检索结果-内蒙古大学图书馆

4th International Conference on Recent Trends in Machine Learning, IoT, Smart Cities, and Applications, ICMISC 2023

作者： Belgaum, Mohammad Riyaz Sowmya, Kurni Sireesha, Kuruva Priyanka, Tatagari Tony Vyshnavi, Uppara Uravakonda Department of Computer Science and Engineering G. Pullaiah College of Engineering and Technology Kurnool India Faculty of Computing and Informatics Multimedia University Cyberjaya Malaysia

ISBN: (纸本)9789819994410

Sign Language Recognition (SLR) tries to convert sign language into written or spoken form to enable communication between a deaf-mute person and a normal person. The task of communicating with disabled and impaired persons is extremely challenging, owing to its complexity and variety of hand motions that have a major societal impact. In order to depict sign language motions, SLR approaches are increasingly being used. These classification models are based on hand-crafted characteristics. Building reliable features that can adapt to the diverse range of hand signs is nonetheless challenging. To address this issue, the authors proposed a special 3D convolutional neural network (CNN) to ease the communication between normal and mute communities. Our proposed model eliminates the requirement to create features by automatically extracting discriminative spatial–temporal features from the actual livestream without any prior information. To improve performance, the 3D CNN is fed with multiple channels of video feeds that include colour, depth, trajectory information, joint body locations, and depth clues. We illustrate the proposed model's superiority to the conventional methods based on hand-crafted characteristics by testing them against a real dataset collected using a depth camera. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Audition

来源：评论

学校读者我要写书评

暂无评论

Optical Ciphering Scheme for Cancellable Speaker Identification System

引用

computer Systems science & engineering 2023年第4期45卷 563-578页

作者： Walid El-Shafai Marwa A.Elsayed Mohsen A.Rashwan Moawad I.Dessouky Adel S.El-Fishawy Naglaa F.Soliman Amel A.Alhussan Fathi EAbd El-Samie Department of Electronics and Electrical Communications Engineering Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Security Engineering Laboratory Department of Computer SciencePrince Sultan UniversityRiyadh11586Saudi Arabia Department of Electronics and Communications Faculty of EngineeringCairo UniversityCairoEgypt Department of Information Technology College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadhSaudi Arabia

Most current security and authentication systems are based on personal *** security problem is a major issue in the field of biometric *** is due to the use in databases of the original *** biometrics will forever be lost if these databases are *** privacy is the most important goal of cancelable *** order to protect privacy,therefore,cancelable biometrics should be non-invertible in such a way that no information can be inverted from the cancelable biometric templates stored in personal identification/verification *** methodology to achieve non-invertibility is the employment of non-invertible *** work suggests an encryption process for cancellable speaker identification using a hybrid encryption *** system includes the 3D Jigsaw transforms and Fractional Fourier Transform(FrFT).The proposed scheme is compared with the optical Double Random Phase Encoding(DRPE)encryption *** evaluation of simulation results of cancellable biometrics shows that the algorithm proposed is secure,authoritative,and *** encryption and cancelability effects are good and reveal good ***,it introduces recommended security and robustness levels for its utilization for achieving efficient cancellable biometrics systems.

关键词： Cancellable biometrics jigsaw transform FrFT DRPE speaker identification

来源：评论

学校读者我要写书评

暂无评论

Numerical Predictions of Laminar Forced Convection Heat Transfer with and without Buoyancy Effects from an Isothermal Horizontal Flat Plate to Supercritical Nitrogen

引用

Frontiers in Heat and Mass Transfer 2024年第3期22卷 889-917页

作者： K.S.Rajendra Prasad Sathya Sai T.R.Seetharam Adithya Garimella Department of Mechanical and Industrial Engineering Manipal Institute of Technology BengaluruManipal Academy of Higher EducationManipal576104India Sustainable Energy Technology Faculty of Electrical EngineeringMathematics and Computer ScienceDelft University of TechnologyDelft2600 AANetherlands Department of Mechanical Engineering PES UniversityBengaluru560085India

Numerical predictions are made for Laminar Forced convection heat transfer with and without buoyancy effects for Supercritical Nitrogen flowing over an isothermal horizontal flat plate with a heated surface facing *** are performed by varying the value ofΔT from5 to 30 K and P_(∞)/P_(cr)ratio from1.1 to *** of all the thermophysical properties of supercritical Nitrogen is *** wall temperatures are chosen in such a way that two values of Tw are less than T∗(T*is the temperature at which the fluid has a maximum value of Cp for the given pressure),one value equal to T∗and two values greater than T∗.Three different values of U∞are used to obtain Re∞range of 3.6×10_(4)to 4.74×10^(5)for forced convection without buoyancy effects and Gr_(∞)/Re^(2)_(∞)range of 0.011 to 3.107 for the case where buoyancy effects are *** different forms of correlations are proposed based on numerical predictions and are compared with actual numerical *** has been found that in all six forms of correlations,the maximum deviations are found to occur in those cases where the pseudocritical temperature TT∗lies between the wall temperature and bulk fluid temperature.

关键词： Supercritical nitrogen laminar flow numerical methods forced convection heat transfer isothermal horizontal surface

来源：评论

学校读者我要写书评

暂无评论

Vibration analysis of elastically supported sandwich beam with damaged core and functionally graded face sheets

引用

Steel and Composite Structures 2025年第1期54卷 71-83页

作者： Wang, Lulu Mohsin, Hasan F. Bains, Pardeep Singh Sharma, Rohit Bohlooli, Nasrin College of Mechanical and Electrical Engineering Guangdong University of Science and Technology Guangdong Dongguan523083 China Computer Techniques Engineering Department Faculty of Information Technology Imam Ja’afar Al-Sadiq University Baghdad10011 Iraq Computer Technical Engineering Department College of Technical Engineering The Islamic University Najaf54001 Iraq University Karnataka Bengaluru560069 India Department of Mechanical Engineering Vivekananda Global University Rajasthan Jaipur303012 India School of Engineering and Technology Shobhit University Uttar Pradesh Gangoh247341 India Department of Mechanical Engineering Arka Jain University Jharkhand Jamshedpur831001 India Nabi Data Science & Computational Intelligence Research Co. Tehran Iran

This paper presents the influence of carbon nanotubes (CNTs) waviness, aspect ratio and damaged core on the vibrational behavior of functionally graded nanocomposite sandwich beams resting on two-parameter elastic foundations. The distributions of CNTs are considered functionally graded (FG) or uniform along the thickness of upper and bottom layers of the sandwich beam and their mechanical properties are estimated by an extended rule of mixture. In this study, the classical theory concerning the mechanical efficiency of a matrix embedding finite length fibers has been modified by introducing the tube-to-tube random contact, which explicitly accounts for the progressive reduction of the tubes’ effective aspect ratio as the filler content increases. A damage model is introduced to provide an analytical description of an irreversible rheological process that causes the decay of the mechanical properties, in terms of engineering constants. An isotropic damage is considered for the core of the sandwich beams. The equations of motion are derived based on Timoshenko beam theory and employing Hamilton’s principle. The problem is modeled using a semi-analytical approach composed of generalized differential quadrature method (GDQM) and series solution adopted to solve the equations of motion. Detailed parametric studies are carried out to investigate the mechanical behavior of these multi-layered structures depending on the damage features, through-the-thickness distribution and boundary conditions. Also, the effects of carbon nanotubes (CNTs) waviness, CNT aspect ratio, Winkler foundation modulus, shear elastic foundation modulus and geometrical conditions on the vibrational behavior of the sandwich structure are studied. © 2025 Techno-Press, Ltd.

关键词： Aspect ratio

来源：评论

学校读者我要写书评

暂无评论

LTL Model Checking for Verification of Electronic Medical Record (EMR) Design 8th

LTL Model Checking for Verification of Electronic Medical R...

引用

8th International Conference on Mathematics: Pure, Applied and Computation, ICoMPAC 2023

作者： Taryana, Acep Adzkiya, Dieky Mufid, Muhammad Syifa’ul Mukhlash, Imam Abate, Alessandro Department of Mathematics Faculty of Science and Data Analytics Institut Teknologi Sepuluh Nopember Surabaya Indonesia Department of Electrical Engineering Engineering Faculty Universitas Jenderal Soedirman Purwokerto Indonesia Department of Computer Science University of Oxford Oxford United Kingdom

ISBN: (纸本)9789819721351

This paper presents an in-depth investigation into the verification of a software design model, focusing on the context of Electronic Medical Record (EMR) systems. Verification plays a critical role in ensuring the correctness and reliability of such systems, making it a topic of paramount importance. In this study, we undertake the task of remodeling the EMR requirements using a finite transition system to facilitate rigorous analysis and verification. Additionally, we express the formal specification through Linear Temporal Logic (LTL), leveraging its expressive power and ability to capture temporal properties accurately. To assess the validity of the design model, we employ the widely recognized SPIN model checker, a tool known for its effectiveness in detecting errors and inconsistencies in software systems. Our analysis reveals several critical findings. Specifically, the model checker successfully identifies paths within the design model that fail to satisfy the specified LTL formula, shedding light on potential areas of concern. Moreover, the generation of a comprehensive counterexample provides valuable insights for further analysis and improvement of the software design. Overall, this research highlights the significance of verification techniques in software design and emphasizes the applicability of the finite transition system and LTL in this context. The findings underscore the importance of thorough verification and the potential benefits of employing tools like SPIN to enhance the reliability and robustness of EMR systems. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

A Review on the Applications of Natural Language Processing in Healthcare 4

A Review on the Applications of Natural Language Processing ...

引用

4th International Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2024

作者： Warbhe, Mohan K. Verma, Prateek Faculty of Engineering and Technology Department of Computer Science and Design Sawangi Maharashtra Wardha442001 India Faculty of Engineering and Technology Department of Artificial Intelligence and Machine Learning Sawangi Maharashtra Wardha442001 India

ISBN: (纸本)9798331529635

In healthcare, Natural Language Processing (NLP) is a technique to improve clinical decision support, patient care, and medical research. By automating clinical recording, NLP enhances the calibre of medical records and professional communication. It makes Electronic Health Records (EHRs) easier to use by facilitating quick and easy data entry, retrieval, and access to vital patient data that helps with precise diagnosis and efficient treatment planning. Through the analysis of patient-specific data, NLP supports clinical decision support by delivering prompt recommendations. Chatbots and virtual assistants managing repetitive duties like booking appointments also improve patient connection. NLP makes it easier to analyse vast amounts of literature for medical research, facilitating the extraction and summary of important discoveries. Healthcare data processing requires text preparation, sentiment analysis, Named Entity Recognition (NER), semantic parsing, and Natural Language Generation (NLG). However, there are obstacles to overcome, like bias, ethical concerns, system integration, privacy, and data quality. The healthcare industry can use NLP to enhance patient outcomes, promote personalized medication, and streamline healthcare delivery by guaranteeing interoperability and setting standards. © 2024 IEEE.

关键词： Challenges of NLP in Healthcare Future treads of NLP for healthcare Healthcare NLP

来源：评论

学校读者我要写书评

暂无评论

Enhancing Algorithmic Trading Strategies with Sentiment Analysis: A Reinforcement Learning Approach 3

Enhancing Algorithmic Trading Strategies with Sentiment Anal...

引用

3rd IEEE World Conference on Applied Intelligence and Computing, AIC 2024

作者： Bharathi Mohan, G. Prasanna Kumar, R. Vifert Jenuben Daniel, V. Praghaadeesh, R. Maniappan, Varun Doss, Srinath Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Chennai India University Botswana Faculty of Engineering and Technology Botho Botswana

ISBN: (纸本)9798350384598

This paper discusses the application of deep reinforcement learning algorithms in stock trading, where the stock market environment is highly dynamic in nature. To represent the dynamics of the stock market, news headlines are a key factor in order to predict whether the market direction is bullish (upward) or bearish (downward). So we use different sentiment analysis models like Finbert and Roberta to see how the sentiment scores given by these models affect our trading agent's strategy. These sentiment scores are added to our custom trading environment, where we combine these scores as part of the state along with other parameters like open, high, low, close prices and trading *** for the reinforcement learning part, we used various policy gradient methods like Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Deep Q-Network (DQN) to train our agent in this custom environment. These models were then back-tested on historic data, where the trading strategies devised by these deep RL agents during the training phase were applied. The results provided by these models were very promising. The evaluation metrics used were the Sharpe score and Sortino score. The highest Sharpe ratio was given by the PPO agent, which was 3.0 for Facebook data and 2.834 for Goldman Sachs data, using the Roberta sentiment model. Whereas for the Finbert model, PPO got 3.24 for Facebook data and 3.03 for Goldman Sachs data. This explains that the trading portfolio is performing really well. © 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

Artificial Intelligent Applications in Smart Cities 4

Artificial Intelligent Applications in Smart Cities

引用

4th IEEE International Conference on Smart Information Systems and Technologies, SIST 2024

作者： Caglayan, Ruhi Zafer Kayisli, Korhan Coteli, Resul Omirgaliyev, Ruslan Zhakiyev, Nurkhat Faculty of Engineering TED University Ankara Turkey Faculty of Engineering Gazi University Ankara Turkey Faculty of Technology Firat University Elazig Turkey Department of Computer Engineering Astana IT University Astana Kazakhstan Department of Science and Innovation Astana IT University Astana Kazakhstan

ISBN: (纸本)9798350374865

History shows us that people move towards a more stable lifestyle after undergoing significant changes. During these times, the way communities and buildings were designed started to change too. Different periods in history are known for their standout moments, each bringing its own set of needs and tech breakthroughs. Nowadays, tech keeps evolving. People nowadays aim for a more straightforward life, and technology has been shaping up to meet this need. We live in times highlighted by the rise of smart technology, like artificial intelligence and the Internet of Things, which not only make daily tasks easier but also transform how we think about our cities and personal spaces. This piece focuses on exploring the smart city idea, touching upon various associated subjects. As we delve into these areas, we'll also look at some important research related to them. © 2024 IEEE.

关键词： Artificial intelligence intelligence systems Internet of Things Smart City

来源：评论

学校读者我要写书评

暂无评论

Arduino-Based Real-Time Obstacle Detection in Vehicles Using Proximity Sensors

Arduino-Based Real-Time Obstacle Detection in Vehicles Using...

引用

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

作者： Gupta, Meenu Kumar, Rakesh Das, Sunaina Sharma, Rohan Obaid, Ahmed J. Chandigarh University Department of Computer Science & Engineering Punjab India University of Kufa Faculty of Computer Science and Mathematics Najaf Iraq Al-Ayen University Technical Engineering College Department of Computer Technical Engineering Thi-Qar Iraq

ISBN: (纸本)9798350344387

Vehicle collision is currently one of the major problems for fatal traffic accidents where people lose their lives. To avoid this issue, intelligent vehicles pay more attention to people. The current anti-collision vehicles are lacking with the black path follower, and it is a high risk of loss of human lives. To overcome these challenges, an Arduino-based anti-collision device is suggested to reduce the count of accidents to avoid head-to-back vehicle collisions. Nowadays, one of the evolving technologies in the automotive sector is detecting obstacles using anti-collision vehicle systems. In the automobile sector, an anti-collision system is a safety system that automatically prevents collision among cars and objects. In this work, a microcontroller-based automated car anti-collision system is proposed. The proposed system is skilled at spotting obstacles using a precise distance sensor, alerting the driver when a collision is imminent, and automatically applying the brakes via an actuator, when necessary, without the driver's assistance. The proposed system will automatically stop the vehicle in case the driver avoids the collision as the system monitors the vehicle's condition continuously. This system can safeguard drivers from mishaps and lower accidental death rates because it is user-friendly and adaptable. This mechanism can be used in any automobile vehicle as it's a prudent system. © 2023 IEEE.

关键词： Accident Anti-collision Arduino Obstacle Detection Proximity Sensors Risk Ultrasonic Sensor Cars Vehicle

来源：评论

学校读者我要写书评

暂无评论

Enhancing Microgrid Energy Security Through Optimal Power Sharing in Multi-Modal Energy Storage Systems 4

Enhancing Microgrid Energy Security Through Optimal Power Sh...

引用

4th International Conference on Robotics, Electrical and Signal Processing Techniques, ICREST 2025

作者： Anik, Shaikh Tawhidul Islam Mithil, Md Salman Khan Ahmad, Shameem Hazari, Md. Rifat Islam, Mahmoodul Ahmed, Tofael Parvez, Md. Shahariar Hassan, Mahamudul American International University-Bangladesh Faculty of Engineering Department of Electrical and Electronic Engineering Dhaka1229 Bangladesh Department of Electrical Engineering and Computer Science Rapid CitySD57701 United States Chittagong University of Engineering & Technology Department of Electrical and Electronic Engineering Chattogram4349 Bangladesh American International University-Bangladesh Faculty of Engineering Department of Industrial and Production Engineering Dhaka1229 Bangladesh

ISBN: (纸本)9798331530938

Microgrids (MGs), which combine distributed energy resources (DERs) with energy storage systems (ESS), offer improved energy security, reliability and sustainability by utilizing renewable energy sources for subsequent use. However, single ESS options often face challenges such as short life cycles, low power density etc. More than one ESS can resolve the mentioned issues though it increases complexity and maintaining stability becomes an issue. This paper proposes an effective energy management strategy between two ESS namely battery and supercapacitor to increase energy security in MG. The proposed strategy is designed in such a way that one of the two ESS stays connected all the time to the DC bus to ensure uninterruptable power supply to loads. Due to the use of DC bus, the system complexity decreases as there is no need to control frequency. Two cases were considered to verify the performance of the proposed energy management strategy in Matlab/Simulink. In the first case, during the unavailability of supercapacitor, the battery supplies 50 W to the load in addition to PV whereas supercapacitor supplies 136 W in the absence of battery along with PV. Furthermore, it was shown that the absence of PV has no negative effect in terms of power flow by ESS to meet load demand. © 2025 IEEE.

关键词： Energy security Energy Storage Systems Microgrid Power sharing Supercapacitor

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：