• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.9
• /
• pp.811-819
• /
• 2014

Activity recognition is a key component in identifying the context of a user for providing services based on the application such as medical, entertainment and tactical scenarios. Instead of applying numerous sensor devices, as observed in many previous investigations, we are proposing the use of smartphone with its built-in multimodal sensors as an unobtrusive sensor device for recognition of six physical daily activities. As an improvement to previous works, accelerometer, gyroscope and magnetometer data are fused to recognize activities more reliably. The evaluation indicates that the IBK classifier using window size of 2s with 50% overlapping yields the highest accuracy (i.e., up to 99.33%). To achieve this peak accuracy, simple time-domain and frequency-domain features were extracted from raw sensor data of the smartphone.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.163-177
• /
• 2019

As smartphones are getting widely used, human activity recognition (HAR) tasks for recognizing personal activities of smartphone users with multimodal data have been actively studied recently. The research area is expanding from the recognition of the simple body movement of an individual user to the recognition of low-level behavior and high-level behavior. However, HAR tasks for recognizing interaction behavior with other people, such as whether the user is accompanying or communicating with someone else, have gotten less attention so far. And previous research for recognizing interaction behavior has usually depended on audio, Bluetooth, and Wi-Fi sensors, which are vulnerable to privacy issues and require much time to collect enough data. Whereas physical sensors including accelerometer, magnetic field and gyroscope sensors are less vulnerable to privacy issues and can collect a large amount of data within a short time. In this paper, a method for detecting accompanying status based on deep learning model by only using multimodal physical sensor data, such as an accelerometer, magnetic field and gyroscope, was proposed. The accompanying status was defined as a redefinition of a part of the user interaction behavior, including whether the user is accompanying with an acquaintance at a close distance and the user is actively communicating with the acquaintance. A framework based on convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent networks for classifying accompanying and conversation was proposed. First, a data preprocessing method which consists of time synchronization of multimodal data from different physical sensors, data normalization and sequence data generation was introduced. We applied the nearest interpolation to synchronize the time of collected data from different sensors. Normalization was performed for each x, y, z axis value of the sensor data, and the sequence data was generated according to the sliding window method. Then, the sequence data became the input for CNN, where feature maps representing local dependencies of the original sequence are extracted. The CNN consisted of 3 convolutional layers and did not have a pooling layer to maintain the temporal information of the sequence data. Next, LSTM recurrent networks received the feature maps, learned long-term dependencies from them and extracted features. The LSTM recurrent networks consisted of two layers, each with 128 cells. Finally, the extracted features were used for classification by softmax classifier. The loss function of the model was cross entropy function and the weights of the model were randomly initialized on a normal distribution with an average of 0 and a standard deviation of 0.1. The model was trained using adaptive moment estimation (ADAM) optimization algorithm and the mini batch size was set to 128. We applied dropout to input values of the LSTM recurrent networks to prevent overfitting. The initial learning rate was set to 0.001, and it decreased exponentially by 0.99 at the end of each epoch training. An Android smartphone application was developed and released to collect data. We collected smartphone data for a total of 18 subjects. Using the data, the model classified accompanying and conversation by 98.74% and 98.83% accuracy each. Both the F1 score and accuracy of the model were higher than the F1 score and accuracy of the majority vote classifier, support vector machine, and deep recurrent neural network. In the future research, we will focus on more rigorous multimodal sensor data synchronization methods that minimize the time stamp differences. In addition, we will further study transfer learning method that enables transfer of trained models tailored to the training data to the evaluation data that follows a different distribution. It is expected that a model capable of exhibiting robust recognition performance against changes in data that is not considered in the model learning stage will be obtained.

• Journal of Korea Multimedia Society
• /
• v.17 no.8
• /
• pp.968-976
• /
• 2014

Authentication methods on smartphone are demanded to be implicit to users with minimum users' interaction. Existing authentication methods (e.g. PINs, passwords, visual patterns, etc.) are not effectively considering remembrance and privacy issues. Behavioral biometrics such as keystroke dynamics and gait biometrics can be acquired easily and implicitly by using integrated sensors on smartphone. We propose a biometric model involving keystroke dynamics for implicit authentication on smartphone. We first design a feature extraction method for keystroke dynamics. And then, we build a fusion model of keystroke dynamics and gait to improve the authentication performance of single behavioral biometric on smartphone. We operate the fusion at both feature extraction level and matching score level. Experiment using linear Support Vector Machines (SVM) classifier reveals that the best results are achieved with score fusion: a recognition rate approximately 97.86% under identification mode and an error rate approximately 1.11% under authentication mode.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.2
• /
• pp.112-119
• /
• 2023

In urban environments, signals of Global Positioning System (GPS) can be blocked and reflected by tall buildings, large vehicles, and complex components of road network. Therefore, the performance of the positioning system using the GPS module in urban areas can be degraded due to the loss of GPS signals necessary for the position estimation. To deal with this issue, various localization schemes using inertial measurement unit (IMU) sensors, such as gyroscope and accelerometer, and Bayesian filters, such as Kalman filter (KF) and particle filter (PF), have been designed to enhance the performance of the GPS-based positioning system. Among Bayesian filters, the PF has been widely used for the target tracking and vehicle navigation, since it can provide superior performance in estimating the state of a dynamic system under nonlinear/non-Gaussian circumstance. This paper presents a positioning system that uses the double-stacked particle filter (DSPF) as well as the accelerometer, gyroscope, and GPS receiver on the smartphone to provide higher pedestrian positioning accuracy in urban environments. The DSPF employs a nonparametric technique (Parzen-window) to create the multimodal target distribution that approximates the posterior distribution. Experimental results show that the DSPF-based positioning system can provide the significant improvement of the pedestrian position estimation in urban environments.

• KIISE Transactions on Computing Practices
• /
• v.21 no.1
• /
• pp.64-69
• /
• 2015

Place awareness is an essential for location-based services that are widely provided to smartphone users. However, traditional GPS-based methods are only valid outdoors where the GPS signal is strong and also require symbolic place information of the physical location. In this paper, environmental sounds and images are used to recognize important aspects of each place. The proposed method extracts feature vectors from visual, auditory and location data recorded by a smartphone with built-in camera, microphone and GPS sensors modules. The heterogeneous feature vectors were then learned by an ensemble learning method that learns each group of feature vectors for each classifier respectively and votes to produce the highest weighted result. The proposed method is evaluated for place recognition using a data group of 3000 samples in six places and the experimental results show a remarkably improved recognition accuracy when using all kinds of sensory data comparing to results using data from a single sensor or audio-visual integrated data only.