Forthcoming and Online First Articles

International Journal of System of Systems Engineering

International Journal of System of Systems Engineering (IJSSE)

Forthcoming articles have been peer-reviewed and accepted for publication but are pending final changes, are not yet published and may not appear here in their final order of publication until they are assigned to issues. Therefore, the content conforms to our standards but the presentation (e.g. typesetting and proof-reading) is not necessarily up to the Inderscience standard. Additionally, titles, authors, abstracts and keywords may change before publication. Articles will not be published until the final proofs are validated by their authors.

Forthcoming articles must be purchased for the purposes of research, teaching and private study only. These articles can be cited using the expression "in press". For example: Smith, J. (in press). Article Title. Journal Title.

Articles marked with this shopping trolley icon are available for purchase - click on the icon to send an email request to purchase.

Online First articles are published online here, before they appear in a journal issue. Online First articles are fully citeable, complete with a DOI. They can be cited, read, and downloaded. Online First articles are published as Open Access (OA) articles to make the latest research available as early as possible.

Open AccessArticles marked with this Open Access icon are Online First articles. They are freely available and openly accessible to all without any restriction except the ones stated in their respective CC licenses.

Register for our alerting service, which notifies you by email when new issues are published online.

We also offer which provide timely updates of tables of contents, newly published articles and calls for papers.

International Journal of System of Systems Engineering (15 papers in press)

Regular Issues

  • Ten years research mine for security and privacy concerns of health information systems adoption and acceptance: Coherent taxonomy, motivations and open challenges   Order a copy of this article
    by Odai Enaizan, Ashraf Saleh, Bilal Eneizan, Mohammad Almaaitah 
    Abstract: Objectives: this survey provides a taxonomy of the privacy and security factors influencing the acceptance and adoption of Health Information Systems. Methods: We implemented a focused search for each article on (1) health information systems (2) acceptance (3) privacy or security, in six main databases. These databases are considered detailed enough to include both health systems and privacy and security literature. Results: The final set included 65 articles. Most of the articles (50.76%; 33/65) are empirical studies, refers to user perspective about privacy and security of health information systems. The next largest portion of articles (36.92%; 24/65) is reviews and surveys papers which indicate to the literature to explain the existing health information systems for privacy and security to provide a general review. The smallest and the last section of works (12.30%; 8/65) refers to proposals for frameworks or models which present the privacy and security factors.
    Keywords: privacy and security; acceptance and adoption; health information system; Taxonomy.
    DOI: 10.1504/IJSSE.2023.10052449
     
  • Random Forest and Genetic Algorithm united with hyperparameter for Diabetes Prediction by using WBSMOTE, Wrapper Approach   Order a copy of this article
    by Usha Nandhini A, K. Dharmarajan 
    Abstract: Food is converted into energy by the human body, but diabetes develops when insulin stops working properly and glucose remains in the bloodstream. Heart disease, stroke, renal failure, blindness, nerve damage, gum disease, and even amputations can all be caused by hyperglycemia, or high blood sugar. In recent years, machine learning has made great strides, and its usage has improved numerous areas of healthcare. This research aimed to construct a model that could accurately predict a person's likelihood of developing diabetes. In this article, we focus on preprocessing techniques and the problem of data imbalance. In this research, diabetes diagnosis was accomplished using the Random Forest classifier (RFC), WBSMOTE, and the wrapping method. Accuracy in the RFC was improved when evolutionary algorithms were used with the Hyperparameter Optimization technique. The UCI machine learning repository's PIMA Indian Diabetes (PIDD) dataset was used for the tests. The outcomes demonstrated that the suggested method outperformed with a maximum accuracy of 93%.
    Keywords: Diabetes; Machine Learning; Random Forest; EFS; WBSMOTE; Genetic Algorithm; Health industry.
    DOI: 10.1504/IJSSE.2023.10053108
     
  • An Efficient Ciphertext-Policy Attribute-Based Encryption with Attribute and User Revocation Scheme in Cloud Environment   Order a copy of this article
    by Prathap Nayudu, Krovi Rajasekhar 
    Abstract: In cloud environment, ciphertext-policy attribute-based encryption (CP-ABE) has the important role to attain fine-grained data access control and confidentiality. In CP-ABE, since each attribute can be shared by number of users and each user can maintain multiple attributes, the attribute will not be deleted for other users with the same attribute in practice, which may affect other users. Thus, how to revoke attributes is a significant and complex issue with CP-ABE schemes. To solve these issues, we present a novel CP-ABE with an efficient user or attribute revocation model. In this approach, the attribute revocation problem is effectively solved using the attribute group concept. The attribute controller (AC) in the proposed model updates the non-revoked user’s secret key if a user or attribute revoked from the group. Besides, the proposed revocation model enhances the security against the cooperation between revoked and non-revoked users. Simulation results depict that the proposed revocation model attained better key update time, ciphertext update time, encryption time and decryption time.
    Keywords: CP-ABE; attribute revocation; user revocation; key update time.
    DOI: 10.1504/IJSSE.2023.10053655
     
  • An Optimized Extreme Learning Machine (OELM) for Simultaneous localization and mapping in Autonomous vehicles   Order a copy of this article
    by Sindhu S, SARAVANAN M 
    Abstract: Autonomous robots can navigate unexpected situations without human involvement. Multiple sensors for object recognition and mapping are used in autonomous driving, factory automation, and security service robots. Motion planning advances allow autonomous cars to recognise their position and orientation relative to a map. Estimations of vehicle position may accumulate errors and depart from reality. Various SLAM algorithms exist to map an unknown environment and estimate a vehicle’s position. To exploit deep learning networks, we offer a grey wolf optimised extreme learning machine algorithm that can construct an environment map independently and assist the system in navigating autonomously. First, a CNN-GRU hybrid model is presented for training Stereo pictures and IMU sensor data. Next, ELM is optimised for simultaneous localization and mapping (SLAM). The suggested approach allows autonomous vehicle movement with minimal pose estimate error. Our approach captures autonomous driving scenarios using the KITTI dataset. Stereo pictures and IMU sensors capture
    Keywords: Simultaneous localization and mapping (SLAM); Autonomous robots; Autonomous driving systems; Optimized Extreme Learning machine; KITTI.
    DOI: 10.1504/IJSSE.2023.10053682
     
  • Machine Learning Approaches to Intelligent Sign Language Recognition and Classification   Order a copy of this article
    by Edwin Shalom Soji, T. Kamalakannan 
    Abstract: Sign language is a great visual communication technique for those who have auditory or speech impairments. The deaf and dumb people have long relied on sign language recognition (SLR) to communicate and integrate into society. The objective of this paper is to use Indian Sign Language to conduct elementary sign-language gesture identification of image/video material and to compare a few different machine language algorithms. In order to improve the efficacy of the deployed models, images are meant to be handled with various pre-processing and feature extraction methods. The goal is to create a system that uses an efficient classifier to deliver reliable hand sign-language gesture recognition. For the recognition of the Indian Sign Language dataset for the Sign Language Translation and Recognition ISL-CSLTR database, the accuracy and precision of classification methods are analysed and compared. When compared to the decision tree and KNN models, the Random Forest model had a
    Keywords: Sign Language Recognition; Indian Sign Language; Machine learning; Feature Extraction; Decision Tree; Random Forest; Accuracy and Precision.
    DOI: 10.1504/IJSSE.2023.10053816
     
  • Encryption of Medical Images Using a Chaotic Multi-Level Scheme   Order a copy of this article
    by HELEN AROCKIA SELVI J, T. Rajendran 
    Abstract: Encryption of medical images is an essential component of the overall security infrastructure of the healthcare industry. Within the current context of digital technology for the storage, transmission, and evaluation of medical data, teleradiology is becoming an increasingly important field. A chaos-based multilevel encryption and decryption scheme is proposed for use with medical images in this research effort. When contrasted with traditional single-level encryption, the logistic chao-based multilevel encryption and decryption were determined to be superior in terms of their effectiveness. The pixel information of the photos is used, along with a permutation method and Xor operations, to construct the secret keys for the images. Metrics such as entropy, correlation measures, the number of pixels change rate, and the unified average changing intensity was utilised during the performance validation process. The strategy that was proposed was evaluated and found to be secure against the most common kinds of cryptographic attacks. The dataset used for testing and training is the ADNI Dataset which consists of medical MRI images of the human brain and the total MRI image used is 2660.
    Keywords: Image processing; chaos; encryption; decryption; Medical image encryption; Correlation; Binary; Linkage; Entropy; Randomness; Probability; Variability; Steganographic,.
    DOI: 10.1504/IJSSE.2023.10054271
     
  • Design and Development of Fusion-based Expert System for Multimodal Biometric Recognition with Facemask Authentication   Order a copy of this article
    by Arindam Mondal, Sahadev Roy 
    Abstract: A multimodal biometric system can be processed on more than one biometric feature and make the authentication process more impactful in comparison with the traditional identification system. Here in this paper, with the help of Discrete Cosine Transformation (DCT), Hough transformation technique, and Discrete Wavelet Transformation (DWT) we have designed a decision-level fusion-based authentication. In our proposed authentication model, the system will take the face, ear, and iris images individually and doing DCT, DWT, and Hough transformation, finally apply decision level fusion for the biometric features extraction. Our proposed system has more authentication capability due to iris authentication features, which can’t be easily tampered with. This experimental process clearly shows that the proposed multimodal systems have more efficiency, reliability, and are more robust than other existing biometric multimodal systems and are able to authenticate with or without wearing a surgical face mask, useful for hazardous and contaminated environments.
    Keywords: Authentication; Discrete Cosine Transformation; Discrete Wavelet Transformation; Fusion; Multimodal Biometric.
    DOI: 10.1504/IJSSE.2023.10054303
     
  • AIOps Research Innovations, Performance Impact and Challenges Faced   Order a copy of this article
    by Ajay Reddy Yeruva, Vivek Basavegowda Ramu 
    Abstract: AIOps (Artificial Intelligence for IT Operations) has become a vital element of the IT business, especially in software development in this Big Data and Internet of Things era (IoT). AIOps is a robust solution that helps programme managers and developers construct, execute, and boost online programmes utilising AI and ML techniques. Productivity, security, performance, and ease of operation are sought-after benefits. Developers and site reliability engineers will work faster, lowering time and effort, operational costs and boosting service quality and customer delight. Future operations may use AIOps, although the Methodologies section offers few techniques. This essay discusses AIOps development. This study highlights the deficiencies in research studies in several domains of AIOps and more so with cases anomaly detection, how to improve system performance leveraging AIOps, and Root Cause Analysis in the Literature Review section, along with suitable suggestions in the form of well-acclaimed performing techniques (Telesto, SLMAD, and Language Learning Models) among others to empower and ensure that th This study covers difficulties and strategies to develop AIOPs solutions to establish a valid AIOps benchmark.
    Keywords: AIOps; Performance; Performance Testing; Analytics; DevOps; Software Cloud Computing; IT& Operations; Artificial Intelligence for IT Operations; Telesto; SLMAD and Language Learning Models.
    DOI: 10.1504/IJSSE.2023.10054431
     
  • Enhancing the Performance Assessment of Network-Based and Machine Learning for Module Availability Estimation   Order a copy of this article
    by Aqeel Luaibi Challoob, Abdullah Hasan Hussein 
    Abstract: Interpreting network telemetry data is difficult. Size and volume are network assets. Production rises. ML predicts traffic trends to help decision-making. Classification and monitoring enable data science, sensor fusion, diagnostic devices, and vulnerability assessment. Complex domains have algorithms. Researchers haven't found a fast, reliable way to categorise a dataset. Most literature evaluates classifiers' accuracy and falsification rate. Classification constraints include model development time, FPR, and precision. AI can estimate network complexity. New technology expands and complicates network messages. First, send facts. Only key nodes send messages in conventional opportunistic networks. Overusing key nodes reduces network life. We provide energy-efficient message-based routing. We assess message relevance and node energy during forwarding. It fixes energy-hungry nodes and prioritizes vital signals. We replace the cache when it’s full. This hinders mobility aid. This study employs machine learning to improve traditional mobility management. It presents a realistic technique using path-based forwarding architectures to identify network links. Instead of destination-based routing, delivery path information is transmitted and advanced using a mandatory access test.
    Keywords: Energy Efficient; Sensor Network; Machine Learning; Network Security; Data Aggregation; Module Availability Estimation; Switchml; Pytorch; Tensorflow; Network Infrastructure.
    DOI: 10.1504/IJSSE.2024.10054530
     
  • Wireless Sensor Network Data Gathering Using Multi-Fold Gravitational Search Algorithm with Mobile Agent   Order a copy of this article
    by SARAVANAN R. VANNIYAR, V. SATHYA 
    Abstract: Wireless sensor network communications fascinate researchers. WSN uses affordable sensor nodes to deliver data wirelessly to a base station. Reduces sensor node energy and transmission costs. Well-tested and implemented MWCSGA. NS-2 is used to evaluate CSOGA’s performance. GA-LEACH and MW-LEACH measure work performance alongside CSOGA. Simulating multiple circumstances tests the methods. TCL and C++ dominate Ns2. Live node deployment is animated (NAM). Tracking files monitor performance. Parameters and values. Metrics include energy use, end-to-end latency, packet, speed, and delivery ratio. This study shows how a WSN for IOT can use a mobile agent and MFGSA. The GSA selects the cluster head (CH) and optimises the MA’s path to sensor nodes. Cluster head optimisation included node energy, BS transmission costs, and neighbouring nodes carrying emergency data. Clustering assigned MA source nodes, and GSA optimised the path. The suggested method's network efficiency and lifetime are compared to older methods. GSA-based itinerary planning for the MA is compared to other task energy consumption methodologies. The new technique enhances MA success rate, network stability, and energy use.
    Keywords: Wireless Sensor Network; Data collection; Multi-Fold Gravitational Search Algorithm (MFGSA); CH selection; Mobile Agent; network lifetime.
    DOI: 10.1504/IJSSE.2024.10054554
     
  • A Hybrid Wrapper Approach for Optimal Feature Selection Based on a Novel Multiobjective Technique   Order a copy of this article
    by PREETHI I, K. Dharmarajan 
    Abstract: Recent technology advances in numerous fields have created data management issues. Data pre-processing is used in machine learning and data mining to remove noisy, irrelevant, and redundant characteristics. Feature selection is a pre-processing strategy that discovers optimum features for dimensionality reduction and improves classifier performance. Many researchers have used a single-objective optimization technique to improve classification performance. Single-objective optimization reduces the classifier’s accuracy. In this study, a hybrid wrapper method feature selection using Recursive Feature Elimination and enhanced Teaching Learning-based optimization with Extreme Learning Classifier (HWFS-RTE) algorithm is utilized to forecast disease. A multiobjective technique of improved teaching Learning-based optimization (iTLBO) is combined with the Recursive feature elimination (RFE) method choose categorization features . iTLBO also performs disease classification with the extreme learning machine (ELM) by tuning ELM’s parameters using iTLBO. TLBO is a population-based optimization strategy, as it requires more rounds to obtain the classification’s fitness value. It combines
    Keywords: Machine learning; Feature selection; Recursive Feature Elimination; Teaching learning-based optimization; Feature Extraction; Health Record; Data Mining; Pre-processing; Dimensionality Reduction; Accu.
    DOI: 10.1504/IJSSE.2023.10054586
     
  • Dynamic LB Mechanism using Chimp Optimization Algorithm in LTE Networks   Order a copy of this article
    by Sivagar M.R., Prabakaran N 
    Abstract: In the recent scenario of communications, the development of high-end mobile devices is increasing the quantity of users, which requires more bandwidth, which is effectively implemented with the key technology called Long Evolution (LTE). Furthermore, the LTE standard should provide high-speed data services with dynamic conditions of distributed devices and radio transmissions. The main problem in the communication network is to effectively handle the increasing data traffic. Therefore, significant factors such as efficient load balance with high efficiency and calibration ratio should be considered. With that in mind, this paper is involved in developing a dynamic load balancing mechanism (DLBM) using chimp optimization algorithm (DLBM-COA). In the proposed work, chimp optimization algorithm focuses on the optimal configuration of the base station and coverage. The results were compared with the existing methods and it was found that the recommendedapproachis more efficient than the others.
    Keywords: Long Term Evolution; Fitness Function; LB; Chimp Optimization Algorithm and optimal configuration.
    DOI: 10.1504/IJSSE.2023.10054700
     
  • An efficient human action recognition framework based on hybrid features and enhanced long short term memory   Order a copy of this article
    by Suresh Kumar B, Viswanadha Raju S 
    Abstract: Due to its extensive variety of applications namely, internal-external surveillance, human-computer communication and human-robot communication, human activity recognition has grown into a desired research area in computer vision and artificial intelligence Although the scientific group has given considerable notice to this, an efficient method of detecting human activity in the physical realm remains elusive because of variations in appearance, interactions between objects, and mutual occlusion So that, in this study an efficient human action recognition system based on hybrid features with enhanced long short term memory (ELSTM) is proposed The proposed approach consists of four main sections namely, key frame selection, pre-processing, feature extraction and classification Initial key frames are extracted from ansequence of input video using the Structural Similarity measure (SSIM) Then, the extracted key frames are fed to the pre-processing stage to eliminate the noise available in the frames After that, the features namely, coverage factor, Space-Time Interest
    Keywords: Human action recognition; Adaptive golden eagle optimization; ELSTM; Space-time interest; Coverage factor; Shape and SSIM.
    DOI: 10.1504/IJSSE.2023.10054704
     
  • TEAMR-AMAA: Trust and Energy Aware Multicast Routing Based On Adaptive Mexican Axolotl Algorithm in WSN   Order a copy of this article
    by Hemantkumar Vijayvergia, Uma Shankar Modani 
    Abstract: In wireless sensor network (WSN), energy efficiency and trust are the major concerns to transmit the data securely from the source to multiple destinations during the process of multicast routing. To achieve these concerns, trust and energy aware multicast routing (TEAMR) is presented in this paper. At first, sensor nodes are clustered using beetle swarm optimization (BSO) algorithm in which clustering fitness is used. Second, reliable intermediate nodes between the source and multiple destinations are selected. Depend on the maximal value of trust and residual energy of each node, intermediate nodes are selected. Third, to improve the security and energy efficiency of the network, optimal paths between the source and multiple destinations are selected using the adaptive Mexican axolotl algorithm (AMAA).
    Keywords: WSN; TEAMR; AMAA; OBL; BSO.
    DOI: 10.1504/IJSSE.2023.10054708
     
  • Design and Development of Dynamic Gesture Recognition System Based on Deep Neural Network for Driver Assistive Devices   Order a copy of this article
    by Arindam Mondal, Sahadev Roy 
    Abstract: Signal acknowledgment dependent on computer vision has bit by bit become a hot exploration heading in the field of human-computer cooperation. In this paper, in light of the above issues, the Kinect-based motion acknowledgment is investigated exhaustively, and a unique motion acknowledgment strategy dependent on Hidden Markov Model and Dynamic-Signal evidence hypothesis is proposed. Base on the first Hidden Markov Model, the digression point and signal change at various snapshots of the palm direction are utilized as the qualities of the perplexing movement motion, and the element of the direction digression is diminished by the quantity of quantization codes. Then, at that point the boundary model preparing of Hidden Markov Model is finished. At last, joined with Dynamic-Signal evidence hypothesis, combinatorial rationale is judged, dynamic signal acknowledgment is completed, and a superior acknowledgment impact is acquired, which establishes a decent framework for human-computer collaboration under the Internet of Things innovation.
    Keywords: Deep Neural Network (DNN); Driver Assistive System; D-S evidence theory; Gesture recognition; Hidden Markov model (HMM).
    DOI: 10.1504/IJSSE.2023.10054728