International Journal of Autonomous and Adaptive Communications Systems (38 papers in press)

Regular Issues

• A Hole Repair Algorithm For Wireless Sensor Networks Based On Virtual Attractive Force Constraint  
  by Ting Hu 
  Abstract: There are some problems in the traditional algorithm, such as long running time and poor coverage effect. In this paper, a new algorithm based on virtual attractive force constraint is proposed. Based on the virtual attractive force model of intensity-based virtual force algorithm with boundary forces (IVFA-B), aiming at the particularity of ideal distance between heterogeneous network nodes, this paper analyzes the relationship between the perception radius of two heterogeneous nodes and the optimal distance between nodes when realizing the maximum coverage in grid. By combining the best distance and the best distance threshold of virtual force algorithm, the adaptability of heterogeneous network is provided. At the same time, the node moving probability is introduced into the node’s moving distance formula to repair the hole in wireless sensor network node. The simulation results show that the proposed algorithm can achieve better coverage effect and reduce the running time effectively, which proves that the proposed algorithm has better application performance.
  Keywords: Virtual attractive force constraint; Wireless sensor; Hole repair of network node.
  DOI: 10.1504/IJAACS.2023.10034566
   
  
• PREDICTION OF BIRD SPECIES USING RANDOM FOREST ALGORITHM-INTERNET OF BIRDS  
  by VIMAL SHANMUGANATHAN, Kaliappan M, Vijayalakshmi K, Muthulakshmi S, Selva Ishwarya 
  Abstract: In our routine life, we tend to stumble upon several birds. Bird-watching may be an in-style hobby that offers relaxation in way of life. Infinite individuals look at the class of various bird species while visiting bird sanctuaries., to make the bird watchers easy tool for developed where we can assist birders to acknowledge 60 bird species however we tend to can not ready to acknowledge the kind of that bird species. To beat this downside we tend to stumble upon an answer of building a package as a project. From DCNN formula may be foreseen at 88. We can notice additional correct and stable prediction of the image exploitation random formula in Jupyter notebook.
  Keywords: image recognition; random forest algorithm; internet of birds; deep learning; DCNN.
  DOI: 10.1504/IJAACS.2023.10042235
   
  
• IoT Based Vehicular Accident Detection Using Deep Learning Model  
  by Ishu Rani, Bhushan Thakre, K. Jairam Naik 
  Abstract: With increase of population and running valuable time, the demand for cars has skyrocketed creating an unprecedented condition in spite of traffic risks and road collisions. The crashes are growing at an unprecedented pace hence it causes death. Now, when Machine Learning has taken over, the previously complex problems have become feasible, and the real-life applications of these artificial ML models have been very promising. In this article, a learning model that learns over an image dataset, thereby classifying never before seen images and data has been proposed. It aims at classifying the real-time accidents based on the level of damage. For that an ANN is utilized to train the model and to learn the similarities among images and accident data. The proposed solution is efficient as it was tried to improve the efficiency of existing model using certain literature mentioned, augmenting different extractions and leaning techniques.
  Keywords: Vehicles; Accident detection; Classification; Accuracy; Deep Learning; IoT; Training model; Image polarity.
  DOI: 10.1504/IJAACS.2025.10046127
   
  
• Twitter Sentiment Analysis using Ensemble Classifiers on Tamil and Malayalam Languages  
  by Gokula Krishnan V, Deepa J, Pinagadi Venkateswara Rao, Divya V 
  Abstract: The proliferation of social network is generating a huge amount of texts and drawing attentions Sentiment Analysis (SA) extracts useful information from such data Maximum researches on SA have been done on the English language, but others main languages such as Tamil and Malaya requests obligation too It is pivotal to work on Tamil and Malaya social posts because it is the most spoken language by native speakers and heavily used in social media Although such a crowd, modest work has been done on different languages SA This paper proposes to automatically classify the overall polarity of sentiments expressed in Tamil and Malaya tweets posts by Twitter users in three classes: Positive, Negative and Neutral, and determine a fruitful approach to solve this problem Two samples of Tamil and Malaya languages are collected and later divided into two different types of corpuses Each sample in both corpuses is annotated
  Keywords: English Language; Malaya; Polarity; Tamil; Twitter; Sentiment Analysis; Long-Short Term Memory; Sentiment Analysis; Ensemble Classifiers.
  DOI: 10.1504/IJAACS.2023.10046016
   
  
• A multi-level autopoietic system to develop an artificial embryogenesis process  
  by Rima HIOUANI, Nour Eddine DJEDI, Sylvain Cussat-blanc, Yves Duthen 
  Abstract: This paper presents a new model for the self-creation of an artificial multicellular organism from one cell, which is inspired by “The Autopoietic System Theory” at different levels. This theory has been proposed to define the universal self-organization and the self-creation of living systems, the use of this concept allows the development of the artificial organism as a closed organization, and it has been widely used to understand the living systems and their capabilities such as self-organization, self-creation, autonomy, evolution, reproduction... We proposed MLAS “Multi-level Autopoietic System" beside the self-organization to embody this autopoietic system. However, in contrast to the proposed system by Varela, we set it up according to various levels (organs autopoietic machine, tissues autopoietic machine, and cells autopoietic machine). Inside the level of cell autopoietic machine, we proposed the second contribution in this paper, which is a Boolean Artificial GRN with an epigenetic part; lead the cells to create its history during evolution.
  Keywords: Autopoietic System; self-organization; self-adaptation; Artificial Gene regulatory network; evolution; diversity.
  DOI: 10.1504/IJAACS.2024.10047330
   
  
• Face Forgery Detection with Cross-Level Attention  
  by Yaju Liu, Jianwei Fei, Peipeng Yu, Chengsheng Yuan, Haopeng Liang 
  Abstract: Currently, face videos manipulated using deep learning models are widely spread on social media, which violates personal privacy and may disturb social security. In this study, we start by discovering the essential differences between real and fake faces. To extract Multi-scale artifacts and increase the perceptual field of the downsampling layer, we introduce atrous spatial pyramid pooling (ASPP). Considering the drawback that ASPP does not use all pixels for computation and may lose information, we design a Cross-Level Attention(CLA) module to interact with the output of the ASPP block with the backbone. Our proposed attention mechanism allows the network to focus on locally manipulated areas without destroying other features of the model. Experimental results on the large publicly available facial manipulation database Faceforensics++ show that our method effectively improves detection accuracy and generalization, and confirms that great detection performance is achieved even for compressed images.
  Keywords: Face forgery detection ASPP Attention mechanism.
  DOI: 10.1504/IJAACS.2025.10059644
   
  
• Analysis and optimization of RON loss via compound variable selection and BP neural network  
  by Yunshu Dai, Jianwei Fei, Fei Gu, Chengsheng Yuan 
  Abstract: The loss of octane in gasoline refining process can cause huge economic losses. Reducing the loss of octane has high practical significance. However, octane loss involves many operations in gasoline refining process, which are coupled with each other and have a highly nonlinear relationship with octane loss. Therefore, the analyze and optimization of octane loss is a high-dimensional nonlinear programming problem. Therefore, this paper proposes a compound variable selection scheme. Based on the selection of independent variables by outlier filtering and high correlation filtering, the representative operations are selected by random forest and grey correlation analysis, and the octane loss is predicted by BP neural network and XGBoost algorithm. To optimize the octane loss, an operation optimization scheme based on fast gradient modification is proposed. Based on the octane loss prediction network, the main operations are gradually fine-tuned to reduce the octane loss.
  Keywords: RON loss optimization; variable selection; XGBoost; BP neural network.
  DOI: 10.1504/IJAACS.2024.10059645
   
  
• Exposing deepfakes in online communication:detection based on ensemble strategy  
  by Jie Xu, Guoqiang Wang, Tianxiong Zhou 
  Abstract: In recent years, deepfake techniques appeared in people's lives. As a product of deep learning, it can generate realistic face-swapping videos. Due to high fidelity, deepfake is often used to produce porn videos and guide public opinion, so as to pose a great threat to social stability. Previous studies have been able to get better detection accuracy. This paper aims to improve the detection ability of existing schemes by using the ensemble learning scheme from the perspective of model learning. Specifically, our scheme includes feature extraction, feature selection, feature classification and combination strategy. The experimental results on several datasets demonstrate that our scheme can effectively improve the detection ability of the model.
  Keywords: deepfake detection; ensemble strategy; online communication; video forensics; deep learning.
  DOI: 10.1504/IJAACS.2022.10049685
   
  
• Optimal Load Balancing Strategy-based Centralized Sensor for WSN-based Cloud-IoT Framework using Hybrid Meta-heuristic Strategy  
  by Yogaraja G. S. R, Thippeswamy M. N, Venkatesh K 
  Abstract: This paper is to implement a load balancing centralized server to control the Wireless Sensor Networks (WSN) connected with IoT and cloud. The WSN gathers data pertaining to diverse applications and transfer it to centralized server in the cloud through IoT channel. Sever controls the routing of each node in the WSN through optimal load balancing strategy. A hybrid meta-heuristic algorithm with Forest-Cat Optimization Algorithm (F-COA) is introduced for accomplishing centralized load balanced strategy in communication system. The fundamental constraints used in the proposed models are clustering parameters like distance between nodes, energy, and delay, load balancing parameters like response time, turnaround time, server load, and QoS parameters like resource utilization, execution time, and throughput. The experimental results present the superior performance through multi objectives optimization when compared to the other approaches in terms of different constraints.
  Keywords: Internet of Things; Cloud Computing; Wireless Sensor Networks; Optimal Routing; Forest-Cat Optimization Algorithm; Load Balancing; Multi-Objective Function.
  DOI: 10.1504/IJAACS.2024.10051757
   
  
• Automated Anomaly Detection and Multi-label Anomaly Classification in Crowd Scenes based on Optimal Thresholding and Deep Learning Strategy  
  by Harshadkumar S. Modi, Dhaval A. Parikh 
  Abstract: This paper plan to develop the anomaly detection and multi-label anomaly classification in crowd scenes using the enhanced deep learning strategy. The two main phases of the proposed model are the anomaly detection and the multi-label anomaly classification. In the first phase of anomaly detection, pre-processing of frames is done by the Histogram Equalization, and patches are extracted from the video frames. The extracted patches are further subjected to the Convolutional Neural Network for obtaining the movement score and appearance score of the frame. The extraction of movement score and appearance score helps to know the deep insight of the object behavior in the video, which thus helps to detect whether the objects are anomaly or not. For detecting that, a threshold is fixed for the movement score and appearance score.
  Keywords: Automated Anomaly Detection; Multi-label Anomaly Classification; Optimal Thresholding; Convolutional Neural Network; Enhanced Recurrent Neural Network; Elephant Herding-Grey Wolf Optimization.
  DOI: 10.1504/IJAACS.2024.10051758
   
  
• Deepfake detection and localization based on illumination inconsistency  
  by Fei Gu, Yunshu Dai, Jianwei Fei, Xianyi Chen 
  Abstract: The rapid development of image synthesis technology has encouraged the spread of some fake news, making people gradually lose trust in digital media. The compression in the process of image propagation brings a major challenge to the existing face forgery detection method. In this paper, we propose a multi-task Deepfake detection method according to the motivation of illumination inconsistency between tampered and non-tampered areas. Specifically, we trained a Siamese network as a feature extractor to estimate the illumination, then distinguish the face image and predict the forged region through a U-shaped network. Our method has achieved great accuracy in classification tasks and can still maintain a good performance in compressing data. In addition, we can also show the intensity of tampering while locating the forged area.
  Keywords: Deepfakes; illumination estimation; Siamese network; UNet.
  DOI: 10.1504/IJAACS.2024.10052496
   
  
• ASER analysis of DF relay assisted communication systems with diversity receiver at destination subject to Nakagami-m fading channels  
  by RAJKISHUR MUDOI, Darilangi S. Lyngdoh 
  Abstract: In recent years, relay assisted communications have been extensively used for low power and long-distance transmission of information. The average symbol error rate (ASER) performance of a decode and forward (DF) relay assisted communication method is analysed using maximal ratio combining (MRC) as well as selection combining (SC) receiver at the destination node. All links of the wireless system are influenced by Nakagami-m fading distribution. The closed-form representation of ASER is derived using the MGF based approach for coherent as well as noncoherent modulation techniques. The results show an improvement in the ASER performance with the MRC receiver compared to the SC receiver at the destination node. The ASER performance improves with an enhancement of the fading parameter. The mathematical expressions are supported using computer simulations that give the correctness of the results.
  Keywords: ASER; Decode-and-Forward; Maximal Ratio Combining; MGF; Nakagami-m fading; and Selection Combining.
  DOI: 10.1504/IJAACS.2024.10052604
   
  
• Energy Harvesting based Performance analysis in Nakagami-m fading channels  
  by Nandita Deka, Rupaban Subadar 
  Abstract: : Energy harvesting (EH) is an emerging technology to harvest energy from the transmitter's radio frequency (RF) signals to the receiver. In this paper, a novel closed-form expression for the outage probability (OP) and average bit error rate (ABER) based on energy harvesting are derived over Nakagami-m fading channel. Moreover, we assume the power splitting (PS) harvesting technique in our proposed system. The power splitting receiver separates the received signal into information transmission and energy harvesting receiver with a power splitter factor. Numerical results are also presented to analyze the impact of various system parameters, such as the power splitter factor and shaping parameter of the considered fading channel.
  Keywords: Nakagami-m fading; RF signals; Energy harvesting; PS factor; Outage probability; ABER.
  DOI: 10.1504/IJAACS.2024.10055334
   
  
• Performance estimation of rotation antenna with directional selectivity in IEEE 802.11 wireless networks  
  by Ridhima Mehta  
  Abstract: Spatially separated antenna devices in wireless communication system determine the effectiveness of the radio network performance. Non-uniform directional antenna mounted for wireless node localization radiates energy along one particular direction more than others. In this paper, the performance evaluation of a software controlled wireless antenna system is presented. The specific type of wireless network application with frequency reconfigurable rotation antenna incorporating the directional selectivity characteristic is employed in the context of IEEE 802.11 wireless networks. The wireless antenna system is tested in terms of various queuing related metrics of average buffer length, mean queuing time and packet arrival rate. In addition, the quality-of-service (QoS) performance attributes of wireless communication network are estimated including the packet interference rate, average round trip delay and application throughput. Furthermore, the efficient performance of our model is significantly compared with the previous works in terms of throughput and delay parameters.
  Keywords: Delay; IEEE 802.11 Wireless Network; Rotation Antenna; Throughput.
  DOI: 10.1504/IJAACS.2024.10055459
   
  
• Optimal SVM Classifier based Cross-layer Design in Ad-hoc Wireless Network  
  by Ridhima Mehta  
  Abstract: The rapid advancement of wireless technology and routing devices has led to expeditious evolution of the ad-hoc type of networking. The infrastructure-less dynamic network with the error-prone wireless medium in the resource-constrained ad-hoc communication system poses several challenges for efficient routing and design optimization. In this paper, an optimal cross-layer design architecture for ad-hoc wireless network is developed based on the supervised categorization algorithm. Specifically, the Support Vector Machine (SVM) classification scheme is employed to evaluate the margin and error associated with the disparate features of a wireless communication system. This technique ensures that the margin obtained with the computed linear separating plane is maximum from the labeled training samples belonging to two different categories of a two-class problem. The contemplated networking attributes considered for the integrated application of cross-layer information exchange and binary SVM models include the throughput, persistence probability, and transmit power associated with the directed wireless links.
  Keywords: Ad-hoc network; Cross-layer design; Persistence probability; Power; SVM; Throughput.
  DOI: 10.1504/IJAACS.2024.10055462
   
  
• Applications, Merits and Demerits of WSN with IoT- A Detailed Review  
  by Mantripragada Yaswanth Bhanu Murthy, Anne Koteswararao 
  Abstract: This article provides an in-depth survey of WSN and IoT. It explores the diverse applications of IoT and WSN in healthcare, agriculture, transportation, automation, etc. The paper provides the various merits and demerits of IoT and WSN technologies. It also investigates the research works exploiting both IoT and WSN technologies for distinct applications and describes the various advantages of integrating these technologies. The paper provides a comparative study of explored applications based on common performance metrics, publication year, technologies used and results achieved. Through exploring the diverse applications, strengths and weaknesses of IoT and WSN systems, this paper offers the thorough knowledge on IoT and WSN technologies to readers for encouraging better and more applications exploiting WSN with IoT.
  Keywords: IoT; WSNs; Applications; Smart devices.
  DOI: 10.1504/IJAACS.2024.10055464
   
  
• SNGPLDP: Social Network Graph Generation Based on Personalized Local Differential Privacy  
  by Zixuan Shen, Jianwei Fei, Zhihua Xia 
  Abstract: The social network graph (SNG) can display valuable information mined from the massive data Its generation needs vast amounts of users’ data However, with the increasing awareness of personal privacy protection, conflicts arise between generating the SNG and protecting the sensitive data therein To balance the problem, some SNG generation schemes are proposed by using local differential privacy (LDP) techniques In this way, the users can upload the perturbed data to the server with the privacy protected, and the server can generate an approximate SNG using the perturbed data However, the existing schemes do not consider the personalized privacy requirements of users This paper proposes an SNG generation scheme by designing a personalized LDP (PLDP) method, named SNGPLDP. Experiments performed on four real datasets show the effectiveness of SNGPLDP in providing PLDP protection with general graph properties. Moreover, the proposed scheme achieves higher network structure cohesion.
  Keywords: Personalized Local Differential Privacy; Social Network Graph; Randomized Response.
  DOI: 10.1504/IJAACS.2024.10055601
   
  
• DSHS: A Secure Decentralized Smart Healthcare System using Smart Contract  
  by A.N.U. RAJ, Shiva Prakash 
  Abstract: Social distancing has been implemented to stop the COVID-19 outbreak, which is currently a major public health concern on a global scale. Telemedicine is used by medical professionals to monitor their patients, especially those with chronic diseases. However, various implementation-related risks including data breaches, access restrictions within the medical community, inaccurate diagnosis, etc are faced by traditional telemedicine. We proposed the enhanced decentralized smart healthcare system (DSHS) to reduce the risks associated with traditional telemedicine healthcare solutions that utilize blockchain-based smart contracts to monitor, supervise, and carry out transactions. An immutable Modified Merkel tree structure is used to hold the transaction for viewing and accessing revocation contracts on a public blockchain, updating and sharing patient health records with all entities. Performance evaluation is done on Ethereum Platform. The simulation results show that proposed framework outperforms existing telemedicine solutions by enhancing transparency, boosting efficiency, and reducing average latency in the system.
  Keywords: Telemedicine; Ethereum; Blockchain; Smart Contract; Patient Health Record; Modified Merkle tree.
  DOI: 10.1504/IJAACS.2025.10059646
   
  
• Antenna Performance Enhancement Using Inter-Coupling Effect Reducing Mechanisms  
  by Gebrehiwet Gebrekrstos Lema  
  Abstract: Recently, thinning an antenna has resulted in to attractive antenna radiation characteristics enhancement. This performance enhancement using thin antenna array is achieved because the inter-coupling effects of the array elements are reduced. Though the thinning both reduces the weight of the antenna and enhances the radiation characteristics, iterative algorithms can further enhance the performance and hence, in this research, an optimizer algorithm and inter-coupling reducing mechanisms are applied. The excitation weights of the individual array elements are thinned by turning some of the elements turned off while some of the elements turned on. The purpose of the thinning is to enhance the antenna performances like reduced SLL, high directivity, reduced power consumption and flexible radiation pattern. The SLL attenuation mechanism is applied to reduce the SLL in addition to the SLL reduction using the thinning and beamforming. Hence, in this paper, the three techniques (thinning, beamforming and SLL attenuation) are proposed to be integrated to enhance the antenna radiation characteristics. In general, the proposed combined method has resulted in to much better SLL reduction, directivity improvement and power wastage reduction.
  Keywords: Antenna design; beam forming; antenna array; side lobe; directivity.
  DOI: 10.1504/IJAACS.2024.10055765
   
  
• Secure Framework for Data Transmission and Amalgamation of the Medical Device in IoMT
  by Rajkumar Gaur, Shiva Prakash 
  Abstract: The various application of IoT, one of the IoMT, is used in medical health care and medical monitoring techniques such as healthcare. It examines medical reports (EMR), online cases, primary level control, patient supervision, and fundamental problems. Urgent care can most affect support due to the current lack of a hospital or procedure and the possible long clinical medical centre. Due to the instant transfer of patient information, security is a crucial problem. Then the various attack moves and constructs are challenging in a device and secure information. So, our proposed architecture and security scheme is essential for the Internet of Medical Things. The architecture and scheme minimize resources, cost, and service the security system secures the information of patients and hospitals. Also, analyse the information integrity, confidentiality, and non-repudiation in the data transmission for IoMT applications. The next discusses the future challenges and implementation of the innovative healthcare system.
  Keywords: IoMT; domain; data flow; secure; hospital services; e-health.
  
  
• Classification of Insect's Acoustic Signals Using a Hybrid Approach: Mel-Frequency Hilbert-Huang Transformation
  by Rekha Kaushik, Jyoti Singhai 
  Abstract: Insects present in stored grain, wood, soil, plants, and environment have distinctive set of acoustic features. This paper developed an insect detection and classification system using their sound dataset. A novel approach has been proposed based on the combination of features: Mel-frequency Cepstral Coefficient and Hilbert Huang transform named Mel-frequency Hilbert Huang Transform (MFHTT) for acoustic feature extraction. The proposed method integrates the ability of Principal Component Analysis to reduce the dimensions and de-correlate the coefficients for insect sound classification. Support Vector Machine, K-Nearest Neighbour, Random Forest, Na
  Keywords: Acoustic sensing; Classification algorithms; Feature extraction; Hilbert- Huang transformation; Insect; Mel-frequency Cepstral Coefficient.
  
  
• Privacy-Preserving Image Retrieval Based on Additive Secret Sharing  
  by Zhihua Xia, Qi Gu, Lizhi Xiong, Wenhao Zhou 
  Abstract: The rapid growth of digital images motivates individuals to upload their images to the cloud server. To preserve privacy, image owners would prefer to encrypt the images before uploading, but it would limit the efficient usage of images. Plenty of schemes on privacy-preserving content-based image retrieval (PPCBIR) tries to seek the balance between security and retrieval ability. However, compared to the works in content-based image retrieval (CBIR), the existing schemes are far deficient in both accuracy and efficiency. In this paper, inspired by additive secret sharing technology, we propose a series of secure computation protocols and show their application in PPCBIR. The experiments and security analysis demonstrate the efficiency, accuracy, and security of our scheme.
  Keywords: Privacy-preserving Image Retrieval; Additive Secret Sharing; Pre-trained CNN; Secure PCA.
  DOI: 10.1504/IJAACS.2024.10055815
   
  
• An Abnormal Behavior Recognition of MOOC Online Learning Based on Multidimensional Data Mining  
  by Meng Qu 
  Abstract: To solve the problems of low recall rate, low recognition rate and long time-consuming of the traditional MOOC online learning abnormal behavior identification method, an abnormal behavior recognition method of MOOC online learning based on multidimensional data mining is designed. The CFSFDP algorithm is used to mine MOOC online learning multidimensional data, the Lagrangian function is used to improve the SVM, and the improved SVM is used to classify the collected data. A neural network structure based on multi-head self-attention mechanism is constructed, and the feature vector of each class of MOOC online learning data is extracted by this network, and the abnormal behavior of MOOC online learning is identified according to the feature vector. The experimental results show that the recall rate of the method in this paper is always above 93%, the average recognition rate is 95.9%, and the maximum recognition time is only 0.4s
  Keywords: Multidimensional data mining; MOOC; online learning; abnormal behavior recognition; multi-head self-attention mechanism; neural network structure; recognizer.
  DOI: 10.1504/IJAACS.2024.10055816
   
  
• Proxy-CPM: A collaborative high definition map update for autonomous and connected vehicles  
  by Anis BOUBAKRI, Sonia Mateli 
  Abstract: Autonomous cooperative driving systems allow autonomous vehicles to operate safely. However, these driving systems are limited by the difficulty of retrieving, in a timely manner, the data needed for traffic. HD maps act as an additional sensor for the purpose of informing autonomous vehicles in advance by changes in the traffic environment. So you have to update the HD map. In our solution we have proposed a service that allows to notify the vehicles by the updates of the traffic environment in order to minimize the dangerous situations.
  Keywords: HD map; Edge computing; Autonomous vehicles; Connected vehicles; Collaborative perception.
  DOI: 10.1504/IJAACS.2024.10055954
   
  
• Bi-LSTM with Attention Pooling Based on Joint Motion and Difference Entropy for Action Recognition  
  by Lunzheng Tan, Chunping Huang, Xia Limin, Jiaxiao Li 
  Abstract: Human action recognition is one of the most challenging tasks in computer vision due to its complex background changes and redundancy of long-term video information. To tackle these issues, we propose a novel action recognition framework called Bi-LSTM with Attention Pooling based on Joint motion and difference Entropy (JEAP-BiLSTM). Firstly, we extracts critical points of motion flow field as the key points of optical flow field, then compute the motion and difference entropy maps of the key points’ optical flow as short-term features. On this basis, we then use Bi-LSTM to extract video long-term temporal features from forward and backward simultaneously. In order to solve the problem of background change, we introduce attention pooling to the extracted features to highlight the region of interest. Experiments demonstrate that the proposed JEAP-BiLSTM outperforms state-of-the-art action recognition methods.
  Keywords: Action recognition; Attention mechanism; Entropy map; Bi-LSTM.
  DOI: 10.1504/IJAACS.2024.10056109
   
  
• Performance analysis of antenna selection based MIMO systems subject to Fisher-Snedecor F fading channels  
  by Hubha Saikia, Rajkishur Mudoi 
  Abstract: The antenna selection is a prominent technique which decreases the number of radio frequency (RF) links in a multiple-input-multiple-output (MIMO) scheme. This article analyses the outage probability (OP), capacity as well as bit error rate (BER) of MIMO system with antenna selection subject to independent and identically distributed (i.i.d.) Fisher-Snedecor F fading channels. Two types of systems namely transmit antenna selection (TAS) connected with maximal ratio combining (MRC) receiver as well as joint transmit and receive antenna selection system are evaluated. Analytical expressions are derived in terms of infinite series representation. The OP, BER and channel capacity are illustrated for different values of fading parameters as well as shadowing parameters. All the obtained statements are endorsed by Monte-Carlo simulation data.
  Keywords: Bit error rate; Fisher-Snedecor F fading; Transmit antenna selection; Outage probability; Maximal ratio combining.
  DOI: 10.1504/IJAACS.2024.10056127
   
  
• A novel copy-move detection and location technique based on tamper detection and similarity feature fusion  
  by Guangyang He, Xiang Zhang, Fan Wang, Zhangjie Fu 
  Abstract: Copy-move is a tampering method that moves a part of the image to another area. Since the colour and brightness of the images before and after being tampered are roughly the same, it is laborious to be recognised by the human eye. To address the problem of weak feature extraction capability in current copy-move tampering detection models, this article proposes a new image copy-move detection method. This method effectively extracts noise and edge information from the tested image through multi-angle feature fusion technology, and further improves the detection performance on image tampering edges by combining dilated convolutions and attention mechanisms. In addition, the model embeds tampering detection features into similarity features, enabling similarity detection to focus on specific areas, which effectively improves the detection efficiency and accuracy of model. Compared with existing copy-move detection methods, this method has strong robustness to various attacks while achieving good detection accuracy.
  Keywords: Deep learning; Image tampering localisation; Edge features.
  DOI: 10.1504/IJAACS.2024.10056233
   
  
• A discrete bat algorithm for collaborative scheduling of discrete manufacturing logistics  
  by Chen Huajun, Yanguang Cai 
  Abstract: In this paper, a collaborative scheduling of discrete manufacturing logistics (CSDML) model is established for a single factory with multiple customers, considering multi-vehicle, delay, time window and capacity constraints. Based on the basic principle of bat algorithm, discrete bat algorithm(DBA) is proposed to solve the CSDML problem. A coding and decoding scheme is proposed to map the continuous domain to the discrete domain, the objective function is defined, and a local search strategy is adopted to enhance the search effect of the algorithm. Compared with DBA with random search and DBA without search, the proposed algorithm can get better experimental results.
  Keywords: discrete manufacturing; logistics transportation; discrete bat algorithm; collaborative scheduling.
  DOI: 10.1504/IJAACS.2024.10056274
   
  
• An improved salp swarm algorithm for collaborative scheduling of discrete manufacturing logistics with time windows  
  by Chen Huajun, Yanguang Cai 
  Abstract: Considering the constraints of time windows and capacity in the case of single factory and multiple customers, a collaborative scheduling of discrete manufacturing logistics with time windows (CSDMLTW) model is established. The problem includes discrete manufacturing process and logistics transportation scheduling process. In the discrete manufacturing process, parallel machine scheduling(PMS) is considered. Logistics transportation scheduling considers vehicle routing problem with time windows (VRPTW). In this paper, improved salp swarm algorithm (ISSA) is proposed to solve CSDMLTW problem based on the basic principle of salp swarm algorithm. Compared with simulated annealing algorithm, genetic algorithm and particle swarm optimization algorithm, the results are relatively better. Experimental results verify the feasibility of solving this problem.
  Keywords: parallel machine scheduling; vehicle routing; discrete manufacturing; collaborative scheduling.
  DOI: 10.1504/IJAACS.2024.10056281
   
  
• Energy Efficient Techniques in 5G Communication: A Survey  
  by Gracelin Sheena B, N. Snehalatha 
  Abstract: Fifth Generation (5G) technology is a huge demand in the communication scenario due to the advanced features. The 5G communication shifts the wireless signal to the frequency range of 30 to 300 gigahertz (GHz) and minimizes the wavelength from centimeter to millimeter. Hence, it generates large bandwidth and reduces the traffic congestion in network. In this survey, 50 research papers are reviewed based on the beamforming techniques used to enable the data rate in network. 5G mobile communication methods are classified based on the beamforming methods, like phased array, network slicing, millimeter wave, Filter Bank Multi Carrier (FBMC), and wideband approach. Moreover, the challenges faced by the existing techniques are explained in the gaps and issues section. The analysis based on the classification, toolset, and the performance metrics are discussed. The future dimension of the research is based on the gaps and issues identified from the existing research works.
  Keywords: Beamforming; mobile communication; millimeter wave (mm wave); Phased array antenna; dual band antenna.
  DOI: 10.1504/IJAACS.2024.10056426
   
  
• ADAPTIVE CHANNEL EQUALIZATION USING DIFFERENT HYBRID METAHEURISTIC ALGORITHMS IN DIGITAL COMMUNICATION  
  by Shwetha N, Manoj Priyatham M, Gangadhar N 
  Abstract: In digital communication, the transmitted signal may be dispersive causing the information not to be transmitted as same Due to distortion, the communication channel is affected by Inter-Symbol Interference (ISI) An adaptive channel equalization concept is used to reduce the effects of ISI in digital communication The equalization process is considered as an optimization issue to minimize the mean square error (MSE) between the transmitted signal and the output of the equalizer Therefore, metaheuristic algorithms are widely adopted to enhance the function of adaptive channel equalizers In this paper, five different hybrid metaheuristic algorithms are introduced to optimize the Finite Impulse Response (FIR) channel for reducing the effects of ISI Accordingly, a bio-inspired Emperor Penguin Optimization (EPO) algorithm is individually hybridized with different algorithms like Tunicate Swarm Algorithm (TSA), Bald Eagle Search (BES), Jellyfish Search Optimization (JS), Manta ray foraging (MRF) and Chimp optimization algorithm (ChOA) The main role of these algorithms is to optimise the weights or coefficients of the equaliser for reducing the effect of ISI. Finally, the performance of each algorithm in channel equalisation is assessed, it is observed that EPO incorporated with both manta ray foraging and tunicate swarm algorithm have obtained relatively better equalisation results than other hybrid optimisation algorithms.
  Keywords: Adaptive Channel Equalization; Hybrid Optimization; FIR Filters; Mean Square Error; Inter Symbol Interference and Metaheuristic Algorithm.
  DOI: 10.1504/IJAACS.2024.10056434
   
  
• An improved salp swarm algorithm for collaborative scheduling of discrete manufacturing logistics with multiple depots  
  by Chen Huajun, Yanguang Cai 
  Abstract: Aiming at the situation of a single factory, multiple depots and multiple customers, considering storage, time windows and capacity constraints, a collaborative scheduling of discrete manufacturing logistics with multiple depots (CSDMLMD) model is established. This problem includes discrete manufacturing process, depot storage process and logistics transportation scheduling process. Based on the basic principle of salp swarm algorithm, an improved salp swarm algorithm (ISSA) is proposed to solve the CSDMLMD problem. It is compared with simulated annealing algorithm, genetic algorithm and particle swarm algorithm, and relatively good results can be obtained. The experimental results presented in this paper verify the feasibility of solving this problem.
  Keywords: open shop scheduling; vehicle routing; discrete manufacturing; collaborative scheduling.
  DOI: 10.1504/IJAACS.2025.10059647
   
  
• Detection of Primary User Emulation Attack using the Share and hunt optimization based deep CNN classifier
  by Asmita A. Desai Asmita A. Desai, Pramod B. Patil 
  Abstract: In this research, the share and hunt optimization-based deep classifier is developed for accurate PUEA detection, which improvise the efficiency of utilization. The detection of primary user emulation attacks and enhancing the primary user performance is done by the three-layered approach in the cognitive radio network. The proposed method investigates the malicious user actions in the CR network, which prevents interference involved in the primary user. The performance of the proposed three-layered approach using the share and hunt optimization based deep CNN classifier is evaluated using the parameters, such as detection rate, delay, and throughput, and the analysis is performed using the Rayleigh and the awgn channel in the CR environment. The detection rate and the throughput of the attack detection are highly accurate and the delay is rapid for the developed method. In imminent, the protection of the CR network is highly improved with other enhanced approaches.
  Keywords: Cognitive Radio Network; Deep CNN; PUEA detection; Optimization; Secured Spectrum sensing.
  
  
• A Theoretical Framework for Key Factors Affecting Adoption of E-procurement  
  by Zhang Guozheng, Li Peng, Donghui Li, Fang Wang, Yongdong Shi 
  Abstract: We proposed a theoretical framework to identify key factors influencing e-procurement adoption. The framework combines the theory of planned behavior and the model of technological acceptance, commonly used in B2B analyses. Through a literature review, we developed the model, drawing insights from a leading B2B e-commerce company in China. Data from 518 completed questionnaires were analyzed using structural equation modeling. The study found that behavioral attitudes, subjective norms, and behavioral control are crucial for predicting e-procurement technology usage. Internal and information barriers are important for corporate clients integrating new procurement platforms. The study provides suggestions to solution providers to overcome barriers and promote electronic procurement. The paper concludes by discussing the study's limitations and future research directions.
  Keywords: Planned behavior theory; technology acceptance model; e-procurement adoption; internal barriers; information barrier.
  DOI: 10.1504/IJAACS.2025.10059648
   
  
• Reversible Data Hiding in Encrypted Images Based on Histogram Shifting and Prediction Error Block Coding
  by Zhilin Chen, Jiaohua Qin 
  Abstract: To reduce prediction errors and create more room for embedding data, the paper proposes a reversible data hiding in encrypted images scheme based on histogram shifting and prediction error block coding. Firstly, the histogram of the prediction error image is shifted according to the signs of prediction errors. Next, the prediction error plane is partitioned into uniformly sized blocks, and these blocks are labeled as three types: an all-zero block, a block containing only one 1, and a block containing more than one 1. These three types of blocks are compressed using labeling, binary tree coding, and Huffman coding, respectively. To better compress the label map, an improved extended run-length coding is proposed. Finally, the image is secured by encryption and the secret data is hidden within it. The experimental results indicate a significant improvement in the embedding rate of the scheme compared to other schemes.
  Keywords: RDH; reversible data hiding; prediction error; Huffman coding; encrypted images; extended run-length coding.
  
  
• Survey on Sport Video Analysis and Event Detection  
  by Suhas Patel, Dipesh Kamdar 
  Abstract: In recent years, sports video analysis has gained prominence in areas such as sports coaching, player tracking, and event detection. This survey focuses on two main approaches: handcrafted features and deep learning methods. Handcrafted feature-based methods like SIFT, HOG, and SURF show promise in sports video analysis, but have limitations in handling complex actions and require manual parameter tuning. In contrast, deep learning methods, including CNNs and LSTMs, offer automated feature learning and high accuracy in action recognition and event detection. This survey offers insights into the latest techniques, their performance, and future research possibilities. By reviewing research on handcrafted features and deep learning in sports video analysis, it provides a comprehensive understanding of state-of-the-art techniques and research gaps. Sports video analysis can extract crucial information from large video datasets, including action recognition, event detection, and team behavior analysis. Advanced computer vision and machine learning automate analysis for valuable insights.
  Keywords: Sports Video Analysis; Event Detection; CNN; RNN; VGG-16,Hand Crafted Features; Deep Learning.
  DOI: 10.1504/IJAACS.2025.10059628
   
  
• E-commerce Live Streaming Impact Analysis Based on Stimulus-Organism Response Theory  
  by Donghui Li, Li Peng, Zhang Guozheng, Fang Wang, Yongdong Shi 
  Abstract: The rise of live e-commerce has not only ushered in a new consumption paradigm but has also improved people's leisure activities. The research on impact factors in e-commerce live streaming has practical implications. Based on Stimulus-Organism-Response(S-O-R) framework, this paper introduces two latent variables, perceived trust, and flow experience, to model a mechanism on how product value and celebrity value influence consumers' purchase intention in e-commerce live streaming, and then validate the result with structural equation model. For verifying the hypothesis, this study applies a questionnaire survey and random sampling. Statistical methods are used to conduct the credibility and efficacy test of the Model, significance analysis of the model, and effects between variables in the model. The empirical result shows that product value and celebrity value both have a significant direct impact on consumers' purchase intention in e-commerce live streaming.
  Keywords: E-commerce live streaming; SOR theory; product value; celebrity value; perceived trust; flow experience theory.
  DOI: 10.1504/IJAACS.2024.10059668
   
  
• ASER with QAM techniques for SISO communication system over Fisher-Snedecor F fading channels
  by RAJKISHUR MUDOI 
  Abstract: The average symbol error rate (ASER) applying various quadrature amplitude modulation (QAM) techniques is analyzed for single input and single output (SISO) system. QAM schemes are more useful to increase bandwidth efficiency for 5G and beyond wireless transmission systems. The channel of the system is influenced by Fisher-Snedecor F composite distribution. This distribution is commonly used to model fading channels due to its high accuracy and mathematical conformity. Various QAM schemes like hexagonal QAM, cross-QAM, square QAM and rectangular QAM are employed for ASER derivations. ASER expressions are acquired with regard to the Fox H-function which is the most general function and Prony approximation for Gaussian Q-function is utilized. Computer simulation is achieved to verify the certainty of the analyzed ASER equations.
  Keywords: Fisher-Snedecor F fading; ASER; Quadrature amplitude modulation (QAM); Prony approximation.