Intelligent Automation & Soft Computing

About the Journal

Intelligent Automation & Soft Computing: An International Journal seeks to provide a common forum for the dissemination of accurate results about the world of artificial intelligence, intelligent automation, control, computer science, modeling and systems engineering. It is intended that the articles published in the journal will encompass both the short and the long term effects of soft computing and other related fields such as robotics, control, computer, cyber security, vision, speech recognition, pattern recognition, data mining, big data, data analytics, machine intelligence and deep learning. It further hopes it will address the existing and emerging relationships between automation, systems engineering, system of computer engineering and soft computing.

Indexing and Abstracting

SCIE: 2019 Impact Factor 1.276; Scopus CiteScore (Impact per Publication 2019): 2.0; SNIP (Source Normalized Impact per Paper 2019): 0.85; Essential Science Indicators(ESI), etc.

Previously published by TSI Press (http://www.wacong.org/autosoft/auto/), Intelligent Automation & Soft Computing starts to be published by Tech Science Press from the third issue of 2020 and supports Open Access Policy.

  • Short-term Forecasting of Air Passengers Based on the Hybrid Rough Set and the Double Exponential Smoothing Model
  • Abstract This article focuses on the use of the rough set theory in modeling of time series forecasting. In this paper, we have used the double exponential smoothing (DES) model for forecasting. The classical DES model has been improved by using the rough set technique. The improved double exponential smoothing (IDES) method can be used for the time series data without any statistical assumptions. The proposed method is applied on tourism demand of the air transportation passenger data set in Australia and the results are compared with the classical DES model. It has been observed that the forecasting accuracy of the… More
  •   Views:22       Downloads:19        Download PDF
  • PID Tuning Method Using Single-Valued Neutrosophic Cosine Measure and Genetic Algorithm
  • Abstract Because existing proportional-integral-derivative (PID) tuning method using similarity measures of single-valued neutrosophic sets (SVNSs) and an increasing step algorithm shows its complexity and inconvenience, this paper proposes a PID tuning method using a cosine similarity measure of SVNSs and genetic algorithm (GA) to improve the existing PID tuning method. In the tuning process, the step response characteristic values (rising time, settling time, overshoot ratio, undershoot ratio, peak time, and steady-state error) of the control system are converted into the single-valued neutrosophic set (SVNS) by the neutrosophic membership functions (Neutrosophication). Then the values of three appropriate parameters in a PID controller… More
  •   Views:19       Downloads:14        Download PDF
  • Dynamic Task Assignment for Multi-AUV Cooperative Hunting
  • Abstract For cooperative hunting by a multi-AUV (multiple autonomous underwater vehicles) team, not only basic problems such as path planning and collision avoidance should be considered but also task assignments in a dynamic way. In this paper, an integrated algorithm is proposed by combining the self-organizing map (SOM) neural network and the Glasius Bio-Inspired Neural Network (GBNN) approach to improve the efficiency of multi-AUV cooperative hunting. With this integrated algorithm, the SOM neural network is adopted for dynamic allocation, while the GBNN is employed for path planning. It deals with various situations for single/multiple target(s) hunting in underwater environments with obstacles.… More
  •   Views:14       Downloads:11        Download PDF
  • An Improved K-nearest Neighbor Algorithm Using Tree Structure and Pruning Technology
  • Abstract K-Nearest Neighbor algorithm (KNN) is a simple and mature classification method. However there are susceptible factors influencing the classification performance, such as k value determination, the overlarge search space, unbalanced and multi-class patterns, etc. To deal with the above problems, a new classification algorithm that absorbs tree structure, tree pruning and adaptive k value method was proposed. The proposed algorithm can overcome the shortcoming of KNN, improve the performance of multi-class and unbalanced classification, reduce the scale of dataset maintaining the comparable classification accuracy. The simulations are conducted and the proposed algorithm is compared with several existing algorithms. The results… More
  •   Views:13       Downloads:13        Download PDF
  • Formal Modelling of Real-Time Self-Adaptive Multi-Agent Systems
  • Abstract The paradigm of multi-agent systems is very expressive to model distributed real-time systems. These real-time multi-agent systems by their working nature have temporal constraints as they need to operate in pervasive, dynamic and unpredictable environments. To achieve better fault-tolerance, they need to have the ability of self-adaptivity making them adaptable to the failures. Presently there is a lack of vocabulary for the formal modelling of real-time multi-agent systems with self-adaptive ability. In this research we proposed a framework named SMARTS for the formal modelling of self-adaptive real-time multi-agent systems. Our framework integrates MAPE-K interfaces, reflection perspective and unification with distribution… More
  •   Views:9       Downloads:11        Download PDF
  • Simulation of Real‐Time Path Planning for Large‐Scale Transportation Network Using Parallel Computation
  • Abstract To guarantee both the efficiency and accuracy of the transportation system, the real-time status should be analyzed to provide a reasonable plan for the near future. This paper proposes a model for simulating the real-world transportation networks by representing the irregular road networks with static and dynamic attributes, and the vehicles as moving agents constrained by the road networks. The all pairs shortest paths (APSP) for the networks are calculated in a real-time manner, and the ever-changing paths can be used for navigating the moving vehicles with real-time positioning devices. In addition, parallel computation is used to accelerate the shortest… More
  •   Views:12       Downloads:10        Download PDF
  • A Distributed Heterogeneous Inspection System for High Performance Inline Surface Defect Detection
  • Abstract This paper presents the Distributed Heterogeneous Inspection System (DHIS), which comprises two CUDA workstations and is equipped with CPU distributed computing, CPU concurrent computing, and GPU concurrent computing functions. Thirty-two grayscale images, each with 5,000× 12,288 pixels and simulated defect patterns, were created to evaluate the performances of three system configurations: (1) DHIS; (2) two CUDA workstations with CPU distributed computing and GPU concurrent computing; (3) one CUDA workstation with GPU concurrent computing. Experimental results indicated that: (1) only DHIS can satisfy the time limit, and the average turnaround time of DHIS is 37.65% of the time limit; (2) a… More
  •   Views:11       Downloads:10        Download PDF
  • An Accelerated Convergent Particle Swarm Optimizer (ACPSO) of Multimodal Functions
  • Abstract Particle swarm optimization (PSO) algorithm is a global optimization technique that is used to find the optimal solution in multimodal problems. However, one of the limitation of PSO is its slow convergence rate along with a local trapping dilemma in complex multimodal problems. To address this issue, this paper provides an alternative technique known as ACPSO algorithm, which enables to adopt a new simplified velocity update rule to enhance the performance of PSO. As a result, the efficiency of convergence speed and solution accuracy can be maximized. The experimental results show that the ACPSO outperforms most of the compared PSO… More
  •   Views:12       Downloads:11        Download PDF
  • Surgical Outcome Prediction in Total Knee Arthroplasty Using Machine Learning
  • Abstract This work aimed to predict postoperative knee functions of a new patient prior to total knee arthroplasty (TKA) surgery using machine learning, because such prediction is essential for surgical planning and for patients to better understand the TKA outcome. However, the main difficulty is to determine the relationships among individual varieties of preoperative and postoperative knee kinematics. The problem was solved by constructing predictive models from the knee kinematics data of 35 osteoarthritis patients, operated by posterior stabilized implant, based on generalized linear regression (GLR) analysis. Two prediction methods (without and with principal component analysis followed by GLR) along with… More
  •   Views:10       Downloads:11        Download PDF
  • Cyber-security Risk Assessment Framework for Critical Infrastructures
  • Abstract A critical infrastructure provides essential services to a nation’s population. Interruptions in its smooth operations are highly undesirable because they will cause significant and devastating consequences on all stakeholders in the society. In order to provide sustained protection to a nation’s critical infrastructure, we must continually assess and evaluate the risks thereof. We propose a risk assessment framework that can evaluate the risks posed to the security of a critical infrastructure from threat agents, with a special emphasis on the smart grid communications infrastructure. The framework defines finegrained risk identification to help quantify and assess exploitable vulnerabilities within a critical… More
  •   Views:15       Downloads:12        Download PDF
  • The Design and Implementation of a Multidimensional and Hierarchical Web Anomaly Detection System
  • Abstract The traditional web anomaly detection systems face the challenges derived from the constantly evolving of the web malicious attacks, which therefore result in high false positive rate, poor adaptability, easy over-fitting, and high time complexity. Due to these limitations, we need a new anomaly detection system to satisfy the requirements of enterprise-level anomaly detection. There are lots of anomaly detection systems designed for different application domains. However, as for web anomaly detection, it has to describe the network accessing behaviours characters from as many dimensions as possible to improve the performance. In this paper we design and implement a Multidimensional… More
  •   Views:11       Downloads:14        Download PDF
  • Protecting Android Applications with Multiple DEX Files Against Static Reverse Engineering Attacks
  • Abstract The Android application package (APK) uses the DEX format as an executable file format. Since DEX files are in Java bytecode format, you can easily get Java source code using static reverse engineering tools. This feature makes it easy to steal Android applications. Tools such as ijiami, liapp, alibaba, etc. can be used to protect applications from static reverse engineering attacks. These tools typically save encrypted classes.dex in the APK file, and then decrypt and load dynamically when the application starts. However, these tools do not protect multidex Android applications. A multidex Android application is an APK that contains multiple… More
  •   Views:14       Downloads:12        Download PDF
  • Trust Provision in the Internet of Things Using Transversal Blockchain Networks
  • Abstract The Internet-of-Things (IoT) paradigm faces new and genuine challenges and problems associated, mainly, with the ubiquitous access to the Internet, the huge number of devices involved and the heterogeneity of the components making up this new global network. In this context, protecting these systems against cyberattacks and cybercrimes has turn into a basic issue. In relation to this topic, most proposed solutions in the literature are focused on security; however other aspects have to be considered (such as privacy or trust). Therefore, in this paper we define a theoretical framework for trust in IoT scenarios, including a mathematical formalization and… More
  •   Views:12       Downloads:11        Download PDF
  • A Novel Privacy‐Preserving Multi‐Attribute Reverse Auction Scheme with Bidder Anonymity Using Multi‐Server Homomorphic Computation
  • Abstract With the further development of Internet, the decision-making ability of the smart service is getting stronger and stronger, and the electronic auction is paid attention to as one of the ways of decision system. In this paper, a secure multi-attribute reverse auction protocol without the trusted third party is proposed. It uses the Paillier public key cryptosystem with homomorphism and combines with oblivious transfer and anonymization techniques. A single auction server easily collides with a bidder, in order to solve this problem, a single auction server is replaced with multiple auction servers. The proposed scheme uses multiple auction servers to… More
  •   Views:13       Downloads:12        Download PDF
  • Cracking of WPA & WPA2 Using GPUs and Rule‐based Method
  • Abstract Wi-Fi Protected Access (WPA) and Wi-Fi Protected Access II (WPA2) are two security protocols developed by the Wi-Fi Alliance to secure wireless computer networks. The prevailing usage of GPUs improves the brute force attacks and cryptanalysis on access points of the wireless networks. It is time-consuming for the cryptanalysis with the huge total combinations of 9563 max. Now, it is the turning point that the leap progress of GPUs makes the Wi-Fi cryptanalysis much more efficient than before. In this research, we proposed a rule-based password cracking scheme without dictionary files which improves the efficiency of cracking WPA/WPA2 protected access… More
  •   Views:13       Downloads:11        Download PDF
  • User Authentication System Based on Baseline‐corrected ECG for Biometrics
  • Abstract Recently, ECG-based user authentication technology, which is strong against forgery and falsification, has been actively studied compared to fingerprint and face authentication. It is impossible to measure the open ECG DB measured with expensive medical equipment in daily living, and the ECG measured with the developed device for easy ECG measurement has much noise. In this paper, we developed a device that easily measures the ECG for user authentication in everyday life, measured the ECG through the development equipment, adjusted the baseline correction of the measured ECG, extracted it from the adjusted ECG do. The proposed system includes the steps… More
  •   Views:12       Downloads:11        Download PDF
  • Visual Object Detection and Tracking Using Analytical Learning Approach of Validity Level
  • Abstract Object tracking plays an important role in many vision applications. This paper proposes a novel and robust object detection and tracking method to localize and track a visual object in video stream. The proposed method is consisted of three modules; object detection, tracking and learning. Detection module finds and localizes all apparent objects, corrects the tracker if necessary. Tracking module follows the interest object by every frame of sequences. Learning module estimates a detecting error, and updates its value of credibility level. With a validity level where the tracking is failed on tracing the learned object, detection module finds again… More
  •   Views:14       Downloads:12        Download PDF
  • Active Detecting DDoS Attack Approach Based on Entropy Measurement for the Next Generation Instant Messaging App on Smartphones
  • Abstract Nowadays, more and more smartphones communicate to each other’s by using some popular Next Generation Instant Messaging (NGIM) applications (Apps) which are based on the blockchain (BC) technologies, such as XChat, via IPv4/IPv6 dual stack network environments. Owing to XChat addresses are soon to be implemented as stealth addresses, any DoS attack activated form malicious XChat node will be treated as a kind of DDoS attack. Therefore, the huge NGIM usages with stealth addresses in IPv4/IPv6 dual stack mobile networks, mobile devices will suffer the Distributed Denial of Service (DDoS) attack from Internet. The probing method is deployed in this… More
  •   Views:16       Downloads:40        Download PDF