Brain tumor is a deadly neurological disease caused by an abnormal and uncontrollable growth of cells inside the brain or skull. The mortality ratio of patients suffering from this disease is growing gradually. Analysing Magnetic Resonance Images (MRIs) manually is inadequate for efficient and accurate brain tumor diagnosis. An early diagnosis of the disease can activate a timely treatment consequently elevating the survival ratio of the patients. Modern brain imaging methodologies have augmented the detection ratio of brain tumor. In the past few years, a lot of research has been carried out for computer-aided diagnosis of human brain tumor to achieve 100% diagnosis accuracy. The focus of this research is on early diagnosis of brain tumor via Convolution Neural Network (CNN) to enhance state-of-the-art diagnosis accuracy. The proposed CNN is trained on a benchmark dataset, BR35H, containing brain tumor MRIs. The performance and sustainability of the model is evaluated on six different datasets, i.e., BMI-I, BTI, BMI-II, BTS, BMI-III, and BD-BT. To improve the performance of the model and to make it sustainable for totally unseen data, different geometric data augmentation techniques, along with statistical standardization, are employed. The proposed CNN-based CAD system for brain tumor diagnosis performs better than other systems by achieving an average accuracy of around 98.8% and a specificity of around 0.99. It also reveals 100% correct diagnosis for two brain MRI datasets, i.e., BTS and BD-BT. The performance of the proposed system is also compared with the other existing systems, and the analysis reveals that the proposed system outperforms all of them.

Alzheimer’s disease (AD) is a slow neurological disorder that destroys the thought process, and consciousness, of a human. It directly affects the development of mental ability and neurocognitive functionality. The number of patients with Alzheimer’s disease is increasing day by day, especially in old aged people, who are above 60 years of age, and, gradually, it becomes cause of their death. In this research, we discuss the segmentation and classification of the Magnetic resonance imaging (MRI) of Alzheimer’s disease, through the concept of transfer learning and customizing of the convolutional neural network (CNN) by specifically using images that are segmented by the Gray Matter (GM) of the brain. Instead of training and computing the proposed model accuracy from the start, we used a pre-trained deep learning model as our base model, and, after that, transfer learning was applied. The accuracy of the proposed model was tested over a different number of epochs, 10, 25, and 50. The overall accuracy of the proposed model was 97.84%.

Internet of things (IoT) and machine learning based systems incorporating smart wearable technology are rapidly evolving to monitor and manage healthcare and physical activities. This paper is focused on the proposition of a fog-centric wireless, real-time, smart wearable and IoT-based framework for ubiquitous health and fitness analysis in a smart gym environment. The proposed framework aims to aid in the health and fitness industry based on body vitals, body movement and health related data. The framework is expected to assist athletes, trainers and physicians with the interpretation of multiple physical signs and raise alerts in case of any health hazard. We proposed a method to collect and analyze exercise specific data which can be used to measure exercise intensity and its benefit to athlete's health and serve as recommendation system for upcoming athletes. We determined the validity of the proposed framework by giving a six weeks workout plan with six days a week for workout activity targeting all muscles followed by one day for recovery. We recorded the electrocardiogram, heart rate, heart rate variability, breath rate, and determined athlete's movement using a 3D-acceleration. The collected data in the research is used in two modules. A Health zone module implemented on body vitals data which categorizes athlete's health state into various categories. Hzone module is responsible for health hazards identification and alarming. Outstandingly, the Hzone module is able to identify an athlete's physical state with 97% accuracy. A gym activity recognition (GAR) module is implemented to recognize workout activity in real-time using body movements and body vitals data. The purpose of the GAR module is to collect and analyze exercise specific data. The GAR module achieved an accuracy of above 89% on athlete independent model based on muscle group.

Automatic tracking and quantification of exercises not only helps in motivating people but also contributes towards improving health conditions. Weight training, in addition to aerobic exercises, is an important component of a balanced exercise program. Excellent trackers are available for aerobic exercises but, in contrast, tracking free weight exercises is still performed manually. This study presents the details of our data acquisition effort using a single chest-mounted tri-axial accelerometer, followed by a novel method for the recognition of a wide range of gym-based free weight exercises. Exercises are recognized using LSTM neural networks and the reported results confirm the feasibility of the proposed approach. We train and test several LSTM-based gym exercise recognition models. More specifically, in one set of experiments, we experiment with separate models, one for each muscle group. In another experiment, we develop a universal model for all exercises. We believe that the promising results will potentially contribute to the vision of an automated system for comprehensive monitoring and analysis of gym-based exercises and create a new experience for exercising by freeing the exerciser from manual record-keeping.

In recent times, there has been a huge increase in the average number of cases of skin cancer per year, which sometimes become life threatening for humans. Early detection of various skin diseases through automated detection techniques plays a crucial role. However, the presence of numerous artefacts makes this task challenging. Dermoscopic images exhibit various variations, including hair artefacts, markers, and ill-defined boundaries. These artefacts make automatic analysis of skin lesion quite a difficult task. To address these issues, it is essential to have an accurate and efficient automated method which will delineate a skin lesion from the rest of the image. Unfortunately, due to the presence of several types of skin artefacts, there is no such thresholding method that can provide a sufficient segmentation result for every type of skin lesion. To overcome this limitation, an ensemble-based method is proposed that selects the optimal thresholding based on an objective function. A group of state-of-the-art different thresholding methods such as Otsu, Kapur, Harris hawk, and grey level are used. The proposed method obtained superior results (dice score = 0.89 with p-value ≤ 0.05) as compared to other state-of-the-art methods (Otsu = 0.79, Kapur = 0.80, Harris hawk = 0.60, grey level = 0.69, active contour model = 0.72). The experiments conducted in this study utilize the ISIC 2016 dataset, which is publicly available and specifically designed for skin-related research. Accurate segmentation will help in the early detection of many skin diseases.

Stroke is the second leading cause of death and disability worldwide, with ischemic stroke as the most common type. The preferred diagnostic procedure at the acute stage is the acquisition of multi-parametric magnetic resonance imaging (MRI). This type of imaging not only detects and locates the stroke lesion, but also provides the blood flow dynamics that helps clinicians in assessing the risks and benefits of reperfusion therapies. However, evaluating the outcome of these risky therapies beforehand is a complicated task due to the variability of lesion location, size, shape, and cerebral hemodynamics involved. Though the fully automated model for predicting treatment outcomes using multi-parametric imaging would be highly valuable in clinical settings, MRI datasets acquired at the acute stage are mostly scarce and suffer high class imbalance. In this paper, parallel multi-parametric feature embedded siamese network (PMFE-SN) is proposed that can learn with few samples and can handle skewness in multi-parametric MRI data. Moreover, five suitable evaluation metrics that are insensitive to imbalance are defined for this problem. The results show that PMFE-SN not only outperforms other state-of-the-art techniques in all these metrics but also can predict the class with a small number of samples, as well as the class with high number of samples. An accuracy of 0.67 on leave one cross out testing has been achieved with only two samples (minority class) for training and accuracy of 0.61 with the highest number of samples (majority class). In comparison, state-of-the-art using hand crafted features has 0 accuracy for minority class and 0.33 accuracy for majority class.