Types Of Shoes Research Articles

Maximalist Shoes: Separating Science From Hype.

One of the most discussed but misunderstood topics in foot and ankle is shoe wear choices and the purported benefits of each type of shoe versus their actual scientific advantages. All foot and ankle care providers should be familiar with the various shoe wear types available to patients to improve their overall foot health. Recently, mainstream popularity and media coverage of maximalist shoes has created increased interest in the science and potential clinical benefits of maximalist shoes. The purpose of this review is to present the current biomechanical evidence of maximalist shoes and to help inform the foot and ankle community of their potential therapeutic applications.Levels of Evidence: Level V.

AFPILD: Acoustic footstep dataset collected using one microphone array and LiDAR sensor for person identification and localization

Empowering the auditory perception-based person identification and localization could enable the service robots to navigate among the crowds in a more socially compliant manner. And it is more user-friendly with fewer privacy concerns compared to the widely studied camera-supported approaches. One way to achieve such auditory person identification and localization is to identify and locate the subject by hearing her/his footstep. As far as we know, although several related acoustic identification benchmark datasets have been made, the dataset that simultaneously concentrates on acoustic identification and localization is absent. Aiming at the shortage of such benchmark datasets, we propose to build the acoustic footstep-based person identification and localization dataset (AFPILD) by unifying the identify and locate tasks for the first time, concerning the clothing and shoe type covariates from the human-aware mobile service robot navigation perspective. Specifically, we record the walking sounds of 40 subjects with a lightweight microphone array in one real unstrained indoor room. For ground truth localization label annotation, we record the point clouds of the walking subjects with a multi-line LiDAR synchronously. The AFPILD contains nearly 10 h of footstep audios (around 62,174 footstep events). To the best of our knowledge, this is the largest and most comprehensive conducted acoustic footstep dataset built for person identification and localization study up to now. We also present the baseline works concerning the identification, localization, and synchronous identify-locate tasks, respectively, to compare various potential approaches on this dataset in the future. Experimental results show that the covariates of clothing and shoe type degrade the footstep identification (around 12% of clothing and 33% of shoe type), while their impacts on the localization are unobvious.

Slip Risk Prediction Using Intelligent Insoles and a Slip Simulator

Slip and fall accidents are the leading cause of injuries for all ages, and for fatal injuries in adults over 65 years. Various factors, such as floor surface conditions and contaminants, shoe tread patterns, and gait behavior, affect the slip risk. Moreover, the friction between the shoe outsoles and the floor continuously changes as their surfaces undergo normal wear over time. However, continuous assessment of slip resistance is very challenging with conventional measurement techniques. This study addresses this challenge by introducing a novel approach that combines sensor fusion technology and machine learning techniques to create intelligent insoles designed for fall risk prediction. In addition, a state-of-the-art slip simulator, capable of mimicking the foot’s motion during a slip, was developed and utilized for the assessment of slipperiness between various shoes and floor surfaces. Data acquisition involved the collection of pressure data and three-axial accelerations using instrumented shoe insoles, complemented by friction coefficient measurements via the slip simulator. The collected dataset includes four types of shoes, three floor surfaces, and four surface conditions, including dry, wet, soapy, and oily. After preprocessing of the collected dataset, the simulator was used to train five different machine learning algorithms for slip risk classification. The trained algorithms provided promising results for slip risk prediction for different conditions, offering the potential to be employed in real-time slip risk prediction and safety enhancement.

Calculation Analysis Break Even Point on Profit Planning Case Study At Ladang Online 2022

Ladang Online is a business in the home industry that produces various types of shoes. This study aims to find out how to calculate the Break Even Point as well as further studies to find out what the operating breakeven point is, the amount of contribution margin, Margin of Safety, to further studies related to cost sensitivity analysis. This research is necessary considering the very dynamic conditions of the business world which require business actors to know how the business conditions they are running, whether they are in a profitable condition or are in a loss condition. The data analysis method used in this research is descriptive analysis method with a quantitative quantitative approach. The data analyzed and used in this study are in the form of interview results and documentation which will be processed first.The results of the research in the Break Even Point analysis at the Toko Sepatu Ladang Online have been able to optimize their performance so that they have been able to obtain sales above the Break Even Point, which means that the Ladang Online Shoe Store has been able to achieve maximum profits every year with predetermined profit target.

Comparison of lower extremity kinematics and ground reaction forces between adolescents who run in motion control shoes with adolescents who run in neutral shoes

Differences in running biomechanics have been reported in adult long-distance runners when running in motion control or neutral shoes. The influence of growth and coordination refinement during puberty limits the generalisability of adult research to adolescents and it is unknown if biomechanics differ between adolescent who run in different types of shoes. The purpose of our study was to compare lower extremity kinematics and ground reaction forces between adolescents running in motion control or neutral shoes. We matched 18 adolescent long-distance runners who ran in motion control shoes with 18 adolescent long-distance runners who ran in neutral shoes according to running speed, sex, and physical maturation. We collected three-dimensional kinematic and ground reaction force data during overground running and performed statistical parametric mapping to compare joint angle and ground reaction force waveforms between the motion control and neutral shoe groups. We found no significant differences for hip, knee, or ankle joint angles (average differences <2°) or ground reaction forces (average differences <0.05 N/kg) between runners who ran in motion control or neutral shoes. Lower extremity kinematics and ground reaction forces were similar between adolescents who ran in motion control or neutral shoes.

The ecological footprint of outdoor activities: Factors affecting human-vectored seed dispersal on clothing

In the Anthropocene, humans are among the most abundant long-distance seed dispersal vectors globally, due to our increasing mobility and the growing global population. However, there are several knowledge gaps related to the process of human-vectored dispersal (HVD) on clothing. In a multi-site field experiment covering various habitat types in three countries of Central-Europe, we involved 88 volunteer participants and collected 251 HVD samples and 2008 subsamples from their socks and shoes. We analysed the number of diaspores and species in the samples. Specifically, we studied the effects of site characteristics (variables related to habitat types and season), vector characteristics (activity type, gender, clothing type, shoe type) and plant characteristics (species pool of the visited habitats and plant traits) on the number of diaspores and array of species dispersed. We assessed the habits of people that could be relevant for HVD with a questionnaire survey. A total of 35,935 diaspores of 229 plant taxa were identified from the samples, which indicates a huge potential of HVD in dispersing diaspores across habitats and regions. Most diaspores were recorded in grassland habitats, and more diaspores were dispersed during fieldwork than excursions. Clothing type also played a decisive role: there were more diaspores and species when wearing short-top shoes and short trousers than long ones. Even though our study was carried out mainly in natural or semi-natural habitats, a large number of dispersed species were disturbance-tolerants and weeds and only a few were specialists, suggesting the controversial role of HVD in conservation. At the individual level, people can reduce the number of diaspores through their clothing choices and diaspore removal habits, while providing adequate equipment for staff, operating cleaning stations, and increasing awareness of employees are main ways in which unintended diaspore dispersal can be tackled at the institutional level.

Response Characteristics and Suppression of Transverse Vibrations of Mine Hoisting Conveyances Excited by Multiple Faults

The failures of steel guides can excite complex and intense transverse oscillations of hoisting containers in the mine hoisting process. The present paper mainly contributes to reveal the response characteristics of the transverse oscillations of mine conveyances excited by various faults such as interface misalignment, local bulge, orbital gap, bending deformation, and orbital tilt. First, a rigid-flexible coupled virtual prototype model between the conveyance and the steel guide was established. Subsequently, the vibration response characteristics of the container under various single and coupling excitations were simulated and analyzed. Eventually, a new type of roller cage shoe with a magnetorheological damper was put forward to decrease the transverse impact responses. Based on the hyperbolic tangent model of magnetorheological dampers, a semiactive fuzzy PID method was studied to explore the vibration suppression of the container. The results showed the fuzzy PID method can play a good role in the vibration reduction. This paper can give a fine scheme for the virtual simulation and semiactive vibration control of the mine hoisting system.

Determinants of Podoconiosis in Bensa District, Sidama Region, Ethiopia: A case control study.

Podoconiosis is one of the neglected tropical diseases (NTD) with the greatest potential for elimination. Despite its public health importance, podoconiosis is a poorly understood disease which led to a widespread misconception about its cause, prevention, and treatment. Even though the exact global burden is still to be measured, it is estimated that at least 4 million people are affected with podoconiosis worldwide, of which more than 1.5 million people are in Ethiopia. The objective of this study was to identify the determinants of podoconiosis in Bensa District, Sidama Regional State, Ethiopia. A community-based unmatched case-control study was used to identify the determinants of podoconiosis. The sample size was estimated using the double population proportion formula. An interviewer-administered structured questionnaire was used for data collection. Blood specimens collected from cases were tested by Filariasis Test Strip to exclude lymphatic filariasis. Data were checked for completeness, coded and entered into Epi-data Version 4.6, and exported to the SPSS version 22 software. Variables with a p<0.2 in the bivariate analysis were further analyzed using multivariable binary logistic regression. Multivariable logistic regression analysis was used to examine determinants that could be associated with podoconiosis with a 95% confidence interval. A total of 459 (153 cases and 306 controls) participants were included with a response rate of 100%. Factors such as the age of participant [AOR = 0.34, 95% CI (0.13-0.87)], being female [AOR = 2.90, 95% CI (1.40-6.10)], age at which shoe wearing started [AOR = 0.7, 95% CI (0.03-0.16)], not wearing shoe daily [AOR = 2.26, 95% CI (1.05-4.86)], wearing hard plastic shoe [AOR = 3.38, 95% CI (1.31-10.89)], and family history with a similar disease (leg swelling) [AOR = 10.2, 95% CI (3.97-26.37)] were significantly associated with the occurrence of podoconiosis. The age of the participants, gender, the age at which shoe wearing started, type of shoe the participants' wear, frequency of shoe wearing, traveling barefoot, and family history with similar disease (leg swelling) were significantly associated with the occurrence of podoconiosis. Sidama regional health bureau along with non-governmental organizations working on the neglected tropical disease should plan modalities on awareness creation and comprehensive health education on shoe wearing and foot hygiene.

Wearable Foot Pressure Sensing System for Fallen Arch Analysis

The main purpose of this research is to distinguish the extent of fallen arch by analyzing the center of foot pressure when people are walking. Fallen arch is often called the flatfoot. There are two types of flatfoot, the rigid flatfoot and the acquired flatfoot. The rigid flatfoot is because of bones formation, and people often get rigid flatfoot when they are young. The acquired flatfoot occurs usually on adults because of the walking postures, shoe types, weight and so on. Since these reasons, it is possible that we can improve or prevent the acquired flatfoot through wearing orthotic insoles or changing the walking posture. That’s the reason why our research is focusing on the acquired flatfoot. In this research, we develop a wearable foot pressure sensing system, consist of wireless Bluetooth transmit module and sensing insoles. The wireless Bluetooth transmit module helps to accomplish our measuring system as a wearable device. The sampling rate of wireless Bluetooth transmit module is one thousand samples per second. As a result, we can get a very detailed track on the walking motions. The sensing insoles are made of triboelectric nanogenerator (TENG) technology. The working principle of TENG is based on the coupling of triboelectric effect and electrostatic induction. Depending on the property of triboelectric generation of different materials and through continuous contact and separation, there is an electrostatic induction and current flow between the triboelectric layers and the electrodes, thus causing the potential difference. By detecting the potential differences, we can get the signals of pressure, so we can calculate the center of foot pressure and compare with the standard to check which walking posture we can apply to improve the fallen arch and find out where the center of foot pressure should be placed. Using this system, we can get the real-time foot pressure information and collect the information anytime and anywhere, accomplishing the smart medical.

An Individualized Machine Learning Approach for Human Body Weight Estimation Using Smart Shoe Insoles.

Rapid significant weight fluctuations can indicate severe health conditions such as edema due to congestive heart failure or severe dehydration that could require prompt intervention. Daily body weighing does not accurately represent the patient's body weight fluctuations occurring within a day. The patient's lack of compliance with tracking their weight measurements is also a predominant issue. Using shoe insole sensors embedded into footwear could achieve accurate real-time monitoring systems for estimating continuous body weight changes. Here, the machine learning models' predictive capabilities for continuous real-time weight estimation using the insole data are presented. The lack of availability of public datasets to feed these models is also addressed by introducing two novel datasets. The proposed framework is designed to adapt to the patient, considering several unique factors such as shoe type, posture, foot shape, and gait pattern. The proposed framework estimates the mean absolute percentage error of 0.61% and 0.74% and the MAE of 1.009 lbs. and 1.154 lbs. for the less controlled and more controlled experimental settings, respectively. This will help researchers utilize machine learning techniques for more accurate real-time continuous weight estimation using sensor data and enable more reliable aging-in-place monitoring and telehealth.

Low back pain in a sample of Syrian pregnant women: A cross-sectional study.

Low back pain related to pregnancy occurs in 60%-70% of pregnancies, at any time during pregnancy. During pregnancy, many factors such as weight gain, and others are the causes of the back pain. In Syria, due to the circumstances of the war, many pregnant women may be exposed to increase the risk of lower back pain, so this study will determine the prevalence of lower back pain among pregnant women and its potential risk factors. We aimed to evaluate the prevalence of low back pain in pregnant women and to assess the risk factors related to it. A cross-sectional, observational study was conducted between May 2020 and December 2022 at Obstetrics and Gynecology University Hospital in Damascus, Syria. Pregnant women aged over 18 years were selected from the outpatient clinic. Participants, after signing the informed consent, fill out the survey, which included the following parameters: age, weight, height, body mass index (BMI), education, parity, shoe type, weekly walking hours, occupation, low back pain, in which semester, radiation, onset, alleviating and aggravating factors, disability, and pain in previous pregnancies. We used Excel 2010, and the Statistical Package for the Social Sciences version 23.0. p < 0.05 was considered statistically significant, and we used the Chi-square test (χ 2 test), t student test to test the basal differences between groups. A number of 551 pregnant participants were included and low back pain prevalence was 62%. There was a statistically significant relation between low back pain and each of the following: Obesity, weekly walking hours, pain in previous pregnancies, and occupation. Low back pain is prevalent during pregnancy and the most important risk factors include obesity and pain in previous pregnancies whereas walking and employment are protective measures to prevent low back pain.

Different Influencing Factors for Risk of Falls Between Men and Women while Descending from Mount Fuji.

Annually, approximately 250,000 people climb Mount Fuji in Japan. Nonetheless, only few studies have examined the prevalence of falls and related factors on Mount Fuji. We conducted a questionnaire survey of 1061 participants (703 men and 358 women) who had climbed Mount Fuji. The following information was collected: age, height, body weight, luggage weight, experience on Mount Fuji, experience on other mountains, presence or absence of a tour guide, single-day climber or overnight-stay lodger, information on the downhill trail (volcanic gravel, long distance, and the risk of falls), presence or absence of trekking poles, shoe type, shoe sole condition, and fatigue feeling. The fall rate in women (174/358; 49%) was greater than that in men (246/703; 35%). A prediction model using multiple logistic regression (no fall, 0; fall, 1) indicated that the following factors decreased the risk of falls: male sex, younger age, previous experience on Mount Fuji, having information about long-distance downhill trails, wearing hiking shoes or mountaineering boots rather than other types of shoes (eg, running shoes, sneakers) or worn-out shoes, and not feeling fatigued. Additionally, the following factors may decrease the risk of falls in women only: experience hiking on any other mountains, not being part of a guided tour, and using trekking poles. Women had a higher risk of falls on Mount Fuji than men. Specifically, having less experience on any other mountains, being part of a guided tour, and nonuse of trekking poles may relate to higher risks of falls in women. These results suggest that different precautionary measures for men and women are useful.

Application of the Trend Moment Method to Predict Shoes Sales

The N+2 Fashion store is engaged in selling trend shoes which is located in Air Batu City. Activities in the N+2 Fashion Store include ordering and selling trending shoes. Checking the supply of trending shoes is done by checking them one by one, of course this will make it very difficult for employees to estimate the number of trend shoes they want to order from each trending type of shoe. The large number of trend shoe brands is an obstacle in carrying out business processes which results in wrong prices for these trend shoes. In predicting trend shoes must ensure the sales process, minimize costs and time required. The problem faced by the N+2 Fashion Store is the difficulty in predicting the number of items that must be available for the next period in order to meet customer needs and not cause a buildup of goods in the long term. To overcome this problem, predictions are made using the trend moment method which is a forecasting method used to see trends (data that have increased) based on historical data from one variable using time series data. The results of the research obtained a prediction that in September 2022 there would be 9 pcs of Adidas shoes sold with a MAPE error rate of 16.33%.

RECONSTRUCTING THE CLOTHES OF BOSPORAN WOMAN.

The study of clothes of people who lived in Ukrainian territories during Scythia times has large bibliography. The sources for reconstruction of different types of clothes, shoes, headwear and jewelry are archaeological art materials, most of which come from the burials. The burials located in Crimea provide a peculiar information regarding clothes of Bosporan Kingdom’s citizens. Near Tobechiv lake the kurgans which are called Three Brothers were excavated. One of them (N 1 Elder Brother) had the burial of the middle-aged woman with accompanying individual. The burial rite, the objects and mainly — the jewelry on the clothes, indicate the high status of this woman. While recreating her clothes, the central image on the burial stele which marks the burial 1 has high importance. We are talking about the image of the woman wearing the headwear — the kalafa — on top of the stlenhida with, probably, pendants. The buried woman had similar headwear. It is indicated by golden arc-shaped with relievo ornament. The main part depicts the fight between crouching panther (on the left) and lion (on the right). Above them is the ornament of palmette and lotus flower.&#x0D; The thin golden plate is the applique which preserved the outline of the headwear of kalafa type — the crown which resembles the basked or cut cone, turned up with its wider side. The lover part of the plate, in the forehead part, has pendants with several particles: beads, plates with double spirals and bean-shaped pendants.&#x0D; The woman had another headwear — forehead ribbon. It had small golden plates with the image of goddess Nika and palmettes. While women of Bosporus combined kalafa and stlenhida, Scythian women combined their headwears with forehead ribbons decorated with golden stripes or plates. The decoration of headwear had protective functions as well as religions sense — animal and plant images depict gods of nature.&#x0D; The earrings were hanged to ribbons, as well as to stlenhidas. In this case it is the beautiful creations of Greek masters — sculptural creations depicting the sphinx. They created the composition along with the headwear decoration. The demonstration of earrings in this way fully represented their art and sense characteristics. The costume is also represented by the bracelets and rings. The rich costume, which decoration represents the symbols of gods of nature, might indicate the spiritual functions of the woman.

Shoe configuration effects on third phalanx and capsule motion of unaffected and laminitic equine hooves in-situ.

Equine shoes provide hoof protection and support weakened or damaged hoof tissues. Two hypotheses were tested in this study: 1) motion of the third phalanx (P3) and hoof wall deformation are greater in laminitic versus unaffected hooves regardless of shoe type; 2) P3 displacement and hoof wall deformation are greatest while unshod (US), less with open-heel (OH), then egg-bar (EB) shoes, and least with heart-bar (HB) shoes for both hoof conditions. Distal forelimbs (8/condition) were subjected to compressive forces (1.0x102-5.5x103 N) while a real-time motion detection system recorded markers on P3 and the hoof wall coronary band, vertical midpoint, and solar margin. Magnitude and direction of P3 displacement and changes in proximal and distal hemi-circumference, quarter and heel height and proximal and distal heel width were quantified. Hoof condition and shoe effects were assessed with 2-way ANOVA (p<0.05). P3 displacement was greater in laminitic hooves when US or with OH, and EB and HB reduced P3 displacement in laminitic hooves. P3 displacement was similar among shoes in unaffected hooves and greatest in laminitic hooves with OH, then US, EB and HB. EB and HB increased P3 displacement from the dorsal wall in unaffected hooves and decreased it in laminitic hooves. OH and EB increased P3 motion from the coronary band in laminitic hooves, and HB decreased P3 motion toward the solar margin in unaffected and laminitic hooves. In laminitic hooves, HB reduced distal hemi-circumference and quarter deformation and increased heel deformation and expansion. Proximal hemi-circumference constriction was inversely related to proximal heel expansion with and without shoes. Overall, shoe configuration alters hoof deformation distinctly between unaffected and laminitic hooves, and HB provided the greatest P3 stability in laminitic hooves. These unique results about P3 motion and hoof deformation in laminitic and unaffected hooves inform shoe selection and design.

갯벌 고립사고 대응 인명구조대원을 위한 갯벌 보행용 안전신발의 적정 유형 연구

갯벌 고립사고 대응 인명구조대원을 위한 갯벌 보행용 안전신발의 적정 유형 연구

A Review of Techniques on Gait-Based Person Re-Identification

Survey/review study A Review of Techniques on Gait-Based Person Re-Identification Babak Rahi 1,*, Maozhen Li 1, and Man Qi 2 1 Department of Electronics and Computer Engineering, Brunel University London, Uxbridge, Middlesex, UB8 3PH, United Kingdom 2 The School of Engineering, University of Warwick, Coventry CV4 7AL, United Kingdom * Correspondence: babak.h.rahi@hotmail.com Received: 16 October 2022 Accepted: 14 December 2022 Published: 27 March 2023 Abstract: Person re-identification at a distance across multiple non-overlapping cameras has been an active research area for years. In the past ten years, short-term Person re-identification techniques have made great strides in accuracy using only appearance features in limited environments. However, massive intra-class variations and inter-class confusion limit their ability to be used in practical applications. Moreover, appearance consistency can only be assumed in a short time span from one camera to the other. Since the holistic appearance will change drastically over days and weeks, the technique, as mentioned above, will be ineffective. Practical applications usually require a long-term solution in which the subject's appearance and clothing might have changed after the elapse of a significant period. Facing these problems, soft biometric features such as Gait has stirred much interest in the past years. Nevertheless, even Gait can vary with illness, ageing and emotional states, walking surfaces, shoe types, clothes types, carried objects (by the subject) and even environment clutters. Therefore, Gait is considered as a temporal cue that could provide biometric motion information. On the other hand, the shape of the human body could be viewed as a spatial signal which can produce valuable information. So extracting discriminative features from both spatial and temporal domains would benefit this research. This article examines the main approaches used in gait analysis for re-identification over the past decade. We identify several relevant dimensions of the problem and provide a taxonomic analysis of current research. We conclude by reviewing the performance levels achievable with current technology and providing a perspective on the most challenging and promising research directions.

Effect of shoeing horses with eggbar shoes and shoes with wedge pads on blood flow parameters in the lateral digital artery in the Doppler ultrasound.

A sound knowledge of horseshoe impact on blood flow parameters is required for making shoeing decisions and selecting the most appropriate types of shoes. The aim of this study was to determine the effect of horse shoeing with egg bar shoes and shoes with wedge pads on blood flow parameters in the lateral palmar digital artery measured by Doppler ultrasound. The study was conducted on 16 horses divided into two groups. Horses from group 1 were shod with egg bar shoes. Horses from group 2 were shod with shoes with wedge pads. Doppler ultrasound parameters of the lateral palmar digital artery at the level of the metacarpophalangeal joint were evaluated. Doppler tests were performed before and after shoeing within a monthly interval. The results of the study indicate that egg bar shoes have a greater impact on blood circulation in the distal part of the equine limb than shoes with wedge pads. However, the only parameters to have changed substantially after shoeing with egg bar shoes were end-diastolic velocity (EDV) and mean velocity (Vmn) in the lateral palmar digital artery. A low-resistance blood flow pattern was noted before shoeing. After shoeing in group 1, it remained unchanged in 5 horses, whereas a high-resistance pattern was observed in 3 animals. A low-resistance blood flow pattern was noted in all group 2 horses after shoeing. The difference between the analyzed shoeing techniques could be attributed to increased pressure in the heel bulb area in horses shod with egg bar shoes. Wedge pads shift the load away from the heel bulbs, which might reduce the pressure on the palmar digital vessels and exert a smaller influence on the parameters measured in the Doppler ultrasound test.

Three Step Volumetric Segmentation for Automated Shoe Fitting

This work presents a three-step segmentation process based on Convolutional Neural Networks. The task is to identify the different parts of shoes from Computed Tomography scans of boxed pairs of shoes. The first step of the three-step algorithm uses a scaled-down volume image to separate the shoe material from its surroundings. The second step segments the shoe's inside volume, i.e. the space enclosed by shoe material. The third and last step splits the segmented shoe material into individual components: shoe upper material, outer and insole. The complete process employs CNNs derived from three-dimensional UNets. Residual SE UNet, Dense UNet, and Bottleneck Residual UNet are evaluated for the three steps. The architectures are modified for large receptive fields. The networks are trained and tested for each step separately and conjointly on CT scans comprising various shoe types. The test results inspire hope for using the process for automated segmentation and extraction of meshes from large batches of CT scans. In particular, the first step using a Residual SE UNet achieves an F1-score of 88.2 % for shoes and 58.9 % for the packing material. The second step segments the inside volume with an F1-score of 81.0 %. The third step segments the shoe into its components and achieves an F1-score for insole of 79.5 %, outer sole of 88.7 % and upper material of 81.3 %.

Semi-supervised approach to identify steps, shoes, and gender of older adults under semi-naturalistic conditions using a waist-worn inertial sensor.

An emerging source of information to recognize individuals' characteristics are the walking pattern-related parameters. The elderly can be one of the populations that can benefit most from recognition-based applications, which may help to increase their possibilities of living independently at home. Approaches have been mostly focused on gait events' identification or assessment; nonetheless, such information can also be used to obtain seniors' characteristics that depend on physiological or environmental factors. These factors can be useful to provide a customized assistance based on contextual information. In this paper, we propose a method focused on seniors, to detect steps, and to recognize gender and type of shoes by using only the initial foot contact (IC) data obtained from inertial sensors during semi-controlled walking. Data were collected from 20 older adults who walked at self-speed in a natural environment. The method consists of first clustering the IC using k-means; then, a trained recurrent neural network recognizes gender, type of shoes, and the step phases (IC and other phases); to finally conduct step detection (SD) using a ruled-based method. The method recognizes gender and the type of shoes with an accuracy of 93% and 83.07%, respectively, whereas there were not misrecognitions of the step phases. SD achieved a mean absolute percentage error equal to . The good results show that the method is appropriate for users' characteristics recognition applications without depending on assumptions based on individualities. Likewise, the method can be useful to monitor physical activity or systems aimed to keep safe older adults.