Waseda University · Medicine
Professor Ziheng Wang's research lab specializes in interdisciplinary data science, focusing on advanced machine learning and multimodal data analysis for biomedical and healthcare applications. The lab develops innovative models that integrate spatio-temporal dynamics, structured sparsity in deep learning, and hierarchical relationships among biological or behavioral signals—such as facial expressions, action units, and muscle activity. A key research direction involves leveraging hidden information and multi-omics data to enhance model interpretability and performance in low-data regimes, particularly for aging and disease prediction. The lab also pioneers efficient deep learning inference techniques, such as sparse computation acceleration, to support real-world deployment in healthcare systems.
Figures are computed from collected data and may differ slightly.
Spatial-temporal relations among facial muscles carry crucial information about facial expressions yet have not been thoroughly exploited. One contributing factor for this is the limited ability of the current dynamic models in capturing complex spatial and temporal relations. Existing dynamic models can only capture simple local temporal relations among sequential events, or lack the ability for incorporating uncertainties. To overcome these limitations and take full advantage of the spatio-tem
In this paper we tackle the problem of facial action unit (AU) recognition by exploiting the complex semantic relationships among AUs, which carry crucial top-down information yet have not been thoroughly exploited. Towards this goal, we build a hierarchical model that combines the bottom-level image features and the top-level AU relationships to jointly recognize AUs in a principled manner. The proposed model has two major advantages over existing methods. 1) Unlike methods that can only captur
The application of multi-omics in drug discovery is rapidly advancing, but its trends and hotspots have not been fully analyzed. By reviewing key achievements and research hotspots in this field, the aim is to provide new insights for scholars. Relevant literature on the application of multi-omics in cancer research was obtained from the Web of Science Core Collection, covering the period from 2007 to October 31, 2024. Bibliometric analysis was conducted using CiteSpace, VOSviewer, and R softwar
In recent years, there has been a flurry of research in deep neural network pruning and compression. Early approaches prune weights individually. However, it is difficult to take advantage of the resulting unstructured sparsity patterns on modern hardware like GPUs. As a result, pruning strategies which impose sparsity structures in the weights have become more popular. However,these structured pruning approaches typically lead to higher losses in accuracy than unstructured pruning. In this pape
Traditional data-driven classifier learning approaches become limited when the training data is inadequate either in quantity or quality. To address this issue, in this paper we propose to combine hidden information and data to enhance classifier learning. Hidden information represents information that is only available during training but not available during testing. It often exists in many applications yet has not been thoroughly exploited, and existing methods to utilize hidden information a
Background: Sarcopenia is a geriatric syndrome characterized by decreased skeletal muscle mass and function with age. It is well-established that resistance exercise and Yi Jin Jing improve the skeletal muscle mass of older adults with sarcopenia. Accordingly, we designed an exercise program incorporating resistance exercise and Yi Jin Jing to increase skeletal muscle mass and reverse sarcopenia in older adults. Additionally, machine learning simulations were used to predict the sarcopenia statu
Background: Due to the low physical fitness of the frail elderly, current exercise program strategies have a limited impact. Eight-form Tai Chi has a low intensity, but high effectiveness in the elderly. Inspired by it, we designed an exercise program that incorporates eight-form Tai Chi, strength, and endurance exercises, to improve physical fitness and reverse frailty in the elderly. Additionally, for the ease of use in clinical practice, machine learning simulations were used to predict the f
Abstract Zero‐valent iron nanoparticles (NZVI) were synthesized and dispersed in solutions of sodium oleate (SO), sodium laurate (SL), sodium dodecyl phosphonate (SDP), and sodium dodecyl sulfate (SDS). The reactivity of these dispersions was evaluated to assess the impact of surfactants on the reduction rate of hydrophilic reactive black 5 (RB5) and hydrophobic carbon tetrachloride (CT) model contaminants. SO and SL, used at their critical micelle concentration (CMC), lowered the reduction rate
Among the participants with different physical fitness, a similar training has different training effects. This study demonstrates that appropriate training intensity and content are vital to improve physical and mental health.
In this paper, an efficient face recognition algorithm is proposed, which is robust to illumination, expression and occlusion. In our method, a human face image is considered as a multiplication of a reflectance image and an illumination image. Then, this illumination model is used to transfer input images. After the transformation, the robust principal component analysis is employed to recover the intrinsic information of a sequence of images of one person. Finally, a new similarity metric is d
The hybrid exercise program that combined Baduanjin with strength and endurance training proved more effective at improving fitness and reversing frailty in elderly individuals. Based on the stacking model, it is possible to predict whether an elderly person will exhibit reversed frailty following an exercise program.
Open papers in the app to read, cite, and organize with AI.
