检索结果-内蒙古大学图书馆

Dataset of Large Gathering Images for Person Identification and Tracking

computers, Materials & Continua 2023年第3期74卷 6065-6080页

作者： Adnan Nadeem Amir Mehmood Kashif Rizwan Muhammad Ashraf Nauman Qadeer Ali Alzahrani Qammer H.Abbasi Fazal Noor Majed Alhaisoni Nadeem Mahmood Faculty of Computer and Information System Islamic University of MadinahMadinah42351Saudi Arabia Department of Computer Science and Information Technology Sir Syed University of Engineering and TechnologyKarachi75300Pakistan Department of Computer Science Federal Urdu University of ArtsScience&TechnologyIslamabad45570Pakistan Department of Physics Federal Urdu University of ArtsScience&TechnologyKarachi75300Pakistan James Watt School of Engineering University of GlasgowGlasgowG128QQUK Computer Sciences Department College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Computer Science University of KarachiKarachi75270Pakistan

This paper presents a large gathering dataset of images extracted from publicly filmed videos by 24 cameras installed on the premises of Masjid Al-Nabvi,Madinah,Saudi *** dataset consists of raw and processed images reflecting a highly challenging and unconstraint *** methodology for building the dataset consists of four core phases;that include acquisition of videos,extraction of frames,localization of face regions,and cropping and resizing of detected face *** raw images in the dataset consist of a total of 4613 frames obtained fromvideo *** processed images in the dataset consist of the face regions of 250 persons extracted from raw data images to ensure the authenticity of the presented *** dataset further consists of 8 images corresponding to each of the 250 subjects(persons)for a total of 2000 *** portrays a highly unconstrained and challenging environment with human faces of varying sizes and pixel quality(resolution).Since the face regions in video sequences are severely degraded due to various unavoidable factors,it can be used as a benchmark to test and evaluate face detection and recognition algorithms for research *** have also gathered and displayed records of the presence of subjects who appear in presented frames;in a temporal *** can also be used as a temporal benchmark for tracking,finding persons,activity monitoring,and crowd counting in large crowd scenarios.

关键词： Large crowd gatherings a dataset of large crowd images highly uncontrolled environment tracking missing persons face recognition activity monitoring

来源：评论

学校读者我要写书评

暂无评论

AI-Powered Developments in Oncological Diagnostic Imaging: Revolutionary Approaches to Cancer Treatment

AI-Powered Developments in Oncological Diagnostic Imaging: R...

引用

2023 International Conference on Advances in Computation, communication and Information Technology, ICAICCIT 2023

作者： Singh, Shweta Ashwini, B. Vivek, V. Maharishi University of Information Technology Maharishi School of Engineering & Technology Uttar Pradesh India Presidency University Department of Electronics and Communication Engineering Karnataka Bangalore India Faculty of Engineering and Technology Department of Computer Science Engineering Karnataka Bangalore India

ISBN: (纸本)9798350344387

This project aims to demonstrate new uses of deep learning techniques in the detection of cancer. A huge body of examples that show the desired behaviour may be used to train a system using deep learning, which is a family of algorithms. Introduction of deep learning methods to tumour imaging may help pathologists identify and categorise cancer early on so that patients can get the right therapies to improve their chances of surviving or recovering. Utilising statistics and other analytical techniques and ScienceDirect have data, it appears that since the late 1990s, a sharp increase in research on deep learning technologies in medical imaging has been motivated by the exceptionally high mortality rates of some cancer types in order to address the concomitant issues of a more precise recognition and the identification of cancer types to use effective therapies for cancer. This study also identifies the institutions, nations, and intellectual subject areas with the greatest levels of intellectual output in multiple disciplines as the origins of the trajectory of deep learning technology in cancer detection. According to Amara's law, this novel technique may result in a change in the way that cancer diagnoses and treats its many forms. When they can submit digital photos to laboratories in other developed nations to have malignancy kinds diagnosed, this fresh innovation may also aid developing regions, narrowing the present healthcare divide as much as feasible. © 2023 IEEE.

关键词： Cancer Detection Cancer Types Deep Learning Early Diagnosis Machine Learning Medical Imaging Metastatic Cancer Pathologists and Clinical Oncology Therapies Tumour Imaging

来源：评论

学校读者我要写书评

暂无评论

The Cloud's Balancing Confidentiality and Collaboration

The Cloud's Balancing Confidentiality and Collaboration

引用

2023 International Conference on Power Energy, Environment and Intelligent Control, PEEIC 2023

作者： Vivek, V. Sahoo, Girija Shankar Kehkeshan Jallal, S. Faculty of Engineering and Technology Department of Computer Science Engineering Karnataka Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Presidency University Department of Electronics and Communication Engineering Karnataka Bangalore India

ISBN: (纸本)9798350357769

Group data sharing in cloud settings has become more popular recently as a result of cloud computing's broad acceptance. The need for efficient and safe data exchange in such settings is currently urgent. Another particular problem in cloud-based exchange of data is finding a balance of anonymity and traceability. In order to preserve anonymity, this study focuses on providing safe and effective data exchange and storage for organizations via the cloud. In order to accommodate numerous users surreptitiously in public clouds, it suggests a unique traceable collective data sharing system that makes use of key collaboration and group signature techniques. This system ensures that member identities may be tracked when required while enabling group members to converse anonymously using group signatures. Additionally, to allow for safe data exchange and preservation among group members, a shared conference key is obtained via key agreement. Notably, the key generation process for the system uses a symmetrically balanced incomplete block architecture, greatly easing the load on participants while determining a shared conference key. The suggested approach for collective information sharing on the internet of things is shown to be secure and effective via theoretical investigation and empirical assessments. © 2023 IEEE.

关键词： (KA-ABE) access control anonymity Cloud computing data breaches data integrity fault tolerance group data sharing multiple-to-many data sharing traceability

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Thyroid Diagnosis system Utilizing Multiple Ensemble and Explainable Algorithms with Medical Supported Attributes

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第6期5卷 2840-2855页

作者： Sutradhar, Ananda Al Rafi, Mustahsin Ghosh, Pronab Shamrat, F M Javed Mehedi Moniruzzaman, Md. Ahmed, Kawsar Azad, A.K.M. Bui, Francis M. Chen, Li Moni, Mohammad Ali Daffodil International University Department of Computer Science and Engineering Dhaka1216 Bangladesh Lakehead University Department of Computer Science Thunder BayONP7B 5E1 Canada University of Malaya Department of Computer System and Technology Kuala Lumpur50603 Malaysia Lakehead University Department of Software Engineering Thunder BayONP7B 5E1 Canada University of Saskatchewan Department of Electrical and Computer Engineering SaskatoonSK S7N 5A9 Canada Imam Mohammad Ibn Saud Islamic University Faculty of Science Department of Mathematics and Statistics Riyadh13318 Saudi Arabia Charles Stuart University AI and Cyber Futures Institute BathurstNSW2795 Australia

The widespread impact of thyroid disease and its diagnosis is a challenging task for healthcare experts. The conventional technique for predicting such a vital disease is complex and time-consuming. A data-driven approach may offer predictive solutions, but it relies on all relevant attributes, which are computationally expensive. Hence, we propose a novel machine learning (ML) based disease prediction system that could potentially predict it by considering three crucial steps. First, to reduce the dimension of the dataset, three feature selection techniques were employed, including feature importance (FIS), information gain selections (IGS), and least absolute shrinkage and selection operator (LAS). Moreover, recommended medical references were considered while developing a feature set having the identical attributes as high-risk factors (HRF). Second, the models, including the three stage hybrid classifier (3SHC) and the three stage hybrid artificial neural network (3SHANN), are used as classifiers on the training data set. Third, a local interpretable model-agnostic explanations (LIME) to the 3SHC with the HRF samples was applied to individually explain the predictions. Then, the overall behaviors of both gender and age categories were explored with the help of a partial dependence plot (PDP). Finally, the proposed system is validated with extensive experiments, where the 3SHC achieves an accuracy (ACC) of 99.29%, which can play a crucial role in preventing thyroid disease and alleviating stress in the healthcare sector. © 2020 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Secure and Tailored Health Solutions for People with Specific Requirements Leveraging Advanced AI Techniques 3

Secure and Tailored Health Solutions for People with Specifi...

引用

3rd IEEE International Conference on ICT in Business Industry and Government, ICTBIG 2023

作者： Singh, Vaishali Veena, C.S. Raja Praveen, K.N. Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Presidency University Department of Electronics and Communication Engineering Karnataka Bangalore India Faculty of Engineering and Technology Department of Computer Science Engineering Karnataka Bangalore India

ISBN: (纸本)9798350343274

Our proposed method aims to revolutionize healthcare by leveraging advanced AI techniques to tailor health solutions for individuals with specific health requirements. This innovative approach integrates three powerful AI algorithms: Deep Neural Network (DNN), Long Short-Term Memory (LSTM), and Generative Adversarial Network (GAN). These algorithms work collaboratively to develop secure, precise, and individualized healthcare services. The DNN mimics the brain's structure to extract intricate patterns, the LSTM handles sequential data and long-term dependencies, and the GAN generates data resembling real distributions. Security and privacy are ensured through data encryption and secure communication. The tailored health solution is a result of integrating these techniques, providing enhanced healthcare services. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

The Role of Modern Machine Intelligence in Decoding Activity Patterns from Visual Data of Various Organisms

The Role of Modern Machine Intelligence in Decoding Activity...

引用

2023 International Conference on Recent Advances in Science and engineering Technology, ICRASET 2023

作者： Gowrishankar, J. Kumar, Ritesh Srivastava, Dharmesh Kumar Faculty of Engineering and Technology Department of Computer Science Engineering Karnataka Bangalore India Maharishi University of Information Technology Maharishi School of Engineering & Technology Uttar Pradesh India Presidency University Department of Electronics and Communication Engineering Karnataka Bangalore India

ISBN: (纸本)9798350306927

The integration of modern machine intelligence presents a transformative paradigm in the study of organisms' behaviors through visual data analysis. Leveraging deep learning algorithms like Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), this approach automates the extraction of intricate patterns from images and videos, enabling comprehensive insights into diverse organisms. Object detection algorithms further facilitate precise tracking. By surpassing traditional methods, it enhances accuracy and scalability. Ethical considerations guide responsible research. This fusion of technology and ecology fosters a deeper understanding of natural ecosystems, paving the way for sustainable coexistence with the environment and the preservation of biodiversity. © 2023 IEEE.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of 5G NR Cell Using Classical Scheduling Algorithms and Different MIMO 8th

Performance Analysis of 5G NR Cell Using Classical Schedulin...

引用

8th International Conference on ICT for Sustainable Development, ICT4SD 2023

作者： Kumar, Rajesh Sinwar, Deepak Singh, Vijander Department of Computer and Communication Engineering Manipal University Jaipur Rajasthan Jaipur303007 India Department of ICT and Science Faculty of Information Technology and Electrical Engineering NTNU–Norwegian University of Science and Technology Ålesund Norway

ISBN: (纸本)9789819949311

5G NR has been deployed in most of the countries and covers three major use case scenarios, viz. enhanced mobile broadband (eMBB), ultra-reliable low latency communication (URLLC), and massive machine type of communication (mMTC). To enable the 5G services on the existing 4G infrastructure, the non-standalone architecture (NSA) of 5G NR is equally popular. For NSA deployment, many countries are utilizing the 3.5 GHz band on time division duplex (TDD) transmission. For both uplink and downlink transmissions, TDD is utilizing same frequency bands and scheduling of resources in such environments is quite challenging. Here, the performance of 5G NR is analysed on 20 MHz and 100 MHz channel bandwidth in terms of resource utilization by comparing the performance of different scheduling algorithms, i.e. Professional Fair, Round Robin, and Best CQI on different MIMO (64 × 64, 32 × 32, 16 × 16, 8 × 8) set-up and block error rates. The performance of Best CQI algorithm is found to be better than other scheduling algorithms under considerations. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Predicting Hand Injury Severity Using Bayesian Networks in Cloud-Based Emergency Medicine 10

Predicting Hand Injury Severity Using Bayesian Networks in C...

引用

10th International Conference on communication and Signal Processing, ICCSP 2024

作者： Yuvaraj, S. Thinakaran, K. Srinivas, S. Porandla Sivakumar, S. Ishwarya, M.V. Thirumaraiselvan, P. Srm Institute of Science and Technology Faculty of Engineering and Technology Department of Electronics and Communication Engineering Chennai Tamil Nadu Kattankulathur India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India Malla Reddy Institute of Engineering and Technology Department of Information Technology Telangana Hyderabad India Department of Computer Science Tamil Nadu Perambalur India Agni College of Technology Artificial Intelligence and Data Science Department Tamil Nadu Thazhambur India Adhiparasakthi Engineering College Department of Electronics and Communication Engineering Tamil Nadu Melmaruvathur India

ISBN: (纸本)9798350353068

Predicting the severity of hand injuries in emergency care is the focus of this study, which suggests using cloud-based Bayesian networks. It is crucial to have accurate severity prediction in order to treat emergency hand injuries promptly since they are prevalent. By using the scalability and flexibility of cloud computing, this method constructs a Bayesian severity assessment network with patient data, injury characteristics, and historical medical records. The model's training data comes from a massive database of hand injury cases with different results. Emergency medical professionals may use real-time parameter modifications to strengthen and adapt the Bayesian network. Through the use of the cloud, healthcare providers may simply exchange data and reach consensus. It demonstrates that, compared to other well-established methods of evaluating hand injury severity, the model performs better in making predictions. The suggested method improves severity forecasts and advances cloud-based emergency care. The method for emergency hand injury care uses Bayesian networks in the cloud to improve scalability and accessibility. The findings show that the data-driven and efficient hand injury severity prediction method might transform emergency care by improving patient outcomes. © 2024 IEEE.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

Reassessing Deep Learning in Time Series: Predicting Time with Foresight

Reassessing Deep Learning in Time Series: Predicting Time wi...

引用

2023 International Conference on Advances in Computation, communication and Information Technology, ICAICCIT 2023

作者： Vinutha, C.B. Vivek, V. Pandeya, Megha Presidency University Department of Electronics and Communication Engineering Karnataka Bangalore India Faculty of Engineering and Technology Department of Computer Science Engineering Karnataka Bangalore India Maharishi University of Information Technology Maharishi School of Engineering & Technology Uttar Pradesh India

ISBN: (纸本)9798350344387

Machine learning relies heavily on time series forecasting, which has a wide range of uses, including although not limited to forecasting air quality, traffic patterns, and power use. Recent developments in deep training and matrix factorization models, however, have shown competitive performance and are emerging as alternatives. However, a fundamental disadvantage of these contemporary models over more established ones is their complexity. The Gradient Boosted Regression Tree, a well-known machine learning baseline, and popular deep learning models are compared in this work. We convert the time series forecast challenge into a window-based prediction issue, which is akin to (DNN) models. In addition, we design the GBRT model's input and output structure. In order to construct a single input instance to simulate a multi-output GBRT model, we concatenate the desired values with additional characteristics for each training window before flattening them. Using nine datasets, we undertake a thorough investigation and evaluate eight cutting-edge deep learning models recently presented at prestigious conferences. The findings show that a simple GBRT model performs much better than the state-of-the-art DNN models evaluated in this research thanks to the window-based input transformation. © 2023 IEEE.

关键词： Deep Learning DNN and Temporal Regularized Matrix Factorization Feature engineering Gradient Boosted Regression Trees (GBRT) Time Series Forecasting

来源：评论

学校读者我要写书评

暂无评论

Dual-Band Reflectarray Antennas Using Integrated Resonant and Non-Resonant Natures of Metallic Waveguide Elements at Millimeter Wave Frequencies

引用

Radio Science 2023年第1期58卷 1-13页

作者： Chou, H.-T. Wang, N.-N. Fang, M. Wang, L.-Q. Akkaraekthalin, P. Torrungrueng, D. Graduate Institute of Communication Engineering National Taiwan University Taipei Taiwan School of Electronics and Information Engineering Harbin Institute of Technology Harbin China Department of Electrical and Computer Engineering Faculty of Engineering King Mongkut's University of Technology North Bangkok Bangkok Thailand Research Center of Innovation Digital and Electromagnetic Technology Department of Teacher Training in Electrical Engineering Faculty of Technical Education King Mongkut's University of Technology North Bangkok Bangkok Thailand

Pure metallic reflectarray antennas have good power efficiency and low fabrication cost, limited to single-band operation in the past. A dual-band reflectarray antenna is developed for two directional beams by two feeds. The reflecting elements are metal waveguides and have novel properties of both resonant and non-resonant modes at the two frequency bands. The low and high-frequency bands can be easily separated by the cutoff frequency of waveguide modes. The phase-changing mechanisms via ray optics and fundamental waveguide modes, respectively, provide simple formulations for the elemental structure design of directional beams. Radiation characteristics of the linear and circular polarizations are cross-examined with a good performance by full-wave simulations using HFSS, FEKO, and CST at 28 and 60 GHz bands for 5G front-haul network applications. In particular, we have used HFSS to simulate the reflecting elements' basic characteristics of phase variation, FEKO to simulate the linear polarization antenna case, and CST to simulate the circular polarization antenna case, respectively. © 2023. American Geophysical Union. All Rights Reserved.

关键词： Cutoff frequency

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：