Supply Chain Management Using an Industrial Internet of Things Hyperledger Fabric Network

Rehan Muhammad,Javed Abdul Rehman,Kryvinska Natalia,Gadekallu Thippa Reddy,Srivastava Gautam,Jalil Zunera 한국컴퓨터산업협회 2023 Human-centric Computing and Information Sciences Vol.13 No.-

Supply chain management (SCM) plays a pivotal role in the industrial life cycle. On-time delivery is necessary for a successful SCM system. To maintain a safe and secure supply of products, mode of transportation and management is equally important. The Industrial Internet of Things (IIoT) eases tracking and tracing of supplies using sensor devices and 5G during the supply chain process. Cold chain and ecologically sensitive products such as vaccines, medical supplies, and food items require a specific temperature to maintain the supplies’ genuineness and actuality. A blockchain-based platform (Ethereum) is being used for SCM nowadays. However, it has certain limitations, such as low transaction speed, the requirement for more computation power, and vulnerability to cyberattacks. This research proposes a solution to these problems using a novel approach, named SCMIIOT (supply chain management using industrial Internet of Things). The proposed approach maintains traceability, security, data integrity, transparency, and achieves fast transaction speed. The distributed database system is used to store and transfer transaction ledgers for SCM. In this research, IBM Watson IoT is used as an Internet of Things (IoT) device for input temperature, and the Kubernetes cluster is used as a platform for deploying Hyperledger Fabric. Docker Hub and Hyperledger composer playground provide business network connection for importers, suppliers, retailers, manufacturers, and consumers/end-users. We also demonstrate the working and effectiveness of SCMIIOT through experiments. Results show that SCMIIOT takes only 1 minute to copy local files to storage on the cloud and takes 1 minute to create a genesis block. Similarly, it takes 1 minute for a peer-to-peer connection. Also, the worst-case time complexity of SCMIIOT transaction speed is recorded as 48 seconds on the Watson IoT platform.

Quantum-Enhanced Machine Learning Algorithms for Heart Disease Prediction

Alotaibi Saud S.,Mengash Hanan Abdullah,Dhahbi Sami,Alazwari Sana,Marzouk Radwa,Alkhonaini Mimouna Abdullah,Mohamed Abdullah,Hilal Anwer Mustafa 한국컴퓨터산업협회 2023 Human-centric Computing and Information Sciences Vol.13 No.-

Heart disease has grown more prominent among various age groups. Early prediction of heart failure and treating them with the most care can the human life. Today healthcare system depends on a computer-aided diagnosis system. Quantum improved machine learning approaches are a critical factor, play a significant role in healthcare systems due to their robust nature, and build novel medical traits, patient data, and management of patients’ record and chronic disease detection, etc. Traditional machine learning approaches effectively predict heart disease but still lack efficiency due to noise and appropriate feature size. This informs the researchers to use quantum improved ML that will provide the accurate prediction of chronic diseases in a granular way. Applying these merits of quantum computing, healthcare systems are implementing quantum-based machine learning (QML) approaches for predicting heart disease. This paper proposes a quantum ML with quantum particle swarm optimization (QPSO) to predict heart disease and compare it with the traditional ML approach called multilayer perceptron (MLP) using the evaluation metrics. It uses exploratory preprocessing to normalize the input heart disease data. The number of qubits is the number of features in the dataset. The efficiency of the quantum-ML approaches is evaluated using publicly available heart disease dataset. The proposed QML with QPSO secured an improved accuracy of 96.7%, a false detection rate of 0.09, and a computation time is 135ms. However, the comparison results prove that QML with QPSO confirmed satisfactory results in predicting heart disease with improved accuracy.

Posture Estimation & Posture Sequence Recognition for Martial Artists

Wang Ying,Liu Ping,Feng Jinrui,Wang Lijun 한국컴퓨터산업협회 2023 Human-centric Computing and Information Sciences Vol.13 No.-

Human body pose estimation is a technology for locating the key points of the human body, and has played an important role in many industries and sports. To date, the method of using this technology to locate the key points of the human body is mainly using a regression heat map. There is no good way to make full use of the structural characteristics of the human body and relationship between key points. Faced with the above difficulties, this article solves the problem by studying the posture estimation and posture sequence of martial artists under the grid convolutional coding neural network. Firstly, use the grid to divide the image to roughly locate the key points of the human body, and then accurately locate the key points of the human body from the offset position output by the grid. This positioning method makes the size of the heat map larger than the grid size so as to achieve high precision positioning and cut down the computation of a convolutional neural network. Under the multi-person scenario in actual martial arts sports, we put forward a multi-person posture estimation algorithm which uses the connection between key points of the human body.

Fuzzy Decision Based Energy-Evolutionary System for Sustainable Transport in Ubiquitous Fog Network

Lakhan Abdullah,Mohammed Mazin Abed,Abdulkareem Karrar Hameed,Jaber Mustafa Musa,Kadry Seifedine,Nedoma Jan,Martinek Radek 한국컴퓨터산업협회 2023 Human-centric Computing and Information Sciences Vol.13 No.-

These days, the usage of sustainable transport applications has been growing in practice and has minimized global environmental issues as fuel vehicles did. Sustainable transport applications are distributed and can access data from anywhere in the network. However, due to sustainable electrical transport, much digital data is offloaded to the server to obtain the electricity stations. Therefore, many factors challenge sustainable vehicle applications, such as battery power consumption, service searching cost, execution delay, and execution accuracy. Thus, the existing decision support methods, such as TOPSIS multi-criteria decision method (MCDM), only support the fixed and accurate. Therefore, the fuzzy-based strategy will be more optimal for sustainable transport. The study devises the fuzzy-based energy-efficient decision support system (FBEES), which minimizes energy consumption, delay, and cost and increases scheduling accuracy for sustainable applications. These vehicles are connecting to the ubiquitous fog servers at different data centers in the system and offload their data for their processing. Simulation results show that FBEES minimizes energy by 30%, cost by 29%, delay by 31%, and improves accuracy compared to existing methods for sustainable transport applications.

Hands-Free Presentation Tool with Co-speech Gesture Interactions: A Wizard-of-Oz Study

Shin Ki-Young,Lee Jong-Hyeok,Park Kyudong 한국컴퓨터산업협회 2023 Human-centric Computing and Information Sciences Vol.13 No.-

Despite active research on the design of presentation tools after the emergence of slideshow presentations, there is a lack of research findings on appropriate modalities of interactions for controlling slides in an exploratory manner. The objective of this study is to find the appropriate modality for features of controlling slides and to design usable features. This study used an iterative design process based on the Wizard-of-Oz (WoZ) prototype and participatory design (PD), which was divided into three phases. In the first phase, the participants were directly involved in the ideation process, and they created an initial design set. In the second phase, the initial prototype was evaluated by the participants with WoZ, focusing on the scope of co-speech gesture interactions. Finally, the usability of the final design set was evaluated, and it was demonstrated that the proposed design features were usable in terms of naturalness, controllability, efficiency of information delivery, and efficiency of resource use. The results also showed that verbal modality was more dominant, while many previous studies focused on creating gesture-based systems. This research is expected to provide guidance for designing a hand-free presentation with a co-speech gesture, and benefits for conducting PD research with WoZ.

Fast Visual Tracking with Squeeze and Excitation Region Proposal Network

Cao Dun,Dai Renhua,Wang Jin,Ji Baofeng,Alfarraj Osama,Tolba Amr,Sharma Pradip Kumar,Zhu Min 한국컴퓨터산업협회 2023 Human-centric Computing and Information Sciences Vol.13 No.-

Siamese trackers have achieved significant progress over the past few years. However, the existing methods are either high speed or high performance, and it is difficult for previous Siamese trackers to balance both. In this work, we propose a high-performance yet effective tracker (SiamSERPN), which utilizes MobileNetV2 as the backbone and equips with the proposed squeeze and excitation region proposal network (SERPN). For the SERPN block, we introduce the distance-IoU (DIoU) into the classification and regression branches to remedy the weakness of traditional RPN. Benefiting from the structure of MobileNetV2, we propose a feature aggregation architecture of multi-SERPN blocks to improve performance further. Extensive experiments and comparisons on visual tracking benchmarks, including VOT2016, VOT2018, and GOT-10k, demonstrate that our SiamSERPN can balance speed and performance. Especially on GOT-10k benchmark, our tracker scores 0.604 while running at 75 frames per second (FPS), which is nearly 27 times that of the state-of-the-art tracker.

HQK-FL: Hybrid-Quantum-Key-Based Secure Federated Learning for Distributed Multi-Center Clinical Studies

Park Hyunwoo,Lee Jaedong 한국컴퓨터산업협회 2023 Human-centric Computing and Information Sciences Vol.13 No.-

Federated learning is a decentralized structure for distributed multi-center clinical data research, which is more secure than centralized structures because personal information is not directly shared. However, there are residual threats to information security, such as eavesdropping, training server hacking, and adversarial attacks. This paper presents a hybrid-quantum-key-based secure federated learning (HQK-FL) for distributed multi-center clinical studies. The proposed method is a new approach based on hybrid quantum keys that provides robust security for distributed multi-center disease diagnosis research. We objectively evaluated the effectiveness of the proposed method by experimenting with different models and datasets for predicting coronavirus disease 2019 (COVID-19) and pneumonia using chest X-ray images and predicting sepsis using the Medical Information Mart for Intensive Care (MIMIC-III) dataset, which is a widely used database in medical research. Federated learning showed promising results in improving the accuracy of predicting COVID, pneumonia, and sepsis, and it outperformed the single-center approach. It achieved an average area under the precision–recall curve of 0.791 for COVID, which is 3.7% better than the single-center results. For pneumonia and sepsis, it reached 0.710 and 0.748, which indicates improvements of 6.3% and 3.2%, respectively. We compared and analyzed the resource usage and computational time of HQK-FL through various experiments. HQK-FL can enhance the security of federated learning while maintaining its predictive performance. It can increase the memory usage by up to 4% and slightly increases the computational time. The comparison result showed no significant difference in memory usage and slight differences in the transmission and computational time between the client and server.

Digital Twin-Based Cyberthreat Defense Solution for Smart City Environment

Park Young Sun,Ryou Jae-Cheol 한국컴퓨터산업협회 2023 Human-centric Computing and Information Sciences Vol.13 No.-

The concept of digital twin (DT) has garnered considerable attention from researchers as it promises to revolutionize modern industries with recent advancements in information and communication technology. DT refers to a digital representation of a physical entity that reflects its behavior through real-time data management and bidirectional interaction. The power grid has seen reliable access to information with the deployment of the Internet of Things, which has equipped it with a powerful tool for real-time data management and analysis. This paper aims to propose practical ideas and trace the continuous investigation of DT technology for power systems, including transportation systems, smart grids, and microgrids. The challenges associated with the deployment of DT technology are also discussed. As cities continue to develop, multi-dimensional energy management systems face various challenges, such as real-time management, planning, and analysis of transportation systems and remote data transfer within power grids. These challenges can be addressed by implementing a real twin framework in each section. Additionally, this paper discusses the security of DT technology based on machine learning and provides a comprehensive view for readers to develop and deploy DT technology for various power system applications.

Crowd Counting via Attention and Multi-feature Fused Network

Gao Mingliang,Guo Xiangyu,Pan Jinfeng,Shang Jianrun,Souri Alireza,Li Qilei,Bruno Alessandro 한국컴퓨터산업협회 2023 Human-centric Computing and Information Sciences Vol.13 No.-

With the rapid development of Internet of Everything and artificial intelligence techniques and massive amounts of video surveillance data, crowd counting has drawn extensive attention in computer vision. Inspired by deep learning methods, convolutional neural networks (CNN) have been dedicated to improving the effectiveness of crowd counting. As CNN is unable to capture the continuous size changes of heads in images, the large-scale variations impede the development of crowd counting. To solve this problem, this paper presents an attention and multi-feature fused network (AMFNet) containing a multi-level feature extractor and four attentional density estimator (ADE) modules. The multi-level extractor is used to extract the features of different sizes and various kinds of context information based on a deep network backbone. The existing ADE modules are built to merge different level features to generate a high-quality density map. A channel attention unit is adopted in the ADE modules to identify the head accurately. Then, four ADE modules are applied to exploit multi-level features and generate a fine-grained density map for coping with various scales. The experiment results show that the proposed AMFNet performs well in dense crowd scenarios, and that it is comparable to mainstream methods in terms of accuracy and robustness.

CYBROG-Based Smart Home Security and Power-Saving Control System Using Hybrid Technique

Al-Otaibi Yasser 한국컴퓨터산업협회 2023 Human-centric Computing and Information Sciences Vol.13 No.-

The development of information technology coupled with an improved version of robot-based technology called "cyborgs" play a vital role in the modern lifestyle of an individual. The smart home control system should provide high security using wireless sensor devices. Such a control system should improve the intelligence level of the smart home system, and in this vein, many research works have been developed. However, the issues with these proposals are poorer efficiency and accuracy and more time and storage space being required. This paper presents the smart home security control system based on the hybrid techniques of support vector machine with artificial bee colony algorithm (SVM-ABC). The proposed work on SVM-ABC uses wireless sensor devices for perceiving the smart home environment, provides automatic controlling of common electronic appliances using control module for monitoring real-time data and an alert signal processor, movement of intruders and power saver. Implementing the smart home security system requires communication for transforming information in the periodic time intervals to the server. SVM-ABC monitors each part of the smart home and its appliances via a server to control modules, and optimizes the monitoring of security in the smart home. The accuracy rate of various techniques like SVM for detecting intruders in the smart home system reached 90.44%, With the use of a so-called cyborg or human-intervention robot with the ABC algorithm for power saving in the smart home appliances, the accuracy rate attained 92.28%, and k-nearest neighbor technique in the security-providing smart home system attained the accuracy rate of 89.02%, with the proposed work’s SVM-ABC at 94.56%.