Article
Multidisciplinary Sciences
Chao Chen, Weiyu Guo, Zheng Wang, Yongkui Yang, Zhuoyu Wu, Guannan Li
Summary: This paper proposes a low-overhead, energy-aware runtime manager for processing RNN tasks in edge cloud computing. By dynamically assigning tasks to edge and cloud computing systems based on QoS requirements and optimizing energy on edge systems using DVFS techniques, experimental results show significant reduction in energy consumption compared to existing methods.
Article
Engineering, Mechanical
Jialan Liu, Chi Ma, Hongquan Gui, Shilong Wang
Summary: Production lines require precise and efficient machining, with thermal errors of key equipment affecting geometric accuracy. The CEDTS system, with a four-terminal structure, improves efficiency by predicting and controlling thermal errors through error mechanism analysis and optimization algorithms. Validation on a production line demonstrated significant reduction in machining errors and accelerated execution time with GPU acceleration.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2022)
Article
Computer Science, Information Systems
Sijing Duan, Dan Wang, Ju Ren, Feng Lyu, Ye Zhang, Huaqing Wu, Xuemin Shen
Summary: This paper provides a comprehensive survey on distributed artificial intelligence (DAI) empowered by end-edge-cloud computing (EECC). It explores the benefits of the EECC paradigm in supporting distributed AI, introduces fundamental technologies for distributed AI, and discusses optimization technologies empowered by EECC for distributed training and inference. It also addresses security and privacy threats in the DAI-EECC architecture and reviews defense technologies. Furthermore, it presents promising applications enabled by DAI-EECC and highlights research challenges and open issues.
IEEE COMMUNICATIONS SURVEYS AND TUTORIALS
(2023)
Article
Multidisciplinary Sciences
Tiankuang Zhou, Wei Wu, Jinzhi Zhang, Shaoliang Yu, Lu Fang
Summary: We propose a spatiotemporal photonic computing architecture to achieve dynamic processing, matching highly parallel spatial computing with high-speed temporal computing. A unified training framework is devised to optimize the physical system and the network model. The proposed architecture paves the way for ultrafast advanced machine vision and will find applications in unmanned systems, autonomous driving, ultrafast science, etc.
Article
Computer Science, Information Systems
Shitharth Selvarajan, Gautam Srivastava, Alaa O. Khadidos, Adil O. Khadidos, Mohamed Baza, Ali Alshehri, Jerry Chun-Wei Lin
Summary: This research aims to implement an Artificial Intelligence-based Lightweight Blockchain Security Model (AILBSM) to ensure privacy and security of IIoT systems. By combining the advantages of lightweight blockchain and AI mechanisms, the proposed model reduces the impact of attacks and transforms features into encoded data using an Authentic Intrinsic Analysis (AIA) model. Extensive experiments validate the improved execution time, classification accuracy, and detection performance of the proposed model.
JOURNAL OF CLOUD COMPUTING-ADVANCES SYSTEMS AND APPLICATIONS
(2023)
Article
Materials Science, Multidisciplinary
Qi Liu, Song Gao, Yang Li, Wenjing Yue, Chunwei Zhang, Hao Kan, Guozhen Shen
Summary: This article introduces a WO3/HfO2 heterojunction-based memristor with extraordinary resistive switching behaviors and neuromorphic characteristics. The mechanism behind the electrical performances of this device is studied, and a multilayer perceptron neural network constructed based on the memristor model is explored to enhance recognition accuracy. The proposed memristor contributes to promoting the development of high-density storage and neuromorphic computing technology.
ADVANCED MATERIALS TECHNOLOGIES
(2023)
Article
Engineering, Multidisciplinary
Julian N. Heidenreich, Colin Bonatti, Dirk Mohr
Summary: Mechanics-specific recurrent neural network (RNN) models can describe the complex three-dimensional stress-strain response of elasto-plastic solids for arbitrary loading paths. A strategy of training with datasets comprising random walks in strain space and transfer learning can significantly improve the generalization ability and convergence rates of the models. Ensemble transfer learning from multiple materials further enhances the accuracy and generalization ability of the models.
INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN ENGINEERING
(2023)
Article
Engineering, Chemical
Hyeon-Jun Kim, Soo-Whang Baek
Summary: This study proposes the design and application of wearable gloves that can recognize sign language expressions through image input and generate finger movements and feedback using a vibration motor. The wearable gloves are intended to assist nondisabled people in learning and accurately expressing sign language. Through experiments and data analysis, the proposed method achieved an accuracy of 85% using a LSTM model.
Article
Computer Science, Information Systems
Aiqing Li, Wanli Huang
Summary: In recent years, the sports industry has witnessed the growth of artificial intelligence (AI) and cloud computing. This survey explores the utilization of AI and cloud computing in sports, focusing on their potential to revolutionize athlete performance, injury prevention and rehabilitation, fan experiences, and business operations. It also acknowledges challenges in data privacy, security, transparency, and ethics. The survey highlights the importance of responsible AI adoption and emerging trends such as edge computing, blockchain, and augmented reality (AR). The findings contribute to understanding the transformative potential of AI and cloud computing in sports and provide insights for researchers, practitioners, and stakeholders.
Article
Biochemistry & Molecular Biology
Antonio Agliata, Deborah Giordano, Francesco Bardozzo, Salvatore Bottiglieri, Angelo Facchiano, Roberto Tagliaferri
Summary: Diabetes is a chronic metabolic disease with high blood sugar levels, and type 2 diabetes is the most common type. Early diagnosis and treatment can prevent or delay complications. Previous studies have used machine learning techniques to predict diabetes, and artificial neural networks have shown promising results as a valuable tool for diabetes management and prevention. The study used machine learning methods to uncover associations between health status and the development of type 2 diabetes, aiming to accurately predict its onset or determine the individual's risk level.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2023)
Article
Computer Science, Information Systems
Zakaria Benomar, Francesco Longo, Giovanni Merlino, Antonio Puliafito
Summary: Networking is crucial in cloud computing deployments. Deep integration between the Cloud and IoT is only achievable at the IaaS level. Network virtualization is a key enabler of infrastructure-oriented IoT deployments.
ACM TRANSACTIONS ON INTERNET TECHNOLOGY
(2022)
Article
Computer Science, Information Systems
Sitender, Seema Bawa
Summary: This paper presents a machine translation system named SANSUNL, which can translate Sanskrit text into Universal Networking Language expressions. The system is extended with improvements in POS tagging, Sanskrit language processing, and parsing. The efficiency of the proposed system is evaluated using various metrics, and it is reported to be 95.375%.
MULTIMEDIA SYSTEMS
(2022)
Article
Computer Science, Hardware & Architecture
Xurui Liu, Guobao Zhang
Summary: Nowadays, miniature sensors can communicate with intelligent tools and pervasive computing devices to analyze and assess sports and physical activities. These sensors allow us to collect data from various physical activities using the underlying framework from anywhere, at any time, and in any location. Wearable devices with tiny sensors, edge and cloud computing, and artificial intelligence are the pillars that are capable of enhancing athletes' profiles and improving their training and performance.
MOBILE NETWORKS & APPLICATIONS
(2023)
Article
Chemistry, Physical
Adam Kulawik, Joanna Wrobel, Alexey Mikhailovich Ikonnikov
Summary: The paper aims to create a universal tool for analyzing austenite decomposition during the cooling process of various steel grades. It proposes the use of Recurrent Artificial Neural Networks of the Long Short-Term Memory type to analyze the transition path of the cooling curve, allowing for the determination of austenite transformation during continuous cooling. Using training data from a macroscopic model based on Continuous Cooling Transformation diagrams, the LSTM network can predict incremental changes of phase transformation with assumed changes of temperature.
Article
Computer Science, Information Systems
Vingi Patrick Nzanzu, Emmanuel Adetiba, Joke A. Badejo, Mbasa Joaquim Molo, Matthew Boladele Akanle, Kalimumbalo Daniella Mughole, Victor Akande, Oluwadamilola Oshin, Victoria Oguntosin, Claude Takenga, Maissa Mbaye, Dame Diongue, Ezekiel F. Adebiyi
Summary: Resource management is crucial for quality of service in cloud infrastructure. Monitoring is an important aspect of resource management, providing real-time information on the status and availability of physical resources and services. However, managing resources securely and efficiently in a federated cloud environment, where multiple tenants with diverse monitoring requirements share the cloud, is challenging. To address this, the FEDARGOS-V1 architecture is proposed, offering fast identification of resource constraints in federated cloud platforms. The architecture was evaluated and compared to existing systems in a real-time OpenStack-based FEDGEN cloud testbed.