Problematic smartphone use (PSU) is a social issue affecting daily lives without a definitive treatment. Current PSU treatments rely on self-reported data, which can be inaccurate and lead to ineffective treatments. To address this, we propose using a hidden Markov model to objectively analyze smartphone usage patterns from log data. The model is trained on data from various patients and then individualized, allowing for meaningful interpretation and comparison of usage states. We conduct two case studies on patients attending outpatient clinics for Internet addiction due to PSU. These case studies compare the model-estimated usage state of patients with 1) a daily activity log as reported by the patients and 2) a several-month clinical history of the patients as reported by their attending psychiatrists. Through each case study, we validate the appropriateness of the definitions assigned to each usage state and the effectiveness of the state estimations performed using the proposed method. Our approach demonstrated that it is possible to objectively understand and track changes in PSU, which self-reports alone cannot achieve.

In recent years, there has been a growing problem of smartphone addiction. As the excessive use of smartphones has negatively impacted our daily lives, many apps for reducing smartphone addiction have been developed around the world. In this study, we focus on the app restriction function, which is one of the key features of digital medicines for smartphone addiction, and analyze the usage of the function and verify its effectiveness. The results showed significant differences in both psychological and behavioral aspects between those who used the app restriction function and those who did not. Specifically, we found that the app restriction function was more likely to be used by those who were more aware of their smartphone addiction. We also found that the app restriction function was effective in lessening smartphone usage time, especially when the smartphone addiction is relatively moderate.

The task of an automatic language identification (LID) system is to automatically identify the language in a spoken utterance. Language identification can be applied as front-end to speech-to-speech translation systems, in speaker diarization, and at call centers to automatically route incoming calls to appropriate native speaker operators. In the current study, a method for automatic language identification based on i-vector paradigm and conditional random fields (CRF) is presented. CRF belong to discriminative classifiers and use an exponential distribution to model a sequence given the observation sequence. This allows non-independent observations, and allows also non-local dependencies between state and observation. When the proposed method is evaluated on the NIST 2015 i-vector Machine Learning Challenge task for the recognition of 50 in-set languages, a 3.7% equal error rate (EER) (i.e., miss probability equal to false alarms) is achieved. Using support vector machines (SVM) a 5.2% EER, using probabilistic linear discriminant analysis (PLDA) a 6.7% EER, and when using convolutional neural networks (CNN) a 4.2% EER are achieved.

The current study is focused on automatic speech emotion recognition, and particularly on the effect of additive noise and reverberation on speech emotion recognition. The emotional clean speech is produced by four professional actors, who simulate the neutral, joy, anger, and sadness emotions. To produce noisy emotional speech data, white Gaussian noise is superimposed onto the clean speech at several signal-to-noise ratio (SNR) levels. Concerning the reverberant emotional speech data, a technique is applied which is based on convolution of clean speech data with impulse responses recorded in several environments with different reverberation times. The four emotions are recognized using i-vectors, along with probabilistic linear discriminant analysis (PLDA), widely used in speaker recognition and adapted here for speech emotion recognition. When noisy and reverberant emotional speech data are recognized using clean models, the recognition rates are significantly decreased compared to the clean test data. To address this problem, a method based on multi-style training is applied, which utilizes training data of several SNR levels (different to the SNR level of the test data, therefore SNR-independent), or training on data with different reverberation times. Using multi-style training to recognize emotions in noisy or reverberant environments, the recognition rates are significantly increased, and the differences compared to the clean case are statistically not significant. Furthermore, the i-vector paradigm based classification method is compared with a baseline Gaussian mixture models (GMM) based method, and it demonstrates superior performance.

We propose Vision-based Robust Calibration (ViRC) method for OSTHMDs equipped with a camera. In the ViRC method, calibration parameters are decomposed into off-line parameters that remain constant relative to the positional relationship between the camera and the virtual screen, and on-line parameters related to the user's eye. Calculating the off-line parameters beforehand reduces the number of unknown parameters in the on-line phase, giving robust protection against the user's misalignments during calibration. In the off-line phase, the approximate position of the user's eye is calculated using the PnP algorithm. In the online phase, the actual position of the user's eye is estimated from the approximate one by non-linear minimization. In our experiments, we show that the ViRC method can decrease reprojection error by as much as 83% compared with the conventional method based on the DLT algorithm.

We propose a marker-less Augmented Reality (AR) application based on a realtime hand posture estimation technique for smartphones. A conventional marker-less AR system does not have sufficient accuracy and speed in the detection of a mobile device. This paper presents a fast hand posture estimation algorithm based on a combination of feature points and feature lines that consist of the boundary of fingers. The proposed method realized rendering of virtual 3D models on a hand over 12 frames per second (fps) on a smart-phone. Simulation results show that we can archive about 73% complexity reductions and be more accurate than the conventional method.

We propose a novel tool called short-term principal component analysis (ST-PCA) to analyze motion capture (MoCap) data, which records realistic movements in a high dimensional time series. Our ST-PCA is successfully applied to beat induction, which is an important perception of human motion especially in dances and is required by many applications such as music synchronization [Kim et al. 2003; Shiratori et al. 2006]. Following [Kim et al. 2003], motion beats are defined as the regular moments when the movement is changed significantly in direction or magnitude. Different from the previous approaches [Kim et al. 2003; Shiratori et al. 2006] that analyze MoCap data in each channel, we estimate the motion beats regarding MoCap data as a whole with the proposed ST-PCA, which performs PCA in a sliding window. Our experiments demonstrate that our method can estimate much more accurate beats in a wide range of motions including complicated dances.

This paper proposes a high quality coding mode decision method for MPEG-2 to H.264 transcoding. Here, we evaluate the coding modes of MPEG-2 stream in order to specify whether they should be inherited or changed in H.264 coding since many new coding schemes such as intra prediction have been introduced in H.264. By adaptively determining suitable intra/inter modes according to DCT coefficients, motion vectors (MVs), and neighboring macroblock (MB) modes of input MPEG-2 stream, high quality transcoding has been realized. In the experiment, we observed that the proposed method can improve a peak signal to noise ratio (PSNR) up to 0.29 dB at the cost of 22% more processing time compared with the conventional transcoding method.

In this work, we propose a data embedding scheme in MPEG-1/audio layer II compressed domain. Data embedding is conducted every AAU by using side information (location of sub-band allocated audio signal) as a data carrier. In general, non-zero signals concentrates in low and middle frequency bands. Therefore we utilize sub-bands that are not allocated audio signal in high frequency bands to embed information. The proposed scheme can increase payload while achieving rewritable (reversible) data, embedding by choosing appropriate parameter. We verify the basic performance of our scheme through computer simulation by using some voice and music signals

Recently, several scrambling techniques have been proposed for video digitally archived. These methods realize efficient processing by partial encryption on MPEG compressed data while keeping compatibility to MPEG format. However, they have common drawbacks expanding the entire code. Also, they have not reported on local shuffling in a frame. In this work, we propose a new video scrambling scheme on MPEG compressed domain, which shuffles a part of DC and AC coefficients by DCT in a frame. Our scheme is applicable to local region without data expansion from the original MPEG file

We propose a new algorithm for the fast conversion of MPEG-4 from DV. DV, which is a video compression coding format, is adopted by commercial and non-commercial digital video cameras and achieves high video quality using a fixed high bitrate of 25 Mbps. However, compared with MPEG-4, which is used extensively in IP or mobile phone applications, DV has a higher storage and transmission cost. This is due to the extremely low coding efficiency of DV required to maintain high quality for frame-accurate editing. In this paper, we analyze the difference between DV and MPEG-4, and propose a new algorithm for the fast conversion of MPEG-4 from DV. Our algorithm accelerates the conversion process in the coded domain using the property of conversion matrices, where resolution conversion, quantization, and inverse quantization are integrated. The experimental results indicate that, while the integration and approximation of a conversion matrix do not affect the video quality, this could greatly reduce the number of operands.

H.264/MPEG-4 AVC has become widely used in various applications and services because of its high coding efficiency. With the spread of H.264/MPEG-4 AVC contents, it has been strongly required to edit the H.264/MPEG-4 AVC coded contents with less computational complexity since the compression of H.264/MPEG-4 AVC requires far more processing power than other existing formats such as MPEG-4, MPEG-2. In this paper, we propose a fast frame-accurate editing method for H.264/MPEG-4 AVC contents. In the proposed method, we employed "adaptive bit allocation and GOP-length modification" and "Re-quantization scheme with drift noise management" The proposed editing method can realize frame-accurate cut and splice editing regardless of picture coding types I, P, and B. In the experiment, we could also confirm the effectiveness of the proposed method in terms of processing power and the picture quality of the edited contents when compared with conventional editing

A method to extract traffic events by integrating the low-level, middle-level, and high-level feature extraction modules is developed in this research. The low-level module extracts features such as motion, size, and location. The middle-level module builds a bridge between the road surface plane in the real world and the captured image plane via geometric analysis. Finally, the high-level module identifies traffic events such as "traffic jam", "lane change", and "traffic rule violation", which require the understanding of video content in a specific knowledge domain. In the high-level module, various traffic events are related to motion characteristics obtained from the middle-level module. It is demonstrated by experimental results that the proposed system can achieve robust traffic event extraction.

An approach to extract traffic events by integrating the low-level, middle-level, and high-level feature extraction modules is developed in this research. To be more specific, the low-level module extracts features such as motion, size, and location. The middle-level module builds a bridge between the road surface plane in the real world and the captured image plane by geometric analysis. Finally, the high-level module looks for traffic events such as "traffic jam", "lane change", and "traffic rule violation", which require the understanding of the video contents in a specific knowledge domain. In the high-level module, various traffic events are related to motion characteristics obtained from the middle-level module. It is demonstrated by experimental results that the proposed system can achieve robust traffic event extraction. The effectiveness of the proposed technique is analyzed. Conventional traffic event extraction methods demand the knowledge of capturing conditions for camera calibration. This requirement can be greatly relaxed in our proposed scheme.

A new algorithm to eliminate moving cast shadow for robust vehicle detection and extraction in a vision-based highway monitoring system is investigated. The proposed algorithm is based on a simplified 2D vehicle/shadow model of six types projected on to a 2D image plane. Parameters of the joint 2D vehicle/shadow models can be estimated from the input video without light source and camera calibration information. Simulations are performed to verify that the proposed technique is effective for vision-based highway surveillance systems.

This paper proposes a fast and efficient transcoding algorithm from MPEG-2 video to MPEG-1 video where spatial resolution reduction is involved. We use quantization parameters along with motion information of the incoming MPEG-2 video bitstream to estimate the motion vectors for MPEG-1 transcoding without any additional motion estimation process. Since such information can be directly extracted from the original MPEG-2 video bitstream, very fast transcoding can be achieved. In addition, since the proposed method is not restricted to a specific coding structure, it can be applied to various types of GOP structures. The experimental results show that the proposed method can provide approximate motion vectors to that of full range motion estimation. therefore transcoding efficiency can be increased and picture quality is enhanced when compared with the conventional fast transcoding methods.

Although NLE (nonlinear editing) becomes widely used for multimedia contents creation, its deployment for MPEG has not been exploited much due to the inter-frame coding structure of MPEG. We propose two fast algorithms in order to realize dissolve operation of MPEG coded data. One is based on the baseband method (BBM) where dissolving is performed in the pixel domain. The other uses the transformed domain method (TDM). Since motion estimation is altered due to the transition and its re-calculation process greatly increases the computational complexity, we use texture information to determine dominant motion during dissolving and avoid the motion estimation calculation. In the experiment, it is observed that fast dissolve processing using BBM can be achieved at less than half of the conventional BBM with at most 1 dB penalty. As for TDM, although it achieves the same processing speed of that of the proposed BBM, larger degradation is found due to the restricted motion accuracy.

Audio information classification becomes a very important task for such purposes as automatic keyword spotting and other content-based audio-visual query systems. In this paper, we describe a fast and accurate audio data classification method on the MPEG coded data domain. Firstly silent segments are detected using a robust approach for different recording conditions. Then the non-silent segments are classified into three types, music, speech, and applause using temporal density, bandwidth and center frequency of subband energy. In order to be robust for a variety of audio sources as much as possible, we use Bayes discriminant function for multivariate Gaussian distribution instead of manually adjusting a threshold for each discriminator. In the experiment, every one-second of MPEG audio data is classified and about 90% of audio and speech segments have been successfully detected. As for the detection speed, less than 20% of MPEG audio decoding processing power is required.

Moving object detection is a useful tool for such purposes as intelligent video browsing/analysis and video surveillance systems. Previously several algorithms have been reported on moving object detection from compressed video data. However, in these algorithms, flat regions are often falsely detected. In addition if multiple moving objects are involved, each moving object may not be identified and therefore object tracking becomes very difficult. We describe a fast moving detection and identification method from MPEG coded data. The experimental results show that each moving object is successfully identified for several surveillance sequences.

Although a GOP (group of picture) length is often fixed in MPEG, this may not guarantee the best picture quality from the point of view of coding efficiency. Furthermore, it is also well known that P-picture interval M=3 does not provide the best quality for all sequences. We propose an MPEG encoding algorithm with scene adaptive dynamic GOP structure to enhance the picture quality in the cases mentioned above. Using macroblock characteristics such as luminance activity and simple motion compensation on the activity domain, N and M values are dynamically determined.

Formerly, once the audio data is compressed, transcoding is used to scale the bit rate, where decoding and re-encoding are taking place. Therefore, data manipulation of coded data has been very complex and time consuming work. We describe three algorithms for bit rate scaling in the coded MPEG data domain. One is a bandwidth limitation method cutting higher frequency components until the target data rate is satisfied. The other two use a re-quantization process where a quantization step in each subband is modified. One of them reflects the psychoacoustic model from bit allocation information obtained in the bitstream in order to improve the bit rate scaling efficiency. The simulation results show that the re-quantization process provides a very high conversion efficiency and a nearly equal sound quality can be obtained as directly coding from PCM by reflecting the psychoacoustic model. It is also shown that a very fast scaling (factor of six) have been achieved when compared with the transcoding method.

This paper proposes a very fast and accurate scene change detection algorithm on MPEG coding parameter domain. The fast operation can be obtained by spatio-temporally subsampling coding information and by exploiting only coding parameters extracted in variable length decoding (VLD) stage, while the accurate detection is accomplished by examining the statistical characteristics of various scene changes on the coding parameter domain. The computer simulation shows that the proposed algorithm can accomplish detection more than 5 times faster than that of real-time playback for MPEG-2 video sequences using a standard workstation. It is also shown that most of abrupt scene changes, dissolve transitions, and wipe transitions have been successfully detected.