Browse
Recent Submissions
Item A new green prospective of non-orthogonal multiple access (NOMA) for 5G(MDPI AG, 2020-02-07) Basnayake, Vishaka; Jayakody, Dushantha Nalin K.; Sharma, Vishal; Sharma, Nikhil; Muthuchidambaranathan, P; Mabed, HakimEnergy efficiency is a major concern in the emerging mobile cellular wireless networks since massive connectivity is to be expected with high energy requirements from the network operators. Non-orthogonal multiple access (NOMA) being the frontier multiple access scheme for 5G, there exists numerous research attempts on enhancing the energy efficiency of NOMA enabled wireless networks while maintaining its outstanding performance metrics such as high throughput, data rates and capacity maximized optimally. The concept of green NOMA is introduced in a generalized manner to identify the energy efficient NOMA schemes. These schemes will result in an optimal scenario in which the energy generated for communication is managed sustainably. Hence, the effect on the environment, economy, living beings, etc is minimized. The recent research developments are classified for a better understanding of areas which are lacking attention and needs further improvement. Also, the performance comparison of energy efficient, NOMA schemes against conventional NOMA is presented. Finally, challenges and emerging research trends, for energy efficient NOMA are discussed.Item Hardware impaired self-energized bidirectional sensor networks over complex fading channels(MDPI AG, 2020-09-29) Panic, Stefan R.; Jayakody, Dushantha Nalin K.; Affes, Sofiene; Muthuchidambaranathan, PalaniveluRapid emergence of wireless sensor networks (WSN) faces significant challenges due to limited battery life capacity of composing sensor nodes. It is substantial to construct efficient techniques to prolong the battery life of the connected sensors in order to derive their full potential in the future Internet of Things (IoT) paradigm. For that purpose, different energy harvesting (EH) schemes are relying on a wide array of sources. Following the same objective, in this work, we have observed a time-switching EH for half-duplex (HD) bidirectional WSN, which performed in-between relaying over Hoyt fading channels. For its comprehensive performance analysis, rapidly converging infinite-series expressions have been provided with focus on the outage probability (OP) and achievable throughput of the hardware-impaired system. Additionally, asymptotic behavior of these performance measures has also been provided. Further, an approach to the symbol-error probability (SEP) analysis is also presented in the context of the observed system. Finally, we consider the shadowing influence along the WSN propagation path. Performance analysis of observed EH system operating over Rician-shadowed fading channels has been carried out, with deriving exact corresponding infinite-series expressions for outage probability (OP) and achievable throughput of the system under the hardware impairment conditions. In addition, bidirectional relaying in a mixed fading environment has been considered.Item Design of Hybrid Precoder for mm-Wave MIMO System Based on Generalized Triangular Decomposition Method(Polska Akademia Nauk, 2022-09-06) Thurpati, Sammaiah; Muthuchidambaranathan, PHybrid precoding techniques are lately involved a lot of interest for millimeter-wave (mmWave) massive MIMO systems is due to the cost and power consumption advantages they provide. However, existing hybrid precoding based on the singular value decomposition (SVD) necessitates a difficult bit allocation to fit the varying signal-to-noise ratios (SNRs) of altered sub-channels. In this paper, we propose a generalized triangular decomposition (GTD)-based hybrid precoding to avoid the complicated bit allocation. The development of analog and digital precoders is the reason for the high level of design complexity in analog precoder architecture, which is based on the OMP algorithm, is very non-convex, and so has a high level of complexity. As a result, we suggest using the GTD method to construct hybrid precoding for mmWave mMIMO systems. Simulated studies as various system configurations are used to examine the proposed design. In addition, the archived findings are compared to a hybrid precoding approach in the classic OMP algorithm. The proposed Matrix Decomposition’s simulation results of signal-to-noise ratio vs spectral efficiencies.Item An intelligent age of information based self-energized UAV-assisted wireless communication system(John Wiley and Sons Inc, 2023-10-14) Jeganathan, Anandpushparaj; Dhayabaran, Balaji; Jayakody, Dushantha Nalin K; Don, Sanjaya Arunapriya Ranchagodage; Muthuchidambaranathan, PInternet-of-things is an enabling technology in the fourth-generation industrial revolution. The freshness of the data sent by a sensor node (SN) is an important parameter in the Internet-of-things, unlike the throughput in cellular communications. A relatively new performance metric named age of information (AoI) is used in this paper to quantify the freshness of the data. The SN, located in the transport infrastructure, harvests energy from radio frequency signals transmitted by the FD-UAV. This is used to transmit real-time sensor observations to the data sink via FD-UAV. The SN generates an update after replenishing the battery and transmits it by using the harvested energy. A closed-form expression for average AoI is derived as a function of time allocated for energy harvesting. The optimal time allocation for energy harvesting that maximizes the freshness of data update is identified. A deep learning technique namely long-short term memory is used to predict the average AoI. Simulation results demonstrate the usefulness of the performance bounds in terms of the freshness of data updates.Item Revolutionizing Firefighting: UAV-Based Optical Communication Systems for Wildfires(Multidisciplinary Digital Publishing Institute (MDPI), 2024-07-11) Ali, Mohammad Furqan; Jayakody, Dushantha Nalin K.; Muthuchidambaranathan, PWildfires are one of the most devastating natural disasters in the world. This study proposes an innovative optical wildfire communication system (OWC) that leverages advanced optical technologies for wildfire monitoring and seamless communication towards the 5G and beyond (5GB) wireless networks. The multi-input–multi-output (MIMO) optical link among communication nodes is designed by gamma–gamma (GG) distribution under consideration of intensity modulation and direct-detection (IM/DD) following an on–off-keying (OOK) scheme. In this study, the performance metrics of the proposed MIMO link that enables unmanned aerial vehicles (UAVs) are analytically derived. The end-to-end (E2E) performance metrics and the novel closed-form expressions for the average BER (ABER) and outage probability ((Formula presented.)) are investigated for the proposed system models. Furthermore, the simulation results are obtained based on the real experimental data. The obtained results in this study are improved spatial resolution and accuracy, enabling the detection by communication of even small-scale wildfires at their inception stages. In the further perspective of this research, the development of the proposed system holds the potential to revolutionize wildfire prevention and control efforts, making a substantial impact on safeguarding ecosystems, communities, and economies from the devastating effects of fires.Item Masking technique based attention mechanism for off-type identification in plants(Elsevier Ltd, 2022-03-02) Jaya Brindha, G; Gopi, E.S.Off-type plants, or other distinct varieties of the same plant, need to be detected and removed at early stage from the fields to preserve the genetic integrity and significant traits of a given plant variety. At present, these off-type plants are manually identified in the cultivation fields through morphological analysis of leaves. This method is time-consuming and involves skilled labor to define the off-type plant. Hence, masking technique based attention mechanism is proposed for identifying the off-type from the leaf images captured in the cultivation fields. The proposed method recognizes the plant variety by locating and visualizing the prominent parts of the leaf which is similar to the human visual attention mechanism. When the prominent parts of the leaf image are masked, there is a significant drop in the class probability of the convolutional network. This reflects the importance of such prominent parts which directly account for its variety. An attention module is designed using neural networks which focuses on such significant regions and improves the performance of the network. The proposed method is tested on a field image dataset consisting of 1235 images of Sunflower leaves and achieves the highest mean accuracy of 98.25% in identifying the plant variety.Item Data-driven Approximation of Cumulative Distribution Function Using Particle Swarm Optimization based Finite Mixtures of Logistic Distribution(Modern Education and Computer Science Press, 2024-10-08) Poreddy, Rajasekharreddy; Gopi E.S.This paper proposes a data-driven approximation of the Cumulative Distribution Function using the Finite Mixtures of the Cumulative Distribution Function of Logistic distribution. Since it is not possible to solve the logistic mixture model using the Maximum likelihood method, the mixture model is modeled to approximate the empirical cumulative distribution function using the computational intelligence algorithms. The Probability Density Function is obtained by differentiating the estimate of the Cumulative Distribution Function. The proposed technique estimates the Cumulative Distribution Function of different benchmark distributions. Also, the performance of the proposed technique is compared with the state-of-the-art kernel density estimator and the Gaussian Mixture Model. Experimental results on κ−μ distribution show that the proposed technique performs equally well in estimating the probability density function. In contrast, the proposed technique outperforms in estimating the cumulative distribution function. Also, it is evident from the experimental results that the proposed technique outperforms the state-of-the-art Gaussian Mixture model and kernel density estimation techniques with less training data.Item LiDAR-based estimation of bounding box coordinates using Gaussian process regression and particle swarm optimization(Elsevier B.V., 2023-11-27) K., Vinodha; Gopi E.S.; Agnibhoj, TusharCamera-based object tracking systems in a given closed environment lack privacy and confidentiality. In this study, light detection and ranging (LiDAR) was applied to track objects similar to the camera tracking in a closed environment, guaranteeing privacy and confidentiality. The primary objective was to demonstrate the efficacy of the proposed technique through carefully designed experiments conducted using two scenarios. In Scenario I, the study illustrates the capability of the proposed technique to detect the locations of multiple objects positioned on a flat surface, achieved by analyzing LiDAR data collected from several locations within the closed environment. Scenario II demonstrates the effectiveness of the proposed technique in detecting multiple objects using LiDAR data obtained from a single, fixed location. Real-time experiments are conducted with human subjects navigating predefined paths. Three individuals move within an environment, while LiDAR, fixed at the center, dynamically tracks and identifies their locations at multiple instances. Results demonstrate that a single, strategically positioned LiDAR can adeptly detect objects in motion around it. Furthermore, this study provides a comparison of various regression techniques for predicting bounding box coordinates. Gaussian process regression (GPR), combined with particle swarm optimization (PSO) for prediction, achieves the lowest prediction mean square error of all the regression techniques examined at 0.01. Hyperparameter tuning of GPR using PSO significantly minimizes the regression error. Results of the experiment pave the way for its extension to various real-time applications such as crowd management in malls, surveillance systems, and various Internet of Things scenarios.Item Reliable SRAM using NAND-NOR Gate in beyond-CMOS QCA technology(John Wiley and Sons Inc, 2020-12-15) Raj, Marshal; Gopalakrishnan, Lakshminarayanan; Ko, Seok-BumThe rise in complementary metal-oxide semiconductor (CMOS) limitations has urged the industry to shift its focus towards beyond-CMOS technologies to stay in race with Moore’s law. Quantum-dot cellular automata (QCA) is considered to be a prominent paradigm among the emerging beyond-CMOS technologies. Since QCA is an emerging technology with no proper layout tools, layout generation from hardware description language (HDL) can be done by implementing circuits using the NAND-NOR logic. In QCA, the NAND-NOR logic is realised by combining a majority gate and an inverter or by using some dedicated structures. The Radius of Effect (RoE) is a critical factor that depends on the permittivity of the material used and it has an influence on the columbic interaction, polarisation and kink energy. Lower Radius of Effect values will have an impact on the performance of the circuit. In this work, a cost-efficient NAND-NOR gate using Single Rotated Cell (SRC) inverter is proposed which can operate with lower Radius of Effect. Using the proposed gate, multiplexer, decoder, and innovative memory cell are implemented. In order to demonstrate the ability to implement larger circuits using NAND-NOR logic and the proposed blocks, a 16*16 SRAM is implemented. QCADesigner is used for the simulation and validation of the proposed designs.Item Design and implementation of a nano magnetic logic barrel shifter using beyond-CMOS technology(De Gruyter Open Ltd, 2022-02-01) Kumaresan, Raja Sekar; Raj, Marshal; Gopalakrishnan, LakshminarayananBit manipulation plays a significant role in high-speed digital signal processing (DSP) and data computing systems, and shift and rotation operations are crucial functions in it. In general, barrel shifters are used to perform these operations effectively. Nano magnetic logic circuits are among the promising beyond-CMOS alternative technologies for the design of high-speed circuits. Most of the existing circuits that have been developed using nano magnets are combinational circuits. In this work, a barrel shifter is implemented and realised using in-plane nano magnetic logic. The proposed design is the first of its kind nano magnetic logic circuit. The nano magnetic logic circuit implementation, layout generation, simulation, and validation were performed using the ToPoliNano and ModelSim tools. The logical equivalent design was synthesised and evaluated using the Synopsys Design Compiler tool. The proposed barrel shifter was realised using majority logic has 1769037 nano magnets with a boxing area of 481 × 13104 µm2 and 3276 clock zones after optimisation with the Barycenter algorithm. The proposed barrel shifter realised using Boolean logic has 315276 nano magnets with a boxing area of 265 × 5028 µm2 and 1257 clock zones after optimisation with the Barycenter algorithm. The proposed design results demonstrate that complex systems can be developed using nano magnetic logic by combining combinational and sequential circuits.Item Successive cancellation decoding of polar codes using new hybrid processing element(Institute of Advanced Engineering and Science, 2022-03-11) James, Sujanth Roy; Gopalakrishnan, LakshminarayananPolar codes are one of the best linear block codes that are capacity achieving and incorporating along with it a simplified encoding and decoding routines. Successive cancellation (SC) algorithm is one of the predominantly used decoding algorithms due to its low complexity. It has broad scopes for hardware architecture design and reformulation. For polar code, the trade-off among the long latency and the silicon area of the SC algorithm is a bottleneck for the design of a high throughput polar decoder. The available prior SC polar decoder designs have higher area requirements for higher block length. This paper introduces a unique reformulation of the processing element (PE) block of SC decoding. The proposed reformulation leads to two benefits: firstly, critical path and hardware complexity of the PE are meaningfully reduced by using a unified adder block. Secondly, the silicon area requirement and the power consumption were also reduced considerably without any loss in performance. The proposed PE is used to build the decoder for various block lengths. Moreover, a Gate-level analysis of the proposed decoder has revealed that the design attains an 18% area reduction and 38% reduction in power consumption over the conventional one with similar performance.Item Spatial and polarization angle estimation of mixed-targets in MIMO radar(Electromagnetics Academy, 2019-06-20) Chintagunta, Srinivasarao; Ponnusamy, PalanisamyThis paper proposes an approach for estimating the spatial and polarization angles of mixed-targets in bistatic MIMO radar. Mixed-targets mean the combination of uncorrelated, partially correlated, and groups of coherent targets. The approach resolves rank deficiency of received signal covariance matrix and then exploits the ESPRIT-based method for estimating the angles of direction-of-departure (DOD) and direction-of-arrival (DOA). This paper also presents an analytical review and necessary conditions for resolving the rank deficiency under various scenarios of the MIMO radar. Simulation results show the effectiveness of the proposed approach.Item Direct localization of multiple noncircular sources with a moving nested array(Institute of Electrical and Electronics Engineers Inc., 2019-07-18) Kumar, Gowri; Ponnusamy, Palanisamy; Amiri, Iraj SadeghThis paper proposes a subspace data fusion (SDF)-based direct positioning determination (DPD) method for noncircular sources with a moving nested array (NA). The DPD algorithms using a uniform linear array (ULA) and coprime (CP) array are available in the existing literature. Sparse arrays have larger apertures than ULAs, which enhances degrees of freedom (DOFs). However, the existing sparse CP arrays have limited DOF and also have poor detecting ability. In this paper, the physical sensors of NA are rearranged to obtain a difference sum NA (DSNA) and second-order super NA (II-SNA). The rearranged NA sensors are seen to increase array aperture. The noncircular characteristics of the sources are also used to improve accuracy in positioning. To obtain high DOF in NA, DSNA, and II-SNA, the covariance matrices are vectorized. The coherency of the virtual array is resolved by applying the spatial smoothing technique. Finally, the SDF-based DPD is used to establish the cost function and the target is localized. The simulation results are provided for the NA, DSNA, and II-SNA and are compared with the existing CP array DPD algorithm. The results show that the proposed method shows signi-cant enhancement in localization accuracy. The Cramer-Rao lower bound (CRLB), complexity, and performance comparisons are also described in this paper.Item Polarization difference smoothing in bistatic MIMO radar(Electromagnetics Academy, 2019-12-09) Subramaniam, Karthick; Ponnusamy, Palanisamy; Chintagunta, SrinivasaraoThis paper investigates the joint direction of departure (DOD) and direction of arrival (DOA) estimation of coherent targets in bistatic multiple-input multiple-output (MIMO) radar under the presence of spatially correlated noise. Based on electromagnetic vector sensors at both transmitter and receiver of MIMO radar, a preprocessing method, namely polarization difference smoothing, is proposed to remove the coherence between targets and to suppress the spatially correlated noise. Then DODs and DOAs are estimated using the ESPRIT method. Further, this paper develops a simple approach for pair-matching between the estimated DODs and DOAs. Simulation results are compared with the receive polarization smoothing and transmit-receive polarization smoothing methods available in literature. Results show that the proposed approach improves the performance significantly.Item Disrupted Brain Network Measures in Parkinson’s Disease Patients with Severe Hyposmia and Cognitively Normal Ability(Multidisciplinary Digital Publishing Institute (MDPI), 2024-07-08) Siva, Karthik; Ponnusamy, Palanisamy; Ramanathan, MalmathanrajNeuroscience has revolved around brain structural changes, functional activity, and connectivity alteration in Parkinson’s Disease (PD); however, how the network topology organization becomes altered is still unclear, specifically in Parkinson’s patients with severe hyposmia. In this study, we have examined the functional network topological alteration in patients affected by Parkinson’s Disease with normal cognitive ability (ODN), Parkinson’s Disease with severe hyposmia (ODP), and healthy controls (HCs) using resting-state functional magnetic resonance imaging (rsfMRI) data. We have analyzed brain topological organization using popular graph measures such as network segregation (clustering coefficient, modularity), network integration (participation coefficient, path length), small-worldness, efficiency, centrality, and assortativity. Then, we used a feature ranking approach based on the diagonal adaptation of neighborhood component analysis, aiming to determine a graph measure that is sensitive enough to distinguish between these three different groups. We noted significantly lower segregation and local efficiency and small-worldness in ODP compared to ODN and HCs. On the contrary, we did not find differences in network integration in ODP compared to ODN and HCs, which indicates that the brain network becomes fragmented in ODP. At the brain network level, a progressive increase in the DMN (Default Mode Network) was observed from healthy controls to ODN to ODP, and a continuous decrease in the cingulo-opercular network was observed from healthy controls to ODN to ODP. Further, the feature ranking approach has shown that the whole-brain clustering coefficient and small-worldness are sensitive measures to classify ODP vs. ODN, as well as HCs. Looking at the brain regional network segregation, we have found that the cerebellum and limbic, fronto-parietal, and occipital lobes have higher ODP reductions than ODN and HCs. Our results suggest network topological measures, specifically whole-brain segregation and small-worldness decreases. At the network level, an increase in DMN and a decrease in the cingulo-opercular network could be used as biomarkers to characterize ODN and ODP.Item The Effect of Dopaminergic Therapy in Parkinson’s Disease: A Graph Theory Analysis(Multidisciplinary Digital Publishing Institute (MDPI), 2025-04-02) Siva, Karthik; Ponnusamy, Palanisamy; Chavda, Vishal; Montemurro, NicolaBackground: Dopaminergic therapy (DT) is the gold standard pharmacological treatment for Parkinson’s disease (PD). Currently, understanding the neuromodulation effect in the brain of PD after DT is important for doctors to optimize doses and identify the adverse effects of medication. The objective of this study is to investigate the brain connectivity alteration with and without DT in PD using resting-state EEG. Methods: Graph theory (GT) is an efficient technique for analyzing brain connectivity alteration in healthy and patient groups. We applied GT analyses on three groups, namely healthy control (HC), Parkinson with medication OFF (PD-OFF), and Parkinson with medication ON (PD-ON). Results: Using the clustering coefficient (CC), participation coefficient (PC), and small-worldness (SW) properties of GT, we showed that PD-ON patients’ brain connectivity normalized towards healthy group brain connectivity due to DT. This normalization effect appeared in the brain connectivity of all EEG frequency bands, such as theta, alpha, beta-1, beta-2, and gamma except the delta band. We also analyzed region-wise brain connectivity between 10 regions of interest (ROIs) (right and left frontal, right and left temporal, right and left parietal, right and left occipital, upper and lower midline regions) at the scalp level and compared across conditions. During PD-ON, we observed a significant decrease in alpha band connectivity between right frontal and left parietal (p-value 0.0432) and right frontal and left occipital (p-value 0.008) as well as right frontal and right temporal (p-value 0.041). Conclusion: These findings offer new insights into how dopaminergic therapy modulates brain connectivity across frequency bands and highlight the continuous elevation of both the segregation and small-worldness of the delta band even after medication as a potential biomarker for adverse effects due to medication. Additionally, reduced frontal alpha band connectivity is associated with cognitive impairment and levodopa-induced dyskinesia, highlighting its potential role in Parkinson’s disease progression. This study underscores the need for personalized treatments that address both motor and non-motor symptoms in PD patients.Item Magnitude comparator realization using threshold logic(Blue Eyes Intelligence Engineering and Sciences Publication, 2019-09) Soumya, R; Sureh Babu, V; Gopi, Varun P.Threshold logic design can be regarded as an alternative method of traditional logic gate design. Threshold logic can be considered as the primary logic of brain. Neurons can be considered as threshold logic gates. Each neuron fires when its activation threshold is crossed. The basic idea behind threshold logic is threshold decision principle. Threshold decision principle checks whether the weighted sum of inputs crosses a threshold and accordingly output is defined. Several implementations for threshold logic were proposed. Resistive threshold logic is a new method for threshold logic implementation. In this paper, using the concept of resistive threshold logic, a magnitude comparator is realized. LTSpiceIV and Electric VLSI Design System are the simulation tools used in this work.Item Sub-watershed prioritization using morphometric analysis, principal component analysis, hypsometric analysis, land use/land cover analysis, and machine learning approaches in the Peddavagu River Basin, India(IWA Publishing, 2023-05-24) Shekar, Padala Raja; Mathew, Aneesh; Arun,P.S.; Gopi, Varun P.Water resource management is critical in the face of climate change to reduce water scarcity and meet the demands of an expanding population. Prioritization of watersheds has gained significance in natural resource management, particularly in the context of watershed management. This study prioritizes sub-watersheds for the Peddavagu basin using five methods. The four methods mentioned above can be estimated utilizing remote sensing (RS) and geographic information system (GIS) approaches, while linear discriminant analysis (LDA) is estimated using machine learning techniques. The catchment resulted in the formation of 13 sub-watersheds. The quantitative measurements of morphometric analysis, including linear, relief, and areal, were considered, and 18 morphometric characteristics were chosen to rank and prioritize sub-watersheds. Principal component analysis (PCA) was used to rank and prioritize sub-watersheds based on four highly correlated morphometric parameters. The land use/land cover (LULC) analysis used four features to prioritize sub-watersheds. The LDA analysis used two features to prioritize sub-watersheds. Using hypsometric integral (HI) values, prioritization has been done. Sub-water-sheds were prioritized. Based on five methods, the sub-watersheds were classified as low, medium, and high. Among the sub-watersheds identified as high priority, immediate priority is assigned to SW10. Decision-makers in the research region can use the findings to plan and implement watershed management techniques.Item Multiresolution cascaded attention U-Net for localization and segmentation of optic disc and fovea in fundus images(Nature Research, 2024-10-04) Shalini, R; Gopi, Varun P.Identification of retinal diseases in automated screening methods, such as those used in clinical settings or computer-aided diagnosis, usually depends on the localization and segmentation of the Optic Disc (OD) and fovea. However, this task is difficult since these anatomical features have irregular spatial, texture, and shape characteristics, limited sample sizes, and domain shifts due to different data distributions across datasets. This study proposes a novel Multiresolution Cascaded Attention U-Net (MCAU-Net) model that addresses these problems by optimally balancing receptive field size and computational efficiency. The MCAU-Net utilizes two skip connections to accurately localize and segment the OD and fovea in fundus images. We incorporated a Multiresolution Wavelet Pooling Module (MWPM) into the CNN at each stage of U-Net input to compensate for spatial information loss. Additionally, we integrated a cascaded connection of the spatial and channel attentions as a skip connection in MCAU-Net to concentrate precisely on the target object and improve model convergence for segmenting and localizing OD and fovea centers. The proposed model has a low parameter count of 0.8 million, improving computational efficiency and reducing the risk of overfitting. For OD segmentation, the MCAU-Net achieves high IoU values of 0.9771, 0.945, and 0.946 for the DRISHTI-GS, DRIONS-DB, and IDRiD datasets, respectively, outperforming previous results for all three datasets. For the IDRiD dataset, the MCAU-Net locates the OD center with an Euclidean Distance (ED) of 16.90 pixels and the fovea center with an ED of 33.45 pixels, demonstrating its effectiveness in overcoming the common limitations of state-of-the-art methods.Item VasFAZ-Net: A Hybrid Loss-Optimized E cientNet-scSE Network for Retinal Vasculature and FAZ Segmentation in OCTA(Institute of Mathematics and Computer Science, 2026-05-01) Raja, Nisan Pranavah; Gopi, Varun P.; Francis, Bibin; Devi, Chelli N.Accurate segmentation of ne retinal vessels and the Foveal Avascular Zone (FAZ) in OCTA images remains challenging due to low contrast, noise, and class imbalance. To address this, a lightweight deep learning framework called VasFAZ-Net is proposed, which uses an E cientNet-B0 encoder, a parallel spatial and channel squeeze-and-excitation (scSE) decoder, and a hybrid Dice-Focal loss function, trained on the OCTA-500 dataset with both 3 mm and 6 mm scans. The proposed model achieved Dice scores of up to 88.48% for vessel segmentation and 97.98% for FAZ segmentation with only 8.8 million parameters and an inference time of 18.2 ms per image. These results demonstrate that the proposed method provides accurate, computationally e cient, and clinically deployable multi-target OCTA segmentation for retinal disease analysis.