arXiv subjects

Vincent Chan

Publications and source records attributed to Vincent Chan.

6 recordsLinked to original sources

arXiv2024

Emotion-Aware Embedding Fusion in LLMs (Flan-T5, LLAMA 2, DeepSeek-R1, and ChatGPT 4) for Intelligent Response Generation

Empathetic and coherent responses are critical in auto-mated chatbot-facilitated psychotherapy. This study addresses the challenge of enhancing the emotional and contextual understanding of large language models (LLMs) in psychiatric applications. We introduce Emotion-Aware Embedding Fusion, a novel framework integrating hierarchical fusion and attention mechanisms to prioritize semantic and emotional features in therapy transcripts. Our approach combines multiple emotion lexicons, including NRC Emotion Lexicon, VADER, WordNet, and SentiWordNet, with state-of-the-art LLMs such as Flan-T5, LLAMA 2, DeepSeek-R1, and ChatGPT 4. Therapy session transcripts, comprising over 2,000 samples are segmented into hierarchical levels (word, sentence, and session) using neural networks, while hierarchical fusion combines these features with pooling techniques to refine emotional representations. Atten-tion mechanisms, including multi-head self-attention and cross-attention, further prioritize emotional and contextual features, enabling temporal modeling of emotion-al shifts across sessions. The processed embeddings, computed using BERT, GPT-3, and RoBERTa are stored in the Facebook AI similarity search vector database, which enables efficient similarity search and clustering across dense vector spaces. Upon user queries, relevant segments are retrieved and provided as context to LLMs, enhancing their ability to generate empathetic and con-textually relevant responses. The proposed framework is evaluated across multiple practical use cases to demonstrate real-world applicability, including AI-driven therapy chatbots. The system can be integrated into existing mental health platforms to generate personalized responses based on retrieved therapy session data.

cs.CL↗

arXiv2024

The Impact of an XAI-Augmented Approach on Binary Classification with Scarce Data

Point-of-Care Ultrasound (POCUS) is the practice of clinicians conducting and interpreting ultrasound scans right at the patient's bedside. However, the expertise needed to interpret these images is considerable and may not always be present in emergency situations. This reality makes algorithms such as machine learning classifiers extremely valuable to augment human decisions. POCUS devices are becoming available at a reasonable cost in the size of a mobile phone. The challenge of turning POCUS devices into life-saving tools is that interpretation of ultrasound images requires specialist training and experience. Unfortunately, the difficulty to obtain positive training images represents an important obstacle to building efficient and accurate classifiers. Hence, the problem we try to investigate is how to explore strategies to increase accuracy of classifiers trained with scarce data. We hypothesize that training with a few data instances may not suffice for classifiers to generalize causing them to overfit. Our approach uses an Explainable AI-Augmented approach to help the algorithm learn more from less and potentially help the classifier better generalize.

cs.LG↗

arXiv2024

Interpretable Models for Detecting and Monitoring Elevated Intracranial Pressure

Detecting elevated intracranial pressure (ICP) is crucial in diagnosing and managing various neurological conditions. These fluctuations in pressure are transmitted to the optic nerve sheath (ONS), resulting in changes to its diameter, which can then be detected using ultrasound imaging devices. However, interpreting sonographic images of the ONS can be challenging. In this work, we propose two systems that actively monitor the ONS diameter throughout an ultrasound video and make a final prediction as to whether ICP is elevated. To construct our systems, we leverage subject matter expert (SME) guidance, structuring our processing pipeline according to their collection procedure, while also prioritizing interpretability and computational efficiency. We conduct a number of experiments, demonstrating that our proposed systems are able to outperform various baselines. One of our SMEs then manually validates our top system's performance, lending further credibility to our approach while demonstrating its potential utility in a clinical setting.

eess.IV↗

arXiv2022

MobilePTX: Sparse Coding for Pneumothorax Detection Given Limited Training Examples

Point-of-Care Ultrasound (POCUS) refers to clinician-performed and interpreted ultrasonography at the patient's bedside. Interpreting these images requires a high level of expertise, which may not be available during emergencies. In this paper, we support POCUS by developing classifiers that can aid medical professionals by diagnosing whether or not a patient has pneumothorax. We decomposed the task into multiple steps, using YOLOv4 to extract relevant regions of the video and a 3D sparse coding model to represent video features. Given the difficulty in acquiring positive training videos, we trained a small-data classifier with a maximum of 15 positive and 32 negative examples. To counteract this limitation, we leveraged subject matter expert (SME) knowledge to limit the hypothesis space, thus reducing the cost of data collection. We present results using two lung ultrasound datasets and demonstrate that our model is capable of achieving performance on par with SMEs in pneumothorax identification. We then developed an iOS application that runs our full system in less than 4 seconds on an iPad Pro, and less than 8 seconds on an iPhone 13 Pro, labeling key regions in the lung sonogram to provide interpretable diagnoses.

cs.CV↗

arXiv2013

Finite configurations in sparse sets

Let $E \subseteq R^n$ be a closed set of Hausdorff dimension $α$. For $m \geq n$, let $\{B_1,\ldots,B_k\}$ be $n \times (m-n)$ matrices. We prove that if the system of matrices $B_j$ is non-degenerate in a suitable sense, $α$ is sufficiently close to $n$, and if $E$ supports a probability measure obeying appropriate dimensionality and Fourier decay conditions, then for a range of $m$ depending on $n$ and $k$, the set $E$ contains a translate of a non-trivial $k$-point configuration $\{B_1y,\ldots,B_ky\}$. As a consequence, we are able to establish existence of certain geometric configurations in Salem sets (such as parallelograms in $ R^n$ and isosceles right triangles in $R^2$). This can be viewed as a multidimensional analogue of an earlier result of Laba and Pramanik on 3-term arithmetic progressions in subsets of $R$.

math.CA↗

arXiv2011

Spindown of Isolated Neutron Stars: Gravitational Waves or Magnetic Braking?

We study the spindown of isolated neutron stars from initially rapid rotation rates, driven by two factors: (i) gravitational wave emission due to r-modes and (ii) magnetic braking. In the context of isolated neutron stars, we present the first study including self-consistently the magnetic damping of r-modes in the spin evolution. We track the spin evolution employing the RNS code, which accounts for the rotating structure of neutron stars for various equations of state. We find that, despite the strong damping due to the magnetic field, r-modes alter the braking rate from pure magnetic braking for B<10^{13}G. For realistic values of the saturation amplitude, the r-mode can also decrease the time to reach the threshold central density for quark deconfinement. Within a phenomenological model, we assess the gravitational waveform that would result from r-mode driven spindown of a magnetized neutron star. To contrast with the persistent signal during the spindown phase, we also present a preliminary estimate of the transient gravitational wave signal from an explosive quark-hadron phase transition, which can be a signal for the deconfinement of quarks inside neutron stars.

astro-ph.SR↗