extendGAN+: Transferable Data Augmentation Framework Using WGAN-GP for Data-Driven Indoor Localisation Model.

For indoor localisation, a challenge in data-driven localisation is to ensure sufficient data to train the prediction model to produce a good accuracy. However, for WiFi-based data collection, human effort is still required to capture a large amount of data as the representation Received Signal Strength (RSS) could easily be affected by obstacles and other factors. In this paper, we propose an extendGAN+ pipeline that leverages up-sampling with the Dirichlet distribution to improve location prediction accuracy with small sample sizes, applies transferred WGAN-GP for synthetic data generation, and ensures data quality with a filtering module. The results highlight the effectiveness of the proposed data augmentation method not only by localisation performance but also showcase the variety of RSS patterns it could produce. Benchmarking against the baseline methods such as fingerprint, random forest, and its base dataset with localisation models, extendGAN+ shows improvements of up to 23.47%, 25.35%, and 18.88% respectively. Furthermore, compared to existing GAN+ methods, it reduces training time by a factor of four due to transfer learning and improves performance by 10.13%.

Smartphone Orientation Estimation Algorithm Combining Kalman Filter With Gradient Descent.

Availability and all-in-one functionality of smartphones have become a multipurpose personal tool to improve our daily life. Recent advancements in hardware and accessibility of smartphones have spawn huge potential for assistive healthcare, in particular telerehabilitation. However, using smartphone sensors face certain challenges, in particular, accurate orientation estimation, which is usually less of a problem in specialized motion tracking sensor devices. Drift is one of the challenges. We first propose a simple feedback loop complementary filter (CFF) to reduce the error caused by the integration of the gyroscope's data in the orientation estimation. Next, we propose a new and better orientation estimation algorithm which combines quaternion-based kalman filter with corrector estimates using gradient descent (KFGD). We then evaluate CFF's and KFGD's performance on two early-stage rehabilitation exercises. The results show that CFF is capable of fast motion tracking and confirm that the feedback loop can correct the error caused by the integration of gyroscope data. The KFGD orientation estimation is comparable to XSENS Awinda and has shown itself to be stable than and outperforms CFF. KFGD also outperforms the prominent Madgwick algorithm using mobile data. Thus, KFGD is suitable for low-cost motion sensors or mobile inertial sensors, especially during early recovery stage of sport injuries and exercise for the elderly.

A study on real-time low-quality content detection on Twitter from the users' perspective.

Detection techniques of malicious content such as spam and phishing on Online Social Networks (OSN) are common with little attention paid to other types of low-quality content which actually impacts users' content browsing experience most. The aim of our work is to detect low-quality content from the users' perspective in real time. To define low-quality content comprehensibly, Expectation Maximization (EM) algorithm is first used to coarsely classify low-quality tweets into four categories. Based on this preliminary study, a survey is carefully designed to gather users' opinions on different categories of low-quality content. Both direct and indirect features including newly proposed features are identified to characterize all types of low-quality content. We then further combine word level analysis with the identified features and build a keyword blacklist dictionary to improve the detection performance. We manually label an extensive Twitter dataset of 100,000 tweets and perform low-quality content detection in real time based on the characterized significant features and word level analysis. The results of our research show that our method has a high accuracy of 0.9711 and a good F1 of 0.8379 based on a random forest classifier with real time performance in the detection of low-quality content in tweets. Our work therefore achieves a positive impact in improving user experience in browsing social media content.

Excessive Sensitivity to Uncertain Visual Input in L-DOPA-Induced Dyskinesias in Parkinson's Disease: Further Implications for Cerebellar Involvement.

UNLABELLED: When faced with visual uncertainty during motor performance, humans rely more on predictive forward models and proprioception and attribute lesser importance to the ambiguous visual feedback. Though disrupted predictive control is typical of patients with cerebellar disease, sensorimotor deficits associated with the involuntary and often unconscious nature of l-DOPA-induced dyskinesias in Parkinson's disease (PD) suggests dyskinetic subjects may also demonstrate impaired predictive motor control. METHODS: We investigated the motor performance of 9 dyskinetic and 10 non-dyskinetic PD subjects on and off l-DOPA, and of 10 age-matched control subjects, during a large-amplitude, overlearned, visually guided tracking task. Ambiguous visual feedback was introduced by adding "jitter" to a moving target that followed a Lissajous pattern. Root mean square (RMS) tracking error was calculated, and ANOVA, robust multivariate linear regression, and linear dynamical system analyses were used to determine the contribution of speed and ambiguity to tracking performance. RESULTS: Increasing target ambiguity and speed contributed significantly more to the RMS error of dyskinetic subjects off medication. l-DOPA improved the RMS tracking performance of both PD groups. At higher speeds, controls and PDs without dyskinesia were able to effectively de-weight ambiguous visual information. CONCLUSION: PDs' visually guided motor performance degrades with visual jitter and speed of movement to a greater degree compared to age-matched controls. However, there are fundamental differences in PDs with and without dyskinesia: subjects without dyskinesia are generally slow, and less responsive to dynamic changes in motor task requirements, but in PDs with dyskinesia, there was a trade-off between overall performance and inappropriate reliance on ambiguous visual feedback. This is likely associated with functional changes in posterior parietal-ponto-cerebellar pathways.

Rotated orthogonal transform (ROT) for motion-compensation residual coding.

Discrete cosine transform (DCT) is the orthogonal transform that is most commonly used in image and video compression. The motion-compensation residual (MC-residual) is also compressed with the DCT in most video codecs. However, the MC-residual has different characteristics from a nature image. In this paper, we develop a new orthogonal transform-rotated orthogonal transform (ROT) that can perform better on the MC-residual than the DCT for coding purposes. We derive the proposed ROT based on orthogonal-constrained L1-Norm minimization problem for its sparse property. Using the DCT matrix as the starting point, a better orthogonal transform matrix is derived. In addition, by exploring inter-frame dependency and local motion activity, transmission of substantial side information is avoided. The experiment results confirm that, with small computation overhead, the ROT is adaptive to change of local spatial characteristic of MC-residual frame and provides higher compression efficiency for the MC-residual than DCT, especially for high- and complex-motion videos.

Mode-dependent templates and scan order for H.264/AVC-based intra lossless coding.

In H.264/advanced video coding (AVC), lossless coding and lossy coding share the same entropy coding module. However, the entropy coders in the H.264/AVC standard were original designed for lossy video coding and do not yield adequate performance for lossless video coding. In this paper, we analyze the problem with the current lossless coding scheme and propose a mode-dependent template (MD-template) based method for intra lossless coding. By exploring the statistical redundancy of the prediction residual in the H.264/AVC intra prediction modes, more zero coefficients are generated. By designing a new scan order for each MD-template, the scanned coefficients sequence fits the H.264/AVC entropy coders better. A fast implementation algorithm is also designed. With little computation increase, experimental results confirm that the proposed fast algorithm achieves about 7.2% bit saving compared with the current H.264/AVC fidelity range extensions high profile.

Low-complexity video coding based on two-dimensional singular value decomposition.

In this paper, we propose a low-complexity video coding scheme based upon 2-D singular value decomposition (2-D SVD), which exploits basic temporal correlation in visual signals without resorting to motion estimation (ME). By exploring the energy compaction property of 2-D SVD coefficient matrices, high coding efficiency is achieved. The proposed scheme is for the better compromise of computational complexity and temporal redundancy reduction, i.e., compared with the existing video coding methods. In addition, the problems caused by frame decoding dependence in hybrid video coding, such as unavailability of random access, are avoided. The comparison of the proposed 2-D SVD coding scheme with the existing relevant non-ME-based low-complexity codecs shows its advantages and potential in applications.

Direct intermode selection for H.264 video coding using phase correlation.

The H.264 video coding standard exhibits higher performance compared to the other existing standards such as H.263, MPEG-X. This improved performance is achieved mainly due to the multiple-mode motion estimation and compensation. Recent research tried to reduce the computational time using the predictive motion estimation, early zero motion vector detection, fast motion estimation, and fast mode decision, etc. These approaches reduce the computational time substantially, at the expense of degrading image quality and/or increase bitrates to a certain extent. In this paper, we use phase correlation to capture the motion information between the current and reference blocks and then devise an algorithm for direct motion estimation mode prediction, without excessive motion estimation. A bigger amount of computational time is reduced by the direct mode decision and exploitation of available motion vector information from phase correlation. The experimental results show that the proposed scheme outperforms the existing relevant fast algorithms, in terms of both operating efficiency and video coding quality. To be more specific, 82 ~92% of encoding time is saved compared to the exhaustive mode selection (against 58 ~74% in the relevant state-of-the-art), and this is achieved without jeopardizing image quality (in fact, there is some improvement over the exhaustive mode selection at mid to high bit rates) and for a wide range of videos and bitrates (another advantages over the relevant state-of-the-art).