9 results
Search Results
Now showing 1 - 9 of 9
Article Citation - WoS: 103Citation - Scopus: 160Cassava Disease Recognition From Low-Quality Images Using Enhanced Data Augmentation Model and Deep Learning(Wiley, 2021) Abayomi-Alli, Olusola Oluwakemi; Damasevicius, Robertas; Misra, Sanjay; Maskeliunas, RytisImprovement of deep learning algorithms in smart agriculture is important to support the early detection of plant diseases, thereby improving crop yields. Data acquisition for machine learning applications is an expensive task due to the requirements of expert knowledge and professional equipment. The usability of any application in a real-world setting is often limited by unskilled users and the limitations of devices used for acquiring images for classification. We aim to improve the accuracy of deep learning models on low-quality test images using data augmentation techniques for neural network training. We generate synthetic images with a modified colour value distribution to expand the trainable image colour space and to train the neural network to recognize important colour-based features, which are less sensitive to the deficiencies of low-quality images such as those affected by blurring or motion. This paper introduces a novel image colour histogram transformation technique for generating synthetic images for data augmentation in image classification tasks. The approach is based on the convolution of the Chebyshev orthogonal functions with the probability distribution functions of image colour histograms. To validate our proposed model, we used four methods (resolution down-sampling, Gaussian blurring, motion blur, and overexposure) for reducing image quality from the Cassava leaf disease dataset. The results based on the modified MobileNetV2 neural network showed a statistically significant improvement of cassava leaf disease recognition accuracy on lower-quality testing images when compared with the baseline network. The model can be easily deployed for recognizing and detecting cassava leaf diseases in lower quality images, which is a major factor in practical data acquisition.Article Citation - WoS: 47Citation - Scopus: 66Deep Learning Based Fall Detection Using Smartwatches for Healthcare Applications(Elsevier Sci Ltd, 2022) Sengul, Gokhan; Karakaya, Murat; Misra, Sanjay; Abayomi-Alli, Olusola O.; Damasevicius, RobertasWe implement a smart watch-based system to predict fall detection. We differentiate fall detection from four common daily activities: sitting, squatting, running, and walking. Moreover, we separate falling into falling from a chair and falling from a standing position. We develop a mobile application that collects the acceleration and gyroscope sensor data and transfers them to the cloud. In the cloud, we implement a deep learning algorithm to classify the activity according to the given classes. To increase the number of data samples available for training, we use the Bica cubic Hermite interpolation, which allows us to improve the accuracy of the neural network. The 38 statistical data features were calculated using the rolling update approach and used as input to the classifier. For activity classification, we have adopted the bi-directional long short-term memory (BiLSTM) neural network. The results demonstrate that our system can detect falling with an accuracy of 99.59% (using leave-one-activityout cross-validation) and 97.35% (using leave-one-subject-out cross-validation) considering all activities. When considering only binary classification (falling vs. all other activities), perfect accuracy is achieved.Article Citation - WoS: 36Citation - Scopus: 58A Suite of Object Oriented Cognitive Complexity Metrics(Ieee-inst Electrical Electronics Engineers inc, 2018) Misra, Sanjay; Adewumi, Adewole; Fernandez-Sanz, Luis; Damasevicius, RobertasObject orientation has gained a wide adoption in the software development community. To this end, different metrics that can be utilized in measuring and improving the quality of object-oriented (OO) software have been proposed, by providing insight into the maintainability and reliability of the system. Some of these software metrics are based on cognitive weight and are referred to as cognitive complexity metrics. It is our objective in this paper to present a suite of cognitive complexity metrics that can be used to evaluate OO software projects. The present suite of metrics includes method complexity, message complexity, attribute complexity, weighted class complexity, and code complexity. The metrics suite was evaluated theoretically using measurement theory and Weyuker's properties, practically using Kaner's framework and empirically using thirty projects.Article Citation - WoS: 18Citation - Scopus: 24Fusion of Smartphone Sensor Data for Classification of Daily User Activities(Springer, 2021) Sengul, Gokhan; Ozcelik, Erol; Misra, Sanjay; Damasevicius, Robertas; Maskeliunas, RytisNew mobile applications need to estimate user activities by using sensor data provided by smart wearable devices and deliver context-aware solutions to users living in smart environments. We propose a novel hybrid data fusion method to estimate three types of daily user activities (being in a meeting, walking, and driving with a motorized vehicle) using the accelerometer and gyroscope data acquired from a smart watch using a mobile phone. The approach is based on the matrix time series method for feature fusion, and the modified Better-than-the-Best Fusion (BB-Fus) method with a stochastic gradient descent algorithm for construction of optimal decision trees for classification. For the estimation of user activities, we adopted a statistical pattern recognition approach and used the k-Nearest Neighbor (kNN) and Support Vector Machine (SVM) classifiers. We acquired and used our own dataset of 354 min of data from 20 subjects for this study. We report a classification performance of 98.32 % for SVM and 97.42 % for kNN.Article Citation - WoS: 23Citation - Scopus: 26Reconstruction of 3d Object Shape Using Hybrid Modular Neural Network Architecture Trained on 3d Models From Shapenetcore Dataset(Mdpi, 2019) Kulikajevas, Audrius; Maskeliunas, Rytis; Damasevicius, Robertas; Misra, SanjayDepth-based reconstruction of three-dimensional (3D) shape of objects is one of core problems in computer vision with a lot of commercial applications. However, the 3D scanning for point cloud-based video streaming is expensive and is generally unattainable to an average user due to required setup of multiple depth sensors. We propose a novel hybrid modular artificial neural network (ANN) architecture, which can reconstruct smooth polygonal meshes from a single depth frame, using a priori knowledge. The architecture of neural network consists of separate nodes for recognition of object type and reconstruction thus allowing for easy retraining and extension for new object types. We performed recognition of nine real-world objects using the neural network trained on the ShapeNetCore model dataset. The results evaluated quantitatively using the Intersection-over-Union (IoU), Completeness, Correctness and Quality metrics, and qualitative evaluation by visual inspection demonstrate the robustness of the proposed architecture with respect to different viewing angles and illumination conditions.Article Citation - WoS: 62Citation - Scopus: 78Hybrid Microgrid for Microfinance Institutions in Rural Areas - a Field Demonstration in West Africa(Elsevier, 2019) Ayodele, Esan; Misra, Sanjay; Damasevicius, Robertas; Maskeliunas, RytisWe present a hybrid energy microgrid optimization model for a microbank in a remote rural residential area. The model is based on the use of renewable (wind turbines & solar photovoltaic (PV)) and conventional (gasoline generators) energy sources and battery storage systems. We conducted a detailed assessment of a typical microbank's load, residential loads and energy resources in a village called Ajasse-Ipo in Kwara State, Nigeria. We performed the modeling of a hybrid microgrid system, followed by an economic analysis and sensitivity analysis to optimize the hybrid system design. We performed simulations based on the energy resources available (solar PV, wind, gasoline generator & battery energy storage system) to satisfy the energy demands of the microbank, while the excess energy was supplied to meet the demand of the community loads, i.e. water pumping machine and rural home lighting. The results obtained showed that the hybrid system comprising the solar PV/battery/diesel was most techno-economically viable with a Net Present Cost (NPC) and Cost of Energy (COE) of $468,914 and 0.667$/kWh, respectively. Comparing these results with those obtained using analytical methods, the solar PV, battery and converter sizes obtained were slightly higher than the optimal system configurations as produced by HOMER. The proposed hybrid energy system also allowed to achieve almost 50% reductions in CO2, CO, unburned hydrocarbons, particulate matter, SO2 & NO2. The system can be applicable for other rural regions in the developing countries with similar environmental conditions.Article Citation - WoS: 11Citation - Scopus: 18Prospects of Ocean-Based Renewable Energy for West Africa's Sustainable Energy Future(Emerald Group Publishing Ltd, 2021) Adesanya, Ayokunle; Misra, Sanjay; Maskeliunas, Rytis; Damasevicius, RobertasPurpose The limited supply of fossil fuels, constant rise in the demand of energy and the importance of reducing greenhouse emissions have brought the adoption of renewable energy sources for generation of electrical power. One of these sources that has the potential to supply the world's energy needs is the ocean. Currently, ocean in West African region is mostly utilized for the extraction of oil and gas from the continental shelf. However, this resource is depleting, and the adaptation of ocean energy could be of major importance. The purpose of this paper is to discuss the possibilities of ocean-based renewable energy (OBRE) and analyze the economic impact of adapting an ocean energy using a thermal gradient (OTEC) approach for energy generation. Design/methodology/approach The analysis is conducted from the perspective of cost, energy security and environmental protection. Findings This study shows that adapting ocean energy in the West Africa region can significantly produce the energy needed to match the rising energy demands for sustainable development of Nigeria. Although the transition toward using OBRE will incur high capital cost at the initial stage, eventually, it will lead to a cost-effective generation, transmission, environmental improvement and stable energy supply to match demand when compared with the conventional mode of generation in West Africa. Originality/value The study will contribute toward analysis of the opportunities for adopting renewable energy sources and increasing energy sustainability for the West Africa coast regions.Article Citation - WoS: 85Citation - Scopus: 132Detecting Cassava Mosaic Disease Using a Deep Residual Convolutional Neural Network With Distinct Block Processing(Peerj inc, 2021) Oyewola, David Opeoluwa; Dada, Emmanuel Gbenga; Misra, Sanjay; Damasevicius, RobertasFor people in developing countries, cassava is a major source of calories and carbohydrates. However, Cassava Mosaic Disease (CMD) has become a major cause of concern among farmers in sub-Saharan Africa countries, which rely on cassava for both business and local consumption. The article proposes a novel deep residual convolution neural network (DRNN) for CMD detection in cassava leaf images. With the aid of distinct block processing, we can counterbalance the imbalanced image dataset of the cassava diseases and increase the number of images available for training and testing. Moreover, we adjust low contrast using Gamma correction and decorrelation stretching to enhance the color separation of an image with significant band-to-band correlation. Experimental results demonstrate that using a balanced dataset of images increases the accuracy of classification. The proposed DRNN model outperforms the plain convolutional neural network (PCNN) by a significant margin of 9.25% on the Cassava Disease Dataset from Kaggle.Article Citation - WoS: 37Citation - Scopus: 61Adoption of Mobile Applications for Teaching-Learning Process in Rural Girls' Schools in India: an Empirical Study(Springer, 2020) Chatterjee, Sheshadri; Majumdar, Dipasree; Misra, Sanjay; Damasevicius, RobertasThe purpose of this study is to identify the factors that can impact the adoption of mobile apps for teaching-learning process focusing on the girls' school in rural India. The hypotheses were proposed and a conceptual model has been developed. There is a survey work conducted to collect the data from different respondents using a convenience sampling method. The model has been validated statistically through PLS-SEM analysis covering feedbacks of 271 effective respondents. The study highlights the impact of different antecedents of the behavioural intention of the students of using mobile applications for teaching-learning process. The results also show that among other issues, price value has insignificant influence on the intention of the girl students of the rural India. During survey feedbacks have been obtained from the 271 respondents, which is meagre compared to vastness of the population and school of rural India. Only few predictors have been considered leaving possibilities of inclusion of other boundary conditions to enhance the explanative power more than that has been achieved in the proposed model with the explanative power of 81%. The model has provided laudable inputs to the educational policy makers and technology enablers and administrators to understand the impact of the mobile applications on the rural girls' school of India and facilitate the development of m-learning. Very few studies been conducted to explore the impact of mobile applications on the school education of rural India especially focusing on the girls' schools.
