Mobile QR Code QR CODE

[IEIE SPC] Call for Special Topic

Next-Generation Wireless Systems and the future Internet of Things (IoT)

Wireless communications and Internet of Things (IoT) devices have enabled machine-to-machine communications in a dynamic and heterogeneous environment, as well as low-latency computing and storage resources. Research and development have been conducted on enabling technologies of next-generation wireless systems to support various imperative and tailored services in domains such as industrial applications, the environment, transportation, education, public health and safety, and defense.

The ultimate objective of the Internet of Things is to introduce plug-and-play technology that offers users convenience, flexibility, and remote access control. Using these technological advancements, wireless networks can provide exceptional capacity, infinite interconnectivity, and ultra-low latency communications. In light of these novel ideas, the Internet of Things will transform society by allowing seamless connectivity with next-generation wireless technologies.

To address the technical issues for the Internet of Things and next-generation wireless networks, we are happy to present this special issue to bring together researchers, industry practitioners, and those working in relevant fields.

Topics of interest in this special issue include, but are not limited to:

  • Communication protocols for wireless technology in IoT systems
  • Applications and deep learning model optimization for intelligent edge
  • AIoT (artificial intelligence IoT) for energy management systems in microgrids
  • Distributed communication protocol in wireless sensor network based on IoT
  • Smart environment using 5G wireless communication and the internet of things
  • Financial big data based on IoTs and wireless network communication
  • Emergency data communication in the internet of medical things
  • Machine learning-assisted technique for virtualized IoT devices

The tentative schedule:

  • Manuscript Submission Deadline: June 30, 2023
  • First Revision Notification Date: July 31, 2023 ~
  • Final Decision Notification Date: September 30, 2023 ~
  • Publication Date: October 31, 2023 ~ Dec 31, 2023

Note that some papers could be published after Dec. 2023 because some revisions could be required for a final publication.

※ Your manuscript must include a note indicating that it is for the special topic when you submit it.

Please refer to the following link for more information of IEIE SPC.:

IEIE Transactions on Smart Processing and Computing Editorial Board
Tel. (82-2)553-0255(Ext.4) / Fax. (82-2)552-6093 / E-mail.


BALLORG: State-of-the-art Image Restoration using Block-augmented Lagrangian and Low-rank Gradients

(Laya Tojo) ; (Manju Devi) ; (Vivek Maik) ; (Gurushankar)

In this paper, we propose a blind image deblurring algorithm using block-augmented Lagrangian and low-rank priors (BALLORG) as a non-learning method that can give better results without the complexity of learning-based methods. The proposed algorithm achieves faster convergence within 20 iterations than conventional methods. Regularization priors are used in the form of gradients and sparse low-rank matrices, and recursive rank improvements result in better deblurring performance. The steepest descent in minimization is maintained through weight selection for penalty and regularization parameters. The block processing introduces local and global optimization, leading to better visual quality outputs. The proposed method has excellent performance in terms of the PSNR, SSIM, and FSIM matrix, which is on par with or better than that of other state-of-the-art learning and non-learning-based approaches.

SEIF: A Semantic-enabled IoT Service Framework for Realizing Interoperable Data and Knowledge Retrieval

(Jieun Lee) ; (Komal Gilani) ; (Nargis Khatoon) ; (SeungMyeong Jeong) ; (JaeSeung Song)

The Internet of Things (IoT) has enabled interconnection of embedded computing devices comprised of their own data models in existing infrastructure. Currently, many IoT platforms provide data modeling and information retrieval services. However, the use of various data models and standards causes interoperability issues. Semantic technologies ease such barriers by providing the means to annotate semantic information as IoT data based on common data models. For this reason, semantics is becoming a growing requirement and a major challenge for IoT service layer platforms. The addition of semantic support empowers IoT systems with enhanced meaning in the data gathered from various devices and vertical silos. This paper presents a semantic IoT framework that includes agile support for adding semantic meaning to data, and for knowledge discovery, semantic validation, and accessibility to IoT data through a standardized semantic query language. The proposed evaluation matrix for a possible enhancement-anddevelopment guideline based on a global IoT standard is measured through smart office use cases comprising different sensor information. This paper provides a detailed description of semantic enablement on IoT platforms, including details of its implementation. The results provide a clear guideline for integrating semantic features into the IoT service layer and for data management.

Mathematical Model for Predicting the Appropriate Angle in Target Tracking System

(Ahmed J. Mohammed) ; (Ali A. D. Al-Zuky) ; (Fatin E. M. Al-Obaidi)

Arduino, Servo motor, Image scale, Cascade object detecThe accuracy of object detection, response time, and obstacles are considered the main problems in object detection and tracking system. The latter system plays the main role in various applications, such as human-computer interface, vision-based control, security, animation, and robot vision. The present work aims to calibrate for the MG995 servo motor model to present a mathematical model for predicting the appropriate angle in the target tracking system. The results showed high accuracy in measuring the specified angle with a value equal to zero for average and standard deviation errors. In contrast, reverse relationships resulted in image scale?distance and horizontal orientation angle relationships, respectively.or, MSER

Sleep Stage Classification using Deep Learning Techniques: A Review

(Jiyong Park) ; (Jaewon An) ; (Sang Ho Choi)

Sleep is an essential time for body recovery and healthy living. Therefore, sleep monitoring for health management is important. The gold-standard method for evaluating sleep is polysomnography (PSG), and physicians score the sleep stages using night PSG recording data. However, scoring sleep stages requires considerable time and labor. Hence, more accessible and efficient sleep-scoring methods are required. Because sleep stage information provides significant information for healthcare, studies of automatic sleep scoring have been conducted to overcome the limitations of PSG. This study reviews the progress and challenges of single- and multi-biosignalbased deep learning approaches to classify the sleep stages. In addition, non-contact sensor-based methods are reviewed for long-term monitoring at home.

Optimized Distributive Arithmetic-based Hardware Accelerator for Dual Tree Complex Wavelet Transform Computation

(Computation Yashavanthakumar T. R.) ; (Sampathrao L. Pinjare) ; (Cyril Prasanna Raj P.)

Hardware architectures for fast computation of complex wavelet transforms for image processing require optimized design approaches. The Dual Tree Complex Wavelet Transform (DTCWT) is twice as complex as the Discrete Wavelet Transform (DWT) and was designed while considering the distributive arithmetic (DA) algorithm, which is customized for the design of a 10- tap filter architecture. Redundancy in the filter coefficients was considered in optimizing the DA partial products, reducing the area resources by 97.65%. The reduced architecture was modeled in Verilog HDL and implemented on a Xilinx FPGA. The operating frequency is 312 MHz, and the power dissipation is less than 1 W. The proposed model is suitable for high-speed computation of DTCWT sub-bands on an FPGA platform.

Discrete Cosine Transformed Images Are Easy to Recognize in Vision Transformers

(Jongho Lee) ; (Hyun Kim)

Deep learning models for image classification with adequate parameters show excellent classification performance because they can effectively extract the features of input images. On the other hand, there is a limit to the abilities of deep learning models to interpret images using only spatial information because an image is a signal with great spatial redundancy. Therefore, in this study, the discrete cosine transform was applied to an input image in units of an N×N block size to allow the deep learning model to employ both frequency and spatial information. The proposed method was implemented and verified by selecting a vision transformer using a 16×16 nonoverlapping patch as a baseline and training various datasets of Cifar-10, Cifar-100, and Tiny- ImageNet from the very beginning without pre-trained weights. The experimental results showed that the top-1 accuracy is improved by approximately 3-5% for every dataset with little increase in computational cost.

Image Recognition of Skeletal Action for Online Physical Education Class based on Convolutional Neural Network

(Yan Shi)

In recent years, due to the sudden outbreak of public health events, online teaching has become a mainstream teaching approach, and the number of teaching videos has increased rapidly. Therefore, extracting active image information from videos is of great importance in understanding video. This research proposes extracting image features from the spatiotemporal dimension based on deep learning, usinga spatiotemporal network for action recognition of skeletal action, and building a CSTGAT model based on a convolutional neural network. The experimental results show that the CSTGAT model has an accuracy of 98.47%, a precision rate of 97.43%, and a recall rate of 71.65% after being trained by the convolutional neural network. Furthermore, it only needs 217 iterations to achieve stable target convergence. After 100 tests, the F1 value of the CSTGAT model was 96.83%. In summary, the proposed model has high accuracy, a comprehensive query rate, and good model expressiveness. This model could provide a solution for intelligent longdistance interaction between a human and a machine and could be used in online teaching.

Classification using a Spiking Neural Network: A Review

(Yuntae Park) ; (Unang Sunarya) ; (Geunbo Yang) ; (Choongseop Lee) ; (Jaewoo Baek) ; (Suwhan Baek) ; (Cheolsoo Park)

In this paper, different types of spiking neural network (SNN) and the methods to teach them are addressed. The spiking neural network is especially designed in a biologically plausible way. Like other neural networks, SNNs trained with certain learning methods have been used for image processing, data mining, and classification, etc. Unlike other neural networks, the SNN uses one-bit spike information, and one of its main advantages is reducing energy consumption.

Tweets and PCR Test-based Analysis and Prediction of Social Response to a Future Pandemic. A Case Study

(Ghulam Musa Raza) ; (Byung-Seo Kim)

The COVID-19 pandemic has greatly affected our society badly. It has been a subject of discussion since 2019 due to the increased prevalence of social media and its extensive use, and it has been a source of tension, fear, and disappointment for people all over the world. In this research, we took data from COVID-19 tweets from 10 different regions from July 25, 2020, to August 29, 2020. Using the well-known word embedding technique count-vectorizer, we experimented with different machine learning classifiers on data to train deep neural networks to improve the accuracy of predicted opinions with a low elapsed time. In addition, we collected PCR results from these regions for the same time interval. We compared the opinions in the form of positive or negative responses with the results of the PCR tests per million people. With the help of the results, We figured out a real-time international measure to detect these regions’ behaviors for any future pandemic. If we know how a region thinks about an upcoming pandemic, then we can predict the region’s real-time behavior for the particular pandemic. This would happen if we had past case studies to compare, like in our proposed research.

Speed Control of an Interior Permanent Magnet Synchronous Motor using a Disturbance Observer

(Yongho Jeon) ; (Shinwon Lee)

For precise speed control of an interior permanent magnet synchronous motor (IPMSM), information on load is required. Therefore, in the mechanical system of the motor, the load acting on the rotating shaft was considered as a disturbance, and in the electrical system, a disturbance observer was designed by considering the nonlinear terms as disturbance. The disturbance estimated from the designed observer is reflected in the speed controller and the current controller, respectively. As a result of operating the motor with a constant load of 1 [Nm], it can be confirmed that the undershoot that occurs when a load is applied is improved by about 13.2 [%].