arXiv subjects

Roshan Godaliyadda

Publications and source records attributed to Roshan Godaliyadda.

At least 37 records · Page 2Linked to original sources

arXiv2025

Dual mode multispectral imaging system for food and agricultural product quality estimation

Multispectral imaging coupled with Artificial Intelligence, Machine Learning and Signal Processing techniques work as a feasible alternative for laboratory testing, especially in food quality control. Most of the recent related research has been focused on reflectance multispectral imaging but a system with both reflectance, transmittance capabilities would be ideal for a wide array of specimen types including solid and liquid samples. In this paper, a device which includes a dedicated reflectance mode and a dedicated transmittance mode is proposed. Dual mode operation where fast switching between two modes is facilitated. An innovative merged mode is introduced in which both reflectance and transmittance information of a specimen are combined to form a higher dimensional dataset with more features. Spatial and temporal variations of measurements are analyzed to ensure the quality of measurements. The concept is validated using a standard color palette and specific case studies are done for standard food samples such as turmeric powder and coconut oil proving the validity of proposed contributions. The classification accuracy of standard color palette testing was over 90% and the accuracy of coconut oil adulteration was over 95%. while the merged mode was able to provide the best accuracy of 99% for the turmeric adulteration. A linear functional mapping was done for coconut oil adulteration with an R2 value of 0.9558.

eess.SP↗

arXiv2025

AVSim -- Realistic Simulation Framework for Airborne and Vector-Borne Disease Dynamics

Computational disease modeling plays a crucial role in understanding and controlling the transmission of infectious diseases. While agent-based models (ABMs) provide detailed insights into individual dynamics, accurately replicating human motion remains challenging due to its complex, multi-factorial nature. Most existing frameworks fail to model realistic human motion, leading to oversimplified and less realistic behavior modeling. Furthermore, many current models rely on synthetic assumptions and fail to account for realistic environmental structures, transportation systems, and behavioral heterogeneity across occupation groups. To address these limitations, we introduce AVSim, an agent-based simulation framework designed to model airborne and vector-borne disease dynamics under realistic conditions. A distinguishing feature of AVSim is its ability to accurately model the dual nature of human mobility (both the destinations individuals visit and the duration of their stay) by utilizing GPS traces from real-world participants, characterized by occupation. This enables a significantly more granular and realistic representation of human movement compared to existing approaches. Furthermore, spectral clustering combined with graph-theoretic analysis is used to uncover latent behavioral patterns within occupations, enabling fine-grained modeling of agent behavior. We validate the synthetic human mobility patterns against ground-truth GPS data and demonstrate AVSim's capabilities via simulations of COVID-19 and dengue. The results highlight AVSim's capacity to trace infection pathways, identify high-risk zones, and evaluate interventions such as vaccination, quarantine, and vector control with occupational and geographic specificity.

eess.SY↗

arXiv2025

Precision Spatio-Temporal Feature Fusion for Robust Remote Sensing Change Detection

Remote sensing change detection is vital for monitoring environmental and urban transformations but faces challenges like manual feature extraction and sensitivity to noise. Traditional methods and early deep learning models, such as convolutional neural networks (CNNs), struggle to capture long-range dependencies and global context essential for accurate change detection in complex scenes. While Transformer-based models mitigate these issues, their computational complexity limits their applicability in high-resolution remote sensing. Building upon ChangeMamba architecture, which leverages state space models for efficient global context modeling, this paper proposes precision fusion blocks to capture channel-wise temporal variations and per-pixel differences for fine-grained change detection. An enhanced decoder pipeline, incorporating lightweight channel reduction mechanisms, preserves local details with minimal computational cost. Additionally, an optimized loss function combining Cross Entropy, Dice and Lovasz objectives addresses class imbalance and boosts Intersection-over-Union (IoU). Evaluations on SYSU-CD, LEVIR-CD+, and WHU-CD datasets demonstrate superior precision, recall, F1 score, IoU, and overall accuracy compared to state-of-the-art methods, highlighting the approach's robustness for remote sensing change detection. For complete transparency, the codes and pretrained models are accessible at https://github.com/Buddhi19/MambaCD.git

eess.IV↗

arXiv2025

Performance Benchmarking of Psychomotor Skills Using Wearable Devices: An Application in Sport

Mastering psychomotor skills, such as those essential in sports, rehabilitation, and professional training, often requires a precise understanding of motion patterns and performance metrics. This study proposes a versatile framework for optimizing psychomotor learning through human motion analysis. Utilizing a wearable IMU sensor system, the motion trajectories of a given psychomotor task are acquired and then linked to points in a performance space using a predefined set of quality metrics specific to the psychomotor skill. This enables the identification of a benchmark cluster in the performance space, which represents a group of reference points that define optimal performance across multiple criteria, allowing correspondences to be established between the performance clusters and sets of trajectories in the motion space. As a result, common or specific deviations in the performance space can be identified, enabling remedial actions in the motion space to optimize performance. A thorough validation of the proposed framework is done in this paper using a Table Tennis forehand stroke as a case study. The resulting quantitative and visual representation of performance empowers individuals to optimize their skills and achieve peak performance.

eess.SP↗

arXiv2025

Enhanced SCanNet with CBAM and Dice Loss for Semantic Change Detection

Semantic Change Detection (SCD) in remote sensing imagery requires accurately identifying land-cover changes across multi-temporal image pairs. Despite substantial advancements, including the introduction of transformer-based architectures, current SCD models continue to struggle with challenges such as noisy inputs, subtle class boundaries, and significant class imbalance. In this study, we propose enhancing the Semantic Change Network (SCanNet) by integrating the Convolutional Block Attention Module (CBAM) and employing Dice loss during training. CBAM sequentially applies channel attention to highlight feature maps with the most meaningful content, followed by spatial attention to pinpoint critical regions within these maps. This sequential approach ensures precise suppression of irrelevant features and spatial noise, resulting in more accurate and robust detection performance compared to attention mechanisms that apply both processes simultaneously or independently. Dice loss, designed explicitly for handling class imbalance, further boosts sensitivity to minority change classes. Quantitative experiments conducted on the SECOND dataset demonstrate consistent improvements. Qualitative analysis confirms these improvements, showing clearer segmentation boundaries and more accurate recovery of small-change regions. These findings highlight the effectiveness of attention mechanisms and Dice loss in improving feature representation and addressing class imbalance in semantic change detection tasks.

eess.IV↗

arXiv2025

Devising PoPStat: A Metric Bridging Population Pyramids with Global Disease Mortality

Understanding the relationship between population dynamics and disease-specific mortality is central to evidence-based health policy. This study introduces two novel metrics, PoPDivergence and PoPStat, one to quantify the difference between population pyramids and the other to assess the strength and nature of their association with the mortality of a given disease. PoPDivergence, based on Kullback-Leibler divergence, measures deviations between a countrys population pyramid and a reference pyramid. PoPStat is the correlation between these deviations and the log form of disease-specific mortality rates. The reference population is selected by a brute-force optimization that maximizes this correlation. Utilizing mortality data from the Global Burden of Disease 2021 and population statistics from the United Nations, we applied these metrics to 371 diseases across 204 countries. Results reveal that PoPStat outperforms traditional indicators such as median age, GDP per capita, and Human Development Index in explaining the mortality of most diseases. Noncommunicable diseases (NCDs) like neurological disorders and cancers, communicable diseases (CDs) like neglected tropical diseases, and maternal and neonatal diseases were tightly bound to the underlying demographic attributes whereas NCDs like diabetes, CDs like respiratory infections and injuries including self-harm and interpersonal violence were weakly associated with population pyramid shapes. Notably, except for diabetes, the NCD mortality burden was shared by constrictive population pyramids, while mortality of communicable diseases, maternal and neonatal causes and injuries were largely borne by expansive pyramids. Therefore, PoPStat provides insights into demographic determinants of health and empirical support for models on epidemiological transition. Code and scripts: https://github.com/Buddhi19/DevisingPoPStat.git

stat.AP↗

arXiv2025

The Role of Social Interactions in Mitigating Psychological Distress During the COVID-19 Pandemic: A Study in Sri Lanka

Massive changes in many aspects related to social groups of different socioeconomic backgrounds were caused by the COVID-19 pandemic and as a result, the overall state of mental health was severely affected globally. This study examined how the pandemic affected Sri Lankan citizens representing a range of socioeconomic backgrounds in terms of their mental health. The data used in this research was gathered from 3,020 households using a nationwide face-to-face survey, from which a processed dataset of 921 responses was considered for the final analysis. Four distinct factors were identified by factor analysis (FA) that was conducted and subsequently, the population was clustered using unsupervised clustering to determine which population subgroups were affected similarly. Two such subgroups were identified where the respective relationships to the retrieved principal factors and their demographics were thoroughly examined and interpreted. This resulted in the identification of contrasting perspectives between the two groups toward the maintenance and the state of social relationships during the pandemic, which revealed that one group was more 'socially connected' in nature resulting in their mental state being comparatively better in coping with the pandemic. The other group was seen to be more 'socially reserved' showing an opposite reaction toward social connections while their mental well-being declined showing symptoms such as loneliness, and emptiness in response to the pandemic. The study examined the role of social media, and it was observed that social media was perceived as a substitute for the lack of social connections or primarily used as a coping mechanism in response to the challenges of the pandemic

physics.soc-ph↗

arXiv2024

Impact of Shoe Parameters on Gait Using Wearables

The study of biomechanics during locomotion provides valuable insights into the effects of varying conditions on specific movement patterns. This research focuses on examining the influence of different shoe parameters on walking biomechanics, aiming to understand their impact on gait patterns. To achieve this, various methodologies are explored to estimate human body biomechanics, including computer vision techniques and wearable devices equipped with advanced sensors. Given privacy considerations and the need for robust, accurate measurements, this study employs wearable devices with Inertial Measurement Unit (IMU) sensors. These devices offer a non-invasive, precise, and high-resolution approach to capturing biomechanical data during locomotion. Raw sensor data collected from wearable devices is processed using an Extended Kalman Filter to reduce noise and extract meaningful information. This includes calculating joint angles throughout the gait cycle, enabling a detailed analysis of movement dynamics. The analysis identifies correlations between shoe parameters and key gait characteristics, such as stability, mobility, step time, and propulsion forces. The findings provide deeper insights into how footwear design influences walking efficiency and biomechanics. This study paves the way for advancements in footwear technology and contributes to the development of personalized solutions for enhancing gait performance and mobility.

cs.CY↗

arXiv2024

DE-LIoT: The Data-Energy Networking Paradigm for Sustainable Light-Based Internet of Things

The growing demand for Internet of Things (IoT) networks has sparked interest in sustainable, zero-energy designs through Energy Harvesting (EH) to extend the lifespans of IoT sensors. Visible Light Communication (VLC) is particularly promising, integrating signal transmission with optical power harvesting to enable both data exchange and energy transfer in indoor network nodes. VLC indoor channels, however, can be unstable due to their line-of-sight nature and indoor movements. In conventional EH-based IoT networks, maximum Energy Storage (ES) capacity might halt further harvesting or waste excess energy, leading to resource inefficiency. Addressing these issues, this paper proposes a novel VLC-based WPANs concept that enhances both data and energy harvesting efficiency. The architecture employs densely distributed nodes and a central controller for simultaneous data and energy network operation, ensuring efficient energy exchange and resource optimisation. This approach, with centralised control and energy-state-aware nodes, aims for long-term energy autonomy. The feasibility of the Data-Energy Networking-enabled Light-based Internet of Things (DE-LIoT) concept is validated through real hardware implementation, demonstrating its sustainability and practical applicability. Results show significant improvements in the lifetime of resource-limited nodes, confirming the effectiveness of this new data and energy networking model in enhancing sustainability and resource optimisation in VLC-based WPANs.

cs.NI↗

arXiv2022

GAUSS: Guided Encoder-Decoder Architecture for Hyperspectral Unmixing with Spatial Smoothness

In recent hyperspectral unmixing (HU) literature, the application of deep learning (DL) has become more prominent, especially with the autoencoder (AE) architecture. We propose a split architecture and use a pseudo-ground truth for abundances to guide the `unmixing network' (UN) optimization. Preceding the UN, an `approximation network' (AN) is proposed, which will improve the association between the centre pixel and its neighbourhood. Hence, it will accentuate spatial correlation in the abundances as its output is the input to the UN and the reference for the `mixing network' (MN). In the Guided Encoder-Decoder Architecture for Hyperspectral Unmixing with Spatial Smoothness (GAUSS), we proposed using one-hot encoded abundances as the pseudo-ground truth to guide the UN; computed using the k-means algorithm to exclude the use of prior HU methods. Furthermore, we release the single-layer constraint on MN by introducing the UN generated abundances in contrast to the standard AE for HU. Secondly, we experimented with two modifications on the pre-trained network using the GAUSS method. In GAUSS$_\textit{blind}$, we have concatenated the UN and the MN to back-propagate the reconstruction error gradients to the encoder. Then, in the GAUSS$_\textit{prime}$, abundance results of a signal processing (SP) method with reliable abundance results were used as the pseudo-ground truth with the GAUSS architecture. According to quantitative and graphical results for four experimental datasets, the three architectures either transcended or equated the performance of existing HU algorithms from both DL and SP domains.

cs.CV↗

arXiv2022

Holistic Interpretation of Public Scenes Using Computer Vision and Temporal Graphs to Identify Social Distancing Violations

The COVID-19 pandemic has caused an unprecedented global public health crisis. Given its inherent nature, social distancing measures are proposed as the primary strategies to curb the spread of this pandemic. Therefore, identifying situations where these protocols are violated, has implications for curtailing the spread of the disease and promoting a sustainable lifestyle. This paper proposes a novel computer vision-based system to analyze CCTV footage to provide a threat level assessment of COVID-19 spread. The system strives to holistically capture and interpret the information content of CCTV footage spanning multiple frames to recognize instances of various violations of social distancing protocols, across time and space, as well as identification of group behaviors. This functionality is achieved primarily by utilizing a temporal graph-based structure to represent the information of the CCTV footage and a strategy to holistically interpret the graph and quantify the threat level of the given scene. The individual components are tested and validated on a range of scenarios and the complete system is tested against human expert opinion. The results reflect the dependence of the threat level on people, their physical proximity, interactions, protective clothing, and group dynamics. The system performance has an accuracy of 76%, thus enabling a deployable threat monitoring system in cities, to permit normalcy and sustainability in the society.

cs.CV↗

arXiv2021

An Optical physics inspired CNN approach for intrinsic image decomposition

Intrinsic Image Decomposition is an open problem of generating the constituents of an image. Generating reflectance and shading from a single image is a challenging task specifically when there is no ground truth. There is a lack of unsupervised learning approaches for decomposing an image into reflectance and shading using a single image. We propose a neural network architecture capable of this decomposition using physics-based parameters derived from the image. Through experimental results, we show that (a) the proposed methodology outperforms the existing deep learning-based IID techniques and (b) the derived parameters improve the efficacy significantly. We conclude with a closer analysis of the results (numerical and example images) showing several avenues for improvement.

cs.CV↗

arXiv2021

Assessment of Fetal and Maternal Well-Being During Pregnancy Using Passive Wearable Inertial Sensor

Assessing the health of both the fetus and mother is vital in preventing and identifying possible complications in pregnancy. This paper focuses on a device that can be used effectively by the mother herself with minimal supervision and provide a reasonable estimation of fetal and maternal health while being safe, comfortable, and easy to use. The device proposed uses a belt with a single accelerometer over the mother's uterus to record the required information. The device is expected to monitor both the mother and the fetus constantly over a long period and provide medical professionals with useful information, which they would otherwise overlook due to the low frequency that health monitoring is carried out at the present. The paper shows that simultaneous measurement of respiratory information of the mother and fetal movement is in fact possible even in the presence of mild interferences, which needs to be accounted for if the device is expected to be worn for extended times.

physics.med-ph↗

arXiv2021

A Retinex based GAN Pipeline to Utilize Paired and Unpaired Datasets for Enhancing Low Light Images

Low light image enhancement is an important challenge for the development of robust computer vision algorithms. The machine learning approaches to this have been either unsupervised, supervised based on paired dataset or supervised based on unpaired dataset. This paper presents a novel deep learning pipeline that can learn from both paired and unpaired datasets. Convolution Neural Networks (CNNs) that are optimized to minimize standard loss, and Generative Adversarial Networks (GANs) that are optimized to minimize the adversarial loss are used to achieve different steps of the low light image enhancement process. Cycle consistency loss and a patched discriminator are utilized to further improve the performance. The paper also analyses the functionality and the performance of different components, hidden layers, and the entire pipeline.

eess.IV↗

arXiv2021

A generalized forecasting solution to enable future insights of COVID-19 at sub-national level resolutions

COVID-19 continues to cause a significant impact on public health. To minimize this impact, policy makers undertake containment measures that however, when carried out disproportionately to the actual threat, as a result if errorneous threat assessment, cause undesirable long-term socio-economic complications. In addition, macro-level or national level decision making fails to consider the localized sensitivities in small regions. Hence, the need arises for region-wise threat assessments that provide insights on the behaviour of COVID-19 through time, enabled through accurate forecasts. In this study, a forecasting solution is proposed, to predict daily new cases of COVID-19 in regions small enough where containment measures could be locally implemented, by targeting three main shortcomings that exist in literature; the unreliability of existing data caused by inconsistent testing patterns in smaller regions, weak deploy-ability of forecasting models towards predicting cases in previously unseen regions, and model training biases caused by the imbalanced nature of data in COVID-19 epi-curves. Hence, the contributions of this study are three-fold; an optimized smoothing technique to smoothen less deterministic epi-curves based on epidemiological dynamics of that region, a Long-Short-Term-Memory (LSTM) based forecasting model trained using data from select regions to create a representative and diverse training set that maximizes deploy-ability in regions with lack of historical data, and an adaptive loss function whilst training to mitigate the data imbalances seen in epi-curves. The proposed smoothing technique, the generalized training strategy and the adaptive loss function largely increased the overall accuracy of the forecast, which enables efficient containment measures at a more localized micro-level.

stat.AP↗

arXiv2021

Spatial analysis of COVID-19 and socio-economic factors in Sri Lanka

The spread of the global COVID-19 pandemic affected Sri Lanka similar to how it affected other countries across the globe. The Sri Lankan government took many preventive measures to suppress the pandemic spread. To aid policy makers in taking these preventive measures, we propose a novel district-wise clustering based approach. Using freely available data from the Epidemiological Department of Sri Lanka, a cluster analysis was carried out based on the COVID-19 data and the demographic data of districts. K-Means clustering and spectral clustering models were the selected clustering techniques in this study. From the many district-wise socio-economic factors, population, population density, monthly expenditure and the education level were identified as the demographic variables that exhibit a high similarity with COVID-19 clusters. This approach will positively impact the preventive measures suggested by the relevant policy making parties of the Sri Lankan government.

stat.AP↗

arXiv2021

Comprehensive Study on Denoising of Medical Images Utilizing Neural Network Based Auto-Encoder

Fetal motion discernment utilizing spectral images extracted from accelerometric data incident on pregnant mothers abdomen has gained substantial attention in the state-of-the-art research. It is an essential practice to avoid adverse scenarios such as stillbirths and intrauterine growth restrictions. However, this endeavor of ensuring fetus safety has been arduous due to the existence of random noise in medical images. This novel research is an in depth approach to analyze how the interference of different noise variations affect the retrieval of information in those images. For that, an algorithm employing auto-encoder-based deep learning was modeled and the accuracy of reconstruction of the STFT images mitigating the noise has been measured examining the loss. From the results, it is manifested that even a substantial addition of the Super-Gaussian noises which have a higher correlation of the frequencies possessed by the Fetal movement images can be restored successfully with the slightest error.

eess.SP↗

arXiv2021

Novel Non-Invasive In-house Fabricated Wearable System with a Hybrid Algorithm for Fetal Movement Recognition

Fetal movement count monitoring is one of the most commonly used methods of assessing fetal well-being. While few methods are available to monitor fetal movements, they consist of several adverse qualities such as unreliability as well as the inability to be conducted in a non-clinical setting. Therefore, this research was conducted to design a complete system that will enable pregnant mothers to monitor fetal movement at home. This system consists of a non-invasive, non-transmitting sensor unit that can be fabricated at a low cost. An accelerometer was utilized as the primary sensor and a micro-controller based circuit was implemented. Clinical testing was conducted utilizing this sensor unit. Two phases of clinical testing procedures were done and readings from more than 120 pregnant mothers were taking. Validation was done by conducting an abdominal ultrasound scan which was utilized as the ground truth during the second phase of the clinical testing procedure. A clinical survey was also conducted in parallel with clinical testings in order to improve the sensor unit as well as to improve the final system. Four different signal processing algorithms were implemented on the data set and the performance of each was compared with each other. Consequently, the most feasible as well as the best performing algorithm was determined and it was utilized in the final system. Furthermore, a mobile application was also developed to be used with the sensor unit by pregnant mothers. Finally, a complete end to end method to monitor fetal movement in a non-clinical setting was presented by the proposed system.

eess.SP↗