Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Sezin Kircali Ata has a total of 34 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Graph-Based Modeling of Behavioral Transitions for Digital Health Applications: Trajectory Analysis Framework

    by Sezin Kircali Ata, Weizhuang Zhou, Jesisca Tandi, Wei Qing Lee, Yu En Chan, Feri Guretno, Anitha Veeramani, Wei Liu, Jeremy Tan, Felix B Wijaya, et al.

    Background: Digital health applications generate rich behavioral data; yet, how users transition between behavioral states remains poorly understood. Existing approaches show limited capacity to capture and represent the evolving and nuanced nature of real-world behavioral dynamics, which are essential for informing personalized behavior change interventions. Objective: This study aimed to understand how users’ behaviors evolve within digital health applications by developing a data-driven approach that captures transition dynamics across behavioral features. We aimed to validate modeled transitions against observed user data, analyze transition pathways, and derive interpretable insights. Methods: We analyzed 32 weeks of data from 36,574 users from a population health program run by the Health Promotion Board (HPB) in Singapore. We developed a graph-based behavioral trajectory model (GraphBeTraM ) that models behavioral transitions as shortest paths through user similarity graphs. By aggregating paths over time, the model captures users’ progression toward target behavioral states and quantifies the direction, magnitude, and timing of change. We validated modeled transitions against real-world data by comparing (1) transition matrices and (2) feature-level pathways, using Spearman correlation, Fisher z-transformed means, and cosine distance. We focused on high-variance features and used heatmaps to visualize patterns of change. Finally, characterized transition pathways between behavioral states and distinguished generalizable and context-specific features. Results: We observed strong alignment between observed and modeled transition matrices with strong correlation (Spearman ρ=0.82; P <.001) and low cosine distance (0.05), suggesting that real-world behavioral transitions can be effectively represented through shortest paths with GraphBeTraM. Feature-level pathway validation showed consistent patterns of change across both personalized and real-world pathways. Physical activity features like weekly moderate to vigorous physical activity (MVPA) emerged as stable, generalizable signals of change at the population level, with strong mean correlation (ρ_ personalized =0.97; ρ_ real-world =0.79) and low mean cosine distance (cosine_ personalized =0.24; cosine_ real-world =0.41) across both personalized and real-world transitions. In contrast, features related to personal preferences, including time-related activity patterns (eg, proportion of weekday to weekend MVPA), purchase preferences for healthy foods and drinks, and engagement indicators (eg, last contact with the program or app), exhibited context-specific relevance and reflected change at an individual level. An in-depth transition analysis from an active state with prolonged sedentary periods to an active state with healthy eating habits revealed interpretable patterns in onset, magnitude, and rate of change. Specifically, features such as preferences for healthy food and drink purchases emerged later in the trajectory but then showed sharper and faster transitions once these behaviors began to shift. These insights highlight how GraphBeTraM can guide nudging strategies in alignment with natural behavior dynamics, including both stable and later-onset patterns. Conclusions: GraphBeTraM provides an interpretable framework for modeling behavioral transitions in digital health applications and captures key dynamics that support personalized intervention design.

  • Open Access

    FAPlace: Joint Optimization of Chiplet Placement and Interposer Footprint for 2.5D Systems

    by Yubo Hou, Sezin Kircali Ata, Gen Liang Lim, Richard Chang, Mihai Dragos Rotaru, Rahul Dutta, Ashish James

    The placement of chiplets on a silicon interposer is a pivotal step in 2.5D system integration, yet existing placement approaches typically assume a pre-defined interposer footprint. This creates a circular dependency: the optimal footprint cannot be known without first solving the placement, while the placement itself is constrained by the given dimensions. An undersized interposer may exclude feasible placements, while an oversized one yields unnecessarily sparse solutions. Moreover, even when the footprint area is minimized, few existing approaches explicitly control the interposer’s aspect ratio. To jointly address these challenges, we propose FAPlace, a footprint aware mask guided sequential placement framework. FAPlace operates on a sufficiently large canvas, eliminating the circular dependency by allowing the optimal interposer footprint to emerge as an output of the optimization rather than a pre-specified input. At its core is a novel footprint mask that fuses area compactness with an aspect ratio penalty into a unified spatial cost map. Integrated with wirelength and thermal guidance masks, FAPlace delivers holistic multi-physics optimization in a deterministic, single pass process. Experimental results demonstrate that FAPlace reduces wirelength and footprint area while achieving near-unity aspect ratios, without compromising on thermal performance.

  • Open Access

    Learning to Place Chiplets: A Multi-Objective Reinforcement Learning Approach

    by Richard Chang, Partha Pratim Kundu, Jun Liu, Dingjie Lu, Sezin Ata Kircali, Yubo Hou, Jie Wang, Gen Liang Lim, Sridhar Narayanaswamy, Rotaru Mihai Dragos, et al.

    As heterogeneous systems scale, traditional rule-based and stochastic methods used for chip placement face limitations in convergence, scalability, and thermal management. To address these challenges, we propose a reinforcement learning (RL) framework with multi-objective optimization, employing a customized reward shaping method to minimize interconnect wirelength and improve thermal distribution. We applied our approach to two generic use cases in 2.5D advanced packaging - a 4-chiplet RDL system and a multi-GPU system. Our results outperformed the state-of-the-art methods like Bayesian optimization (BO) by up to \(40\%\) in wirelength reduction with 4°C thermal improvements.

  • The Initialization Effect: Refining Bayesian Optimization for Circuit Design

    by Anusha James, Zhi Hui Kong, Sezin Kircali Ata, Khin Mi Mi Aung, Kiat Seng Yeo, Chuan Sheng Foo, Ashish James

    Bayesian optimization (BO) has emerged as a powerful sample efficient technique for optimizing expensive and time-consuming design of analog circuits. The BO framework leverages probabilistic models to efficiently explore design spaces, allowing for a streamlined approach to identify optimal designs that meet specific performance targets. Traditionally, BO framework is initialized with predefined or randomly generated samples, thereby failing to fully exploit the latent insights concealed within the data leading to suboptimal results and lengthy convergence time. This paper delves into the significance of initialization in BO for analog circuit design, investigating its impact on the efficiency and effectiveness of the optimization process. The study demonstrates that the model can achieve optimal design outcomes using as few as 16 data points, highlighting the potential for data-efficient learning in complex design tasks. Through empirical analysis and experimentation, we explore various initialization strategies and their influence on optimization performance, considering factors such as convergence speed, solution quality etc. The results highlight the influence of initialization strategies, with approaches such as Latin hypercube sampling (LHS) and K-center greedy achieving faster convergence compared to other methods like K-means and random initialization. This study demonstrates how effective initialization strategies in BO can reduce the need for extensive data collection, by optimizing design outcomes with fewer iterations and samples. Furthermore, we elucidate the underlying mechanisms through which different initialization approaches affect the optimization process, providing insights into the interplay between initialization, exploration, and exploitation in analog circuit design optimization. Our findings shed light on the importance of thoughtful initialization strategies in harnessing the full potential of BO for analog circuit design, offering valuable guidelines for circuit designers.

  • Open Access

    Predicting the Textural Properties of Plant-Based Meat Analogs with Machine Learning

    by Sezin Kircali Ata, Jing K. Shi, Xuesi Yao, Xin Yi Hua, Sumanto Haldar, Jie Hong Chiang, Min Wu

    Plant-based meat analogs are food products that mimic the appearance, texture, and taste of real meat. The development process requires laborious experimental iterations and expert knowledge to meet consumer expectations. To address these problems, we propose a machine learning (ML)-based framework to predict the textural properties of meat analogs. We introduce the proximate compositions of the raw materials, namely protein, fat, carbohydrate, fibre, ash, and moisture, in percentages and the “targeted moisture contents” of the meat analogs as input features of the ML models, such as Ridge, XGBoost, and MLP, adopting a build-in feature selection mechanism for predicting “Hardness” and “Chewiness”. We achieved a mean absolute percentage error (MAPE) of 22.9%, root mean square error (RMSE) of 10.101 for Hardness, MAPE of 14.5%, and RMSE of 6.035 for Chewiness. In addition, carbohydrates, fat and targeted moisture content are found to be the most important factors in determining textural properties. We also investigate multicollinearity among the features, linearity of the designed model, and inconsistent food compositions for validation of the experimental design. Our results have shown that ML is an effective aid in formulating plant-based meat analogs, laying out the groundwork to expediently optimize product development cycles to reduce costs.