Muhammad Usman

Ziqiang Li, Muhammad Usman, Rentuo Tao et al.

Generative Adversarial Networks (GANs) have been widely applied in different scenarios thanks to the development of deep neural networks. The original GAN was proposed based on the non-parametric assumption of the infinite capacity of networks. However, it is still unknown whether GANs can fit the target distribution without any prior information. Due to the overconfident assumption, many issues remain unaddressed in GANs' training, such as non-convergence, mode collapses, gradient vanishing. Regularization and normalization are common methods of introducing prior information to stabilize training and improve discrimination. Although a handful number of regularization and normalization methods have been proposed for GANs, to the best of our knowledge, there exists no comprehensive survey that primarily focuses on objectives and development of these methods, apart from some in-comprehensive and limited scope studies. In this work, we conduct a comprehensive survey on the regularization and normalization techniques from different perspectives of GANs training. First, we systematically describe different perspectives of GANs training and thus obtain the different objectives of regularization and normalization. Based on these objectives, we propose a new taxonomy. Furthermore, we compare the performance of the mainstream methods on different datasets and investigate the applications of regularization and normalization techniques that have been frequently employed in state-of-the-art GANs. Finally, we highlight potential future directions of research in this domain. Code and studies related to the regularization and normalization of GANs in this work is summarized on https://github.com/iceli1007/GANs-Regularization-Review.

Zeheng Wang, James Scott Cooper, Muhammad Usman et al.

The rapid advancement of Internet of Things (IoT) necessitates the development of optimized nanoparticle-based Chemiresistive Sensor (CRS) arrays that are energy-efficient, specific, and sensitive. This study introduces an optimization strategy that employs a rapid ensemble learning-based model committee approach to achieve these goals. Utilizing machine learning models such as Elastic Net Regression, Random Forests, and XGBoost, among others, the strategy identifies the most impactful sensors in a CRS array for accurate classification. A weighted voting mechanism is introduced to aggregate the models' opinions in sensor selection, thereby setting up two distinct working modes, termed "Blue" and "Green". The Blue mode operates with all sensors for maximum detection capability, while the Green mode selectively activates only key sensors, significantly reducing energy consumption without compromising detection accuracy. The strategy is validated through theoretical calculations and Monte Carlo simulations, demonstrating its effectiveness and accuracy. The employed optimization strategy elevates the detection capability of CRS arrays while also pushing it closer to theoretical limits, promising significant implications for the development of low-cost, easily fabricable next-generation IoT sensor terminals.

Buliao Huang, Yunhui Zhu, Muhammad Usman et al.

Incomplete instances with various missing attributes in many real-world applications have brought challenges to the classification tasks. Missing values imputation methods are often employed to replace the missing values with substitute values. However, this process often separates the imputation and classification, which may lead to inferior performance since label information are often ignored during imputation. Moreover, traditional methods may rely on improper assumptions to initialize the missing values, whereas the unreliability of such initialization might lead to inferior performance. To address these problems, a novel semi-supervised conditional normalizing flow (SSCFlow) is proposed in this paper. SSCFlow explicitly utilizes the label information to facilitate the imputation and classification simultaneously by estimating the conditional distribution of incomplete instances with a novel semi-supervised normalizing flow. Moreover, SSCFlow treats the initialized missing values as corrupted initial imputation and iteratively reconstructs their latent representations with an overcomplete denoising autoencoder to approximate their true conditional distribution. Experiments on real-world datasets demonstrate the robustness and effectiveness of the proposed algorithm.

Muhammad Usman, Huanhuan Chen

Obesity and being over-weight add to the risk of some major life threatening diseases. According to W.H.O., a considerable population suffers from these disease whereas poor nutrition plays an important role in this context. Traditional food activity monitoring systems like Food Diaries allow manual record keeping of eating activities over time, and conduct nutrition analysis. However, these systems are prone to the problems of manual record keeping and biased-reporting. Therefore, recently, the research community has focused on designing automatic food monitoring systems since the last decade which consist of one or multiple wearable sensors. These systems aim at providing different macro and micro activity detections like chewing, swallowing, eating episodes, and food types as well as estimations like food mass and eating duration. Researchers have emphasized on high detection accuracy, low estimation errors, un-intrusive nature, low cost and real life implementation while designing these systems, however a comprehensive automatic food monitoring system has yet not been developed. Moreover, according to the best of our knowledge, there is no comprehensive survey in this field that delineates the automatic food monitoring paradigm, covers a handful number of research studies, analyses these studies against food intake monitoring tasks using various parameters, enlists the limitations and sets up future directions. In this research work, we delineate the automatic food intake monitoring paradigm and present a survey of research studies. With special focus on studies with wearable sensors, we analyze these studies against food activity monitoring tasks. We provide brief comparison of these studies along with shortcomings based upon experimentation results conducted under these studies. We setup future directions at the end to facilitate the researchers working in this domain.