Hindawi

Wireless Communications and Mobile Computing

Editorial
Artificial Intelligence of Things (AIoT) Technologies
and Applications

Tien-Wen Sung ,1 Pei-Wei Tsai ,2 Tarek Gaber ,3 and Chao-Yang Lee 4

1
Fujian Provincial Key Laboratory of Big Data Mining and Applications, Fujian University of Technology, Fuzhou, China
2
Department of Computer Science and Software Engineering, Swinburne University of Technology, Hawthorn, Australia
3
School of Science, Engineering & Environment, University of Salford, Manchester, UK
4
Department of Aeronautical Engineering, National Formosa University, Yunlin, Taiwan

Correspondence should be addressed to Tien-Wen Sung; tienwen.sung@gmail.com

Received 19 July 2021; Accepted 19 July 2021; Published 15 August 2021

Copyright © 2021 Tien-Wen Sung et al. This is an open access article distributed under the Creative Commons Attribution License,
which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

AIoT (Artificial Intelligence of Things) is a relatively new authors propose an ontology-based approach to deal with the
term that has recently become a hot topic that combines semantic meaning matching problem and propose a compact
two of the hottest acronyms, AI (Artificial Intelligence) and Particle Swarm Optimization (cPSO) algorithm to improve
IoT (Internet of Things). IoT consists of interconnected the quality of ontology alignment in different sensor ontologies.
things with built-in sensors and has the potential to generate The experiment results indicate that the proposed approach
or collect a vast amount of data. Individual IoT systems can statistically outperforms other state-of-the-art sensor ontology
be integrated into a large-scale system for various modern matching techniques.
applications. With that comes a lot of collected or real-time The paper titled “Quasiconformal Mapping Kernel
data, an intelligent and efficient data processing is essential Machine Learning-Based Intelligent Hyperspectral Data
to make effective use of the information generated from these Classification for Internet Information Retrieval” by J. Liu
data. The data can be analyzed and utilized with AI for and Y. Qiao focuses on the proposed intelligent data classifica-
problem-solving or decision-making. Without AI, IoT would tion algorithm based on machine learning. The approach of
have limited value. AI can multiply the value of IoT; con- quasiconformal kernel mapping learning with Mahalanobis
versely, IoT can promote the learning and intelligence of distance kernel functions is presented with a clear framework.
AI. However, there are many challenges while deploying The algorithm can be utilized for Internet-based hyperspectral
AIoT in practice. For instance, machine learning is one of data retrieval, which is important for many AIoT applications
the key technologies to be utilized in AIoT systems. Besides, such as image and video-based ones. In the experiments, it
there are many other issues such as complexity, efficiency, achieves advantages on large training sample construction
scalability, accuracy, and robustness related to the increasing and is effective to image data classification.
modern AIoT systems and applications. The paper titled “Flower End-to-End Detection Based on
This Special Issue is aimed at publishing original and YOLOv4 Using a Mobile Device” by Z. Cheng and F. Zhang
innovative research works that focus on challenging issues in proposes a flower detection approach for smart garden appli-
the field of AIoT technology and applications. After the review cations. The method of anchor-based end-to-end deep con-
process for evaluating all submitted manuscripts, there are volutional neural network with YOLO is presented. With
nine papers accepted for publication in this special issue. the designed architecture of the flower detection system, the
The paper titled “Semantic Integration of Sensor Knowl- proposed method performs an improved detection speed
edge on Artificial Internet of Things” by Y. Huang et al. while the accuracy is similar to that of the other methods.
describes the problem of data meaning matching in coopera- The paper titled “A Node Location Method in Wireless
tions among heterogeneous sensor-based AIoT systems. The Sensor Networks Based on a Hybrid Optimization Algorithm”
2 Wireless Communications and Mobile Computing

by J.-S. Pan et al. deals with the sensor node positioning prob- achieved by several ultrasonic sensors and a fuzzy-based
lem and proposes a new algorithm named WOA-QT that com- obstacle detection method. The proposed method can effec-
bines the Whale Optimization Algorithm (WOA) with QUasi- tively improve the anomaly detection of sensors when facing
Affine Transformation Evolutionary (QUATRE) algorithm. extreme conditions. It has low computational complexity and
The algorithm optimizes the received signal strength indication can facilitate real-time operation in the system. The experi-
(RSSI) ranging and weighted centroid positioning (WCL) for ment was performed in a real indoor environment, and an
improving the positioning accuracy. In the paper, 30 bench- outstanding result was achieved.
mark functions were used to evaluate the performance. The
proposed method achieves a satisfactory positioning accuracy. Tien-Wen Sung
The paper titled “URDNet: A Unified Regression Network Pei-Wei Tsai
for GGO Detection in Lung CT Images” by W. Liu et al. Tarek Gaber
describes the topic of ground-glass opacity (GGO) nodule Chao-Yang Lee
detection in images for medical IoT systems. The authors pro-
pose an end-to-end deep convolutional neural network with a Conflicts of Interest
multi-input and multioutput structure. A two-stage training
method is used, which includes the network backbone training The guest editors declare that they have no conflicts of inter-
and URDNet fine-tuning with pretrained weights. The LIDC- est regarding the publication of this special issue.
IDRI dataset is used to evaluate the performance, and the pro-
posed method achieves a sensitivity of 90.8%. The approach
could offer a useful tool in medical applications.
The paper titled “High-Dimensional Text Clustering by
Dimensionality Reduction and Improved Density Peak” by
Y. Sun and J. Platoš focuses on the intelligent text-based data
clustering technique. The authors propose a Stacked Random
Projection (SRP) method to reduce the dimensionality of
high-dimensional text data. An enhanced algorithm named
DPC-K-means based on density peak clustering algorithm
is also proposed. Seven text datasets, including BBC News
and Amazon product reviews, were used to validate the pro-
posed approach. The experiment results indicate the method
is superior to other compared algorithms.
The paper titled “Applying Robust Intelligent Algorithm
and Internet of Things to Global Maximum Power Point
Tracking of Solar Photovoltaic Systems” by E.-C. Chang pro-
poses an IoT-based model and control approach to monitor
solar photovoltaic (PV) systems and ensure maximum power
point tracking. A neural network based on quantum particle
swarm optimization (QPSO) and radial basis function (RBF)
is proposed. It is used to find the maximum power of the
photovoltaic array and maintain the highest PV energy
conversion efficiency. The mathematical analysis and simula-
tions show the achievement of tracking accuracy and robust
adaptation.
The paper titled “Developing Deep Survival Model for
Remaining Useful Life Estimation Based on Convolutional
and Long Short-Term Memory Neural Networks” by C.-H.
Chu et al. focuses on the remaining useful life estimation
and failure probability of machines for smart manufacturing.
The authors propose an integrated deep learning approach
with the convolutional neural network (CNN) and long
short-term memory (LSTM) network to deal with the prob-
lem. The dataset provided by NASA is utilized to evaluate
the performance. The results indicate that the proposed model
can capture the degradation trend of a fault under complex
conditions and avoid failure with the early prediction.
The paper titled “Fuzzy Obstacle Avoidance for the
Mobile System of Service Robots” by S.-P. Tseng et al. designs
and implements a service robot featured by obstacle avoid-
ance and target user tracking. The obstacle avoidance is