检索结果-内蒙古大学图书馆

Facial Emotion Recognition and Detection

Facial Emotion Recognition and Detection

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

作者： Kumar, Sunil Gupta, Neeraj Kumar Tiwari, Shreyash Shukla, Swapnil Galgotias College of Engineering and Technology Department of Computer Science and Engineering UttarPradesh Greater Noida India

ISBN: (纸本)9798350373783

Facial emotion detection and recognition remains a challenging and interesting in the world of computer vision. Recognizing face expression was always tough nut to crack out as the way a facial expression expressed by a person varies from one man to another. Deep learning is a most reliable technology for the study of facial expression and deep neural network is used to classify the images according to different emotions. Convolutional neural network is the technology helped to classify the images. In this paper we are introducing a new junction of these technologies for the recognition of facial emotions. In recent years, facial emotion recognition has witnessed a great surge in popularity, motivating researchers to dive deeper into this technology, getting promising outcomes in the past. There are several models which provide an overview regarding facial emotions. The main difficulty in this to identify the subtle emotions and the need of some large datasets which are also discussed in this paper. We also highlight some of the important aspect of facial emotion recognition system in many other real-life fields and have lot of scope in future research. The idea is to give overview about this field and and its role and advancement in branch of artificial intelligence and computer vision. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Analysis of Problem Solving Ability by Applying Cognitive Intelligence 1

Analysis of Problem Solving Ability by Applying Cognitive In...

引用

1st IEEE International Conference on Advances in Computing, Communication and Networking, ICAC2N 2024

作者： Bai, K. Jhansi Lakshmi Akhil, Karnam Sumanth, V. Uday Kiran, V. Satwik, P. VNR Vignana Jyothi Institute of Engineering and Technology Department of Computer Science and Engineering Hyderabad India

ISBN: (纸本)9798350356816

This Cognitive intelligence is the ability to understand, process, acquire information, and apply knowledge in a way that optimizes the possible steps to achieve the desired goal. Cognitive intelligence plays an important role in students' lives as it helps them understand and grasp new skills, maintain healthy relationships with people, and work positively in their lives. The levels of intelligence vary from person to person and depend on a variety of elements, including experiences, opinions, environment, and education. A lack of cognitive intelligence can lead to problems for students professionally, personally, and mentally. Cognitive abilities such as problem-solving, hypothesis skills, numerical skills, emotional sense, memory retention, and responses to problems significantly impact behavior and cognitive skills. The proposed work aims to test the cognitive abilities of undergraduate students by conducting surveys. The proposed work identifies various models, theories and techniques of cognitive science and builds a database based on students' survey responses which are based on testing various cognitive abilities. A recommendation mechanism is developed to enhance students' cognitive abilities in real-time scenarios. A knowledge-based recommendation system is provided to recommend solutions based on cognitive science theories to help students identify weak areas and improve their cognitive skills. © 2024 IEEE.

关键词： Knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

Loop Subgraph-Level Greedy Mapping Algorithm for Grid Coarse-Grained Reconfigurable Array

引用

Tsinghua science and technology 2023年第2期28卷 330-343页

作者： Naijin Chen Fei Cheng Chenghao Han Jianhui Jiang Xiaoqing Wen School of Computer and Information Science Anhui Polytechnic UniversityWuhu 241000China School of Software Engineering Tongji UniversityShanghai 201804China Department of Computer Science and Networks Kyushu Institute of TechnologyFukuoka 820-8502Japan

To solve the problem of grid coarse-grained reconfigurable array task mapping under multiple constraints,we propose a Loop Subgraph-Level Greedy Mapping(LSLGM)algorithm using parallelism and processing element *** the constraint of a reconfigurable array,the LSLGM algorithm schedules node from a ready queue to the current reconfigurable cell array *** mapping a node,its successor’s indegree value will be dynamically *** its successor’s indegree is zero,it will be directly scheduled to the ready queue;otherwise,the predecessor must be dynamically *** the predecessor cannot be mapped,it will be scheduled to a blocking *** dynamically adjust the ready node scheduling order,the scheduling function is constructed by exploiting factors,such as node number,node level,and node *** with the loop subgraph-level mapping algorithm,experimental results show that the total cycles of the LSLGM algorithm decreases by an average of 33.0%(PEA44)and 33.9%(PEA_(7×7)).Compared with the epimorphism map algorithm,the total cycles of the LSLGM algorithm decrease by an average of 38.1%(PEA_(4×4))and 39.0%(PEA_(7×7)).The feasibility of LSLGM is verified.

关键词： Grid Coarse-Grained Reconfigurable Array(GCGRA) mapping loop subgraph scheduling

来源：评论

学校读者我要写书评

暂无评论

Blockchain Solutions for Decentralized Supply Chain Management: Challenges and Innovations 4

Blockchain Solutions for Decentralized Supply Chain Manageme...

引用

4th International Conference on Technological Advancements in Computational sciences, ICTACS 2024

作者： Gupta, Ayush Kumar Agarwal, Ambuj Sharda School of Engineering and Technology Department of Computer Science and Engineering UP Greater Noida India

ISBN: (纸本)9798350387490

The article investigates how blockchain technology can be integrated into supply chain management (SCM) implementation. It brings to attention critical constraints impoverishing the traditional SCM methods such as unproductive nature, absence of ideas or information sharing, and centrally controlled decision making. The contemporary perspective uses the blockchain, specifically the Ethereum and Solana platforms, in attempts to enhance transparency, traceability, and efficiency. The use of smart contracts on Ethereum makes processes faster, thereby decreasing opportunities for loss and errors caused by waiting time during the transactions, but the transacting people face some limitations like expensive fees and slow speeds. Whereas Solana has the ability to quickly process transactions with lower fees, allowing for better use of real time applications in SCM, the platform supports a transaction throughput of 65000 TPS. Both platforms are discussed in the article while Solana is claimed to be better at cut-throat time factor, high volumes and the Proof of History mechanism helps in performance on cost efficiency and speed. The research goes on to suggest that Solana's transactions definitely have a potential of optimizing SCM by improving on the transparency factor, costs involved and collaboration among stakeholders. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Enhanced Risk Assessment of Human Health Through Gated Dual-Path RNN and Gravitational Search Algorithm 3rd

Enhanced Risk Assessment of Human Health Through Gated Dual-...

引用

3rd International Conference on Emerging Trends in Expert Applications and Security, ICE-TEAS 2024

作者： Shanthi, M.A. Karthik, S. Sabitha, R. Kavitha, M.S. Department of Computer Science and Engineering SNS College of Engineering Tamilnadu Coimbatore641107 India Department of Computer Science and Engineering SNS College of Technology Tamilnadu Coimbatore641035 India

ISBN: (纸本)9789819739905

The need for precise risk assessment of human health in the healthcare industry has resulted in the integration of advanced technology. This study introduces a unique strategy that combines the Gravitational Search Algorithm (GSA) with Gated Dual-Path Recurrent Neural Networks (RNN) to address the present constraints in risk assessment methodologies. Conventional methods are challenged by the complexity of health-related data and the requirement for real-time risk assessment. The goal of this project is to integrate cutting-edge artificial intelligence and optimization techniques to transform the assessment of risks to human health. Predictions produced by current risk assessment algorithms are frequently inadequate due to their inability to identify complex patterns in health data. Moreover, the accuracy and resilience of these models are hampered by the absence of effective optimization tools. For health risk assessment, there is a noticeable lack of integration between advanced neural network topologies and cutting-edge optimization methods. To close this gap and improve risk prediction accuracy, Gated Dual-Path RNN and Gravitational Search Algorithm are combined. The proposed approach uses the Gravitational Search Algorithm to optimize the model parameters and Gated Dual-Path RNN to take advantage of the temporal relationships found in health data. The model capacity to capture both short- and long-term interdependence is improved by the dual-path architecture, and the gravitational search method effectively adjusts the network parameters. Experiments reveal encouraging outcomes, with increased precision and dependability above conventional risk assessment algorithms. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Benchmark GELU in Secure Multi-Party Computation

Benchmark GELU in Secure Multi-Party Computation

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Zhang, Rui Li, Hongwei Hao, Meng Chen, Hanxiao Liu, Dongxiao Zhang, Yuan Tang, Dianhua University of Electronic Science and Technology of China School of Computer Science and Engineering China Science and Technology on Communication Security Laboratory Chengdu China

ISBN: (纸本)9798350351255

Recently, several technology companies have released online inference services for clients based on Transformer-based large language models, which show excellent performance in various tasks. However, in these services, the inputs usually involve clients' sensitive information. To address this problem, many works have proposed secure inference on language models such as GPT. For language models, complex mathematical functions like Gaussian Error Linear Unit (GELU) are used extensively and dominate the main cost of secure inference. In this work, we systematically study the existing secure GELU protocols and classify previous methods into two categories: polynomial-based protocols and lookup table (LUT)-based protocols. We point out several important characteristics and tradeoffs for these two classes of secure GELU protocols. Based on these observations and analysis, we propose a new secure GELU protocol, called Simple. The main technique that Simple uses involves a LUT of small size to retrieve approximate polynomials for fitting residual error functions caused by a crude approximation for GELU, which achieves state-of-the-art (SOTA) overhead and accuracy performance. We conduct extensive experiments and benchmark the previous 6 secure GELU protocols. The experimental comparison shows that our Simple protocol achieves 1.1 ∼ 8784.3× computation and 1.4 ∼ 188.8× communication improvements while reducing 1.2∼80.2× errors. © 2024 IEEE.

关键词： Table lookup

来源：评论

学校读者我要写书评

暂无评论

Drivers Real time Drowsiness, Attention Detection and Alarm System using Eye Aspect Ratio(EAR) Analysis 3

Drivers Real time Drowsiness, Attention Detection and Alarm ...

引用

3rd International Conference on Advancement in Electrical and Electronic engineering, ICAEEE 2024

作者： Ahmed, Nawshad Romiz, Sk Niyaz Amin, Rohul Shan, Mahe Shahriar Mahmud, Masroor Bangladesh Army University of Science and Technology Department of Electrical and Electronic Engineering Dinajpur Bangladesh Bangladesh Army University of Science and Technology Department of Electrical and Electronic Engineering Satkhira Bangladesh Bangladesh Army University of Science and Technology Department of Computer Science and Engineering Tangail Bangladesh Bangladesh Army University of Science and Technology Department of Electrical and Electronic Engineering Dhaka Bangladesh Bangladesh Army University of Science and Technology Department of Computer Science and Engineering Satkhira Bangladesh

ISBN: (纸本)9798350388282

There is an immediate threat to the highway transportation system from road accidents, which can cause death, serious injury, and property damage. Accidents involving motor vehicles cause significant injury or death to a large number of individuals annually. Fatigue, lack of focus, and lethargy are key contributors to vehicle collisions. In order to identify driver inattention or exhaustion in real-time, this research lays forth a system that combines an emergency alarm system with Eye Aspect Ratio (EAR), which is based on facial landmarks. The method's strength is that it can accurately differentiate between closed eyes and inattention, even in low-light conditions. The experimental results demonstrate the efficacy of the proposed method in resolving these critical issues, offering a practical means to enhance road safety. © 2024 IEEE.

关键词： Aspect ratio

来源：评论

学校读者我要写书评

暂无评论

Hybrid energy efficient deep learning and redactable consortium blockchain-based secure framework for smart parking in smart cities

引用

Multimedia Tools and Applications 2024年第37期83卷 85391-85420页

作者： D, Amu Baskaran, Santhi Department of Computer science and Engineering Puducherry Technological University Puducherry India Department of Information Technology Puducherry Technological University Puducherry India

Management of vehicular parking in the crowded environment is the indispensable requirement for the smart city scenario. The advent and potential development of Information Communication Technologies (ICT) and Internet of things (IoT) helped in proper thinking, operation and planning of parking management in smart city environment. But they suffer from the issue of privacy, security, integrity, energy efficiency, communication bandwidth and centralization. In this paper, Hybrid Deep learning and Redactable consortium blockchain-based Secure Framework (HDLRCBSF) is proposed for achieving the objective of energy-efficient smart parking in smart cities. This HDLRCBSF adopted the merits of Deep Bi-LSTM network for exploring the data associated with parking zones, such that optimal parking zones can be potentially allocated to the drivers with the ideal timing and location. It used the Redactable consortium blockchain network using Road Side Units (RSUs) which helped in attaining data verification and authentication at the security layer. It also implemented Threshold Chameleon Hash (TCH) algorithm for the objective of encrypting and decrypting the data related to the parking zones to establish secure communication. It adopted the significance of Deep Auto Regression Feature Augmented Bi-LSTM Networks in the analysis layer for exploring the cloud data that provides optimal parking lot to the drivers depending on the requirements that include cost, distance, and time. The quantitative and qualitative investigation conducted on the proposed HDLRCBSF confirmed its efficacy in terms of best parking space allocation rate of 21.32%, better than the baseline approaches that offered to the drivers with maximized privacy and security. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Quantum-Accelerated Hyperparameter Tuning for Dynamic NLP Models 2

Quantum-Accelerated Hyperparameter Tuning for Dynamic NLP Mo...

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Ravikumar, S. Raj, Arockia Babu, R. Vijay, K. Ramani, R. Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Tamilnadu Chennai600062 India Department of Computer Science and Engineering PSNA College of Engineering and Technology Dindigul India Department of Computational Intelligence Faculty of College of Engineering and Technology SRM Institute of Science and Technology Tamilnadu Chennai603203 India Department of Computer Science and Engineering Rajalakshmi Engineering College Tamilnadu Chennai602117 India Department of Computer Science and Engineering P.S.R. Engineering College Tamilnadu Sivakasi626140 India

In the rapidly evolving field of natural language processing (NLP), performance optimization of large-scale NLP models is crucial. Through the application of Quantum-Accelerated Hyperparameter Tuning (QAHT), this abstract introduces a novel approach to addressing this issue. Our proposed framework leverages quantum computing capabilities to dynamically optimize NLP model hyperparameters in real-time, catering to the ever-changing character of textual data streams. Traditional hyperparameter optimisation methods usually rely on laborious grid searches or random exploration, which may not be suitable for dynamic NLP jobs. Contrarily, QAHT uses Quantum Neural Network (QNN) architectures that have been specially designed for hyperparameter optimisation. These QNNs improve performance and efficacy by dynamically modifying and improving model configurations. This abstract discusses the key elements of the QAHT architecture, including real-time model deployment, adaptive learning, and continuous data stream processing. In addition to speeding up the hyperparameter optimisation process, QAHT makes sure that NLP models are still flexible and responsive to shifts in the sentiment of the data and its distribution. This method has applications beyond NLP since it provides a foundation for effectively optimising machine learning models in complex, real-time situations. As quantum computing develops, QAHT represents a promising future in machine learning, where quantum-enhanced capabilities satisfy the needs of contemporary data-driven applications. © 2024 Elsevier B.V.. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Denoising Filters for Ultrasound Fetal Head Images

引用

SN computer science 2025年第2期6卷 1-13页

作者： Prasad, Kauleshwar Patnaik, Pawan Kumar Agrawal, Anupam Department of Computer Science and Engineering Bhilai Institute of Technology Chhattisgarh Durg India Department of Electrical and Electronics Engineering Bhilai Institute of Technology Chhattisgarh Durg India

Deep learning has significantly advanced image processing in the medical domain, including the analysis of ultrasound (US) fetal images for prediction of fetal growth retardation. Before analysis of fetal images there is need of correction since they are usually adulterated by noise during acquisition of image. In the recent years, there are various deep learning based denoising methods in which U-Net have attracted the attention of many researchers. This paper describes the comparative study of different filters such as mean filter, gaussian filter, anisotropic diffusion, non-local means (NLM) filter and U-Net based on their performance on denoising fetal images prior to the prediction of fetal growth retardation (FGR). In this article peak signal to noise ratio (PSNR), mean square error (MSE), similarity index measure (SSIM), peak signal to interference ratio (PSIM) and multi scale structural similarity index measure (MSIM) values are analyzed for the performance of these filters. This paper reveals that U-Net performs better in image quality evaluation when compared to other filtering algorithms, based on testing and analytical findings. We have also discussed the significance of MSE, PSNR, SSIM, PSIM, MSIM and U-Net in this article. This article also covers the advantages, disadvantages, and characteristics of different filtering methods, including U-Net. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Deep learning Denoising techniques Fetal growth retardation U-Net

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：