Search

This paper presents a passive exoskeleton for the lower limb with hip and knee joints for walking assistance. The exoskeleton is designed with built-in spring mechanisms at the hip and knee joints to account for the gravity-balanced human leg during the gait cycle. The tension force generated by the internal springs is transformed into balanced torques at the hip and knee joints to counteract the effects of gravity by a set of mating gears. A compact layout and minimal protrusion created by such a design enhance the exoskeleton's safety and user acceptance. In this research, the working principle and design methodology for gravity compensation during the gait cycle is described. An exoskeleton prototype was created by designing and installing all the mechanical components inside the frame in the form of linkages at the thigh and shank, and early tests on healthy volunteers confirmed the exoskeleton's utility. The results show that the required torque of the passive exoskeleton mostly depends upon the tension force generated by the spring and a significant torque reduction was observed when performing the gait cycle at a slower speed. [ABSTRACT FROM AUTHOR]

Person identification based on human action recognition is a dynamic field that combines computer vision, deep learning, and motion analysis to identify and authenticate individuals based on their actions or movements. This technology finds applications in various domains, including security, surveillance, healthcare, and human-computer interaction. In this comprehensive overview, we will delve into the key components, methods, and models used in neural networks for person identification based on human action recognition. An analysis of algorithms working on the basis of these models for personal identification is presented. Also, currently, methods of evaluating and recognizing and identifying human behavior through video images are rapidly developing. Intelligent analysis and processing of video data for personal identification is one of the promising, fastest growing research areas and is widely used in various fields of human activity. In particular, it can be used to solve problems such as video surveillance for security and access to facilities for various purposes (security systems, control systems), fire protection systems, navigation, quality and quantity control of manufactured products, and many videosurveillance. This system helps to catch criminals at airports, railway stations and seaports. [ABSTRACT FROM AUTHOR]

Physical disabilities cause significant distress in people's daily routine, especially for leg amputees as their movement is restricted. The civilized society has the responsibility to provide them with better prosthetics so they can live a normal life. Previously, prosthetic legs were developed for lower leg amputees. Today's electronic prosthesis provides a wide range of mobility compared to a mechanical prosthesis. Powered prosthetics are quite expensive and hence not widely used. We have proposed a low-cost control system above-knee powered prosthetics leg that is reliable, and the complexity of the model is less. The prostheses works by taking input from a sensor placed in the model and six FSR402 sensor and an IMU sensor that record force muscle activity of the thigh during variation of leg movement. The value of motion of the joint knee angle is determined by sensors. In this paper, we are discussing and comparing potential deep learning control system namely artificial neural network (ANN) as baseline and recurrent neural network-long short term memory (RNN-LSTM) to predict human gait cycle. A multi-layer perceptron (MLP) method is implemented. In general, network architecture consists of input layer which is represents by six inputs of the FSR402 sensor and an IMU sensor, fully connected layers, and an output layer as joint knee angle. As the result model of ANN as baseline has metric value MAE and R squared are 6.21 and 68.7% respectively whereas model of RNN-LSTM has metric value MAE and R squared are 4.99 and 96.9% respectively. The result indicates the RNN-LSTM model is most likely to perform fewer errors based on the dataset. RNN-LSTM outperforms the task with a greater value compared to the ANN model as the baseline. This present study suggests that deep learning with the recurrent neural network-long short term memory (RNN-LSTM) is suitable for the prediction of human gait cycle movement from the FSR402 and an IMU signal in the overall walking task. [ABSTRACT FROM AUTHOR]

This research focuses on determining stresses in the knee-ankle-foot-orthosis as a consequence of the effect of vibration throughout the gait cycle for a patient wearing a knee-ankle-foot-orthosis and comparing it with the value of stresses after changing the material selection in the band from aluminum to polypropylene. The experimental part involved measuring the interface pressure between the orthosis and the leg. In addition, an accelerometer is used to measure the acceleration that results from the motion of the defective limb. Results show the maximum stress value with aluminum orthosis at bar contact with Gracilis muscle is reduced by a present 38.92%, where the stresses values in orthosis with polypropylene band are lower than orthosis with the aluminum band. [ABSTRACT FROM AUTHOR]

Walking could be a motion and it's totally different from one person to another. Walking is one in every of life science that helps to see the identity of an individual while not his data and from an excellent distance during this study we tend to planned to extract the dynamic characteristics looking at the characteristics of the skeleton and therefore the angles of the correct elbow, left elbow, right knee and left knee and changing it to a curve. The video was taken by a digital camera, and the video was inserted into the program, which converts it from second to 3D and exploits the temporal and special changes of the walking cycle. [ABSTRACT FROM AUTHOR]

Parkinson's disease is a neurodegenerative disorder which degrades the quality of life of the affected. Caused due to the reduction in dopamine production in the body, PD causes speech impairments, gait problems, tremors, fatigue, depression in the patients. Speech impairments include monotonous speech, hoarse or rough voice, slurring, while gait problems include short steps, hypokinesia, and instability in posture amongst others. Even with the advancements in medicine, there is no cure for PD nor a systematic procedure to detect it. Parkinson's disease is diagnosed by trained neurologists using extensive and invasive tests which are time consuming and expensive. Therefore, extensive research is being undertaken in developing and training machine learning models to aid the PD detection process so that PD can be detected as early as possible in patients ensuring quality treatment and better quality of life. Several modalities are used as training and testing data for the machine learning models including voice signals, gait signals, hand writing and MRI images. In this paper, literature review has been conducted on research undertaken in PD detection focusing on two biomarkers - speech and gait. Gait and Speech abnormalities are amongst the early manifestations of Parkinson's disease, therefore early detection of PD can be aided by using features extracted from these signals. Furthermore, they are non-intrusive and painless methods, thus making the feature extraction and diagnostic process painless and less complex. [ABSTRACT FROM AUTHOR]

The article presents the results of researches of changes in human gait based on the results of measurements using the accelerometric sensor of a mobile phone. The researches were carried out for 6 months. The paper describes the features of measuring gait parameters using a mobile phone, and presents the factors influencing the results of assessing gait parameters. Dependences of gait changes on the type of clothing and footwear, as well as gait changes caused by time factors are given. According to the results of the study, it was revealed that the type of clothing makes a change in gait up to 40%, and time factors up to 10%. The results of the study can be applied in biometric authentication systems and personalized medicine. [ABSTRACT FROM AUTHOR]

Walking is one of the most repetitive activities that humans have done throughout their entire life. Each person has a specific pattern of a walking cycle called gait. Analysis on gait is a great topic to study and can be used in many applications such as to assess and improve athletic performance, to identify and correct pathomechanical dysfunctions and to design suitable footwear. Gait analysis is also a helpful tool to indicate health problems by identifying and addressing abnormalities and asymmetries that are often used by clinicians and researchers. This paper studied the development of portable smart shoe that was used to track and monitor walking gait pattern and gait analysis. The system employed a wireless connection and used four force sensors (FSR) that were located inside the insole according to four-point-critical pressure under the feet. Data from sensors were collected by ESP32 and transmitted in real-time through the internet into the online application. The portable smart shoe provided a data Ground reaction Force (GRF) for every gait phase when healthy subject walked at normal walking speed. Gait analysis was done from the collected data by gait phase characterization and comparing the gait pattern with previous studies to ensure the result was reliable. In normal walking conditions, the highest force was found at FSR1 sensor during the loading response phase while FSR 4 sensor provided the lowest force during pre-swing phase. The gait monitoring system is very useful in the rehabilitation field to identify the abnormalities and problems faced by patients. [ABSTRACT FROM AUTHOR]

An Ankle Foot Orthosis (AFO) is a device that supports the ankle joint to help improve gait. When fitting AFOs, clinicians tune the AFO, and the success of the tuning is often determined by observation, e.g. of a patient walking up and down a corridor. As a result, clinicians do not get a true picture of the patient's gait, therefore this study investigates the use of Inertial Measurement Units (IMU) for gait analysis. The aim is to provide clinicians with quantitative data about the patient's gait in real-world situations, helping them to determine how well the AFOs are performing. In this study, data were collected from one adult volunteer who was a regular wearer of two AFOs. The volunteer performed a series of activities while wearing the AFOs with different heel wedge heights and also while not wearing the AFOs. Data were collected from six IMU sensors but only the data from the shank sensors was used to perform gait analysis. The results from the gait analysis show that the IMU is sensitive to changes in angle- and time-based metrics whilst the volunteer was and was not wearing AFOs. This paper proposes a novel metric called negative momentum, which captures the continual progression of the shank forward which can be an indicator to show if the AFO is tuned correctly. This study suggests that two shank-mounted IMUs can be sufficient to perform gait analysis without the need of a full gait analysis lab. [ABSTRACT FROM AUTHOR]

The use of Head-Mounted Displays (HMDs) in Virtual Reality (VR) can cause gait disturbance problems for users because they are unable to see the real world while in VR. This is particularly challenging for individuals with mobility impairments who rely heavily on visual cues to maintain balance. The limited research that has been conducted on this issue has not focused on ways to solve it. IN this study, we investigated how different visual feedback methods affect walking patterns (i.e., gait) in VR. The study involved 50 participants, including 25 individuals with mobility impairments due to multiple sclerosis and 25 without mobility impairments. The participants completed timed walking tasks in both the real world and in VR environments that included various types of visual feedback, such as spatial, static, and rhythmic. The results showed that static and rhythmic visual feedback significantly improved gait performance in VR for people with mobility impairments compared to no visual feedback in VR. The results will help to make more accessible virtual environments for people with mobility impairments. [ABSTRACT FROM AUTHOR]

This study aimed to characterize the gait variations according to limb dominance in healthy individuals walking on level ground. Ten subjects were recruited, ranging from 18 to 22 years old. The dominant leg was determined for each participant by performing seven tasks. Participants were then asked to walk across the 6-m boardwalk at their self-selected walking speed to collect ground reaction force (GRF); each subject's level gait was recorded three times. From the vertical component of the GRF, the following variables were calculated: magnitudes of the first peak, second peak, valley (mid- stance), impulse, and stance time. The symmetry index (SI) between the dominant leg (DL) and non-dominant leg (NDL) was analyzed. Results showed that the stance time was lower in the NDL than in the NL. Meanwhile, the NDL exhibited higher first and second peaks of the GRF than did the DL. In addition, the SI for the valley (mid-stance) exceeded 9%, indicating asymmetry between the two legs during gait. The results suggest that during unilateral dynamic movements, the risk of injury is greater in the NDL than in the DL. [ABSTRACT FROM AUTHOR]

With increasing life expectancy, the risk of diseases of the central nervous system, such as cancer, strokes, etc., also increases. Strokes often result in injury to the sciatic nerve, which is responsible for controlling the calf muscles (plantar and dorsal flexors). A so-called ankle joint orthosis (AFO) helps to support the pathological gait and to avoid foot drop during gait. Passive orthoses are of particular importance for research, as they do not require additional incoming energy from outside to the orthotic system. However, current passive orthoses are often not personalized. On the one hand, because they usually have only a temporary muscle-building function and, on the other hand, because the individual design process is computationally time consuming and thus expensive. This paper presents a possibility to pre-dimension and pre-design passive orthoses fast and cost-efficiently by reducing the complexity of the model based on volume-optimized truss elements. Therefor a traditional high calculation intensive design procedure is compared with the complexity reduced model to show its effectiviness and the similarity of the results. [ABSTRACT FROM AUTHOR]

Gait analysis research has exploded in recent years for a diversity of applications such as animation, health monitoring, video supervision, and authentication. Recognition of gait is a new clever technology which recognizes people from afar and works well with low-resolution movies. Gait analysis has long been studied and used in industries such as security, medicine and sport. Analysis of clinical gait, in particular, has addressed a key role in enhancing healthcare quality. Techniques based on deep learning to gait analysis have been prominent in recent years as machine learning technology has advanced. When utilizing deep learning, yet, a high quantity of samples are necessary for training models, due to a variety of factors, the quantity of accessible gait-related data could be restricted. Wearable sensors, video sequences, and floor sensors, and publically available datasets, are the modalities for gathering gait data according to sensing technology. The performance of proven deep learning's artificial neural network architectures is compared for each group, with a focus on the temporospatial nature of gait information and the inspiration for multi-modality and multi-sensor fusion. The image data was saved in a database, and subsequently pedestrian identity was determined using real-time cameras or input videos. To make testing easier, an interactive interface derived from PyQt4 was created, which can perform activities like registering pedestrian names on site, acquiring pedestrian gait energy maps and creating databases, refreshing the background, and detecting and recognizing pedestrians. It also allows you to switch between input video detection and real-time camera detection at any time. Deep learning Convolution Neural Networks is demonstrated to beat shallow learning models on the majority of key criteria. The ability to dig out gait features without human intervention in Deep Learning, as contrast to shallow learning using constructed features of gait, is due to the mentioned character of gait data. [ABSTRACT FROM AUTHOR]

Artificial neural networks were implemented satisfactorily to assess gait events from various walking data. This research is to study the suitable network depth in neural network technique for developing human gait cycle prediction model using artificial neural network. Gait dataset is retrieved from public dataset where it is measured from 24 young adults who in the last six months before the data was collected and had no lower-extremity injury and were all free of any orthopedic or neurological diseases that could interfere with their gait patterns. In Artificial Neural Network (ANN) developed model, the depth of neural network is one of factor that determine the performance of the developed model. The performance of the model will be compared in terms of Regression (R) and Mean Square Error (MSE) value. To develop human gait prediction model, the input variable is joint angle and joint moment for hip, ankle, and knee. Moreover, only sagittal plane which is Z-axis is used in this study. A multi-layer perceptron model is implemented, composed with different hidden layers and hidden neurons. With 10th hidden layers attempt, on the 8th hidden layers, the R-Value of gait cycle prediction was 94% for training 95% for testing. And the lowest testing Root Means Square Error (RMSE) is at 59.87. The role of ANN in the prediction gait cycle is discussed in this paper. [ABSTRACT FROM AUTHOR]

There are various advantages of learning algorithm and one of them is making an innovation in global development especially in science expression development. The learning algorithms in neural network technique for human gait cycle prediction is a study that implement the use of a few types learning algorithm determine the best prediction human gait cycle model for the full cycle of human gait. The study aims to achieve the best learning algorithm from three different learning algorithms namely Levenberg-Marquardt (LM), Bayesian Regularization (BR) and Scaled Conjugate Gradient (SCG) that can fit in regression problem This study used MATLAB® to develop the multi-layer perceptron neural network for training and testing of the human gait cycle prediction model while R-value, RMSE value and training period are used as the performance evaluation. As a result, BR record the longest training time of 3 hours 40 minutes, but it contains the high R-value which is 0.999 and has least RMSE value 0.4644 during training but in testing the performance reduce significantly which indicate an overfitting occurred. While the R-value for LM and SCG 0.9471 and 0.8955, respectively with small reduce of performance during testing. It is concluded that the LM training algorithm shows better performance compared to BR algorithm and SCG algorithm. [ABSTRACT FROM AUTHOR]

Normal walking has become the most commonly performed activity in daily human life. Many researchers have adopted the normal walking condition to study the bearing of total hip arthroplasty using realistic loads. Our research aims to evaluate contact pressure in bearing under normal walking conditions using the finite element approach. The 2D model was used to perform computational analysis of CoCrMo-on-CoCrMo under normal walking conditions. Five selected phases have been considered to represent walking activity as loading input. Contact pressure magnitude changes in line with a changed phase of loading input. Its distribution is also wider since higher loading is given under normal walking conditions. [ABSTRACT FROM AUTHOR]

Kinematic analysis of human gait is an effective strategy to detect and assess an individual's gait to diagnose and develop and guide follow-on rehabilitation protocols. So, an accurate, objective gait analysis system has potential to facilitate rehabilitation process. System using smartphone-Kinovea represent an emerging technology for physical activity assessment and that may be relevant for gait analysis. The objective of this study was to determine gait displacement, speed and joint angle by using smartphone-Kinovea software system – to compare the normal gait with four distinct simulated gait abnormalities. Also, to assess validity of the proposed system by compared with QTM as gold standard. 30 participants completed an experiment in which they completed several gait trails on single day. Gait types were analyzed using statistical analysis (two-way MANOVA). As for validation assessment was analyzed using paired t-test by comparing proposed system with QTM. Results shows that joint angles for abnormal gaits are higher mean (Standard Deviation) compared to normal gait during HS and TO. While, normal gait exhibits higher mean (Standard Deviation) for d and s during both IDS and TDS phases compared to other four abnormal gaits in both genders. Also, there are significant different (p<0.05) of gait for all gait comparisons for all parameters, except hip angle of normal-HP with p=0.495. Moreover, there is some gait was similar with other gait due to they shared underlying kinematic aspects such as BA and DP. The validation of the system gives moderate result. These support that the smartphone-Kinovea system have potential in detecting and identifying abnormal gaits, and for future implementation in diagnosis and rehabilitation. [ABSTRACT FROM AUTHOR]

Walking is a common but complex daily activity for human. Walking is done when one leg is elevated and moved forward by flexing the hips and knee. Walking involves association of central nervous system, motor and sensory system. It has been previously shown that disrupted neural communication and musculoskeletal constraints may impair postural control and stability during gait and increase fall risk. Previous research have reported that distance between centre of pressure (COP) and centre of mass (COM) are suitable to study postural stability of patients that is affected by HSP disease. There is no research studied about normal and four types of simulated abnormal gaits which include hemiplegic, diplegic, bilaterally asymmetry and hunchback by analysing COP and COM. Fifteen male subjects and fifteen female subjects were involved in this research. Performances of subjects were captured with QTM system and analysed by Visual 3D software. For females, there was a significant difference in normal and hemiplegic gait in AP direction. For males, normal, hemiplegic and bilaterally asymmetry showed significant differences in AP direction while normal and diplegic demonstrated significant difference in ML direction. This finding concluded that COP-COM method can be suggested for clinical research and rehabilitation purpose. [ABSTRACT FROM AUTHOR]

Despite the potential benefits of Person Generated Health Data (PGHD), data quality issues impede its use. This study examined the effect of different methods for filtering armband data on determining the amount of healthy walking and the consistency between healthy walking captured using armbands and health diaries. Four weeks of armband and health diary data were acquired from 103 college students. Armband data filtering was performed using heart rate measures and minimum daily step counts as a proxy for adequate daily wear time. No substantial differences in the filtered armband datasets were observed by filtering methods. Significant gaps were observed between healthy walking amounts determined from armband data and through the health diary. Future studies need to explore more diverse data filtering methods and their impact on health outcome assessments. [ABSTRACT FROM AUTHOR]

Human gait parameters reveal much information about a person's possible health problems. These parameters can be used for the early diagnosis of neurogenerative diseases and to monitor the healing process during rehabilitation after an injury. The methods of monitoring gait parameters can be divided into two basic approaches. The first approach is to monitor the movement parameters of the lower extremities, tracking with the help of a camera system or with the help of accelerometers placed on the patient's body. The second approach is to monitor the loading of individual leg parts during walking. This paper will present the design of a wearable device for monitoring gait parameters, where several Inertial Measurement Units (each containing an accelerometer, gyroscope, and magnetometer) will be used to process and evaluate the data. The presented design will consist of a microcontroller module, 1 to 3 IMU modules (accelerometer+ gyroscope), and pressure sensors placed in the shoe's sole. [ABSTRACT FROM AUTHOR]

Gait and balance dysfunction troubles a large number of patients in rehabilitation. Traditional exercise rehabilitation methods have limited effects on patients' walking ability. It is rather important to find other ways to improve the current gait rehabilitation therapy. This paper mainly introduces neuromodulation technologies and the current status of the treatment of dyskinesias, especially gait abnormalities, and summarizes and discusses the treatment results of electric, magnetic, and multi-regulation methods. It is found that each method has a certain effect on gait abnormalities. Neuromodulation technologies provide new research, diagnosis, and treatment ideas for gait rehabilitation. [ABSTRACT FROM AUTHOR]

Therapeutic effects for rehabilitation of the older adult are provided by virtual realities therapy, but the body's balance remains unclear. The objective was to characterize the effect of senior physiotherapy therapy treatments with VRT on their balance-rehabilitation. Virtual Reality is a technology often used in many fields of cinema, sport, entertainment and simulation. Machine imaging and materials seek in the present circumstances to simulate a real presence. Their sensory abilities in medicine are of practical value. His significance in the field of healthcare should thus be explored. Older individuals are most frequently affected by injury and injury-related deaths. This study evaluated the effect on the balance and the gait capabilities of falling elderly individuals. Ten articles met the inclusion criteria, which demonstrated variety in treatment types (70%) and evaluated outcomes (60 percent). The article focuses on a review of literature in which we comprehend how this technology solves a medical issue to save the lives and vital applications of a patient. [ABSTRACT FROM AUTHOR]

A force platform prototype for human gait classification as an alternative to vision-based and wearable sensor-based gait classification technologies is proposed. The primary sensors involved in this prototype were load cells. When a volunteer walks on the force platform, the load cells record signal changes corresponding to the walking pattern of the volunteer. These signals were digitized and amplified and stored in a micro-SD card. Five gait features were extracted from the stored data in the micro-SD card, and MATLAB classification learner was used for classification. An accuracy of 94% was observed with Fine Gaussian Support Vector Machines. This shows that the force platform is a good alternative to vision-based and wearable sensor-based gait classification technologies. [ABSTRACT FROM AUTHOR]

Human kinematic analysis remains one of the most challenging tasks for the researchers. In a typical gait analysis study, measurement of various joint angles is carried out with the help of markers attached to the human body. The human activity is captured by a video camera and the video is then analyzed using appropriate software. Locating the markers manually in each frame is cumbersome and may give erroneous results. The problems like, motion blur, scattering, marker occlusion, marker reflection, etc., are also prevalent. The video recording settings play an important role in deciding the marker location precisely. In the present study, the effects of input parameters such as frame rate and shutter speed, on the pixel area of the LED marker were investigated using the Response Surface Methodology (RSM). It has been observed that higher shutter speed time has a negative effect on pixel area of the LED marker and on the area of the bounding box. The experimentation using RSM showed that shutter speed time of 2300 µsec and frame rate of 60 Frame Per Second (FPS) are required to produce pixel area of bounding box of desired quality. [ABSTRACT FROM AUTHOR]

Postural control is a constant re-establishment process for the maintenance of balance and stability. Asymmetric weight distribution (AWD), characterized by uneven leg loading, leads to increased instability, injury, and progressive deterioration of posture and gait. Postural self-correction is automatically affected by the human body in response to visual, vestibular, and proprioceptive sensory information. However, simultaneous cognitive loads can increase the demand for extra resources and require balance monitoring and correction techniques. We address these issues with a novel physiological feedback system that utilizes load sensors for AWD detection, and electrical muscle stimulation (EMS) for automatic correction and restoration of balance by affecting a counter-weight shift. In a user study involving 36 participants, we compare our automatic approach against two alternative feedback systems (Audio and Vibro-tactile). We find that our automatic approach delivered faster correction and outperformed alternative feedback mechanisms and perceived to be interesting, comfortable and a potential commercial product. [ABSTRACT FROM AUTHOR]

Prosthetic legs are needed by individuals with a lower limb amputee to improve their quality of life. However, the current designs have several limitations that requires substantial training for adaptation to improve posture and gait. As an emerging technology, virtual reality (VR) provides prospective capability for such rehabilitation training. This study aimed to propose a framework of VR-based training system for improving stability and gait of prosthetic users, focused on lower limb prosthetic and transfemoral or above-knee amputations. Previous studies have demonstrated the ability of VR to improve both stability and gait. However, the training system used seems to diverse. Based on an extensive literature study, we concluded that the VR-based training system should consider the following three subsystems: technology, content, and feedback. Each sub-system has its alternative combinations. Finally, this study proposes a framework that can be used to test the system efficacy and overall acceptance of the VR-based system. [ABSTRACT FROM AUTHOR]

During last years, we observe an increasing frequency of traffic accidents and the resulting neurological complaints. We present a male patient of 21 years, transferred to our PRM Department one month after neurosurgery (thoracic stabilization) for an important vertebral thoracic fracture. During clinical exam (at the admission), we observed a complete inferior paraplegia with total dependence in activities of daily living (ADL): impossible autonomic movements in the bed, the patient was only in lying position. The patient had urinary catheter and severe urinary infection, treated with antibiotics. We applied a complex rehabilitation, including preformed physical modalities (electrical stimulations), gradual verticalization, individualized physiotherapeutic and occupational therapeutic program, accentuating on balance and gait training, ADL education. Six months after the traumatic spinal cord injury (SCI), we began with robotic rehabilitation with Locomat system (Hocoma). We noticed significant improvement of the range of motion of the cervical spine, pain relief, balance stabilization, amelioration of autonomy in ADL. At the month nine after the SCI the patient have the capacity of autonomic verticalization with a walker and gait – without assistance. We consider that every patient with post-traumatic inferior paraplegia must be included in a longterm physiotherapeutic and ergotherapeutic program, if possible – with robotic rehabilitation. [ABSTRACT FROM AUTHOR]

After valvular cardiosurgery (with extracorporeal circulation), most geriatric patients develop vertebro-basilar insufficiency with balance problems or ataxia signs. Our GOAL was to evaluate the possible impact of balance, gait and coordination training in the complex cardiorehabilitation (CR) algorithm of old patients after cardiac surgery. MATERIAL AND METHODS We observed 369 patients after cardiac surgery. Patients were randomized into three therapeutic groups. The control was done before, during and at the end of the CR course (of 10 treatment days), and one month after its end. In all patients, we applied a complex cardio-rehabilitation (CR) programme of physiotherapy and ergotherapy; including cardio-training, respiratory exercises (predominantly for external and internal intercostal muscles); and goal-oriented activities (standing up, walking and climbing stairs). Group (gr) 1 received only this CR programme. In gr 2 we added balance and gait training exercises. In the next group (gr 3) we applied additionally coordination exercises for the upper and lower extremities. The statistical ANALYSIS OF RESULTS demonstrates in all patients significant improvement of circulatory parameters; upgrade in cardiac functional parameters, enlargement in autonomy. We observed bigger amelioration in quality of life in the third group. CONCLUSION: Balance and coordination training must be included in the CR-algorithm in geriatric patients after cardiosurgery. [ABSTRACT FROM AUTHOR]

In this paper we propose a new analytical approach to the study of a nonlinear dynamical system related to human gait dynamics. A reliable method, namely the Optimal Homotopy Asymptotic Method (OHAM) is employed to obtain explicit and accurate analytical solutions to the considered problem. The capabilities of this new method are successfully tested in the study of a complex dynamical system related to human gait dynamics and an excellent agreement between analytical and numerical solutions is demonstrated. The accuracy of the analytical results is assured by the so-called convergence-control parameters, whose optimal values are rigorously identified in order to provide a fast convergence using only the first iteration. [ABSTRACT FROM AUTHOR]

Doppler radar has been used as a sensing device for human gait identification because it possesses the ability to work in adverse weather and penetrate invisible barriers with maintaining privacy. Doppler explains the velocity of the target's motion, and the micro-Doppler explains the micro-motions of its moving parts. The Doppler and micro-Doppler signatures are used to classify the target. Many studies and approaches were presented for human recognition like fingerprints, retina, palm, face, and voice. The gap of this subject is concentrated on three points, the first one needs the subject's permission and physical attention, the second one is maintaining the privacy. Also, the location of the detector device and the detected human part. This paper introduces a novel approach for human gait recognition based on his shoulder's movement signature and periodic motion to satisfy the recognition and to fill this gap. The micro-Doppler of shoulders (or head) is detected by radar, which was fixed in the ceiling. The radar location was decided because the shoulder movement is in-phase with the line of sight (LOS) of the radar signal. The support vector machine (SVM) was used as a classifier. Five people were tested as classes with many patterns for each class related to a different speed and motion status. The Euclidean and Bhattacharyya distances were used to measure the similarity. The Euclidean distance is overperformed the Bhattacharyya distance in this application by 14% caused by its linearity. Simplicity and accuracy can be considered as the distinguishing features of the proposed system in which the gained classification rate is 96.2%. [ABSTRACT FROM AUTHOR]

Currently, the building and construction industry play an important role. However, development practices recognized as one of the main contributors to environmental problems especially in the production of electrical energy. Faculty of Engineering Universitas Indonesia (FT UI) is one of the largest on-campus electrical consumption of the UI. Because of that, needs an alternative energy to reduce the operational costs of the FT UI. One of them is with utilization of Ground Reaction Force (GRF) on the activity of walking as an alternative at FT UI. Based on the results of previous study, the value of GRF and the potential energy of human gait (walking) on the floor height change as deep as 5 cm yield the greatest value. Therefore, the need for analysis of biomechanics in human gait as design attributes of energy floor (elevation changes on the floor) with inverse dynamics model to find out the level of comfort on the human gait to the floor height of the dynamic factor by doing the calculation of knee and ankle joint moments. Based on the results that the average value of joint moment male Indonesian that walked on the dynamics floor has a value of 5 cm smaller that static floor. In summary, the comfort level can be summed up in the joint segment of the leg and foot were still comfortable conditions when walking on the dynamics floor of 5 cm. [ABSTRACT FROM AUTHOR]

Plantar pressure it is frequently used to evaluate the pathologies of the foot with clinical and research application and less used for methodological issues in areas such as sports medicine. The purpose of this study was to assess the plantar pressure in young athletes by using a RSSCAN pressure plate for identification of reference normative data. Foot complaints and history of trauma, surgery, or other pathologies possible were assessed by a questionnaire and a clinical evaluation was performed for identification of foot pathologies. In total, 106 subjects walked barefoot over a pressure plate and several dependent variables were recorded for each foot and subject, followed by centralization, analysis and statistical interpretation of numerical data and calculation of means, standard deviation, minimum and maximum values. For 16 subjects, the biomechanical parameters showed significant deviations from the average of the parameters recorded during the research at the control group level. A detailed clinical evaluation allowed the identification of some associated pathologies of the kinetic chain for the lower limb. The main findings of this study address to the reliability of the normative database of foot plantar pressure in young athletes and the applicability of measurements in the assessment of gait symmetry, foot stability and early identification of lower limb pathologies. All these aspects led us to the conclusion that the proposed method can be used as screening in detecting risk factors related to structural and / or functional abnormalities of the lower tongue with applications in the prevention of trauma but also in improving sports performance. [ABSTRACT FROM AUTHOR]

Accurate treatment decision-making for disease treatment is important, particularly if it is done in a way that helps to overcome the challenges associated with low resource setting. This include shortage of qualified personnel, infrastructure, ready access to devices, and healthcare by common people. Although real-time gait analysis has been used for the diagnosis of diseases that are associated with gait impairments, the need to improve on the performance of gait-based prediction by augmenting it with other sources of knowledge in a complementary way has been acknowledged. In contrast, to existing approaches, this paper presents the design of a conceptual framework that will enable the semantic integration and use of information from multiple health data sources in order to ensure efficient treatment decision making for gait-related diseases in a low resource setting such as South Africa. The analytical evaluation of the proposed framework suggests that it has sufficient merit and potential to be usable and useful in low-resource settings. [ABSTRACT FROM AUTHOR]

In this paper, we propose XModal-ID, a novel WiFi-video cross-modal gait-based person identification system. Given the WiFi signal measured when an unknown person walks in an unknown area and a video footage of a walking person in another area, XModal-ID can determine whether it is the same person in both cases or not. XModal-ID only uses the Channel State Information (CSI) magnitude measurements of a pair of off-the-shelf WiFi transceivers. It does not need any prior wireless or video measurement of the person to be identified. Similarly, it does not need any knowledge of the operation area or person's track. Finally, it can identify people through walls. XModal-ID utilizes the video footage to simulate the WiFi signal that would be generated if the person in the video walked near a pair of WiFi transceivers. It then uses a new processing approach to robustly extract key gait features from both the real WiFi signal and the video-based simulated one, and compares them to determine if the person in the WiFi area is the same person in the video. We extensively evaluate XModal-ID by building a large test set with 8 subjects, 2 video areas, and 5 WiFi areas, including 3 throughwall areas as well as complex walking paths, all of which are not seen during the training phase. Overall, we have a total of 2,256 WiFi-video test pairs. XModal-ID then achieves an 85% accuracy in predicting whether a pair of WiFi and video samples belong to the same person or not. Furthermore, in a ranking scenario where XModal-ID compares a WiFi sample to 8 candidate video samples, it obtains top-1, top-2, and top-3 accuracies of 75%, 90%, and 97%. These results show that XModal-ID can robustly identify new people walking in new environments, in various practical scenarios. [ABSTRACT FROM AUTHOR]

Huntington Disease (HD) is a genetic neurodegenerative disease which leads to involuntary movements and impaired balance. These changes have been quantified using footstep pressure sensor mats such as Protokinetics’ Zeno Walkway. Drawing from distances between recorded footsteps, patients’ disease severity have been measured in terms of high level gait characteristics such as gait width and stride length. However, little attention has been paid to the pressure data collected during formation of individual footsteps. This work investigates the potential of classifying patient disease severity based on individual footstep pressure data using deep learning techniques. Using the Motor Subscale of the Unified HD Rating Scale (UHDRS) as the gold standard, our experiments showed that using VGG16 and similar modules can achieve classification accuracy of 89%. Image pre-processing are key steps for better model performance. This classification accuracy is compared to results based on 3D CNN (82%) and SVM (86.9%). [ABSTRACT FROM AUTHOR]

Behavioral analysis for identifying changes in cognitive and physical functioning is expected to help detect dementia such as mild cognitive impairment (MCI) at an early stage. Speech and gait features have been especially recognized as behavioral biomarkers for dementia that possibly occur early in its course, including MCI. However, there are no studies investigating whether exploiting the combination of multimodal behavioral data could improve detection accuracy. In this study, we collected speech and gait behavioral data from Japanese seniors consisting of cognitively healthy adults and patients with MCI. Comparing the models using single modality behavioral data, we showed that the model using multimodal behavioral data could improve detection by up to 5.9%, achieving 82.4% accuracy (chance 55.9%). Our results suggest that the combination of multimodal behavioral features capturing different functional changes resulting from dementia might improve accuracy and help timely diagnosis at an early stage. [ABSTRACT FROM AUTHOR]

Gait analysis is a common technique used to identify problems related to movement and posture in people with injuries, and foot-side detection is one of its important challenges. As many commercial sensors only provide limited information and traditional lab-based gait analysis is expensive, the aim of this study is to discriminate between left and right foot steps based on acceleration data from a single chest-worn accelerometer. To achieve this goal, an experimental study was conducted with 25 participants wearing an accelerometer on their chest and walking in a static environment. Several machine learning (ML) classifiers were trained to detect a foot-side from collected acceleration data. All machine learning classifiers achieved high classification accuracy, with Random Forest providing the best results. This result shows that ML-based foot-side classification using a single sensor is achievable and can contribute to develop an efficient health monitoring system to track lower limb's problems. [ABSTRACT FROM AUTHOR]

The study aimed to asssess the effect of simulated leg length discrepancy (LLD) to the gait variability. A total of 10 normal subjects walked at self-selected normal walking pace with simulated LLD of 0, 1.5, 2.0, 2.5, 3.0, 3.5, and 4.0 cm on 3m walkway with embeded force plates. The simulated LLD were applied on the left leg in a randomly selected order. Additionally, the subjects performed walking with and without additional 2 kg of carrying backpacks load. The Centre of Pressure (COP) was computed using the ground reaction forces and moment collected from the two force plates. The standard deviation of anterior-posterior and medial-lateral COP displacement was used to determine the gait variability. In conclusion, changes on the LLD height led to an increases of gait variability which indirectly affect a person's stability during walking. [ABSTRACT FROM AUTHOR]

Paper describes application of the Spline Quaternion Lifting Scheme (SQLS) to multiresolution decomposition of human gait data coded in from of quaternion signal. The analysis was conducted on the base of multiresolution representation and relative energy and entropy to quantitative assessment of energy in each scale (frequency) and information about concentration of energy across scales. The paper describes preliminary analysis results of 18 participants whole body gait time series extracted from treadmill gait sequences which were recorded in the Human Motion Laboratory (HML) of the Polish-Japanese Academy of Information Technology (Bytom, Poland) by the Vicon system. [ABSTRACT FROM AUTHOR]

Bio metric surveillance has become indispensable for every system in the recent years. The contribution of bio metric authentication, identification, and screening purposes are widely used in various domains for preventing unauthorized access. A large amount of data needs to be updated, segregated and safeguarded from malicious software and misuse. Bio metrics is the intrinsic characteristics of each individual. Recently fingerprints, iris, passwords, unique keys, and cards are commonly used for authentication purposes. These methods have various issues related to security and confidentiality. These systems are not yet automated to provide the safety and security. The gait recognition system is the alternative for overcoming the drawbacks of the recent bio metric based authentication systems. Gait recognition is newer as it hasn’t been implemented in the real-world scenario so far. This is an un-intrusive system that requires no knowledge or co-operation of the subject. Gait is a unique behavioral characteristic of every human being which is hard to imitate. The walking style of an individual teamed with the orientation of joints in the skeletal structure and inclinations between them imparts the unique characteristic. A person can alter one’s own external appearance but not skeletal structure. These are real-time, automatic systems that can even process low-resolution images and video frames. In this paper, we have proposed a gait recognition system and compared the performance with conventional bio metric identification systems. [ABSTRACT FROM AUTHOR]

Parkinson's disease (PD) is the second most common neurodegenerative disease. The diagnosis of PD can be difficult, especially in its early stage since there are no existing specific biomarkers. Most biomechanical data characterizing human movement is shown as time series or temporal waveforms representing different joint measures. Principal component analysis (PCA) can be used as a tool to identify differences in gait between healthy persons and those diagnosed with PD. The purpose of this study is to compare hip and knee kinematics during walking in PD group and control (CO) group using PCA, and to identify the specific PCA variables that can be used for differentiating Parkinsonian gait from normal gait. The subjects were divided into two groups: PD group n = 15, control group n = 12. Each subject performed a gait task and kinematics of limbs was measured using nine degrees of freedom inertial measurement unit (IMU). PCA was performed on the angular velocity of right and left side hip and knee joints in the sagittal plane of the gait cycle. Different numbers of principal components (PC) are needed to describe important information from hip (PC -- 3) and knee (PC -- 4) joints in sagittal plane. Statistically significant differences were found between PD and CO groups: right hip PC3 (p=0.0026); left hip PC3 (p=0.0262); right knee PC3 (p=0.0286). The PCA applied in this paper identified differences in gait features between PD and CO groups. Identification of these differences between PD and CO groups could clarify PD progress. [ABSTRACT FROM AUTHOR]

In this paper, we demonstrate a new IMU-based wearable system (dubbed MANA or Mobility ANAlytics) for measuring gait in a clinical setting. The design process and choices that were made to ensure that the technology was invisible and accessible are described. We collect a rich and diverse dataset of walking data from sixty participants, including forty people with Parkinson's Disease (PD). The system is then validated in a clinical setting with this dataset. We present novel and innovative algorithms to measure common gait parameters. The system is able to estimate these gait parameters with high accuracy, with a mean absolute error of 4.0 cm for stride length and 2.6 cm for step length, outperforming all state-of-the-art methods that included data from people with PD. [ABSTRACT FROM AUTHOR]

The authors present an application of Grassmann manifold to the evaluation of human dynamic balance based on the time series representing movements of hip, knee and ankle joints in the sagittal, frontal and transverse planes. Time series were extracted from gait sequences which were recorded in the Human Motion Laboratory (HML) of the Polish-Japanese Academy of Information Technology in Bytom, Poland using the Vicon system. [ABSTRACT FROM AUTHOR]

Indonesia is the country with the largest muslim population in the world, most of the inhabitants do salat every day. THR (Total Hip Replacement) patients are prohibited from doing salat in normal gait. It leads to the damage of the hip joint prostheses due to impingement and dislocation. This paper reports the design of a pin-on-ring tribometer which is used to measure and analyze the wear volume and the impingement of hip joint prostheses during salat. The modifications of the femoral head and acetabular cup holder are performed to design the reciprocating motion for the movement of the hip prostheses. The interesting finding of the present research is a new mechanism of linked-bar which leads to the feasibility of the measurement of the wear volume and the impingement for THR patients during salat. [ABSTRACT FROM AUTHOR]

Mathematical modelling is one of the methods for determination of the mass-inertial parameters of different segments of the body, as well as of the whole body. The current article presents a review of some new results obtained via recently suggested 20-segmental 3D mathematical model of the human body. In order to automatize the calculation of the mass inertial parameters of the body in any of its usual positions, and not only for separate segments – which can be analytically performed --- the model has been also generated in a proper computer environment. We report some new data obtained via utilization of the model pertinent to the segments of the body. In addition, we also present a short review of our recent results related to i) a new type of mathematical modelling of the thigh of the human body; ii) investigation of the mass – inertial characteristics in basic body position as selected by NASA; iii) study of mass-inertial parameters during the eight phases of the human gait cycle; iv) a new approach for generation of the upper limb of the human body. The proposed model shall be helpful in engineering, when designing devices aimed to help disabled people. Finally, we outline some additional improvements and future developments of the model. Let us note that the proposed model and its considered modifications are oriented towards applications in medicine (orthopedics and traumatology), rehabilitation robotics, computer simulations, sports, as well as in areas such as ergonomics, simulation of human behaviour in space, forensics (body fall, body impact) and more. [ABSTRACT FROM AUTHOR]

Gender classification plays an important role in many applications such as surveillance systems and medical applications. Most of approaches for gender classification are based on the features of human face, voice and gait. Recently, gait-based approaches have been focused on more and more since the way they collect information about human gait is noncontact and non-invasive. Therefore, in this paper we propose a novel method to classify human gender from video stream, which is based on gait features. In order to classify gender, we collect silhouettes of human walking pattern from a Microsoft Kinect sensor, and extract two gait features, i.e., Gait Energy Image (GEI) and Denoised Energy Image (DEI) from a sequence images. GEI is an appearance-based gait representation, while DEI is used to remove the noises from GEI. For the gait features, we use feature vector with low dimension. We employ Support Vector Machine (SVM) for the classifier with the gait-based feature vector. The extracted feature dataset are divided into two parts, i.e., training and testing datasets. The training data set are used for training a SVM classifier while the testing dataset are used for the evaluation. According to the experimental results, we know that GEI is an applicable feature for human gait representation. Despite of the limitation of the dataset, e.g., different races and thickness of clothes which weaken the distinct differences between males and females, the average accuracy of the proposed approach reaches up to 87% under 10 times holdout validation. [ABSTRACT FROM AUTHOR]