Benny Lo | Imperial College London (original) (raw)

Papers by Benny Lo

As electronic devices get smaller and more powerful, they are finding new uses in monitoring huma... more As electronic devices get smaller and more powerful, they are finding new uses in monitoring human activity. In this article, Dr Benny Lo of Imperial College London describes a project to develop sensors with uses in medicine, sport and electronic gaming.

IEEE Journal of Biomedical and Health Informatics, Mar 1, 2022

Accurate lower-limb pose estimation is a prerequisite of skeleton based pathological gait analysi... more Accurate lower-limb pose estimation is a prerequisite of skeleton based pathological gait analysis. To achieve this goal in free-living environments for long-term monitoring, single depth sensor has been proposed in research. However, the depth map acquired from a single viewpoint encodes only partial geometric information of the lower limbs and exhibits large variations across different viewpoints. Existing off-the-shelf three-dimensional (3D) pose tracking algorithms and public datasets for depth based human pose estimation are mainly targeted at activity recognition applications. They are relatively insensitive to skeleton estimation accuracy, especially at the foot segments. Furthermore, acquiring ground truth skeleton data for detailed biomechanics analysis also requires considerable efforts. To address these issues, we propose a novel cross-domain self-supervised complete geometric representation learning framework, with knowledge transfer from the unlabelled synthetic point clouds of full lower-limb surfaces. The proposed method can significantly reduce the number of ground truth skeletons (with only 1%) in the training phase, meanwhile ensuring accurate and precise pose estimation and capturing discriminative features across different pathological gait patterns compared to other methods.

Wearable inertial sensors have demonstrated their potential to screen for various neuropathies an... more Wearable inertial sensors have demonstrated their potential to screen for various neuropathies and neurological disorders. Most such research has been based on classification algorithms that differentiate the control group from the pathological group, using biomarkers extracted from wearable data as predictors. However, such methods often lack quantitative evaluation of how much information provided by the wearable biomarkers contributes to the overall prediction. Despite promising results from internal cross validation, their utility in clinical practice remains unclear. In this paper, we highlight in a case study-early screening for diabetic peripheral neuropathy (DPN)-evaluation methods for quantifying the contribution of wearable inertial sensors. Using a quick-to-deploy wearable sensor system, we collected 106 in-hospital diabetic patients' gait data and developed logistic regression models to predict the risk of a diabetic patient having DPN. Adopting various metrics, we evaluated the discriminative information added by gait biomarkers and how much it improved screening. The results show that the proposed wearable system added useful information significantly (p<3e-4) to the existing clinical standards, and boosted the C-index significantly (p<0.02) from 0.75 to 0.84, surpassing the current survey-based screening methods used in clinics.

With increasing popularity of wearable and implantable technologies for medical applications, the... more With increasing popularity of wearable and implantable technologies for medical applications, there is a growing concern on the security and data protection of the on-body Internet-of-Things (IoT) devices. As a solution, cryptographic system is often adopted to encrypt the data, and Random Number Generator (RNG) is of vital importance to such system. This paper proposes a new random number generation method for securing on-body IoT devices based on temporal signal variations of the outputs of the Inertial Measurement Units (IMU) worn by the users while walking. As most new wearable and implantable devices have built-in IMUs and walking gait signals can be extracted from these body sensors, this method can be applied and integrated into the cryptographic systems of these new devices. To generate the random numbers, this method divides IMU signals into gait cycles and generates bits by comparing energy differences between the sensor signals in a gait cycle and the averaged IMU signals in multiple gait cycles. The generated bits are then re-indexed in descending order by the absolute values of the associated energy differences to further randomise the data and generate high-entropy random numbers. Two datasets were used in the studies to generate random numbers, where were rigorously tested and passed four well-known randomness test suites, namely NIST-STS, ENT, Dieharder, and RaBiGeTe.

Blood flow and perfusion monitoring are critical appraisal to ensure survival of tissue flap afte... more Blood flow and perfusion monitoring are critical appraisal to ensure survival of tissue flap after reconstructive surgery. Many techniques have been developed over the years: from optical to chemical, invasive or not, they all have limitations in their price, risks and adaptiveness to the patient. A wireless wearable self-calibrated device, based on near infrared spectroscopy (NIRS) was developed for blood flow and perfusion monitoring contingent on tissue oxygen saturation (StO 2). The use of such device is particularly relevant in the case of free flap myocutaneous reconstructive surgery; postoperative monitoring of the flap is crucial for a prompt intervention in case of thrombosis. Although failure rate is low, the rate of additional surgery following anastomosis problem is about 50%. NIRS has shown promising results for the monitoring of free flap, however lack of adaptation to its environment (ambient light) and users (body mass index (BMI), skin tone, alcohol and smoking habits or physical activity level) hinders the practical use of this technique. To overcome those limitations, a self-calibrated approach is introduced. Tested with ischaemia and cold water experiments on healthy subjects of different skin tones, its ability to personalize its calibration is demonstrated. Furthermore, using a vascular phantom, it is also able to detect pulses, differentiate venous and arterial colouredlike fluids with distinct clusters and detect significant changes in simulated partial venous occlusion. Placed in the trained classifier, partial occlusion data showed similar results between predicted and true classification. Further analysis from partial occlusion data showed that distinct clusters for 75% and 100% occlusion emerged.

IEEE Journal of Biomedical and Health Informatics, 2015

This is a repository copy of Imitation of dynamic walking with BSN for humanoid robot.

Journal of Biomedical Optics, Jun 19, 2019

Free tissue transfer (FTT) surgery for breast reconstruction following mastectomy has become a ro... more Free tissue transfer (FTT) surgery for breast reconstruction following mastectomy has become a routine operation with high success rates. Although failure is low, it can have a devastating impact on patient recovery, prognosis, and psychological well-being. Continuous and objective monitoring of tissue oxygen saturation (StO 2) has been shown to reduce failure rates through rapid detection time of postoperative vascular complications. We have developed a pervasive wearable wireless device that employs near-infrared spectroscopy (NIRS) to continuously monitor FTT via StO 2 measurement. Previously tested on different models, the results of a clinical study are introduced. Our goal for the study is to demonstrate that the developed device can reliably detect StO 2 variations in a clinical setting: 14 patients were recruited. Advanced data analysis was performed on the StO 2 variations, the relative StO 2 gradient change, and the classification of the StO 2 within different clusters of blood occlusion level (from 0% to 100% at 25% step) based on previous studies made on a vascular phantom and animals. The outcomes of the clinical study concur with previous experimental results and the expected biological responses. This suggests that the device is able to correctly detect perfusion changes and provide real-time assessment on the viability of the FTT in a clinical setting.

Information Fusion, May 1, 2018

Gait analysis plays an important role in several conditions, including the rehabilitation of pati... more Gait analysis plays an important role in several conditions, including the rehabilitation of patients with orthopaedic and the monitoring of neurological conditions, mental health problems and the well-being of elderly subjects. It also constitutes an index of good posture and thus it can be used to prevent injuries in athletes and monitor mental health in typical subjects. Usually, accurate gait analysis is based on the measurement of ankle dynamics and ground reaction forces. Therefore, it requires expensive multi-camera systems and pressure sensors, which cannot be easily employed in a free-living environment. We propose a fusion framework that uses an ear worn activity recognition (e-AR) sensor and a single video camera to estimate foot angle during key gait events. To this end we use canonical correlation analysis with a fused-lasso penalty in a two-steps approach that firstly learns a model of the timing distribution of ground reaction forces based on eAR signal only and subsequently models the eversion/inversion as well as the dorsiflexion of the ankle based on the combined features of eAR sensor and the video. The results show that incorporating invariant features of angular ankle information from the video recordings improves the estimation of the foot progression angle, substantially.

IEEE Sensors Journal, 2015

This is a repository copy of Wearable Sensing for Solid Biomechanics: A Review.

IEEE robotics and automation letters, Oct 1, 2022

In this paper, we address the problem of forecasting the trajectory of an egocentric camera weare... more In this paper, we address the problem of forecasting the trajectory of an egocentric camera wearer (ego-person) in crowded spaces. The trajectory forecasting ability learned from the data of different camera wearers walking around in the real world can be transferred to assist visually impaired people in navigation, as well as to instill human navigation behaviours in mobile robots, enabling better human-robot interactions. To this end, a novel egocentric human trajectory forecasting dataset was constructed, containing real trajectories of people navigating in crowded spaces wearing a camera, as well as extracted rich contextual data. We extract and utilize three different modalities to forecast the trajectory of the camera wearer, i.e., his/her past trajectory, the past trajectories of nearby people, and the environment such as the scene semantics or the depth of the scene. A Transformer-based encoder-decoder neural network model, integrated with a novel cascaded cross-attention mechanism that fuses multiple modalities, has been designed to predict the future trajectory of the camera wearer. Extensive experiments have been conducted, with results showing that our model outperforms the state-of-the-art methods in egocentric human trajectory forecasting. Index Terms-Human trajectory forecasting, egocentric vision, multi-modal learning I. INTRODUCTION E GOCENTRIC perception has a pivotal role in agent navigation, whether it is a robot, a human, or an autonomous vehicle. With on-board cameras, forecasting the trajectory of an ego-vehicle, a mobile robot, or their surrounding agents has been actively studied in the fields of autonomous driving and robot navigation to enable better motion planning and to reduce the chances of collision [1], [2], [3]. This provides a new insight for blind navigation [4], [5], [6]. With a wearable camera being the proxy of human eyes and an algorithm

Tremor is a neurological disorder which can significantly impede the daily functions of patients.... more Tremor is a neurological disorder which can significantly impede the daily functions of patients. The available treatments for patients with tremor are mainly pharmacotherapy and neurosurgery, but these treatments often have side effects. A wearable exoskeleton can potentially provide the assistance needed for patients with Parkinsonian or essential tremor to carry out daily activities and enable independent living. This paper presents the design and development of a 3D printed lightweight tremor suppression wearable exoskeleton. One of the major technical challenges for wearable robot is to maintain long battery life meanwhile miniature in size for practical use. This paper proposes an integrated approach where context aware Body Sensor Networks (BSN) sensors are incorporated to characterize voluntary and tremor movement, and detect activities of daily life (ADL). With the contextual information, the system can determine the intention of the user, optimize its control and minimize its power consumption by providing the necessary suppression only when needed. The preliminary result has shown that the wearable robot prototype can reduce the amplitude of simulated tremor by around 77%, and accurately identify different ADL with accuracy above 70%.

IEEE Journal of Biomedical and Health Informatics, May 1, 2019

As the popularity of wearable and the implantable body sensor network (BSN) devices increases, th... more As the popularity of wearable and the implantable body sensor network (BSN) devices increases, there is a growing concern regarding the data security of such power-constrained miniaturized medical devices. With limited computational power, BSN devices are often not able to provide strong security mechanisms to protect sensitive personal and health information, such as one's physiological data. Consequently, many new methods of securing wireless body area networks have been proposed recently. One effective solution is the biometric cryptosystem (BCS) approach. BCS exploits physiological and behavioral biometric traits, including face, iris, fingerprints, electrocardiogram, and photoplethysmography. In this paper, we propose a new BCS approach for securing wireless communications for wearable and implantable healthcare devices using gait signal energy variations and an artificial neural network framework. By simultaneously extracting similar features from BSN sensors using our approach, binary keys can be generated on demand without user intervention. Through an extensive analysis on our BCS approach using a gait dataset, the results have shown that the binary keys generated using our approach have high entropy for all subjects. The keys can pass both National Institute of Standards and Technology and Dieharder statistical tests with high efficiency. The experimental results also show the robustness of the proposed approach in terms of the similarity of intraclass keys and the discriminability of the interclass keys.

Human Activity Recognition provides valuable contextual information for wellbeing, healthcare, an... more Human Activity Recognition provides valuable contextual information for wellbeing, healthcare, and sport applications. Over the past decades, many machine learning approaches have been proposed to identify activities from inertial sensor data for specific applications. Most methods, however, are designed for offline processing rather than processing on the sensor node. In this paper, a human activity recognition technique based on a deep learning methodology is designed to enable accurate and real-time classification for low-power wearable devices. To obtain invariance against changes in sensor orientation, sensor placement, and in sensor acquisition rates, we design a feature generation process that is applied to the spectral domain of the inertial data. Specifically, the proposed method uses sums of temporal convolutions of the transformed input. Accuracy of the proposed approach is evaluated against the current state-of-the-art methods using both laboratory and real world activity datasets. A systematic analysis of the feature generation parameters and a comparison of activity recognition computation times on mobile devices and sensor nodes are also presented.

Blood Pressure (BP) is a crucial vital sign taken into consideration for the general assessment o... more Blood Pressure (BP) is a crucial vital sign taken into consideration for the general assessment of patient's condition: patients with hypertension or hypotension are advised to record their BP routinely. Particularly, hypertension is emphasized by stress, diabetic neuropathy and coronary heart diseases and could lead to stroke. Therefore, routine and long-term monitoring can enable early detection of symptoms and prevent life-threatening events. The gold standard method for measuring BP is the use of a stethoscope and sphygmomanometer to detect systolic and diastolic pressures. However, only discrete measurements are taken. To enable pervasive and continuous monitoring of BP, recent methods have been proposed: pulse arrival time (PAT) or PAT difference (PATD) between different body parts are based on the combination of electrocardiogram (ECG) and photoplethysmography (PPG) sensors. Nevertheless, this technique could be quite obtrusive as in addition to at least two contacts/electrodes to measure the differential voltage across the left arm/leg/chest and the right arm/leg/chest, ECG measurements are easily corrupted by motion artefacts. Although such devices are small, wearable and relatively convenient to use, most devices are not designed for continuous BP measurements. This paper introduces a novel PPG-based pervasive sensing platform for continuous measurements of BP. Based on the principle of using PAT to estimate BP, two PPG sensors are used to measure the PATD between the earlobe and the wrist to measure BP. The device is compared with a gold standard PPG sensor and validation of the concept is conducted with a preliminary study involving 9 healthy subjects. Results show that the mean BP and PATD are correlated with a 0.3 factor. This preliminary study shows the feasibility of continuous monitoring of BP using a pair of PPG placed on the ear lobe and wrist with PATD measurements is possible.

Extracting human attributes, such as gender and age, from biometrics have received much attention... more Extracting human attributes, such as gender and age, from biometrics have received much attention in recent years. Gender and age recognition can provide crucial information for applications such as security, healthcare, and gaming. In this paper, a novel deep learning approach on gender and age recognition using a single inertial sensors is proposed. The proposed approach is tested using the largest available inertial sensor-based gait database with data collected from more than 700 subjects. To demonstrate the robustness and effectiveness of the proposed approach, 10 trials of inter-subject Monte-Carlo cross validation were conducted, and the results show that the proposed approach can achieve an averaged accuracy of 86.6%±2.4% for distinguishing two age groups: teen and adult, and recognizing gender with averaged accuracies of 88.6%±2.5% and 73.9%±2.8% for adults and teens respectively.

With increasing popularity of wearable and Body Sensor Networks technologies, there is a growing ... more With increasing popularity of wearable and Body Sensor Networks technologies, there is a growing concern on the security and data protection of such low-power pervasive devices. With very limited computational power, BSN sensors often cannot provide the necessary data protection to collect and process sensitive personal information. Since conventional network security schemes are too computationally demanding for miniaturized BSN sensors, new methods of securing BSNs have proposed, in which Biometric Cryptosystem (BCS) appears to be an effective solution. With regards to BCS security solutions, physiological traits, such as an individual's face, iris, fingerprint, electrocardiogram (ECG), and photoplethysmogram (PPG) have been widely exploited. However, behavioural traits such as gait are rarely studied. In this paper, a novel lightweight symmetric key generation scheme based on the timing information of gait is proposed. By extracting similar timing information from gait acceleration signals simultaneously from body worn sensors, symmetric keys can be generated on all the sensor nodes at the same time. Based on the characteristics of generated keys and BSNs, a fuzzy commitment based key distribution scheme is also developed to distribute the keys amongst the sensor nodes.

Dyscalculia is a learning difficulty hindering fundamental arithmetical competence. Children with... more Dyscalculia is a learning difficulty hindering fundamental arithmetical competence. Children with dyscalculia often have difficulties in engaging in lessons taught with traditional teaching methods. In contrast, an educational game is an attractive alternative. Recent educational studies have shown that gestures could have a positive impact in learning. With the recent development of low cost wearable sensors, a gesture based educational game could be used as a tool to improve the learning outcomes particularly for children with dyscalculia. In this paper, two generic gesture recognition methods are proposed for developing an interactive educational game with wearable inertial sensors. The first method is a multilayered perceptron classifier based on the accelerometer and gyroscope readings to recognize hand gestures. As gyroscope is more power demanding and not all low-cost wearable device has a gyroscope, we have simplified the method using a nearest centroid classifier for classifying hand gestures with only the accelerometer readings. The method has been integrated into open-source educational games. Experimental results based on 5 subjects have demonstrated the accuracy of inertial sensor based hand gesture recognitions. The results have shown that both methods can recognize 15 different hand gestures with the accuracy over 93%.