Diabetic Retinopathy is a major cause of vision loss and blindness affecting millions of people across the globe. Although there are established screening methods - fluorescein angiography and optical coherence tomography for detection of the disease but in majority of the cases, the patients remain ignorant and fail to undertake such tests at an appropriate time. The early detection of the disease plays an extremely important role in preventing vision loss which is the consequence of diabetes mellitus remaining untreated among patients for a prolonged time period. Various machine learning and deep learning approaches have been implemented on diabetic retinopathy dataset for classification and prediction of the disease but majority of them have neglected the aspect of data pre-processing and dimensionality reduction, leading to biased results. The dataset used in the present study is a diabetes retinopathy dataset collected from the UCI machine learning repository. At its inceptions, the raw dataset is normalized using the Standardscalar technique and then Principal Component Analysis (PCA) is used to extract the most significant features in the dataset. Further, Firefly algorithm is implemented for dimensionality reduction. This reduced dataset is fed into a Deep Neural Network Model for classification. The results generated from the model is evaluated against the prevalent machine learning models and the results justify the superiority of the proposed model in terms of Accuracy, Precision, Recall, Sensitivity and Specificity.

Background: According to the World Health Organization (WHO), dementia is the seventh leading reason of death among all illnesses and one of the leading causes of disability among the world’s elderly people. Day by day the number of Alzheimer’s patients is rising. Considering the increasing rate and the dangers, Alzheimer’s disease should be diagnosed carefully. Machine learning is a potential technique for Alzheimer’s diagnosis but general users do not trust machine learning models due to the black-box nature. Even, some of those models do not provide the best performance because of using only neuroimaging data. Objective: To solve these issues, this paper proposes a novel explainable Alzheimer’s disease prediction model using a multimodal dataset. This approach performs a data-level fusion using clinical data, MRI segmentation data, and psychological data. However, currently, there is very little understanding of multimodal five-class classification of Alzheimer’s disease. Method: For predicting five class classifications, 9 most popular Machine Learning models are used. These models are Random Forest (RF), Logistic Regression (LR), Decision Tree (DT), Multi-Layer Perceptron (MLP), K-Nearest Neighbor (KNN), Gradient Boosting (GB), Adaptive Boosting (AdaB), Support Vector Machine (SVM), and Naive Bayes (NB). Among these models RF has scored the highest value. Besides for explainability, SHapley Additive exPlanation (SHAP) is used in this research work. Results and conclusions: The performance evaluation demonstrates that the RF classifier has a 10-fold cross-validation accuracy of 98.81% for predicting Alzheimer’s disease, cognitively normal, non-Alzheimer’s dementia, uncertain dementia, and others. In addition, the study utilized Explainable Artificial Intelligence based on the SHAP model and analyzed the causes of prediction. To the best of our knowledge, we are the first to present this multimodal (Clinical, Psychological, and MRI segmentation data) five-class classification of Alzheimer’s disease using Open Access Series of Imaging Studies (OASIS-3) dataset. Besides, a novel Alzheimer’s patient management architecture is also proposed in this work.

Agrivoltaic (agriculture–photovoltaic) or solar sharing has gained growing recognition as a promising means of integrating agriculture and solar-energy harvesting. Although this field offers great potential, data on the impact on crop growth and development are insufficient. As such, this study examines the impact of agriculture–photovoltaic farming on crops using energy information and communications technology (ICT). The researched crops were grapes, cultivated land was divided into six sections, photovoltaic panels were installed in three test areas, and not installed in the other three. A 1300 × 520 mm photovoltaic module was installed on a screen that was designed with a shading rate of 30%. In addition, to collect farming-cultivation-environment data and to analyze power generation, sensors for growing environments and wireless-communication devices were used. As a result, normal modules generated 25.2 MWh, bifacial modules generated 21.6 MWh, and transparent modules generated 25.7 MWh over a five-month period. We could not find a difference in grape growth according to the difference of each module. However, a slight slowing of grape growth was found in the experiment group compared to the control group. Nevertheless, the sugar content of the test area of the grape fruit in the harvest season was 17.6 Brix on average, and the sugar content of the control area was measured at 17.2 Brix. Grape sugar-content level was shown to be at almost the same level as that in the control group by delaying the harvest time by about 10 days. In conclusion, this study shows that it is possible to produce renewable energy without any meaningful negative impact on normal grape farming.

Epilepsy is a neurological condition affecting around 50 million individuals worldwide, reported by the World Health Organization. This is identified as a hypersensitive disease by clinical associations. The unique characteristics of Electroencephalography have proven to be stable and universal; therefore, researchers have a lot of credibilities. So, it is the most used test for Epileptic Seizure detection and prediction. This study examines the contributions that have so far been made utilizing Electroencephalography technology to detect, predict, and monitor Epileptic Seizures. We have reviewed around 56 research articles, and those papers are selected from different academic databases. The studies explored various approaches, including Machine Learning, Deep Learning, and the Internet of Things framework. A comprehensive discussion of different classification algorithms is analyzed, and their performances are explored. Furthermore, various open issues of the stated approach are discussed, and potential future works are addressed.

To survive in the competitive environment, most organizations have adopted component-based software development strategies in the rapid technology advancement era and the proper utilization of cloud-based services. To facilitate the continuous configuration, reduce complexity, and faster system delivery for higher user satisfaction in dynamic scenarios. In cloud services, customers select services from web applications dynamically. Healthcare body sensors are commonly used for diagnosis and monitoring patients continuously for their emergency treatment. The healthcare devices are connected with mobile or laptop etc. on cloud environment with network and frequently change applications. Thus, organizations rely on regression testing during changes and implementation to validate the quality and reliability of the system after the alteration. However, for a large application with limited resources and frequently change component management activities in the cloud computing environment, component-based system verification is difficult and challenging due to irrelevant and redundant test cases and faults. In this study, proposed a test case selection and prioritization framework using a design pattern to increase the faults detection rate. First, we select test cases on frequently accessed components using observer patterns and, secondly, prioritize test cases on adopting some strategies. The proposed framework was validated by an experiment and compared with other techniques (previous faults based and random priority). Hence, experimental results show that the proposed framework successfully verified changes. Subsequently, the proposed framework increases the fault detection rate (i.e., more than 90%) than previous faults based and random priority (i.e., more than 80% respectively).

Medical Imaging is the most significant technique that constitutes information needed to diagnose and make the right decisions for treatment. These images suffer from inadequate contrast and noise that occurs during image acquisition. Thus, denoising and contrast enhancement is crucial in increasing the visual quality of the images for obtaining quantitative measures. In this research, an innovative and improvised denoising technique is implemented that applies a sparse aware with convolution neural network (SA_CNN) for investigating various medical modalities. To evaluate and validate, the convolution neural network utilizes patch creation and dictionary methods for obtaining information. The proposed framework is predominant to other current approaches by employing image assessment quantitative measures like peak signal to noise ratio (PSNR), structural similarity index (SSIM), and mean squared error (MSE). The study also optimizes the computational time to achieve increased efficiency and better visual quality of the image. Furthermore, the widespread use of the Internet of Healthcare Things (IoHT) helps to provide security with vault and challenge schemes between IoT devices and servers.