Diabetic retinopathy is a retinal compilation that causes visual impairment. Hemorrhage is one of the pathological symptoms of diabetic retinopathy that emerges during disease development. Therefore, hemorrhage detection reveals the presence of diabetic retinopathy in the early phase. Diagnosing the disease in its initial stage is crucial to adopt proper treatment so the repercussions can be prevented. The automatic deep learning-based hemorrhage detection method is proposed that can be used as the second interpreter for ophthalmologists to reduce the time and complexity of conventional screening methods. The quality of the images was enhanced, and the prospective hemorrhage locations were estimated in the preprocessing stage. Modified gamma correction adaptively illuminates fundus images by using gradient information to address the nonuniform brightness levels of images. The algorithm estimated the locations of potential candidates by using a Gaussian match filter, entropy thresholding, and mathematical morphology. The required objects were segmented using the regional diversity at estimated locations. The novel hemorrhage network is propounded for hemorrhage classification and compared with the renowned deep models. Two datasets benchmarked the model’s performance using sensitivity, specificity, precision, and accuracy metrics. Despite being the shallowest network, the proposed network marked competitive results than LeNet-5, AlexNet, ResNet50, and VGG-16. The hemorrhage network was assessed using training time and classification accuracy through synthetic experimentation. Results showed promising accuracy in the classification stage while significantly reducing training time. The research concluded that increasing deep network layers does not guarantee good results but rather increases training time. The suitable architecture of a deep model and its appropriate parameters are critical for obtaining excellent outcomes.

Diabetic retinopathy (DR) is one of the diseases that cause blindness globally. Untreated accumulation of fat and cholesterol may trigger atherosclerosis in the diabetic patient, which may obstruct blood vessels. Retinal fundus images are used as diagnostic tools to screen abnormalities linked to diseases that affect the eye. Blurriness and low contrast are major problems when segmenting retinal fundus images. This article proposes an algorithm to segment and detect hemorrhages in retinal fundus images. The proposed method first performs preprocessing on retinal fundus images. Then a novel smart windowing-based adaptive threshold is utilized to segment hemorrhages. Finally, conventional and hand-crafted features are extracted from each candidate and classified by a support vector machine. Two datasets are used to evaluate the algorithms. Precision rate (P), recall rate (R), and F1 score are used for quantitative evaluation of segmentation methods. Mean square error, peak signal to noise ratio, information entropy, and contrast are also used to evaluate preprocessing method. The proposed method achieves a high F1 score with 83.85% for the DIARETDB1 image dataset and 72.25% for the DIARETDB0 image dataset. The proposed algorithm adequately adapts when compared with conventional algorithms, hence will act as a tool for segmentation.

The infrastructure industry consumes natural resources and produces construction waste, which has a detrimental impact on the environment. To mitigate these adverse effects and reduce raw material consumption, waste materials can be repurposed to achieve sustainability. However, recycled materials deteriorate the intrinsic properties of concrete. A suitable ratio of natural resources and recycled aggregates can produce the desired compressive strength. Compiling sufficient data in civil engineering laboratories to make reliable conclusions is time-consuming and costly. Therefore, this research proposes a novel approach for predicting compressive strengths using limited data. The generative adversarial network was employed to generate synthetic data. Hybrid training, utilizing either conventional loss or heuristic loss, prevents the model from overfitting by adaptively adjusting the regularization term. Random noise from a multivariate normal distribution is embedded heuristically into the training samples to capture intricate data variations. Sensitivity analysis indicated that the size of recycled coarse aggregate and water are the most significant features, aligning with their correlations. Interestingly, superplasticizer, density of recycled coarse aggregate, and water absorption ratio of recycled coarse aggregate contributed significantly to predictions despite their low correlations. The propounded method outperforms random forest, support vector regression, artificial neural network, and adaptive boosting by scoring a mean squared error of 7.97, a root mean squared error of 2.82, a mean absolute error of 2.13, and a coefficient of determination of 0.96. These results suggest that the proposed technique can effectively contribute to sustainable construction practices by accurately predicting compressive strengths.

Diabetic retinopathy is a prevalent condition and a major public health concern due to its detrimental impact on eyesight. Diabetes is a root cause of its development and damages small blood vessels caused by prolonged high blood sugar levels. The degenerative consequences of diabetic retinopathy are irrevocable if not diagnosed in the early stages of its progression. This ailment triggers the development of retinal lesions, which can be identified for diagnosis and prognosis. However, lesion detection is challenging due to their similarity in intensity profiles to other retinal features, inconsistent sizes, and random locations. This research evaluates a custom deep learning network for classifying retinal images and compares it with the state-of-the-art classifiers. The novel preprocessing method is introduced to reduce the complexity of the diagnostic process and to enhance classification performance by adaptively enhancing images. Despite being a shallow network, the proposed model yields competitive results with an accuracy of 87.66% and an F1-score of 0.78. The evaluation metrics indicate that class imbalance affects the performance of the proposed model despite using the weighted cross-entropy loss. The future contribution will be the inclusion of generative adversarial networks for generating synthetic images to balance the dataset. This research aims to develop a robust computer-aided diagnostic system as a second interpreter for ophthalmologists during the diagnosis and prognosis stages.