Browsing by Author "Hoshino, Y"

Now showing 1 - 7 of 7

Open Access
Brain Activity Associated with the Planning Process during the Long-Time Learning of the Tower of Hanoi (ToH) Task: A Pilot Study
(MDPI, 2022-10-28) Mitani, K; Rathnayake, N; Rathnayake, U; Linh Dang, T; Hoshino, Y
Planning and decision-making are critical managerial functions involving the brain’s executive functions. However, little is known about the effect of cerebral activity during long-time learning while planning and decision-making. This study investigated the impact of planning and decision-making processes in long-time learning, focusing on a cerebral activity before and after learning. The methodology of this study involves the Tower of Hanoi (ToH) to investigate executive functions related to the learning process. Generally, ToH is used to measure baseline performance, learning rate, offline learning (following overnight retention), and transfer. However, this study performs experiments on long-time learning effects for ToH solving. The participants were involved in learning the task over seven weeks. Learning progress was evaluated based on improvement in performance and correlations with the learning curve. All participants showed a significant improvement in planning and decision-making over seven weeks of time duration. Brain activation results from fMRI showed a statistically significant decrease in the activation degree in the dorsolateral prefrontal cortex, parietal lobe, inferior frontal gyrus, and premotor cortex between before and after learning. Our pilot study showed that updating information and shifting issue rules were found in the frontal lobe. Through monitoring performance, we can describe the effect of long-time learning initiated at the frontal lobe and then convert it to a task execution function by analyzing the frontal lobe maps. This process can be observed by comparing the learning curve and the fMRI maps. It was also clear that the degree of activation tends to decrease with the number of tasks, such as through the mid-phase and the end-phase of training. The elucidation of this structure is closely related to decision-making in human behavior, where brain dynamics differ between “thinking and behavior” during complex thinking in the early stages of training and instantaneous “thinking and behavior” after sufficient training. Since this is related to human learning, elucidating these mechanisms will allow the construction of a brain function map model that can be used universally for all training tasks.
Open Access
Cascaded Adaptive Network-Based Fuzzy Inference System for Hydropower Forecasting
(MDPI, 2022-04-10) Rathnayake, N; Rathnayake, U; Dang, T. L; Hoshino, Y
Hydropower stands as a crucial source of power in the current world, and there is a vast range of benefits of forecasting power generation for the future. This paper focuses on the significance of climate change on the future representation of the Samanalawewa Reservoir Hydropower Project using an architecture of the Cascaded ANFIS algorithm. Moreover, we assess the capacity of the novel Cascaded ANFIS algorithm for handling regression problems and compare the results with the state-of-art regression models. The inputs to this system were the rainfall data of selected weather stations inside the catchment. The future rainfalls were generated using Global Climate Models at RCP4.5 and RCP8.5 and corrected for their biases. The Cascaded ANFIS algorithm was selected to handle this regression problem by comparing the best algorithm among the state-of-the-art regression models, such as RNN, LSTM, and GRU. The Cascaded ANFIS could forecast the power generation with a minimum error of 1.01, whereas the second-best algorithm, GRU, scored a 6.5 error rate. The predictions were carried out for the near-future and mid-future and compared against the previous work. The results clearly show the algorithm can predict power generation's variation with rainfall with a slight error rate. This research can be utilized in numerous areas for hydropower development.
Open Access
Deep Machine Learning-Based Water Level Prediction Model for Colombo Flood Detention Area
(MDPI, 2023-02-08) Herath, M; Jayathilaka, T; Hoshino, Y; Rathnayake, U
Machine learning has already been proven as a powerful state-of-the-art technique for many non-linear applications, including environmental changes and climate predictions. Wetlands are among some of the most challenging and complex ecosystems for water level predictions. Wetland water level prediction is vital, as wetlands have their own permissible water levels. Exceeding these water levels can cause flooding and other severe environmental damage. On the other hand, the biodiversity of the wetlands is threatened by the sudden fluctuation of water levels. Hence, early prediction of water levels benefits in mitigating most of such environmental damage. However, monitoring and predicting the water levels in wetlands worldwide have been limited owing to various constraints. This study presents the first-ever application of deep machine-learning techniques (deep neural networks) to predict the water level in an urban wetland in Sri Lanka located in its capital. Moreover, for the first time in water level prediction, it investigates two types of relationships: the traditional relationship between water levels and environmental factors, including temperature, humidity, wind speed, and evaporation, and the temporal relationship between daily water levels. Two types of low load artificial neural networks (ANNs) were developed and employed to analyze two relationships which are feed forward neural networks (FFNN) and long short-term memory (LSTM) neural networks, to conduct the comparison on an unbiased common ground. The LSTM has outperformed FFNN and confirmed that the temporal relationship is much more robust in predicting wetland water levels than the traditional relationship. Further, the study identified interesting relationships between prediction accuracy, data volume, ANN type, and degree of information extraction embedded in wetland data. The LSTM neural networks (NN) has achieved substantial performance, including R2 of 0.8786, mean squared error (MSE) of 0.0004, and mean absolute error (MAE) of 0.0155 compared to existing studies.
Open Access
An Efficient Automatic Fruit-360 Image Identification and Recognition Using a Novel Modified Cascaded-ANFIS Algorithm
(MDPI, 2022-06-10) Rathnayake, N; Rathnayake, U; Dang, T. L; Hoshino, Y
Automated fruit identification is always challenging due to its complex nature. Usually, the fruit types and sub-types are location-dependent; thus, manual fruit categorization is also still a challenging problem. Literature showcases several recent studies incorporating the Convolutional Neural Network-based algorithms (VGG16, Inception V3, MobileNet, and ResNet18) to classify the Fruit-360 dataset. However, none of them are comprehensive and have not been utilized for the total 131 fruit classes. In addition, the computational efficiency was not the best in these models. A novel, robust but comprehensive study is presented here in identifying and predicting the whole Fruit-360 dataset, including 131 fruit classes with 90,483 sample images. An algorithm based on the Cascaded Adaptive Network-based Fuzzy Inference System (Cascaded-ANFIS) was effectively utilized to achieve the research gap. Color Structure, Region Shape, Edge Histogram, Column Layout, Gray-Level Co-Occurrence Matrix, Scale-Invariant Feature Transform, Speeded Up Robust Features, Histogram of Oriented Gradients, and Oriented FAST and rotated BRIEF features are used in this study as the features descriptors in identifying fruit images. The algorithm was validated using two methods: iterations and confusion matrix. The results showcase that the proposed method gives a relative accuracy of 98.36%. The Fruit-360 dataset is unbalanced; therefore, the weighted precision, recall, and FScore were calculated as 0.9843, 0.9841, and 0.9840, respectively. In addition, the developed system was tested and compared against the literature-found state-of-the-art algorithms for the purpose. Comparison studies present the acceptability of the newly developed algorithm handling the whole Fruit-360 dataset and achieving high computational efficiency.
Open Access
Efficient Hotspot Detection in Solar Panels via Computer Vision and Machine Learning
(Multidisciplinary Digital Publishing Institute (MDPI), 2025-07-15) Fernando, N; Seneviratne, L; Weerasinghe, N; Rathnayake, N; Hoshino, Y
Solar power generation is rapidly emerging within renewable energy due to its cost-effectiveness and ease of deployment. However, improper inspection and maintenance lead to significant damage from unnoticed solar hotspots. Even with inspections, factors like shadows, dust, and shading cause localized heat, mimicking hotspot behavior. This study emphasizes interpretability and efficiency, identifying key predictive features through feature-level and What-if Analysis. It evaluates model training and inference times to assess effectiveness in resource-limited environments, aiming to balance accuracy, generalization, and efficiency. Using Unmanned Aerial Vehicle (UAV)-acquired thermal images from five datasets, the study compares five Machine Learning (ML) models and five Deep Learning (DL) models. Explainable AI (XAI) techniques guide the analysis, with a particular focus on MPEG (Moving Picture Experts Group)-7 features for hotspot discrimination, supported by statistical validation. Medium Gaussian SVM achieved the best trade-off, with 99.3% accuracy and 18 s inference time. Feature analysis revealed blue chrominance as a strong early indicator of hotspot detection. Statistical validation across datasets confirmed the discriminative strength of MPEG-7 features. This study revisits the assumption that DL models are inherently superior, presenting an interpretable alternative for hotspot detection; highlighting the potential impact of domain mismatch. Model-level insight shows that both absolute and relative temperature variations are important in solar panel inspections. The relative decrease in “blueness” provides a crucial early indication of faults, especially in low-contrast thermal images where distinguishing normal warm areas from actual hotspot is difficult. Feature-level insight highlights how subtle changes in color composition, particularly reductions in blue components, serve as early indicators of developing anomalies.
Open Access
Projected Water Levels and Identified Future Floods: A Comparative Analysis for Mahaweli River, Sri Lanka
(IEEE, 2023-01) Rathnayake, N; Rathnayake, U; Chathuranika, I; Dang, T. L; Hoshino, Y
The Rainfall-Runoff (R-R) relationship is essential to the hydrological cycle. Sophisticated hydrological models can accurately investigate R-R relationships; however, they require many data. Therefore, machine learning and soft computing techniques have taken the attention in the environment of limited hydrological, meteorological, and geological data. The accuracy of such models depends on the various parameters, including the quality of inputs and outputs and the used algorithms. However, identifying a perfect algorithm is still challenging. This study develops a fuzzy logic-based algorithm called Cascaded-ANFIS to accurately predict runoff based on rainfall. The model was compared against three regression algorithms: Long Short-Term Memory, Grated Recurrent Unit, and Recurrent Neural Networks. These algorithms have been selected due to their outstanding performances in similar studies. The models were tested on the Mahaweli River, the longest in Sri Lanka. The results showcase that the Cascaded-ANFIS-based model outperforms the other algorithms. The correlation coefficient of each algorithm’s predictions was 0.9330, 0.9120, 0.9133, 0.8915, 0.6811, 0.6811, and 0.6734 for the Cascaded-ANFIS, LSTM, GRU, RNN, Linear, Ridge, and Lasso regression models respectively. Hence, this study concludes that the proposed algorithm is 21% more accurate than the second-best LSTM algorithm. In addition, Shared Socio-economic Pathways (SSP2-4.5 and SSP5-8.5 scenarios) were used to generate future rainfalls, forecast the near-future and mid-future water levels, and identify potential flood events. The future forecasting results indicate a decrease in flood events and magnitudes in both SSP2-4.5 and SSP5-8.5 scenarios. Furthermore, the SSP5-8.5 scenario shows drought weather from May to August yearly. The results of this study can effectively be used to manage and control water resources and mitigate flood damages.
Open Access
Wetland Water Level Prediction Using Artificial Neural Networks—A Case Study in the Colombo Flood Detention Area, Sri Lanka
(MDPI, 2023-01) Jayathilake, T; Sarukkalige, R; Hoshino, Y; Rathnayake, U
Historically, wetlands have not been given much attention in terms of their value due to the general public being unaware. Nevertheless, wetlands are still threatened by many anthropogenic activities, in addition to ongoing climate change. With these recent developments, water level prediction of wetlands has become an important task in order to identify potential environmental damage and for the sustainable management of wetlands. Therefore, this study identified a reliable neural network model by which to predict wetland water levels over the Colombo flood detention area, Sri Lanka. This is the first study conducted using machine learning techniques in wetland water level predictions in Sri Lanka. The model was developed with independent meteorological variables, including rainfall, evaporation, temperature, relative humidity, and wind speed. The water levels measurements of previous years were used as dependent variables, and the analysis was based on a seasonal timescale. Two neural network training algorithms, the Levenberg Marquardt algorithm (LM) and the Scaled Conjugate algorithm (SG), were used to model the nonlinear relationship, while the Mean Squared Error (MSE) and Coefficient of Correlation (CC) were used as the performance indices by which to understand the robustness of the model. In addition, uncertainty analysis was carried out using d-factor simulations. The performance indicators showed that the LM algorithm produced better results by which to model the wetland water level ahead of the SC algorithm, with a mean squared error of 0.0002 and a coefficient of correlation of 0.99. In addition, the computational efficiencies were excellent in the LM algorithm compared to the SC algorithm in terms of the prediction of water levels. LM showcased 3–5 epochs, whereas SC showcased 34–50 epochs of computational efficiencies for all four seasonal predictions. However, the d-factor showcased that the results were not within the cluster of uncertainty. Therefore, the overall results suggest that the Artificial Neural Network can be successfully used to predict the wetland water levels, which is immensely important in the management and conservation of the wetlands