Correction: Garcia-Gonzalez, D.; Rivero, D.; Fernandez-Blanco, E.; Luaces, M.R. A Public Domain Dataset for Real-Life Human Activity Recognition Using Smartphone Sensors. Sensors 2020, 20, 2200.
Ontology highlight
ABSTRACT:
SUBMITTER: Garcia-Gonzalez D
PROVIDER: S-EPMC7472614 | biostudies-literature | 2020 Aug
REPOSITORIES: biostudies-literature
Publications
Correction: Garcia-Gonzalez, D.; Rivero, D.; Fernandez-Blanco, E.; Luaces, M.R. A Public Domain Dataset for Real-Life Human Activity Recognition Using Smartphone Sensors. <i>Sensors</i> 2020, <i>20</i>, 2200.
Garcia-Gonzalez Daniel D Rivero Daniel D Fernandez-Blanco Enrique E Luaces Miguel R MR Luaces Miguel R MR
Sensors (Basel, Switzerland) 20200818 16
The authors wish to make the following corrections to this paper [...]. ...[more]
Similar Datasets
Project description:In recent years, human activity recognition has become a hot topic inside the scientific community. The reason to be under the spotlight is its direct application in multiple domains, like healthcare or fitness. Additionally, the current worldwide use of smartphones makes it particularly easy to get this kind of data from people in a non-intrusive and cheaper way, without the need for other wearables. In this paper, we introduce our orientation-independent, placement-independent and subject-independent human activity recognition dataset. The information in this dataset is the measurements from the accelerometer, gyroscope, magnetometer, and GPS of the smartphone. Additionally, each measure is associated with one of the four possible registered activities: inactive, active, walking and driving. This work also proposes asupport vector machine (SVM) model to perform some preliminary experiments on the dataset. Considering that this dataset was taken from smartphones in their actual use, unlike other datasets, the development of a good model on such data is an open problem and a challenge for researchers. By doing so, we would be able to close the gap between the model and a real-life application.
| S-EPMC7218897 | biostudies-literature
Project description:The research reported herein integrates a generic holographic sensor platform and a smartphone-based colour quantification algorithm in order to standardise and improve the determination of the concentration of analytes of interest. The utility of this approach has been exemplified by analysing the replay colour of the captured image of a holographic pH sensor in near real-time. Personalised image encryption followed by a wavelet-based image compression method were applied to secure the image transfer across a bandwidth-limited network to the cloud. The decrypted and decompressed image was processed through four principal steps: Recognition of the hologram in the image with a complex background using a template-based approach, conversion of device-dependent RGB values to device-independent CIEXYZ values using a polynomial model of the camera and computation of the CIEL*a*b* values, use of the colour coordinates of the captured image to segment the image, select the appropriate colour descriptors and, ultimately, locate the region of interest (ROI), i.e. the hologram in this case, and finally, application of a machine learning-based algorithm to correlate the colour coordinates of the ROI to the analyte concentration. Integrating holographic sensors and the colour image processing algorithm potentially offers a cost-effective platform for the remote monitoring of analytes in real time in readily accessible body fluids by minimally trained individuals.
| S-EPMC5687774 | biostudies-literature
Project description:Mobile devices especially smartphones have gained high popularity and become a part of daily life in recent years. Therefore, there are many studies that investigate users' interactions with smartphones and try to extract meaningful information from various inputs. Actually, the main motivation behind these studies is the behavioral differences of users in their interactions with smartphones. In these studies, motion sensors in devices such as accelerometer and gyroscope are widely used. Data obtained from motion sensors allows to detect information such as age-group, gender, activity type, identity of users. In this context, we develop an Android application that gathers accelerometer sensor data while users perform different activities. This application records all accelerometer data and touch event information generated while users are using their devices. Then, we perform two experiments and collect two different data using this application. In the first experiment, we collect data from 107 child users and 100 adult users to analyze the impact of different age-groups' behavior on sensor data. This dataset includes more than 11.000 taps data for child and adult users, in total. In the second experiment, data is collected from 60 female and 60 male users for different activities like sitting and walking. There are more than 6.000 taps data for sitting and walking scenarios separately in the second dataset. This dataset makes it possible to analyze the changes created by different gender and activity types in the sensor data. These data can be used for behavioral biometric analyses on smartphones such as user age-group and gender detection, user identification and authentication.
| S-EPMC8792433 | biostudies-literature
Project description:This article contains dataset on the behavior of international tourists when traveling is related to 1) tourist demographics, 2) things that affect tourists to choose travel destinations when planning, 3) use of mobile data while traveling, 4) how to get internet access while traveling, 5) social media used during traveling, and 6) behavior of smartphone use for tourists during traveling. The raw data presented here can be used as material to analyze the behavior of international tourists related to any media that affects international tourists in planning their trips, and how they behave during traveling. This data is a source of raw data from our research on smartphones and international tourist behavior, besides being used for various other research purposes.
| S-EPMC6806464 | biostudies-literature
Project description:Driving is considered one of the most difficult tasks because the driver is responsible for a variety of other responsibilities in addition to driving. The primary responsibility of a driver should be to properly operate a vehicle while concentrating solely on driving. However, he/she must also complete various secondary jobs at the same time. Modeling realistic driving behavior proved tough for researchers and scientists. With this goal in mind, we constructed a Smartphone sensor dataset of Indian drivers, complete with driving parameters that have a significant impact on driving behavior. As a result, we created a dataset using Smartphone sensors such as the accelerometer and gyroscope. The data is organized into day-by-day folders, each with seven subfolders. We are confident that the suggested dataset will be beneficial in the training, testing, and validation of a machine learning model for driver behavior classification or reorganization.
| S-EPMC8914310 | biostudies-literature
Project description:Parkinson's disease (PD) is a neurodegenerative disease inducing dystrophy of the motor system. Automatic movement analysis systems have potential in improving patient care by enabling personalized and more accurate adjust of treatment. These systems utilize machine learning to classify the movement properties based on the features derived from the signals. Smartphones can provide an inexpensive measurement platform with their built-in sensors for movement assessment. This study compared three feature selection and nine classification methods for identifying PD patients from control subjects based on accelerometer and gyroscope signals measured with a smartphone during a 20-step walking test. Minimum Redundancy Maximum Relevance (mRMR) and sequential feature selection with both forward (SFS) and backward (SBS) propagation directions were used in this study. The number of selected features was narrowed down from 201 to 4-15 features by applying SFS and mRMR methods. From the methods compared in this study, the highest accuracy for individual steps was achieved with SFS (7 features) and Naive Bayes classifier (accuracy 75.3%), and the second highest accuracy with SFS (4 features) and k Nearest neighbours (accuracy 75.1%). Leave-one-subject-out cross-validation was used in the analysis. For the overall classification of each subject, which was based on the majority vote of the classified steps, k Nearest Neighbors provided the most accurate result with an accuracy of 84.5% and an error rate of 15.5%. This study shows the differences in feature selection methods and classifiers and provides generalizations for optimizing methodologies for smartphone-based monitoring of PD patients. The results are promising for further developing the analysis system for longer measurements carried out in free-living conditions.
| S-EPMC7377496 | biostudies-literature
Project description:Realization of navigation in virtual environments remains a challenge as it involves complex operating conditions. Decomposition of such complexity is attainable by fusion of sensors and machine learning techniques. Identifying the right combination of sensory information and the appropriate machine learning technique is a vital ingredient for translating physical actions to virtual movements. The contributions of our work include: (i) Synchronization of actions and movements using suitable multiple sensor units, and (ii) selection of the significant features and an appropriate algorithm to process them. This work proposes an innovative approach that allows users to move in virtual environments by simply moving their legs towards the desired direction. The necessary hardware includes only a smartphone that is strapped to the subjects' lower leg. Data from the gyroscope, accelerometer and campus sensors of the mobile device are transmitted to a PC where the movement is accurately identified using a combination of machine learning techniques. Once the desired movement is identified, the movement of the virtual avatar in the virtual environment is realized. After pre-processing the sensor data using the box plot outliers approach, it is observed that Artificial Neural Networks provided the highest movement identification accuracy of 84.2% on the training dataset and 84.1% on testing dataset.
| S-EPMC6359150 | biostudies-literature
Project description:This article demonstrates a new smartphone-based reusable glucose meter. The glucose meter includes a custom-built smartphone case that houses a permanent bare sensor strip, a stylus that is loaded with enzyme-carbon composite pellets, and sensor instrumentation circuits. A custom-designed Android-based software application was developed to enable easy and clear display of measured glucose concentration. A typical test involves the user loading the software, using the stylus to dispense an enzymatic pellet on top of the bare sensor strip affixed to the case, and then introducing the sample. The electronic module then acquires and wirelessly transmits the data to the application software to be displayed on the screen. The deployed pellet is then discarded to regain the fresh bare sensor surface. Such a unique working principle allows the system to overcome challenges faced by previously reported reusable sensors, such as enzyme degradation, leaching, and hysteresis effects. Studies reveal that the enzyme loaded in the pellets are stable for up to 8 months at ambient conditions, and generate reproducible sensor signals. The work illustrates the significance of the pellet-based sensing system towards realizing a reusable, point-of-care sensor that snugly fits around a smartphone and which does not face issues usually common to reusable sensors. The versatility of this system allows it to be easily modified to detect other analytes for application in a wide range of healthcare, environmental and defense domains.
| S-EPMC5841915 | biostudies-literature
Project description:Smartphone sensors allow measurement of phenomena that are difficult or impossible to capture via self-report (e.g., geographical movement, physical activity). Sensors can reduce respondent burden by eliminating survey questions and improve measurement accuracy by replacing/augmenting self-reports. However, if respondents who are not willing to collect sensor data differ on critical attributes from those who are, the results can be biased. Research on the mechanisms of willingness to collect sensor data mostly comes from (nonprobability) online panels and is hypothetical (i.e., asks participants about the likelihood of participation in a sensor-based study). In a cross-sectional general population randomized experiment, we investigate how features of the request and respondent characteristics influence willingness to share (WTS) and actually sharing smartphone-sensor data. We manipulate the request to either mention or not mention (1) how participation will benefit the participant, (2) participants' autonomy over data collection, and (3) that data will be kept confidential. We assess nonparticipation bias using the administrative records. WTS and actually sharing varies by sensor task, participants' autonomy over data sharing, their smartphone skills, level of privacy concerns, and attitudes toward surveys. Fewer people agree to share photos and a video than geolocation, but all who agreed to share photos or a video actually did. Some nonresponse and nonparticipation biases are substantial and make each other worse, but others jointly reduce the overall bias. Our findings suggest that sensor-data-sharing decisions depend on sample members' situation when asked to share and the nature of the sensor task rather than the sensor type.
| S-EPMC8483283 | biostudies-literature
Project description:The detection of Activities of Daily Living (ADL) holds significant importance in a range of applications, including elderly care and health monitoring. Our research focuses on the relevance of ADL detection in elderly care, highlighting the importance of accurate and unobtrusive monitoring. In this paper, we present a novel approach that that leverages smartphone data as the primary source for detecting ADLs. Additionally, we investigate the possibilities offered by ambient sensors installed in smart home environments to complement the smartphone data and optimize the ADL detection. Our approach uses a Long Short-Term Memory (LSTM) model. One of the key contributions of our work is defining ADL detection as a multilabeling problem, allowing us to detect different activities that occur simultaneously. This is particularly valuable since in real-world scenarios, individuals can perform multiple activities concurrently, such as cooking while watching TV. We also made use of unlabeled data to further enhance the accuracy of our model. Performance is evaluated on a real-world collected dataset, strengthening reliability of our findings. We also made the dataset openly available for further research and analysis. Results show that utilizing smartphone data alone already yields satisfactory results, above 50% true positive rate and balanced accuracy for all activities, providing a convenient and non-intrusive method for ADL detection. However, by incorporating ambient sensors, as an additional data source, one can improve the balanced accuracy of the ADL detection by 7% and 8% of balanced accuracy and true positive rate respectively, on average.
| S-EPMC10914737 | biostudies-literature