A surface electromyography and inertial measurement unit dataset for the Italian Sign Language alphabet.
Ontology highlight
ABSTRACT:
SUBMITTER: Pacifici I
PROVIDER: S-EPMC7644570 | biostudies-literature | 2020 Dec
REPOSITORIES: biostudies-literature
Publications
A surface electromyography and inertial measurement unit dataset for the Italian Sign Language alphabet.
Pacifici Iacopo I Sernani Paolo P Falcionelli Nicola N Tomassini Selene S Dragoni Aldo Franco AF
Data in brief 20201022
Surface Electromyography (EMG) and Inertial Measurement Unit (IMU) sensors are gaining the attention of the research community as data sources for automatic sign language recognition. In this regard, we provide a dataset of EMG and IMU data collected using the Myo Gesture Control Armband, during the execution of the 26 gestures of the Italian Sign Language alphabet. For each gesture, 30 data acquisitions were executed, composing a total of 780 samples included in the dataset. The gestures were p ...[more]
Similar Datasets
Project description:Nowadays, surface electromyography (sEMG) is evolving as a technology for hand gesture recognition. Detailed studies have revealed the capacity of EMG signals to access detailed information, particularly in the classification of hand gestures. Indeed, this advancement emerges as an interesting element in refining the recognition and interpretation of sign languages and exploring deeper into the phonology of signed languages. Aligned with this advancement and the need for a reliable and mobile sign language recognition system, we introduce a specialized sEMG dataset, acquired using the Myo armband. This device is adept at capturing recordings at frequencies of up to 200 Hz. The dataset focuses on the 28 letters of the Arabic alphabet and 10 digits using hand gestures, with each gesture captured into 400 frames. This considerable collection of 18,716 samples was achieved with the cooperation of three contributors, providing a varied and comprehensive range of gestural data.
| S-EPMC10661691 | biostudies-literature
Project description:Deaf and hard-of-hearing individuals use sign language as a means of communication. However, those around them, especially family members like the children of deaf adults, may face communication challenges if they are unfamiliar with sign language. This issue has prompted numerous researchers to conduct studies on sign language translation and recognition. However, there is currently no publicly available dataset specifically for Malaysian sign language. This article introduces an image dataset of the Malaysian Sign Language (MySL) hand gestures used in everyday situations. The dataset, named MyWSL2023, comprises 3,500 images of ten static Malaysian sign language words collected from five participants (two males and three females) aged between 20 and 21 years old. The data collection took place indoors under normal lighting conditions. The MyWSL2023 dataset, which has been made freely accessible to all researchers, serves as a valuable resource for not only investigating and developing automated systems for hearing-impaired and deaf individuals but also gesture and sign language recognition using vision-based methods. The dataset can be accessed for free at https://data.mendeley.com/datasets/zvk55p7ktd.
| S-EPMC10439288 | biostudies-literature
Project description:A fully-labelled dataset of Arabic Sign Language (ArSL) images is developed for research related to sign language recognition. The dataset will provide researcher the opportunity to investigate and develop automated systems for the deaf and hard of hearing people using machine learning, computer vision and deep learning algorithms. The contribution is a large fully-labelled dataset for Arabic Sign Language (ArSL) which is made publically available and free for all researchers. The dataset which is named ArSL2018 consists of 54,049 images for the 32 Arabic sign language sign and alphabets collected from 40 participants in different age groups. Different dimensions and different variations were present in images which can be cleared using pre-processing techniques to remove noise, center the image, etc. The dataset is made available publicly at https://data.mendeley.com/datasets/y7pckrw6z2/1.
| S-EPMC6661066 | biostudies-literature
Project description:Sign Language Recognition (SLR) is crucial for enabling communication between the deaf-mute and hearing communities. Nevertheless, the development of a comprehensive sign language dataset is a challenging task due to the complexity and variations in hand gestures. This challenge is particularly evident in the case of Bangla Sign Language (BdSL), where the limited availability of depth datasets impedes accurate recognition. To address this issue, we propose BdSL47, an open-access depth dataset for 47 one-handed static signs (10 digits, from ০ to ৯; and 37 letters, from অ to ँ) of BdSL. The dataset was created using the MediaPipe framework for extracting depth information. To classify the signs, we developed an Artificial Neural Network (ANN) model with a 63-node input layer, a 47-node output layer, and 4 hidden layers that included dropout in the last two hidden layers, an Adam optimizer, and a ReLU activation function. Based on the selected hyperparameters, the proposed ANN model effectively learns the spatial relationships and patterns from the depth-based gestural input features and gives an F1 score of 97.84 %, indicating the effectiveness of the approach compared to the baselines provided. The availability of BdSL47 as a comprehensive dataset can have an impact on improving the accuracy of SLR for BdSL using more advanced deep-learning models.
| S-EPMC10700367 | biostudies-literature
Project description:Several sign language datasets are available in the literature. Most of them are designed for sign language recognition and translation. This paper presents a new sign language dataset for automatic motion generation. This dataset includes phonemes for each sign (specified in HamNoSys, a transcription system developed at the University of Hamburg, Hamburg, Germany) and the corresponding motion information. The motion information includes sign videos and the sequence of extracted landmarks associated with relevant points of the skeleton (including face, arms, hands, and fingers). The dataset includes signs from three different subjects in three different positions, performing 754 signs including the entire alphabet, numbers from 0 to 100, numbers for hour specification, months, and weekdays, and the most frequent signs used in Spanish Sign Language (LSE). In total, there are 6786 videos and their corresponding phonemes (HamNoSys annotations). From each video, a sequence of landmarks was extracted using MediaPipe. The dataset allows training an automatic system for motion generation from sign language phonemes. This paper also presents preliminary results in motion generation from sign phonemes obtaining a Dynamic Time Warping distance per frame of 0.37.
| S-EPMC10744067 | biostudies-literature
Project description:IntroductionThe use of portable gait measurement systems in research is appealing to collect real-world data at low-cost, low participant burden, and without requirement for dedicated lab space. Most commercially available inertial measurement units (IMU's) designed for running only capture temporospatial data, the ability to capture biomechanics data such as shock and motion metrics with the RunScribe IMU makes it the closest to a lab alternative. The RunScribe system has been validated in running, however, is yet to be validated for walking.MethodQualisys motion capture, AMTI force plates, and Delsys Trigno accelerometers were used as gold standard lab measures for comparison against the RunScribe IMU. Twenty participants completed 10 footsteps per foot (20 total) measured by both systems simultaneously. Variables for validation included: Vertical Ground reaction force (GRF), instantaneous GRF rate, pronation excursion, pronation velocity, total shock, impact force, braking force. Interclass correlation (ICC) was used to determine agreement between the measurement systems, mean differences were used to evaluate group level accuracy.ResultsICC results showed moderate agreement between measurement systems when both limbs were averaged. The greatest agreement was seen for GRF rate, pronation excursion, and pronation velocity (ICC = 0.627, 0.616, 0.539), low agreement was seen for GRF, total shock, impact shock, braking shock (ICC = 0.269, 0.351, 0.244, 0.180). However mean differences show the greatest level of accuracy for GRF, GRF rate, and impact shock.DiscussionResults show mixed agreement between the RunScribe and gold standard lab measures, and varied agreement across left and right limbs. Kinematic variables showed the greatest agreement, however GRF had the lowest relative mean difference for group results. The results show acceptable levels of agreement for most variables, however further work must be done to assess the repeatability and sensitivity of the RunScribe to be applied within areas such as footwear testing and gait retraining protocols.
| S-EPMC9394823 | biostudies-literature
Project description:Locomotion is an important welfare and health trait in turkey production. Current breeding values for locomotion are often based on subjective scoring. Sensor technologies could be applied to obtain objective evaluation of turkey gait. Inertial measurement units (IMUs) measure acceleration and rotational velocity, which makes them attractive devices for gait analysis. The aim of this study was to compare three different methods for step detection from IMU data from turkeys. This is an essential step for future feature extraction for the evaluation of turkey locomotion. Data from turkeys walking through a corridor with IMUs attached to each upper leg were annotated manually. We evaluated change point detection, local extrema approach, and gradient boosting machine in terms of step detection and precision of start and end point of the steps. All three methods were successful in step detection, but local extrema approach showed more false detections. In terms of precision of start and end point of steps, change point detection performed poorly due to significant irregular delay, while gradient boosting machine was most precise. For the allowed distance to the annotated steps of 0.2 s, the precision of gradient boosting machine was 0.81 and the recall was 0.84, which is much better in comparison to the other two methods (<0.61). At an allowed distance of 1 s, performance of the three models was similar. Gradient boosting machine was identified as the most accurate for signal segmentation with a final goal to extract information about turkey gait; however, it requires an annotated training dataset.
| S-EPMC7096551 | biostudies-literature
Project description:Language is a method by which individuals express their thoughts. Each language has its own alphabet and numbers. Oral and written communication are both effective means of human interaction. However, each language has a sign language equivalent. Hearing-impaired and/or nonverbal individuals communicate through sign language. BDSL is the abbreviation for the Bangla sign language. The dataset contains images of hand signs in Bangla. The collection comprises 49 individual sign language images of the Bengali alphabet. BDSL49 is a set of 29,490 images with 49 labels. During data collection, images of fourteen distinct adults, each with a unique appearance and context, were captured. During data preparation, numerous strategies have been utilized to reduce noise. This dataset is available for free to researchers. Using techniques such as machine learning, computer vision, and deep learning, they are able to develop automated systems. Moreover, two models were applied to this dataset. The first is for detection, and the second is for identification.
| S-EPMC10331282 | biostudies-literature
Project description:This study aimed to examine whether a recently developed inertial measurement unit (IMU)-based hip flexion strength-power test could be an indicator of sprint performance, step length (SL) and frequency (SF) during sprinting using sprinters. Sixteen well-trained male sprinters performed 60-m sprints and an IMU-based hip flexion test which consisted of five serial hip flexion-extension motions for each leg with three different conditions (unweighted, 0.75 or 1.5 kg ankle weighted). Running speed, SL and SF from the start to the 50-m mark were measured using a long force platform system. The hip flexion strength-power test variables were collected using one IMU attached to the lateral thigh. The right hip flexion positive work in the 1.5 kg weighted condition was positively correlated with running speed from the 9th-12th to 21st-22nd step sections (r = 0.588-0.761) and with SF at the 17th-20th step section (r = 0.526). The right hip flexion positive mean power in the 1.5 kg weighted condition was positively correlated with running speed from the 13th-16th to 21st-22nd step section (r = 0.547-0.638) and with SF from the 13th-16th to 21st-22nd step section (r = 0.501-0.553). The current results demonstrate that, among well-trained male sprinters, hip flexion positive work and mean power measured using IMU-based strength-power test in the 1.5 kg weighted right leg condition can be a determinant of better sprint performance through higher SF during the later acceleration section approaching maximal speed.
| S-EPMC7739800 | biostudies-literature
Project description:Sign language is a form of communication medium for speech and hearing disabled people. It has various forms with different troublesome patterns, which are difficult for the general mass to comprehend. Bengali sign language (BdSL) is one of the difficult sign languages due to its immense number of alphabet, words, and expression techniques. Machine translation can ease the difficulty for disabled people to communicate with generals. From the machine learning (ML) domain, computer vision can be the solution for them, and every ML solution requires a optimized model and a proper dataset. Therefore, in this research work, we have created a BdSL dataset and named `KU-BdSL', which consists of 30 classes describing 38 consonants ('banjonborno') of the Bengali alphabet. The dataset includes 1500 images of hand signs in total, each representing Bengali consonant(s). Thirty-nine participants (30 males and 9 females) of different ages (21-38 years) participated in the creation of this dataset. We adopted smartphones to capture the images due to the availability of their high-definition cameras. We believe that this dataset can be beneficial to the deaf and dumb (D&D) community. Identification of Bengali consonants of BdSL from images or videos is feasible using the dataset. It can also be employed for a human-machine interface for disabled people. In the future, we will work on the vowels and word level of BdSL.
| S-EPMC10700577 | biostudies-literature