News

Mouse brains are often used as model systems in medical studies, as they share many similarities with the human brain in function and structure. By observing biomarkers in brain tissue, researchers can gain insight into how neurons and blood vessels interact to support processes such as learning, memory, and sensory perception (especially to triggers of content/stress and so on).

Our studies on 3D microscopic images of mouse brains involve two biomarkers: lectin and cFOS. Lectin is a protein which binds specifically to certain sugar molecules on the surface of cells lining blood vessels, and can therefore be stained with a fluorescent dye to mark the network of blood vessels. cFOS labelling, on the other hand, marks neurons that were recently active, serving as an “activity map” of brain regions responding to external stimuli or behavioural tasks. The detailed information of both biomarkers is obtained through the dissection of the mouse (especially cFOS, which requires observation around 2 hours after stimulation), which means that it cannot be observed through imaging of the human brain.

These datasets are typically large per brain, high-dimensional, and require pixel-level interpretation. Manual labelling for such data is often time-consuming, and could vary depending on the experience level of the person labelling. A single brain can produce gigabytes to terabytes of 3D imaging data, containing complex vessel networks and cellular activation patterns. As cFOS shows up as very small points on the image, labelling those accurately proves to be difficult in practice as well.

Green learning offers an efficient method for automatically segmenting and analysing these complex images. Deep learning often demands extensive labelled data and computational resources, and such data is often hard to find when it comes to medical applications. In contrast, [...]

The rapid evolution of 5G and emerging 6G networks creates an urgent need for intelligent, adaptive, and energy-efficient solutions that can operate at the edge under strict compute and power constraints. Current deep learning approaches are accurate but computationally expensive, limiting deployment in real-world embedded systems.

In this study, we introduce an efficient and transparent green learning pipeline designed to address the Automatic Modulation Classification (AMC) problem which is essential for cognitive radio. The goal of this pipeline is to enable wireless receivers to blindly identify modulation schemes of incoming signals in a computationally efficient manner while maintaining a compact model size suitable for deployment on edge or embedded systems. Our proposed approach consists of three main stages. First, the input signal is converted into a precise intermediate representation using a sparse coding method, which captures essential structural and statistical characteristics while suppressing redundant information. Second, we extract a diverse set of informative features from this sparse representation and the original signal statistics to ensure robustness against channel distortions and noise variations. Finally, a hierarchical classification subspace is constructed based on a tree-structured model, allowing the system to progressively distinguish between modulation categories with minimal computational burden.

We are very happy to welcome a new MCL member, Claire Wang. Here is a quick interview with Claire:

1. Could you briefly introduce yourself and your research interests?My name is Claire Wang, and I am currently a Ph.D. student in Electrical Engineering at USC. I received my bachelor’s degree from National Taiwan University (NTU). My research interests include machine learning and image processing, especially their applications in interdisciplinary problems. Outside of academics, I enjoy traveling, reading, singing and photography.

2. What is your impression of MCL and USC?My impression of MCL lab is that it provides a highly collaborative, strong and warm community where students are encouraged to explore research ideas under the guidance of experienced mentors. USC feels very dynamic and diverse, offering not only strong academic resources but also opportunities to connect with people from different cultural and professional backgrounds.

3. What is your future expectation and plan in MCL?

In MCL, I hope to build strong interactions with lab members, exchange ideas and collaborate on projects. I also look forward to learning from both Professor Kuo and my peers, not only to strengthen my research abilities but also to broaden my perspectives. I would like to gain a deeper understanding of Green Learning, explore its applications, and steadily contribute to the lab’s progress.

Congratulations to Aolin Feng for passing his Qualifying Exam! His thesis proposal is titled “ Green Image Coding: Principle, Implementation, and Performance Evaluation.” His Qualifying Exam Committee members include Jay Kuo (Chair), Antonio Ortega, Bhaskar Krishnamachari, Feng Qian, and Shanghao Teng (Outside Member). Here is a summary of his thesis proposal:

Image compression has long been dominated by two paradigms: the hybrid coding framework that adopts prediction and transform followed by scalar quantization, and deep learning-based codecs that leverage end-to-end optimization. While hybrid codecs offer reliable rate–distortion (RD) performance, they face a bottleneck for RD gain when integrating additional coding tools. In contrast, deep learning-based codecs achieve superior RD performance through end-to-end optimization but often suffer from high computational cost, especially for the decoder side.

The thesis proposal introduces Green Image Coding (GIC), a novel framework aiming for lightweight, RD-efficient, and scalable image compression. Different from the hybrid and deep learning-based coding, GIC is built upon two key designs: multigrid representation and vector quantization (VQ). The multigrid representation decomposes images into hierarchical layers, redistributing energy and reducing intra-layer content diversity. Each layer is then encoded using VQ-based techniques. 

Regarding the two key designs, we contribute both theoretical foundations and practical solutions: multigrid rate control and a set of advanced VQ techniques. For the multigrid rate control, we develop a theory that reduces a high-dimensional optimization to equivalent sequential parameter decisions, with comprehensive experimental validation. The theoretical conclusion guides the design of our rate control strategy, which improves the scalability and balance between rate and distortion. For the advanced VQ techniques, we start with tree-structured vector quantization (TSVQ) to build multi-rate coding capability, and propose an RD-oriented VQ codebook construction method. We also propose the cascade VQ strategy to tackle the [...]

This work introduces Green IR Drop (GIRD), an energy-efficient and high-performance static IR-drop estimation method built on green learning principles. GIRD processes IC design inputs in three stages. First, the circuit netlist is transformed into multichannel maps, from which joint spatial–spectral representations are extracted using PixelHop. Next, discriminant features are identified through the Relevant Feature Test (RFT). Finally, these selected features are passed to an eXtreme Gradient Boosting (XGBoost) regressor. Both PixelHop and RFT belong to the family of green learning tools. Thanks to their lightweight design, GIRD achieves a low carbon footprint with significantly smaller model sizes and reduced computational complexity. Moreover, GIRD maintains strong performance even with limited training data. Experimental results on both synthetic and real-world circuits confirm its superior effectiveness. In terms of efficiency, GIRD’s model size and floating-point operation count (FLOPs) are only about 10⁻³ and 10⁻² of those required by deep learning methods, respectively.