Review
Chemistry, Analytical
Pandiaraj Manickam, Siva Ananth Mariappan, Sindhu Monica Murugesan, Shekhar Hansda, Ajeet Kaushik, Ravikumar Shinde, S. P. Thipperudraswamy
Summary: Artificial intelligence (AI) is a modern approach in computer science that develops intelligent and efficient devices through programs and algorithms. The Internet of Medical Things (IoMT) combines network-linked biomedical devices and software applications as a next-generation bio-analytical tool. This review discusses the importance of AI in enhancing the capabilities of IoMT and point-of-care devices in healthcare, as well as its role and challenges in advanced biomedical applications.
Article
Chemistry, Analytical
Assia El Mahdaoui, Abdeldjalil Ouahabi, Mohamed Said Moulay
Summary: This paper presents a compressed sensing reconstruction method called DCSR, which combines total variation regularization and non-local self-similarity constraint. Compared to other methods, DCSR achieves significant improvements in denoising efficiency and visual quality.
Article
Automation & Control Systems
Mudasir Ahmed Memon, Marif Daula Siddique, Saad Mekhilef, Marizan Mubin
Summary: This article proposes a hybrid asynchronous particle swarm optimization-genetic algorithm (APSO-GA) for the removal of unwanted lower order harmonics in the cascaded H-bridge multilevel inverter. The APSO-GA combines the exploration capability of APSO with the exploitation capability of GA, and is capable of easily finding feasible solutions with low computational complexity.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2022)
Article
Acoustics
Xiaonan Liu, Shunda Qiao, Guowei Han, Jinxing Liang, Yufei Ma
Summary: A highly sensitive hydrogen fluoride (HF) sensor based on light-induced thermoelastic spectroscopy (LITES) technique is reported in this study. The sensor utilizes a simple structure and a robust shallow neural network (SNN) fitting algorithm for denoising the spectroscopy data. The system stability is demonstrated through Allan variance analysis and a low minimum detection limit (MDL) is achieved.
Article
Automation & Control Systems
Daming Wang, Zheng John Shen, Xin Yin, Sai Tang, Xifei Liu, Chao Zhang, Jun Wang, Jose Rodriguez, Margarita Norambuena
Summary: In this article, a new approach called ANN-MPC is proposed as a solution to the increasing complexity and demand of computing resources in power electronic applications. The approach uses an artificial neural network to train an MPC controller and eliminates the need for heavy mathematical computation. Simulation and experimental results demonstrate that the FPGA-based ANN-MPC controller can significantly reduce the resource requirement while offering the same control performance as conventional MPC.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2022)
Review
Chemistry, Analytical
Ramraj Dangi, Praveen Lalwani, Gaurav Choudhary, Ilsun You, Giovanni Pau
Summary: This paper presents the characteristics and advantages of 5G technology as the latest generation of mobile networks, highlighting how businesses can utilize the opportunities brought by 5G.
Article
Chemistry, Analytical
Zexuan Guo, Chensheng Wang, Guang Yang, Zeyuan Huang, Guo Li
Summary: With the development of artificial intelligence technology and the popularity of intelligent production projects, intelligent inspection systems have become a hot topic in the industrial field. This paper introduces the improved MSFT-YOLO model for object detection in the industry, which addresses challenges such as background interference and scale changes. The model achieves real-time detection and shows higher detection accuracy compared to baseline models, offering advantages and improvements.
Article
Automation & Control Systems
Qi Li, Xiang Meng, Fei Gao, Guorui Zhang, Weirong Chen
Summary: Energy management strategy (EMS) plays a crucial role in fuel cell/battery hybrid systems. This paper introduces a TCO model that considers energy consumption, equivalent energy consumption, and power source degradation, and proposes an optimal EMS using Double Q-learning RL algorithm. Through experiments, it is demonstrated that the proposed strategy exhibits high global optimality and excellent SOC control ability under different operating conditions.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2022)
Article
Chemistry, Analytical
Xiaonan Liu, Yufei Ma
Summary: This paper demonstrates a temperature measurement method based on the tunable diode laser absorption spectroscopy (TDLAS) technique using a single diode laser. The TDLAS system showed advantages such as immunity to laser wavelength shift, simple system structure, reduced cost, and increased system robustness. The system was tested on a McKenna flat flame burner and a scramjet model engine, and exhibited excellent dynamic range and fast response.
Review
Chemistry, Analytical
Haftay Gebreslasie Abreha, Mohammad Hayajneh, Mohamed Adel Serhani
Summary: Edge Computing is a new architecture that extends Cloud Computing services closer to data sources. When combined with Deep Learning, it becomes a promising technology widely used in various applications. However, the traditional DL architectures with EC enabled often face practical challenges due to high bandwidth requirements, legal issues, and privacy vulnerabilities. Federated Learning has emerged as a potential solution to address these challenges by enabling collaborative learning and model optimization while ensuring data localization. This paper provides a systematic survey of the implementation of Federated Learning in Edge Computing environments, including protocols, architectures, frameworks, and hardware requirements. It also discusses applications, challenges, related solutions, and presents case studies and potential directions for future research.
Review
Engineering, Multidisciplinary
Zheng Yang, Binbin Xu, Wei Luo, Fei Chen
Summary: With the increase in size and complexity of mechanical equipment, traditional intelligent fault diagnosis based on shallow machine learning methods is insufficient for coupling faults. The development of deep learning, particularly the use of Autoencoder-based representation learning, has provided new opportunities for intelligent fault diagnosis. This article introduces the theoretical foundations and training methods of multi-type Autoencoders and reviews the advancements in their applications, aiming to improve representation learning. Two case studies are presented to demonstrate the application of Autoencoder-based methods on ideal and complex engineering systems. The challenges and prospects of Autoencoder-based representation learning are also discussed, offering guidance for future research directions.
Article
Automation & Control Systems
Yihao Qin, Yayun Yan, Hongquan Ji, Youqing Wang
Summary: This article proposes a new method combining correlative statistical analysis and the sliding window technique for detecting incipient faults. By utilizing information from process and quality variables, this method improves computational burden and algorithm complexity, and its effectiveness and advantages are demonstrated through a numerical example and application in thermal power plant process.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2022)
Article
Engineering, Multidisciplinary
Murat Koklu, M. Fahri Unlersen, Ilker Ali Ozkan, M. Fatih Aslan, Kadir Sabanci
Summary: This study uses deep learning-based classification to classify images of grapevine leaves. By extracting features and using SVM kernels for classification, a classification success rate of 97.60% is achieved.
Article
Automation & Control Systems
Chao Deng, Fanghong Guo, Changyun Wen, Dong Yue, Yu Wang
Summary: This article proposes a cooperative resilient control method for dc microgrid to mitigate the adverse effects of communication delays and DoS attacks. By introducing a new time-varying sampling period and an improved communication mechanism, a resilient secondary controller is designed. The developed method is theoretically shown to achieve bus voltage restoration and current sharing even in the presence of communication delays and DoS attacks.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2022)
Article
Construction & Building Technology
Liyuan Cao, Chunxiang Li
Summary: This paper introduces a novel high performance hybrid passive base-isolated system BIS+TTMDI, which achieves optimal control performance through parameter optimization and evaluations under different inertia and isolation characteristics. Results demonstrate the system's effectiveness in reducing displacement and acceleration, energy dissipation, stiffness and damping evolution.
STRUCTURAL CONTROL & HEALTH MONITORING
(2022)
Article
Engineering, Electrical & Electronic
Yudong Zhang, Suresh Chandra Satapathy, Li-Yao Zhu, Juan Manuel Gorriz, Shuihua Wang
Summary: This study proposed a novel seven layer convolutional neural network based smart diagnosis model for COVID-19 diagnosis in chest CT images. The experimental results show that the proposed model achieves a sensitivity of 94.44 +/- 0.73, a specificity of 93.63 +/- 1.60, and an accuracy of 94.03 +/- 0.80. Data augmentation and stochastic pooling methods are proven to be effective.
IEEE SENSORS JOURNAL
(2022)
Article
Chemistry, Analytical
Zhen Yuan, Qiuni Zhao, Chunyan Xie, Junge Liang, Xiaohui Duan, Zaihua Duan, Shaorong Li, Yadong Jiang, Huiling Tai
Summary: In this study, gold-loaded tellurium nanobelts were synthesized through a hydrothermal process, and the resulting Au@Te sensor demonstrated rapid response, high sensitivity, good repeatability, and selectivity for the detection of NO2. The long-term stability of the sensor was also evaluated, with stable response observed over a period of 28 days.
SENSORS AND ACTUATORS B-CHEMICAL
(2022)
Article
Engineering, Multidisciplinary
Anil Kumar, C. P. Gandhi, Govind Vashishtha, Pradeep Kundu, Hesheng Tang, Adam Glowacz, Rajendra Kumar Shukla, Jiawei Xiang
Summary: This paper presents a method for early identification of rolling element defects using variational mode decomposition (VMD) and trigonometric entropy measure. The experimental results show that the proposed method is capable of raising the alarm about the initiation of defects at a very early stage and outperforms existing indicators in defect degradation monitoring.
MEASUREMENT SCIENCE AND TECHNOLOGY
(2022)
Article
Automation & Control Systems
Qiankang Hou, Shihong Ding, Xinghuo Yu, Keqi Mei
Summary: A new STLF controller is proposed in this article to improve the control performance for SPMSM system by replacing the discontinuous switching function with a nonsmooth term, providing stronger anti-disturbance capability and achieving desired control performance through parameter adjustments. Comparative experiments demonstrate the feasibility and effectiveness of the proposed STLF technique when compared with conventional controllers.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2022)
Article
Chemistry, Analytical
Runing Lai, Pengcheng Shi, Zao Yi, Hailiang Li, Yougen Yi
Summary: This paper introduces a novel metamaterial absorber based on surface plasmon resonance (SPR) that has triple-mode perfect absorption, polarization independence, incident angle insensitivity, tunability, high sensitivity, and a high figure of merit (FOM). The structure of the absorber consists of a graphene array, SiO2 layer, and a gold mirror. The absorber achieves perfect absorption at frequencies of 4.04 THz, 6.76 THz, and 9.40 THz, with absorption peaks of 99.404%, 99.353%, and 99.146%, respectively. It also demonstrates maximum sensitivities in refractive index sensing and has potential applications in photodetectors, optoelectronic devices, and chemical sensors.