of AI & ML School of Engineering Malla Redy University Hyderabad Hyderabad Telangana India GGITS MP India

ISBN: (数字)9798331518981

ISBN: (纸本)9798331518998

Electronic fetal monitoring is an essential diagnostic aid in pregnant women for the evaluation of fetal status and possible pathology. In this research, a sophisticated neural network model is suggested as a means for the arrangement of fetal heart rate indicators with multi attribute analysis to assist in maximizing the classification. We thus use an ANFIS that incorporates the capability of learning from the neural network on the one hand and the reasoning of fuzzy logic on the other. The system employs ECG data and the signals are processed by Independent Component Analysis method to extract the fetal signals. Further, PSD transforming of a signal and RR-interval measurements are incorporated to obtain significant signal characteristics making the discrimination more sensitive and specific. The investigational outcomes also show that the proposed model achieves a much higher overall accuracy than the traditional methods, providing an effective means for the fetal heart monitoring in practice.

关键词： Training Pregnancy Accuracy Fetal heart rate Pattern classification Medical services Electrocardiography Signal analysis Monitoring Biological neural networks

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Unsupervised Learning Architecture to Enhance User Behavior Anomaly Detection

A Lightweight Unsupervised Learning Architecture to Enhance ...

引用

IEEE Latin-American Conference on Communications, LATINCOM

作者： André L. B. Molina Vinícius P. Gonçalves Rafael T. De Sousa Marcel Pividal Rodolfo I. Meneguette Geraldo P. Rocha Filho Electrical Engineering Department University of Brasilia Brasilia Brazil World Wide Specialist Organization AI/ML Amazon Web Services Miami United States Institute of Mathematical and Computer Sciences University of Sao Paulo Sao Carlos Brazil Computer Science Department University of Brasilia Brasilia Brazil

In recent years, user behavior anomaly detection has been gaining attention in cybersecurity. A crucial challenge that has been discussed in the literature is that supervised models that use vast amounts of data for training do not apply to real scenarios for anomaly detection. Within this context, the requirement to gather datasets with labeled behavior anomalies has proven to be a significant limiting factor for evaluating different models. This paper presents WEAPON, an unsupervised learning-based architecture for user behavior anomaly detection that requires a small amount of data for building behavior profiles considering the individuality of each user. WEAPON implements the weak supervision-based behavior anomaly labeling approach using Snorkel. When compared to other approaches, WEAPON proved to be more efficient, surpassing the ROC curve of the second best model by 4.31%. Furthermore, WEAPON outperforms rule-based methods by finding anomalies that an expert would not anticipate.

关键词： Training Limiting Convolution Weapons Memory management Data models Behavioral sciences

来源：评论

学校读者我要写书评

暂无评论

Advancing Precision Heart Disease Diagnosis for Proactive Healthcare Management using RF-IGE

Advancing Precision Heart Disease Diagnosis for Proactive He...

引用

International Conference on Image Information Processing

作者： Zahraa M. Rashid T.B Sivakumar S K Rajesh Kanna Minal Saxena U Saritha Malik Jawarneh Medical Instrumentation Department Technical Institute of Babylon Al-furat Al-AWsat Technical University Babylon Iraq Department of CSE School of Computing Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai Tamilnadu India Department of Mechanical Engineering Rajalakshmi Institute of Technology Chennai Tamilnadu India Linnaeous University Sweden Department of CSE (AI&ML) CMR Technical Campus Hyderabad Telangana India Oman College of Management and Technology Muscat Oman

ISBN: (数字)9798350371406

ISBN: (纸本)9798350371413

Heart disease remains a leading cause of mortality worldwide, emphasizing the need for accurate and timely prediction to improve patient outcomes and reduce healthcare burdens. In this research, we present a novel approach to predict heart disease utilizing Random Forest with Information Gain Entropy (RF-IGE) as the predictive model. The combination of Random Forest and Information Gain Entropy aims to enhance the accuracy and efficiency of heart disease prediction, catering to the complex and heterogeneous nature of the disease. By leveraging the RF-IGE methodology, we analyze and identify the most informative features crucial for heart disease prediction. The model's robustness is evaluated using comprehensive datasets encompassing diverse patient profiles, ensuring its generalizability and applicability across different populations. The proposed predictive model exhibits promising results, demonstrating a high level of accuracy in distinguishing individuals with heart disease from healthy individuals. This research contributes valuable insights into the utilization of Random Forest and Information Gain Entropy in predicting heart disease, showcasing the potential for improved diagnosis and personalized treatment strategies. The ultimate goal is to develop a reliable and practical predictive tool that aids healthcare professionals in making informed decisions for early detection and optimal management of heart disease, ultimately leading to better patient care and outcomes.

关键词： Heart Training Predictive models Streaming media Feature extraction Entropy Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Scoring Algorithm for English Translation Based on DNN

Artificial Intelligence Scoring Algorithm for English Transl...

引用

International Conference on Smart Technologies For Smart Nation (SmartTechCon)

作者： R Krishna Priya Sabarmathi K R Aanandha Saravanan K Niranjanamurthy M Aashish A. Gadgil Azarudeen K Department of Engineering-Electrical Section College of Engineering and Technology University of Technology and Applied Sciences Shinas Sultanate of Oman Department of Information Technology Bannari Amman Institute of Technology Sathyamangalam Tamilnadu India Department of ECE Veltech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai India Department of AI ML BMS Institute of Technology and Management Bangalore Karnataka India Department of ECE KLS GOGTE Institute of Technology Belagavi Karnataka India Department of Computer Science and Engineering Velammal College of Engineering and Technology Madurai India

With the popularity of languages and the increasing demand for language translation, the optimization of artificial intelligence scoring algorithm for English translation has become the urgent need of the translation market. Based on the deep neural network(DNN) algorithm, it continuously integrates modern technology to realize information collection, storage, analysis and application, which promotes the deep integration of the DNN algorithm in the field of intelligent identification and expands the application scope of artificial intelligence identification technology. This paper focuses on how to efficiently optimize the model of English translation artificial intelligence scoring algorithm by DNN, specifically studying the DNN model, by studying the mathematical model and algorithm flow of the DNN optimization algorithm, and the basic principle of the DNN model; Based on the DNN model, a learning ability analysis model of English translation algorithm is proposed. Experiments show that this model can optimize the artificial intelligence scoring algorithm of English translation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Feature fusion based deep learning model for Alzheimer's neurological disorder classification

Neuroscience Informatics

引用

Neuroscience Informatics 2025年第2期5卷 100196-100196页

作者： Kumar, Arhath Pradeep, S. Arora, Kumud Sreeram, G. Pankajam, A. Patil, Trupti Sahu, Aradhana Department of MCA NMAM Institute of Technology Nitte (Deemed to be University) Karnataka Udupi India Department of CSE Malla Reddy Engineering College for Women (UGC Autonomous) Telangana Secunderabad India Department of CSE- AI & ML Inderprastha Engineering College Uttar Pradesh Ghaziabad India Department of CSE Vignana Bharathi Institute of Technology Telangana Hyderabad India Department of Business Administration Avinashilingam Institute for Home Science and Higher Education for Women Tamil Nadu Coimbatore 641043 India Department of Information Technology K.J. Somaiya Institute of Technology Sion Maharashtra Mumbai India Department of Computer Science and Engineering Rungta College of Engineering and Technology Bhilai Chhattisgarh India

Alzheimer's disease (AD) is a severe brain disorder that can cause degradation of brain tissue and memory loss. Owing to Alzheimer's disease's high cost, a number of deep learning-based models have been put out to accurately identify the illness. This study introduces a new way to classify Alzheimer's disease using deep learning and combining different types of features. The 3D lightweight MBANet developed in this research has less parameters and can concentrate on more discriminative deep structures than conventional artificial neural networks like CNN, according to experimental data. We first create a Multi-Branch Attention Network (MBANet) to gather detailed features of the hippocampus from large sets of data. A new method is created to capture texture features in the hippocampus. It uses two techniques: multi-Tree Wavelet Transform (MTWT) and Gray Length Matrix (GLM). This method works in three dimensions and at different scales. Also, standard methods are used to measure the size and shape of the hippocampus. A mixed feature fusion network is created to simplify and combine data from the hippocampus, helping to classify Alzheimer's disease more effectively. Tests on the EADC-ADNI dataset show that the proposed method for classifying Alzheimer's disease achieves an accuracy of 93.39%, a F₁-score of 93.10%, and an AUC of 93.21%. The test results show that the proposed method for classifying Alzheimer's disease is effective and better than traditional methods. © 2025 The Author(s)

关键词： Alzheimer's disease Deep learning MBANet Neuroscience Wavelet transform

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：