Automatic activity recognition systems aim to capture the state of the user and its environment by exploiting heterogeneous sensors, and permit continuous monitoring of numerous physiological signals, where these sensors are attached to the subject's body. This can be immensely useful in healthcare applications, for automatic and intelligent daily activity monitoring for elderly people. In this paper, we present novel data analytic scheme for intelligent Human Activity Recognition (AR) using smartphone inertial sensors based on information theory based feature ranking algorithm and classifiers based on random forests, ensemble learning and lazy learning. Extensive experiments with a publicly available database1 of human activity with smart phone inertial sensors show that the proposed approach can indeed lead to development of intelligent and automatic real time human activity monitoring for eHealth application scenarios for elderly, disabled and people with special needs

Real estate appraisal is an important tool for evaluating property values when purchasing, selling, insuring, lending or taxing on residency properties. The traditional way to do real estate appraisal is to analyse recent sales data with basic information, such as bedrooms, bathrooms, land-size, and suburb to estimate house price prediction by comparing and selecting similar properties to the property that is being evaluated. Real estate agents are widely using this method for their clients to help them determine a price to list when selling a home or a price to offer when buying a home. However, the traditional method is very subjective and depends heavily on the experience and knowledge of real estate agents and two different agents might come up with different estimate prices. Today, machine learning and deep learning techniques provide an objective, advanced and robust option, making the joint analysis of tabular data combined with visual content possible. We are interested in estimating the real estate prices like real estate agents. In this paper, we examine to use deep learning combining with extreme Gradient Boosting (XGBoost) for real estate appraisal, by analysing historical sale records together with visual content, with online house pictures, and by scoring each image from an aesthetic point of view to make a house price prediction. Our experiment shows that an improvement in performance of house price prediction accuracy, with replacing the last output layer with XGBoost.

Malaria in the rural and remote regions of tropical countries remain a major public health challenge. Early diagnosis and prompt effective treatment are the basis for the management of malaria and for reducing malaria mortality and morbidity worldwide and the key to malaria elimination. While Rapid Diagnostic Test (RDT) remains the current mainstay testing malaria infections, it is usually used in conjunction with clinical findings and lab tests of blood films through Microscopy- the gold standard of malaria diagnosis. Recent reports suggest that the accuracy of RDTs could be compromised due to parasite antigen gene deletion(s), and the lack of expertise and high turnover time makes microscopy impractical to be used in rural and remote areas which impede the diagnosis and treatment of the disease. Delay in receiving treatment for uncomplicated malaria is reported to increase the risk of developing severe malaria and mortality. Thus, the need to develop advanced, faster, and smarter tools for malaria diagnosis is paramount, specially to reinforce the gold standard method, i.e., malaria microscopy which is a full-proof tool given the limitations be addressed. Deep learning-based methods have proven to provide human expert level performance on object detection/classification on image data. Such methods can be utilized for automation of repetitive task in assessing large number of microscope images of blood samples. In this paper, we propose a novel approach to improve the performance of deep learning models through consistent labelling of ground truth bounding box for the task of pathogen detection on microscope images of thick blood smears. Recommendations are made on the reliability and repeatability testing of the trained models. A custom deep learning architecture (YOLO-mp) is developed based on the design criteria of optimizing accuracy and speed of detection with minimal resources. The custom three-layered YOLO-mp-3l and four-layered YOLO-mp-4l models achieved the best mAP scores of 93.99 (@IoU=0.5) and 94.07 (@IoU=0.5), respectively outperforming standard YOLOv4 (mAP 92.56 @IoU=0.5) for detection of malaria pathogen on a public dataset of thick blood smear microscope images captured using phone camera. YOLO-mp-3l (BFLOPs =21.8, model size =24.5Mb) and YOLO-mp-4l (BFLOPs=24.477, model size =25.4Mb) outperformed standard YOLOv4 (BFLOPs=127.232, model size = 244Mb) in terms of computation and memory requirements proving them suitable to run on low resource devices.

Human Gait recognition is one of the most promising research areas at the moment. Gait is the style or manner of walking on foot. Gait recognition aims to identify individuals by the manner in which they walk. Existing Gait representations which capture both motion and appearance information are sensitive to changes in various covariate conditions such as carrying and clothing. In this paper, we propose a novel temporal representation of Gait using Pal and Pal Entropy (GPPE) for each cycle of the silhouettes. The Principal component analysis is applied to each of the features extracted to create a feature matrix. Support Vector Machine (SVM) is used for training and testing of individuals by the proposed method. Extensive experiments on the Treadmill dataset and the CASIA datasets A, B, C have been carried out to demonstrate the effectiveness of the proposed representation of Gait.

In this paper we present the details of the multilevel liveness verification (MLLV) framework proposed for realizing a secure face-voice biometric authentication system that can thwart different types of audio and video replay attacks. The proposed MLLV framework based on novel feature extraction and multimodal fusion approaches, uncovers the static and dynamic relationship between voice and face information from speaking faces, and allows multiple levels of security. Experiments with three different speaking corpora VidTIMIT, UCBN and AVOZES shows a significant improvement in system performance in terms of DET curves and equal error rates (EER) for different types of replay and synthesis attacks.