Movement Of Persons Research Articles

A robust optimized convolutional neural network model for human activity recognition using sensing devices

AbstractHuman activity recognition has become an expansive field of interest in recent years, both in academic and industrial research. Human Activity recognition (HAR) is concerning the prediction of person's movement or action such as walking, standing, sitting, up and downstairs, etc. Convolutional neural network (CNN) is a key component with deep learning. The main objective of this study is to design and implement an activity recognition algorithm in the state of the art of deep learning systems which accomplish superlative performance to detect human activities. Accordingly, an extensive comparison has been developed between different deep learning algorithms such as classical (CNN) models and Recurrent Neural Network (RNN) models with respect to the major human activities. Furthermore, a robust (CNN) deep learning model has been built up and proposed in order to enhance the recognition precision of human activities. This proposed model uses raw data acquired from a set of inertial sensor and exploring numerous human achas been built up and proposedtivities; sitting, standing, jogging, walking, and etc. Experimental results show that the precision of the proposed deep structure has achieved 97.5% with respect to the NAdam optimizer which would be considered as the most effectively recognizer compared to other deep learning architectures.

Chest-Worn Heart Rate Variability Monitor With a Self-Injection-Locked Oscillator Tag

This article presents a chest-worn device for monitoring the heart rate variability (HRV) of a person in motion without direct contact with the skin. The device operates at 5.8 GHz and mainly consists of a self-injection-locked oscillator (SILO) and a tag antenna. The device transmits the output signal of an SILO that is frequency-modulated (FM) by the Doppler effect of the physiological movement of the chest via the tag antenna to a remote FM receiver. Accordingly, the heartbeat is detected and the HRV can be estimated. The tag antenna comprises a circularly polarized ring slot antenna and a split-ring resonator (SRR) array in stack to enhance sensing directivity while reducing the moving clutter in the joint sensing and transmission process. For validation, an HRV monitoring system was developed, based on the proposed device, to detect the cardiac intervals of a wearer who performs various activities, including walking and running. The results thus obtained agree closely with electrocardiogram (ECG) measurements.

Performance Assessment of Fuzzy Logic Control Approach for MR-Damper Based-Transfemoral Prosthetic Leg

Transfemoral amputation commonly occurs due to some stroke, diabetes, physical or mental trauma, which reduces the person's movement capability. Therefore, an efficient prosthetic leg is essential to improve the life of an amputee by replacing the lost limb. This letter addresses the fuzzy logic-based control strategy for magneto-rheological damper based prosthetic leg for transfemoral amputees. The primary focus of this letter is to present the performance analysis of the control to achieve the entire gait cycle (both swing and stance phases) for a transfemoral prosthesis. The performance and robustness analysis of the developed prosthetic leg is tested for real-time gait data to obtain the precise and more natural gait by the transfemoral amputee.

Human gait recognition using firefly template segmentation

ABSTRACT Gait recognition is one of the advanced behavioural biometric technology, which aims to distinguish people by their walking style. The unique advantage of gait recognition is its capability to catch gait at a distance without the prior consent of the subject. In the gait recognition process, the features of human motion are automatically extracted and later used to authenticate the identity of the person in motion. The template-based model-free gait recognition method offers an optimal solution for gait recognition through gait energy image (GEI) and gradient gait energy image (GGEI), which increases the performance of gait recognition against covariates like normal walking conditions, bag, and coat. In this paper, we propose a novel firefly template segmentation (FTS) method, which employs the firefly algorithm to accomplish the boundary selection process. The principal component analysis (PCA) technique is used for dimensional reduction and the multiple discriminant analysis (MDA) technique applies to achieve better class separability. The proposed work is tested on a publicly available CASIA-B dataset and the experimental results show excellent performance in comparison with other gait recognition methods reported in the literature.

Control and Implementation of 2-DOF Lower Limb Exoskeleton Experiment Platform

In this study, a humanoid prototype of 2-DOF (degrees of freedom) lower limb exoskeleton is introduced to evaluate the wearable comfortable effect between person and exoskeleton. To improve the detection accuracy of the human-robot interaction torque, a BPNN (backpropagation neural networks) is proposed to estimate this interaction force and to compensate for the measurement error of the 3D-force/torque sensor. Meanwhile, the backstepping controller is designed to realize the exoskeleton's passive position control, which means that the person passively adapts to the exoskeleton. On the other hand, a variable admittance controller is used to implement the exoskeleton's active follow-up control, which means that the person's motion is motivated by his/her intention and the exoskeleton control tries best to improve the human-robot wearable comfortable performance. To improve the wearable comfortable effect, serval regular gait tasks with different admittance parameters and step frequencies are statistically performed to obtain the optimal admittance control parameters. Finally, the BPNN compensation algorithm and two controllers are verified by the experimental exoskeleton prototype with human-robot cooperative motion.

Electrostatic mechanisms for the spread of coronaviruses

Clothing of a person in motion electrifies and causes around his body intensive reproduction of particles of air ions, atoms, and air molecules, aerosols (similar in size to particles of coronaviruses), which are non-contact, in moments of discharge from clothing, currents of displacement and transmission (or air flow) are transferred to the environment, similar to the processes of inhalation of electroaerosols or powder. Waveform recorded outbreaks of coronal discharges (CD) - (pulses of more than 25.0 kV/m) the electrostatic field intensity tension (EFI) recorded by the IRI-04M device on human clothing in casual clothing and shoes, and non-contact (0.4-1.2) m of communication of people in the process of movement in the winter road. In the process of human interaction in antistatic clothing and footwear, current emissions (pulses less than 3.0 kV/m), almost not recorded, indicates the absence of outbreaks of CD. The most likely mechanical attachment (the first phase of absorption) to the target cell was shown to be performed by negatively charged (rather than neutral) particles of coronaviruses. The peak of the spread of coronaviruses in the premises occurs in the conditions of the heating period. In the environment, the peak of distribution depends on seasonal conditions of atmospheric electricity - in autumn and spring higher, in winter and summer being 3-5 times lower. Recommendations are given to normalize anti-static conditions in the premises and to monitor the safety of the clothes of the medical worker at the entrance to the danger zone. The method, the self-control tool (the instrument IRI-04M, located on the sternum of the body) and the criterion of safe electrification of the human - a tension of less than 4.5 kV/m, when there is still no reproduction and transfer of coronavirus particles with a diameter of more than 30 nm.

IBN RUSYD (Kritik Terhadap al-Gazali dan Pengaruhnya di Eropa)

This article aims to explore the treasures of Ibn Rushd's philosophy of rationality versus Al-Gazali's fundamental religious thought related to 3 (three) metaphysical problems, namely: (1). Qadimnya (eternal) nature, (2) God does not need to take care of small things (3). There is no physical resurrection. To understand and know the three problems, it can be described as follows:
 One: Qadim or eternal nature. The scholars represented by Al-Gazali argue that God created this universe from nothing into existence. According to Ibn Rushd, the opinion of the ulama represented by Al-Gazali cannot be justified. Therefore, what is true is that there are 2 (two) substances of two things which are both eternal (eternal), namely God and Nature, although the nature of God is not the same as the nature of Nature. The existence of God was earlier while the existence of Nature was later or later. Initially, God and finally Nature are not in terms of time or time, but from the side of the level of matter, as previously the movement of a person with the movement of his shadow. In fact, a person's movement occurs first, followed by a moving image, but both of them move at the same time and time. Although it is different from the side of its origin.
 Second: God doesn't have to take care of little things. Al-Gazali argues that knowledge is something that stands alone, even though it has a relationship or relationship with matter, science stands alone, the matter stands alone, but both of them manifest in one substance. Therefore, God is obliged to know everything big and small.
 Third: Resurrection of the body. Al-Gazali argues that the bodily awakening coincides with the spirit. This reasoning is based on a large number of texts from the Al-Qur'an which informs about the awakening between the body and the spirit. This is as informed by God through the incident of the Prophet Moses who asked God so that God could show Prophet Moses how God brought life to the dead. The Lord answered, O Moses, chop a bird then put the bird's flesh separately into all the mountains, after that call the bird, surely the meats that you spread will gather together and immediately come before you. When the Prophet Musa cried out to the bird, suddenly the meat quickly moved to one another to become a bird as before.

Personogenesis Through Imitating Human Behavior in a Humanoid Robot "Alter3".

In this study, we report the investigations conducted on the mimetic behavior of a new humanoid robot called Alter3. Alter3 autonomously imitates the motions of a person in front of it and stores the motion sequences in its memory. Alter3 also uses a self-simulator to simulate its own motions before executing them and generates a self-image. If the visual perception (of a person's motion being imitated) and the imitating self-image differ significantly, Alter3 retrieves a motion sequence closer to the target motion from its memory and executes it. We investigate how this mimetic behavior develops interacting with human, by analyzing memory dynamics and information flow between Alter3 and a interacting person. One important observation from this study is that when Alter3 fails to imitate a person's motion, the person tend to imitate Alter3 instead. This tendency is quantified by the alternation of the direction of information flow. This spontaneous role-switching behavior between a human and Alter3 is a way to initiate personality formation (i.e., personogenesis) in Alter3.

“Grabbing the ‘Bull’ by the ‘Horns’”: A Critical Analysis of the Establishment of AfCFTA

The establishment of the Free Trade Area (FTA) covering the whole of Africa is intended to combine the existing Free Trade Areas (FTAs) within the Regional Economic Communities (RECs), to attain maximum gains from trade and bolster AU’s growth and development objectives. But several regional blocs, including the Tripartite Free Trade Areas (T-FTA), have all missed their deadlines set to achieve the objectives of the Abuja Treaty of 1991 in six stages. This means that the launch of the CFTA has become a parallel process with immediate effect since all FTAs and T-FTA are to collapse into the Af- CFTA when trading commences. The question therefore is, why hasn’t the AU waited until it can harmonize, that is, combine existing arrangements of trade and the movement of persons, under its “building blocs” concept for continental unity? In launching the AfCFTA by the AU, does such a “hasty act,” tantamount to the removal of layers of complexity in Africa’s existing arrangements? The prevailing continental state system in Africa, according to functionalists, contributes to continental tensions and conflicts because it is institutionally inadequate. Accordingly, it cannot deal with the basic continental problems because it has arbitrarily divided continental society into national units based on territory, and not on the problems (or issues) to be solved. This is because any successful integration project requires autonomous and credible central institutions that can act as motors of acceleration. Employing theories of functionalism and neo-functionalism, this paper is of the view that the attempt to launch the AfCFTA by the AU is an act of rebooting the dormant Custom Unions across the respective RECs. The action by the AU is to arrest their failures, hence “grabbing the bull by the horns,” so as to empower and also embolden RECs to own the regional integration processes and to build resilience against global shocks.

People’s Fast Moving Detection Method in Buses Based on YOLOv5

To ensure the public’s safety such as in buses, it is very important to accurately judge people’s behaviors and give early warnings. If by watching the video surveillance manually, the cost will be very high, and it cannot be effectively popularized, so video automatic monitoring is preferred. For buses, its environmental space is closed as well as narrow, and at the same time, it is often in a non-stationary state, so traditional behavior detection methods cannot be used here as they are easily affected by moving environment and difficult to fulfill object behavior identification in real time. Aiming at this problem, for people’s fast-moving in buses, a kind of detection method based on YOLOv5 is proposed in this paper. Firstly, the method detects people through one-stage object detection. Secondly, in order to obtain the person's movement trajectory quickly and accurately, an improved two-stage object matching algorithm is designed to track different people. Then, the speed curves of a person during normal activities and fast moving are compared. Finally, an abnormal alarm mechanism is constructed to realize the effective fast movement alarm. Surveillance video in the bus was used to test and evaluate the effectiveness of the method. Results show that the accuracy rate of our method can get 95.4%.

Not Quite Yourself Today

The shortcomings of the traditional password-based authentication mechanism are becoming increasingly apparent as we transition from "one user - one device" to a richer "multiple users - multiple devices" computing paradigm. The currently dominant research direction focuses on on-device biometrics, which require sensitive information, such as images of a user's face, to be constantly streamed from a single recording source, often the device on which a user is getting authenticated. Instead, in this work we explore the possibilities offered by heterogeneous devices that opportunistically collect non-sensitive data in smart environments. We construct an IoT testbed in which we gather data pertaining to a person's movement in space, interaction with certain physical objects, PC terminal usage, and keyboard typing, and construct machine learning models capturing the person's behaviour traits. We commence our examination with models constructed from data sensed during a previously-completed task run and with such models we achieve up to 68% user identification accuracy (c.f. 7% baseline) among up to 20 individuals. Taking into account the limits of behaviour persistence we then revise our approach to continuously refine the model with the most recently sampled sensor data. This method allows us to achieve 99.3% user verification accuracy and successfully prevent a session takeover attack within 12 seconds with less than 1% of false attack detection.

Development of a novel real-time simulation of human skeleton/muscles

The objective of this research work was to develop a model of human skeleton with the capability of real-time simulation of the physical movements of a person in front of the motion capture hardware (Kinect) in order to analyze the motion data and measure the changes of joint torques. Mevea simulation software has been utilized for this purpose, which is a novel application of this software in the field of biomechanics. The model of the human skeleton was created in Mevea using the graphics built in 3ds Max. Simulink external interface for Mevea was established. Simulink acts as a connection between the Mevea software and Kinect for controlling the model. The developed model has been tested through three case studies involving the elbow joint, thoracic joint, and full body. Changes in torque and angular position of joints based on the input of joints are presented as graphs. The developed real-time model of the human skeleton in Mevea can execute the real-time simulation of a person's movements in front of a motion capture camera and provide the changes of torques, which are dependent on the angular positions of the body joints. This work provides the possibility to use the developed real-time model for physiotherapeutic rehabilitation to identify problematic muscles based on produced torque of the joints in order to specify the therapeutic options. The future research direction would be creating a reference databank by measuring healthy individuals' muscle forces for comparison purposes.

Localization of a person moving with an unknown character of motion

ABSTRACT In the last decade, it has been shown that short-range ultra-wideband (UWB) sensors can provide promising solutions to the issue of people localization in many interesting applications. The applicability of particular localization methods utilizing this wireless technology depends on the form of the motion of the monitored person. Therefore, great effort was initially taken to localize people who always carry out the same type of movement, i.e. to localize either moving or only static persons. In real life, people do not move always by the same form of the motion, but the character of their movement is normally time-variable. Moreover, a person-monitoring system has usually no a priori information about the movement status of the person to be monitored. The issue of localization of persons moving both by an unknown and changing character of motion has not been satisfactorily addressed. Motivated by these findings, we will introduce a new concept of UWB sensor signal processing focused on localization of a person moving with an unknown and time-variable character of motion. This concept is based on the decomposition of possible motion activities of persons into a finite set of basic forms of movement defining the so-called types of persons, while a specific signal processing procedure is proposed. The corresponding form of a person's movement is first identified and then the person is detected and localized. The performance properties of this concept will be illustrated by its application for through-the-wall localization of a person moving with short and long stops.

A Deep Learning Approach to Diagnosing Multiple Sclerosis from Smartphone Data.

Multiple sclerosis (MS) affects the central nervous system with a wide range of symptoms. MS can, for example, cause pain, changes in mood and fatigue, and may impair a person's movement, speech and visual functions. Diagnosis of MS typically involves a combination of complex clinical assessments and tests to rule out other diseases with similar symptoms. New technologies, such as smartphone monitoring in free-living conditions, could potentially aid in objectively assessing the symptoms of MS by quantifying symptom presence and intensity over long periods of time. Here, we present a deep-learning approach to diagnosing MS from smartphone-derived digital biomarkers that uses a novel combination of a multilayer perceptron with neural soft attention to improve learning of patterns in long-term smartphone monitoring data. Using data from a cohort of 774 participants, we demonstrate that our deep-learning models are able to distinguish between people with and without MS with an area under the receiver operating characteristic curve of 0.88 (95% CI: 0.70, 0.88). Our experimental results indicate that digital biomarkers derived from smartphone data could in the future be used as additional diagnostic criteria for MS.

Perceptual simultaneity and its modulation during EMG-triggered motion induction with electrical muscle stimulation.

When human movement is assisted or controlled with a muscle actuator, such as electrical muscle stimulation, a critical issue is the integration of such induced movement with the person’s motion intention and how this movement then affects their motor control. Towards achieving optimal integration and reducing feelings of artificiality and enforcement, we explored perceptual simultaneity through electrical muscle stimulation, which involved changing the interval between intentional and induced movements. We report on two experiments in which we evaluated the ranges between detection and stimulus for perceptual simultaneity achievable with an electromyography-triggered electrical muscle stimulation system. We found that the peak range was approximately 80-160 ms, with the timing of perceptual simultaneity shifting according to different adaptation states. Our results indicate that perceptual simultaneity is controllable using this adaptation strategy.

Body Mass Index in Human Gait for Building Risk Assessment Using Graph Theory.

This article presents a comprehensive study of human physiology to determine the impact of body mass index (BMI) on human gait. The approach followed in this study consists of a mathematical model based on the centre of mass of the human body, the inertia of a person in motion and the human gait speed. Moreover, the study includes the representation of a building using graph theory and emulates the presence of a person inside the building when an emergency takes place. The optimal evacuation route is obtained using the breadth-first search (BFS) algorithm, and the evacuation time prediction is calculated using a Gaussian process model. Then, the risk of the building is quantified by using a non-sequential Monte Carlo simulation. The results open up a new horizon for developing a more realistic model for the assessment of civil safety.

Analysis of movement of persons with disabilities during evacuation by lift

Abstract Lifts are indispensable for the evacuation of mobility-impaired people from buildings in case of emergency. It is necessary to quantify the movement parameters of these people and describe the entire process using a suitable algorithm. The aim of the research was to quantify the times and speeds of movement for a person using a wheelchair and for an injured person. An experiment in situ was used. During the experiment, arrivals at the lift, cabin entries, and exits were monitored. The results include the times and speeds of a mobility-impaired person's movement. The experiments showed that a person using a wheelchair was slower than an injured person. The results can be used to expand computational models to account for the possibility of using lifts for evacuation.

Movement parameters of persons with disabilities on evacuation by lifts

In 2010 it was defined five challenges for the solution of evacuation of persons in buildings to 2020. One of the challenges is to implement helpfull technologies during evacuations from buildings – lifts. Needed steps for fulfilling this challenge are also quantification of missing data which are dealing with evacuation of persons with disabilities. From 2002 all public buildings in Slovak Republic have to be also accessible to persons with disabilities, but it is also a global problem. In present exists just small number of informations of movement parameters of persons with disabilities during evacuation by lift. There for, this work was focused on collecting these informations. The data collection was realized by using an in-situ experiment. The aim of the work was to quantify the phase stages of evacuation by elevators for persons with disabilities (speed, time, movement and capacity parameters). Person's movements were monitored during the measurements, arrival to lift, cabin entry and exit from the cabin, including leaving the bounded area. Arrival to lift included movement in the bounded area in front of the lift, until the moment of pushing the button was pressed to call the lift. The time of cabin entering includes the time from the beginning of opening the lift doors to the beginning of closing of the lift doors. The exit from the cabin includes the time from opening the lift doors, passing through the lift doors to leaving the bounded area. In total, ten participating persons in the experiments imitated wheelchair movement and movement with leg fracture. Measurements were made on two lifts, where person evacuating himself or with the help of another person. Everyone performed each measurement three times. A total of 720 measurements were performed in the work. According to the results of the experiment it can be stated that cabin entry is longer for a person on the wheelchair than for a person with a leg fracture, but the difference is even bigger during exit from the cabin, including leaving the bounded area. During the experiment, various movement techniques have been observed that may affect their overall the time of cabin entry and exit from the cabin. Obtained results can extend existing evacuation model to the possibility of using the lift. The obtained results quantify the individual phase stages of entering to the lift and exiting of the lift for persons with limited movement.

Collaborative Trajectory Mining in Smart-Homes to Support Early Diagnosis of Cognitive Decline

Our ageing world population claims for innovative tools to support healthcare and independent living. In this article, we address this challenge by introducing a novel system to recognize symptoms of cognitive decline by exploiting modern smart-home sensors. Since several studies indicate that cognitive issues are frequently associated to locomotion anomalies, our work relies on clinical models of wandering behavior. Previous works tried to recognize wandering of elderly people in outdoor environments, using GPS data and location trace analysis. However, the recognition of wandering indoors poses additional challenges. On the one hand, when moving in a restricted indoor environment, a system for wandering recognition may produce a large number of false positive, since a person's movements are frequently more intricate indoors than outdoors. On the other hand, several indoor movements resembling wandering may be actually due to the normal execution of daily living activities, or to the particular shape of the home. To address these challenges, we adopt a collaborative learning approach, using a training set of trajectories shared by individuals living in smart-homes. New wandering episodes are classified using a personalized model, built considering the homes’ shape and the individuals’ profiles. We apply a long-term analysis of classified wandering episodes to provide a hypothesis of diagnosis to be communicated to a medical center for further inspection. We implemented our algorithms and evaluated the system with a large dataset of real-world subjects, including people with dementia, MCI persons, and cognitively healthy people. The results indicate the potential utility of this system to support the early diagnosis of cognitive impairment.

Fusion-Based Approach for Respiratory Rate Recognition From Facial Video Images

The respiratory rate is an important vital parameter that provides information about persons’ physical condition. In clinical practice it is currently only monitored using contact-based techniques, which can have negative effects on patients. In this study, a new algorithm for remote respiratory rate recognition is presented using photoplethysmographic signals derived from facial video images in the visible light spectrum. The effects of different implementation steps in the presented algorithm are investigated in order to optimize the approach and gain new findings in this research field. In addition, a detailed examination of already implemented procedures is performed and the results are compared on two different databases. We show that by fusing the results of seven different respiratory-induced modulations in combination with other processing steps, very good estimates for the respiratory rate on both moving and non-moving data are achieved. The obtained detection rates of 72.16 % and 87.68 % are significantly higher than those of the best comparison algorithm with 37.37 % and 59.13 %. The comparison algorithms developed so far are not competitive with the newly designed method, especially for video recordings involving persons in motion. This paper provides important new findings in the field of facial video-based respiratory rate recognition for the research community. A new method has been created that delivers significantly better estimates of the respiratory rate than previously developed techniques.