Pneumonia is one of the leading causes of death in both infants and elderly people, with approximately 4 million deaths each year. It may be a virus, bacterial, or fungal, depending on the contagious pathogen that damages the lung’s tiny air sacs (alveoli). Patients with underlying disorders such as asthma, a weakened immune system, hospitalized babies, and older persons on ventilators are all at risk, particularly if pneumonia is not detected early. Despite the existing approaches for its diagnosis, low accuracy and efficiency require further research for more accurate systems. This study is a similar endeavor for the detection of pneumonia by the use of X-ray images. The dataset is preprocessed to make it suitable for transfer learning tasks. Different pre-trained convolutional neural network (CNN) variants are utilized, including VGG16, Inception-v3, and ResNet50. Ensembles are made by incorporating CNN with Inception-V3, VGG-16, and ResNet50. Besides the common evaluation metrics, the performance of the pre-trained and ensemble deep learning models is measured with Cohen’s kappa as well as the area under the curve (AUC). Experimental results show that Inception-V3 with CNN attained the highest accuracy and recall score of 99.29% and 99.73%, respectively.

Thyroid disease prediction has emerged as an important task recently. Despite existing approaches for its diagnosis, often the target is binary classification, the used datasets are small-sized and results are not validated either. Predominantly, existing approaches focus on model optimization and the feature engineering part is less investigated. To overcome these limitations, this study presents an approach that investigates feature engineering for machine learning and deep learning models. Forward feature selection, backward feature elimination, bidirectional feature elimination, and machine learning-based feature selection using extra tree classifiers are adopted. The proposed approach can predict Hashimoto’s thyroiditis (primary hypothyroid), binding protein (increased binding protein), autoimmune thyroiditis (compensated hypothyroid), and non-thyroidal syndrome (NTIS) (concurrent non-thyroidal illness). Extensive experiments show that the extra tree classifier-based selected feature yields the best results with 0.99 accuracy and an F1 score when used with the random forest classifier. Results suggest that the machine learning models are a better choice for thyroid disease detection regarding the provided accuracy and the computational complexity. K-fold cross-validation and performance comparison with existing studies corroborate the superior performance of the proposed approach.

Deep learning is used to address a wide range of challenging issues including large data analysis, image processing, object detection, and autonomous control. In the same way, deep learning techniques are also used to develop software and techniques that pose a danger to privacy, democracy, and national security. Fake content in the form of images and videos using digital manipulation with artificial intelligence (AI) approaches has become widespread during the past few years. Deepfakes, in the form of audio, images, and videos, have become a major concern during the past few years. Complemented by artificial intelligence, deepfakes swap the face of one person with the other and generate hyper-realistic videos. Accompanying the speed of social media, deepfakes can immediately reach millions of people and can be very dangerous to make fake news, hoaxes, and fraud. Besides the well-known movie stars, politicians have been victims of deepfakes in the past, especially US presidents Barak Obama and Donald Trump, however, the public at large can be the target of deepfakes. To overcome the challenge of deepfake identification and mitigate its impact, large efforts have been carried out to devise novel methods to detect face manipulation. This study also discusses how to counter the threats from deepfake technology and alleviate its impact. The outcomes recommend that despite a serious threat to society, business, and political institutions, they can be combated through appropriate policies, regulation, individual actions, training, and education. In addition, the evolution of technology is desired for deepfake identification, content authentication, and deepfake prevention. Different studies have performed deepfake detection using machine learning and deep learning techniques such as support vector machine, random forest, multilayer perceptron, k-nearest neighbors, convolutional neural networks with and without long short-term memory, and other similar models. This study aims to highlight the recent research in deepfake images and video detection, such as deepfake creation, various detection algorithms on self-made datasets, and existing benchmark datasets.

With rapid urbanization, high rates of industrialization, and inappropriate waste disposal, water quality has been substantially degraded during the past decade. So, water quality prediction, an essential element for a healthy society, has become a task of great significance to protecting the water environment. Existing approaches focus predominantly on either water quality or water consumption prediction, utilizing complex algorithms that reduce the accuracy of imbalanced datasets and increase computational complexity. This study proposes a simple architecture of neural networks which is more efficient and accurate and can work for predicting both water quality and water consumption. An artificial neural network (ANN) consisting of one hidden layer and a couple of dropout and activation layers is utilized in this regard. The approach is tested using two datasets for predicting water quality and water consumption. Results show a 0.96 accuracy for water quality prediction which is better than existing studies. A 0.99 $R^2$ score is obtained for water consumption prediction which is superior to existing state-of-the-art approaches.

Building energy consumption prediction has become an important research problem within the context of sustainable homes and smart cities. Data-driven approaches have been regarded as the most suitable for integration into smart houses. With the wide deployment of IoT sensors, the data generated from these sensors can be used for modeling and forecasting energy consumption patterns. Existing studies lag in prediction accuracy and various attributes of buildings are not very well studied. This study follows a data-driven approach in this regard. The novelty of the paper lies in the fact that an ensemble model is proposed, which provides higher performance regarding cooling and heating load prediction. Moreover, the influence of different features on heating and cooling load is investigated. Experiments are performed by considering different features such as glazing area, orientation, height, relative compactness, roof area, surface area, and wall area. Results indicate that relative compactness, surface area, and wall area play a significant role in selecting the appropriate cooling and heating load for a building. The proposed model achieves 0.999 $R^2$ for heating load prediction and 0.997 $R^2$ for cooling load prediction, which is superior to existing state-of-the-art models. The precise prediction of heating and cooling load, can help engineers design energy-efficient buildings, especially in the context of future smart homes.

One of the toughest biometrics and document forensics problems is confirming a signature’s authenticity and legal identity. A forgery may vary from a genuine signature by specific distortions. Therefore, it is necessary to continuously monitor crucial distinctions between real and forged signatures for secure work and economic growth, but this is particularly difficult in writer-independent tasks. We thus propose an innovative and sustainable writer-independent approach based on a Siamese neural network for offline signature verification. The Siamese network is a twin-like structure with shared weights and parameters. Similar and dissimilar images are exposed to this network, and the Euclidean distances between them are calculated. The distance is reduced for identical signatures, and the distance is increased for different signatures. Three datasets, namely GPDS, BHsig260 Hindi, and BHsig260 Bengali datasets, were tested in this work. The proposed model was analyzed by comparing the results of different parameters such as optimizers, batch size, and the number of epochs on all three datasets. The proposed Siamese neural network outperforms the GPDS synthetic dataset in the English language, with an accuracy of 92%. It also performs well for the Hindi and Bengali datasets while considering skilled forgeries.