Electrical and Electronic Engineering, Control and Systems Engineering, Artificial Intelligence, Computer Vision and Pattern Recognition
11
Scopus Publications
1072
Scholar Citations
16
Scholar h-index
17
Scholar i10-index
Scopus Publications
Edge-prioritization based multi-head attention in graph convolutional network for electrical resistance image reconstruction Sathesh Ammaiappan, Anand Raju, Guanghui Liang, Awais Ahmed, Chao Tan, Feng Dong Measurement Science and Technology, 2026 Electrical resistance tomography (ERT) uses a network of boundary electrodes to visualize and analyze processes involving multiphase flow effectively. Nonlinearity and ill-posed problems are challenging for ERT reconstruction. However, reconstruction image accuracy is in demand. Due to a lack of suitable training, the existing deep learning network for ERT image reconstruction depends on sparse information flow and gradient flow. It is challenges to represent the structural topological link among internal conductivity characteristics using the usual reconstruction approach. By propagating feature representation across topological connections, the non-Euclidean structure of the ERT measurement encodes the problems. Capturing spatial and topological dependencies requires adaptive learning to handle irregular prominent feature positions and conductivity domains. The adaptive learning is modulated by edge priority for different graph states in a dynamic graph where edge features embed spatial constraints and graph geometry. Therefore, a multi-head attention mechanism is incorporated into the graph convolutional network to maintain the local smoothness while preserving sharp transitions. The dynamic graph is learned through edge weights jointly with node features using the RMSprop optimization method. Adaptive edge learning can identify object geometries and real-time flow patterns. Using extensive numerical simulation and experiment results, the proposed algorithm improves the imaging accuracy compared to the traditional methods without dense connections. It is compared with existing deep learning methods.
Design Analysis of a Seven-Level Active Neutral Point Clamped (ANPC) Inverter Based on Switched Technique Shujaat Ali, Yanbo Che, Sathesh Ammaiappan, Mubashar Javed, Yazeed Mohammad Qasaymeh, Mohammad Alibakhshikenari Radio Science, 2026 A novel switch‐based Active‐Neutral‐Clamped (ANPC) inverter for low DC‐link voltage is presented in this paper. The proposed ANPC topology minimizes switches and achieves 1.5 times better voltage gain than standard inverters. The main objective of this design is to reduce active switches in the inverter to increase system efficiency. A Flying Capacitor (FC) with self‐voltage balancing makes this inverter unique. This flying capacitor enables the inverter to produce a 7‐L output voltage. This study comprehensively analyses how it performs compared to existing technologies. The theoretical aspects of this proposed design have experienced thorough validation through a combination of experimental and simulation results, ensuring its efficacy and practical feasibility. The benchmark comparison further indicates reduced standing voltage requirement (TSV × Vin = 6.5) and a rated efficiency of 97.5%, supporting improved cost, control simplicity, and loss performance. Simulation and experimental results demonstrate the feasibility and effectiveness of the topology in terms of voltage balance, load adaptability, and modulation index adjustment. Simulation tests reveal stable voltage levels and current waveforms under different load conditions, with the peak output voltage reaching 1.5 times the initial input voltage. Experiments on a laboratory prototype validate the topology's dynamic response and self‐balancing capability, showcasing its practical viability. The proposed 7L‐ANPC topology offers a promising solution for enhancing power conversion efficiency and reliability in diverse applications.
Improved stacked sparse auto encoder by adaptive shuffled shepherd optimization algorithm for ERT image reconstruction Sathesh Ammaiappan, Guanghui Liang, Feng Dong Measurement Science and Technology, 2025 Electrical resistance tomography (ERT) is a visualization detection technology possessing unique advantages in industrial dynamic process monitoring. ERT image reconstruction is an ill-posed inverse problem that is nonlinear and susceptible to measurement noise. In recent years, deep learning models have been used to learn complex patterns and relationships in sparse data, leading to more accurate and robust image reconstruction. A stacked sparse autoencoder (SSAE) based deep learning approach is proposed to map complex nonlinear functions for ERT image reconstruction. In the proposed SSAE, global conditional gradient steps employ the back projection concept and non-convex local search with the predicted model for fine-tuning. The proposed method guarantees a global optimum for the neural network sparse constraint. The model improves feature learning and representation, while the optimization technique effectively optimizes weight changes during training. A sparse autoencoder imposes sparsity constraints on the hidden layers to minimize the sparsity effect. The proposed model uses adaptive strategies to dynamically shuffle and optimize encoder-decoder weights in the architecture and optimize sparse features by shuffle shepherd optimization (SSO), which can take advantage of the proposed model’s ability to capture complex hierarchical features and the SSO’s adaptability in optimizing autoencoder parameters. The fusion of SSAE and SSO algorithms obtains an average structural similarity (SSIM) index of 0.8371 under an optimal sparsity constraint of 0.047 for reconstruction. The proposed model significantly enhances reconstruction performance with a loss of convergence of 0.0124, providing faster training and robust image reconstruction capabilities for ERT. Simulation and experimental tests are conducted to evaluate the network’s generalization ability and practicality.
Image reconstruction of ultrasonic transmission tomography using spectral-based graph convolution network Sathesh Ammaiappan, Guanghui Liang, Feng Dong Measurement Science and Technology, 2025 Ultrasonic transmission tomography (UTT) is a crucial imaging modality for non-destructive testing and quality assessment in industrial settings. The reconstruction of high-quality images from limited, irregular, and noisy measurement of ultrasound measurements poses a significant challenge due to the ill-posed nature of the inverse problem. Therefore, the proposed method involves formulating the UTT image reconstruction problem into a graph-based learning task. In this task, nodes symbolize locations on the inspected object, while edges illustrate the connections between those locations. Furthermore, it employs the graph Laplacian function to inject graph structure into the learning algorithm to extract the structural details of the acoustic parameter distribution from the ultrasound measurements. The spectral graph convolutional neural networks (SGCNNs) enforce smoothness across the graph. The unbiased risk estimation-based spectral approach efficiently shapes the irregularity graph structure. The proposed SGCNN is tailored to effectively learn and exploit the complex relationships between transmitted ultrasound measurements and the underlying substantial properties in an ultrasound spectrum. Simulation and experimental tests are carried out to validate the proposed algorithm’s performance. In addition, the SGCNN algorithm is compared to graph convolution neural network and traditional reconstruction methods, showcasing its superior ability to reconstruct detailed and accurate images by evaluating performance metrics.
A Hybrid Convolutional Feature Reconstruction Network for Electrical Resistance Tomography Image Reconstruction Awais Ahmed, Sathesh Ammaiappan, Guanghui Liang, Feng Dong Chinese Control Conference Ccc, 2025 Electrical resistance tomography (ERT) is a non-intrusive imaging method employed for capturing internal conductivity distributions of an object or medium by applying currents through boundary electrodes and collecting the resulting voltages. The primary challenge in ERT image reconstruction is caused by the inverse problem, and the traditional image reconstruction methods suffer to achieve high accuracy and resolution. To improve the image reconstruction accuracy, the Hybrid Convolutional Feature Reconstruction Network (HCFR-Net) is proposed. Fully connected layers are mostly used in CNN in which the size of inputs remain constant so they fail to capture spatial features from the data which causes less accurate reconstruction. To maintain important details in the data and enhance spatial features through the process of reconstruction, the up-sampling layer is introduced with FCN element to mitigate these issues successfully. The outcomes from simulation and experimental tests show that the proposed HCFR-Net algorithm has higher accuracy for image reconstruction.
Self-Attention-Powered Graph Convolution Network for Image Reconstruction in ERT/UTT Dual-Modality Tomography Sathesh Ammaiappan, Guanghui Liang, Chao Tan, Feng Dong IEEE Sensors Journal, 2025 A self-attention powered graph convolution network (GCN) is proposed for electrical resistance tomography (ERT) and ultrasonic transmission tomography (UTT) dual-modality tomography. It’s promising to improve the imaging accuracy in cross-sectional media distribution detection. The proposed model uses polynomial feature generation to pre-process the two input layers of measurement data. The dual-branch measurement spatial information is fused by the feature level at the dense layer with the same dimension. The proposed model calculates attention scores to extract contrasts from complex non-Euclidean distance measurement data structures. The GCN with an attention mechanism (GCNAM) identifies expressive complementary features from the combined ERT/UTT measurement data, improving prediction accuracy. During training, the attention mechanism predicts the various modal features using learnable parameters; the model then adapts to the good reconstruction target. It promotes the effective fusion and image reconstruction of dual-modal information between different modal features. The optimizer RMSprop further fine-tunes the proposed model to enhance the generalization ability. The simulation and experiment tests are carried out to evaluate the proposed model’s performance. Furthermore, it conducts generalization and robustness tests on all state-of-the-art models to evaluate their performance under varying conditions. The results demonstrate that the proposed model maintains higher imaging accuracy and stability using structural similarity (SSIM) index and root mean square error (RMSE) metrics.
A Novel Deep Structure Auto Encoder for Image Reconstruction in Electrical Resistance Tomography Sathesh Ammaiappan, Guanghui Liang, Feng Dong Chinese Control Conference Ccc, 2024 As a non-invasive and non-radiative process visualization technique, electrical resistance tomography (ERT) has attracted more and more attention in industrial and biomedical fields. Image reconstruction play a vital role in ERT. The research proposes a deep-learning approach to ERT image reconstruction using an auto-encoder network. The stacked layered structure of the auto-encoder neural network can extract latent features for well-posed spatial information that provides improved imaging accuracy. For more thorough retrieval of latent information and improved image accuracy, the stacking design of the auto-encoder neural network is crucial. A novel deep structure auto encoder (SAE) is proposed here by stacking several layers in a neural network and an upgraded adaptive moment estimation (ADAM) optimizer is used to enhance image accuracy beyond the standard reconstruction approach. A well-designed proposed SAE model can enable smooth transitions between various distributions, allowing good generalizations to new instances that best fit the training data’s learned distribution. Simulation and experimental tests are carried out and the results verify the effectiveness of the proposed method.
A Priority-Based Adaptive Firefly Optimized Conv-BiLSTM Algorithm for Electrical Resistance Image Reconstruction Sathesh Ammaiappan, Guanghui Liang, Chao Tan, Feng Dong IEEE Sensors Journal, 2024 As a high-speed, noninvasive process measurement technology, electrical resistance tomography (ERT) is well suited for visualization of media distribution in industrial and biomedical fields. An innovative optimal hybrid deep-learning strategy utilizing a 1-D convolution neural network (CNN) and recurrent neural network (RNN) is proposed to solve the ERT inverse problem. In the proposed hybrid deep-learning model, the priority-based adaptive firefly algorithm (PAFA) optimizes the neuron structure by feature engineering and adaptively estimates the local optimum to accelerate convergence. The feature selection technique controls randomness through efficient local search and finding the optimal value fit. The input and output relation is enforced by local recurrent cells in the hybrid model feedback with a bidirectional long-short-term memory (BiLSTM) network. The proposed model extracts the latent features from the prior cells during the training period of the network architecture. Simulation and experimental tests are carried out, and the quantitative analysis shows that the proposed hybrid deep-learning model has better imaging accuracy than the traditional image reconstruction methods.
Spodoptera Litura Damage Severity Detection and Classification in Tomato Leaves Sathesh A Journal of Innovative Image Processing, 2023 Agriculture plays a key role in global economy. Tomato is India's third most prioritized crop after potato and onion, but it is the world's second most prioritized crop after potato. Worldwide, India ranks second in tomato production. However, Tomato crop is constantly threatened by different pest infections. The most significant pest infection that highly affects the tomato crop yield is Spodoptera Litura. Emerging from the family of Noctuidae with vigorous eating pattern, this insect primarily feed on leaves and fruits by leaving the entire crop completely destroyed. Monitoring the pest spread dynamics will reduce the probability of an outbreak. Early detection of pests can assist farmers in taking the required precautions to limit the spread of the infection. This paper provides a brief introduction to performs an assessment on the infection spread by Spodoptera Litura in the tomato plants. Here, the plants are classified as low, moderate and high pest infestation and further the severity of the damage is assessed by analyzing the number of S. Litura Larvae present in Tomato crop and also the percentage of pest infestation in tomato plants. The primary goal of this research study is to detect pests as early as possible and decline the usage of pesticides on the crops by taking early sustainable alternative measures.
Neutral current and harmonic mitigation using ZSBR with various transformer topologies R Anuraj, A Sathesh, S. Smys 2nd International Conference on Electronics and Communication Systems Icecs 2015, 2015 Mostly all domestic and commercial installation uses 3-phase 4-wire distribution system, but pretty much appliances are single phased which may create unbalance in the supply system also typical loads like TV, personal computers, mobile phone chargers, Air conditioners etc. uses power electronic converters and draws non-sinusoidal currents, these two situations may cause high neutral current and create harmonics in the supply system. It may cause wiring failures, rising of neutral potentials, transformer overheating, etc. In response to this problem, this paper proposes some passive compensation methods for minimizing the neutral current and harmonics in the three-phase four-wire distribution system. The proposing methodology using combinations of ZSBR with various transformers like T-connected transformers, star delta transformer, Scott connected transformer, star polygon transformer and star hexagon transformer. In this paper, analysis is carried to evaluate the performance of various transformers in combination with ZSBR under unbalanced and non-linear loads. The simulation results shows that the neutral current is reduced to negligible value and the total harmonic distortion has been reduced below 50% as in the supply lines.
Edge-prioritization based multi-head attention in graph convolutional network for electrical resistance image reconstruction S Ammaiappan, A Raju, G Liang, A Ahmed, C Tan, F Dong Measurement Science and Technology 37 (15), 155408 , 2026 2026
Self-Attention Powered Graph Convolution Network for Image Reconstruction in ERT/UTT Dual-Modality Tomography S Ammaiappan, G Liang, C Tan, F Dong IEEE Sensors Journal , 2025 2025
A Hybrid Convolutional Feature Reconstruction Network for Electrical Resistance Tomography Image Reconstruction A Ahmed, S Ammaiappan, G Liang, F Dong 2025 44th Chinese Control Conference (CCC), 3603-3608 , 2025 2025
Improved stacked sparse auto encoder by adaptive shuffled shepherd optimization algorithm for ERT image reconstruction S Ammaiappan, G Liang, F Dong Measurement Science and Technology 36 (6), 065406 , 2025 2025 Citations: 1
Image reconstruction of ultrasonic transmission tomography using spectral-based graph convolution network S Ammaiappan, G Liang, F Dong Measurement Science and Technology 36 (4), 045412 , 2025 2025 Citations: 2
A novel deep structure auto encoder for image reconstruction in electrical resistance tomography S Ammaiappan, G Liang, F Dong 2024 43rd Chinese Control Conference (CCC), 3295-3300 , 2024 2024 Citations: 2
A priority-based adaptive firefly optimized Conv-BiLSTM algorithm for electrical resistance image reconstruction S Ammaiappan, G Liang, C Tan, F Dong IEEE Sensors Journal 24 (1), 624-634 , 2023 2023 Citations: 9
Deep learning based handwriting recognition with adversarial feature deformation and regularization YB Hamdan, A Sathesh Journal of innovative image processing 3 (4), 367 , 2021 2021 Citations: 15
Speedy detection module for abandoned belongings in airport using improved image processing technique A Sathesh, YB Hamdan J Trends Comput Sci Smart Technol 3 (4), 251 , 2021 2021 Citations: 6
Analysis of software sizing and project estimation prediction by machine learning classification A Sathesh, YB Hamdan Journal of Ubiquitous Computing and Communication Technologies 3 (4), 303-313 , 2021 2021 Citations: 5
Hybrid parallel image processing algorithm for binary images with image thinning technique A Sathesh, EEB Adam Journal of Artificial Intelligence 3 (03), 243-258 , 2021 2021 Citations: 35
Construction of accurate crack identification on concrete structure using hybrid deep learning approach EEB Adam, A Sathesh Journal of Innovative Image Processing (JIIP) 3 (02), 85-99 , 2021 2021 Citations: 44
Construction of statistical SVM based recognition model for handwritten character recognition YB Hamdan, A Sathesh Journal of Information Technology 3 (02), 92-107 , 2021 2021 Citations: 180
Evaluation of fingerprint liveness detection by machine learning approach-a systematic view EEB Adam, A Sathesh Journal of ISMAC 3 (01), 16-30 , 2021 2021 Citations: 67
Three Phase Coil based Optimized Wireless Charging System for Electric Vehicles EEB Adam, A Sathesh 2021
Construction of efficient smart voting machine with liveness detection module YB Hamdan, A Sathesh Journal of Innovative Image Processing 3 (3), 255-268 , 2021 2021 Citations: 20
Early diagnosis of lung cancer with probability of malignancy calculation and automatic segmentation of lung CT scan images S Manoharan, A Sathesh Journal of Innovative Image Processing (JIIP) 2 (04), 175-186 , 2020 2020 Citations: 146
Patient diet recommendation system using K clique and deep learning classifiers S Manoharan, A Sathesh Journal of Artificial Intelligence 2 (02), 121-130 , 2020 2020 Citations: 100
Computer vision on IOT based patient preference management system A Sathesh Journal of trends in Computer Science and Smart technology 2 (2), 68-77 , 2020 2020 Citations: 67
Geospatial and social media analytics for emotion analysis of theme park visitors using text mining and gis S Manoharan, A Sathesh Journal of Information Technology 2 (02), 100-107 , 2020 2020 Citations: 52
MOST CITED SCHOLAR PUBLICATIONS
Construction of statistical SVM based recognition model for handwritten character recognition YB Hamdan, A Sathesh Journal of Information Technology 3 (02), 92-107 , 2021 2021 Citations: 180
Early diagnosis of lung cancer with probability of malignancy calculation and automatic segmentation of lung CT scan images S Manoharan, A Sathesh Journal of Innovative Image Processing (JIIP) 2 (04), 175-186 , 2020 2020 Citations: 146
Patient diet recommendation system using K clique and deep learning classifiers S Manoharan, A Sathesh Journal of Artificial Intelligence 2 (02), 121-130 , 2020 2020 Citations: 100
Enhanced soft computing approaches for intrusion detection schemes in social media networks A Sathesh Journal of Soft Computing Paradigm (JSCP) 1 (02), 69-79 , 2019 2019 Citations: 84
Evaluation of fingerprint liveness detection by machine learning approach-a systematic view EEB Adam, A Sathesh Journal of ISMAC 3 (01), 16-30 , 2021 2021 Citations: 67
Computer vision on IOT based patient preference management system A Sathesh Journal of trends in Computer Science and Smart technology 2 (2), 68-77 , 2020 2020 Citations: 67
Geospatial and social media analytics for emotion analysis of theme park visitors using text mining and gis S Manoharan, A Sathesh Journal of Information Technology 2 (02), 100-107 , 2020 2020 Citations: 52
Improved version of graph-cut algorithm for CT images of lung cancer with clinical property condition S Manoharan Journal of Artificial Intelligence 2 (04), 201-206 , 2020 2020 Citations: 52
Population based meta heuristics algorithm for performance improvement of feed forward neural network S Manoharan, A Sathesh Journal of Soft Computing Paradigm 2 (1), 36-46 , 2020 2020 Citations: 49
Construction of accurate crack identification on concrete structure using hybrid deep learning approach EEB Adam, A Sathesh Journal of Innovative Image Processing (JIIP) 3 (02), 85-99 , 2021 2021 Citations: 44
Hybrid parallel image processing algorithm for binary images with image thinning technique A Sathesh, EEB Adam Journal of Artificial Intelligence 3 (03), 243-258 , 2021 2021 Citations: 35
Optimized multi-objective routing for wireless communication with load balancing A Sathesh Journal of trends in Computer Science and Smart technology (TCSST) 1 (02 … , 2019 2019 Citations: 25
Adaptive shape based interactive approach to segmentation for nodule in Lung CT scans A Sathesh Journal of Soft Computing Paradigm 2 (4), 216-225 , 2020 2020 Citations: 21
Construction of efficient smart voting machine with liveness detection module YB Hamdan, A Sathesh Journal of Innovative Image Processing 3 (3), 255-268 , 2021 2021 Citations: 20
Metaheuristics optimizations for speed regulation in self driving vehicles A Sathesh Journal of Information Technology and Digital World 2 (1), 43-52 , 2020 2020 Citations: 19
Performance analysis of granular computing model in soft computing paradigm for monitoring of fetal echocardiography A Sathesh Journal of Soft Computing Paradigm (JSCP) 1 (01), 14-23 , 2019 2019 Citations: 17
Deep learning based handwriting recognition with adversarial feature deformation and regularization YB Hamdan, A Sathesh Journal of innovative image processing 3 (4), 367 , 2021 2021 Citations: 15
A priority-based adaptive firefly optimized Conv-BiLSTM algorithm for electrical resistance image reconstruction S Ammaiappan, G Liang, C Tan, F Dong IEEE Sensors Journal 24 (1), 624-634 , 2023 2023 Citations: 9
Light field image coding with image prediction in redundancy A Sathesh Journal of Soft Computing Paradigm 2 (3), 160-167 , 2020 2020 Citations: 9
Typing Eyes: A Human Computer Interface Technology A Sathesh Journal of Electronics and Informatics 1 (2), 80-88 , 2019 2019 Citations: 9
