The success of deep machine learning (DML) models in gaming and robotics has increased its trial in clinical and public healthcare solutions. In applying DML to healthcare problems, a special challenge of inadequate electrical energy and computing resources exists in regional and developing areas of the world. In this paper, we evaluate and report the computational and predictive performance design trade-offs for four candidate deep learning models that can be deployed for rapid malaria case finding. The goal is to maximise malaria detection accuracy while reducing computing resource and energy consumption. Based on our experimental results using a blood smear malaria test data set, the quantised versions of Basic Convolutional Neural Network (B-CNN) and MobileNetV2 have better malaria detection performance (up to 99% recall), lower memory usage (2MB 8-bit quantised model) and shorter inference time (33–95 microseconds on mobile phones) than VGG-19 fine-tuned and quantised models. Hence, we have implemented MobileNetV2 in our mobile application as it has even a lower memory requirement than B-CNN. This work will help to counter the negative effects of COVID-19 on the previous successes towards global malaria elimination.

Efficient, adaptive, locomotor function is critically important for maintaining our health and independence, but falls-related injuries when walking are a significant risk factor, particularly for more vulnerable populations such as older people and post-stroke individuals. Tripping is the leading cause of falls, and the swing-phase event Minimum Foot Clearance (MFC) is recognised as the key biomechanical determinant of tripping probability. MFC is defined as the minimum swing foot clearance, which is seen approximately mid-swing, and it is routinely measured in gait biomechanics laboratories using precise, high-speed, camera-based 3D motion capture systems. For practical intervention strategies designed to predict, and possibly assist, swing foot trajectory to prevent tripping, identification of the MFC event is essential; however, no technique is currently available to determine MFC timing in real-life settings outside the laboratory. One strategy has been to use wearable sensors, such as Inertial Measurement Units (IMUs), but these data are limited to primarily providing only tri-axial linear acceleration and angular velocity. The aim of this study was to develop Machine Learning (ML) algorithms to predict MFC timing based on the preceding toe-off gait event. The ML algorithms were trained using 13 young adults’ foot trajectory data recorded from an Optotrak 3D motion capture system. A Deep Learning configuration was developed based on a Recurrent Neural Network with a Long Short-Term Memory (LSTM) architecture and Huber loss-functions to minimise MFC-timing prediction error. We succeeded in predicting MFC timing from toe-off characteristics with a mean absolute error of 0.07 s. Although further algorithm training using population-specific inputs are needed. The ML algorithms designed here can be used for real-time actuation of wearable active devices to increase foot clearance at critical MFC and reduce devastating tripping falls. Further developments in ML-guided actuation for active exoskeletons could prove highly effective in developing technologies to reduce tripping-related falls across a range of gait impaired populations.

Recent advances in biomedical sensors, data acquisition techniques, microelectronics and wireless communication systems opened up the use of wearable technology for ehealth monitoring. We introduce a galvanic coupled intrabody communication for monitoring human body hydration. Studies in hydration provide the information necessary for understanding the desired fluid levels for optimal performance of the body’s physiological and metabolic processes during exercise and activities of daily living. Current measurement techniques are mostly suitable for laboratory purposes due to their complexity and technical requirements. Less technical methods such as urine color observation and skin turgor testing are subjective and cannot be integrated into a wearable device. Bioelectrical impedance methods are popular but mostly used for estimating total body water with limited accuracy and sensitive to 800 mL–1000 mL change in body fluid levels. We introduce a non-intrusive and simple method of tracking hydration rates that can detect up to 1.30 dB reduction in attenuation when as little as 100 mL of water is consumed. Our results show that galvanic coupled intrabody signal propagation can provide qualitative hydration and dehydration rates in line with changes in an individual’s urine specific gravity and body mass. The real-time changes in galvanic coupled intrabody signal attenuation can be integrated into wearable electronic devices to evaluate body fluid levels on a particular area of interest and can aid diagnosis and treatment of fluid disorders such as lymphoedema.

The study of human body hydration is increasingly leading to new practical applications, including online assessment techniques for whole body water level and novel techniques for real time assessment methods as well as characterization for fitness and exercise performance. In this review, we will discuss the different techniques for assessing hydration from electrical properties of tissues and their components and the biological relations between tissues. This will be done mainly in the context of engineering while highlighting some applications in medicine, mobile health and sports.

Lymphoedema is a disease associated with abnormal functioning of the lymph that leads to swelling of the body due to accumulation of tissue fluid on the affected area. Tissue fluid contains ions and electrolytes that affect electrical conductivity. The flow of tissue fluid helps to distribute vital nutrients and other important elements necessary for healthy living. When tissue fluid is stagnated, a high concentration of electrolytes accumulate on the affected area, which in turn affects an electrical signal passing through that area to be minimally attenuated in relation to a free-flowing fluid. We demonstrate that a galvanic coupled signal propagating along a lymphoedema affected limb could capture these changes by the amount of attenuation the propagating signal experiences in time. Our results show that average rate of signal attenuation on a lymphoedema affected part of the body could be as slow as 0.16 dB/min, while the rate of signal attenuation on a healthy part is as high as 1.83 dB/min. This means that fluid accumulation could slow down the exchange of body electrolytes up to twice less the rate on an unaffected contralateral part of the body. Monitoring these changes by observing the average rate of change of a galvanic coupled signal attenuation on the affected body part can be used for diagnosing early developments of oedema in the body and for evaluating recovery in response to treatment procedures.