Skip to main content
eScholarship
Open Access Publications from the University of California

Electrical Engineering and Computer Science - Open Access Policy Deposits

This series is automatically populated with publications deposited by UC Irvine Samueli School of Engineering Electrical Engineering and Computer Science researchers in accordance with the University of California’s open access policies. For more information see Open Access Policy Deposits and the UC Publication Management System.

Cover page of Foundation metrics for evaluating effectiveness of healthcare conversations powered by generative AI

Foundation metrics for evaluating effectiveness of healthcare conversations powered by generative AI

(2024)

Generative Artificial Intelligence is set to revolutionize healthcare delivery by transforming traditional patient care into a more personalized, efficient, and proactive process. Chatbots, serving as interactive conversational models, will probably drive this patient-centered transformation in healthcare. Through the provision of various services, including diagnosis, personalized lifestyle recommendations, dynamic scheduling of follow-ups, and mental health support, the objective is to substantially augment patient health outcomes, all the while mitigating the workload burden on healthcare providers. The life-critical nature of healthcare applications necessitates establishing a unified and comprehensive set of evaluation metrics for conversational models. Existing evaluation metrics proposed for various generic large language models (LLMs) demonstrate a lack of comprehension regarding medical and health concepts and their significance in promoting patients’ well-being. Moreover, these metrics neglect pivotal user-centered aspects, including trust-building, ethics, personalization, empathy, user comprehension, and emotional support. The purpose of this paper is to explore state-of-the-art LLM-based evaluation metrics that are specifically applicable to the assessment of interactive conversational models in healthcare. Subsequently, we present a comprehensive set of evaluation metrics designed to thoroughly assess the performance of healthcare chatbots from an end-user perspective. These metrics encompass an evaluation of language processing abilities, impact on real-world clinical tasks, and effectiveness in user-interactive conversations. Finally, we engage in a discussion concerning the challenges associated with defining and implementing these metrics, with particular emphasis on confounding factors such as the target audience, evaluation methods, and prompt techniques involved in the evaluation process.

Cover page of Physiological and emotional assessment of college students using wearable and mobile devices during the 2020 COVID-19 lockdown: An intensive, longitudinal dataset

Physiological and emotional assessment of college students using wearable and mobile devices during the 2020 COVID-19 lockdown: An intensive, longitudinal dataset

(2024)

This dataset was collected from university students before, during, and after the COVID-19 lockdown in Southern California. Data collection happened continuously for the average of 7.8 months (SD=3.8, MIN=1.0, MAX=13.4) from a population of 21 students of which 12 have also completed an exit survey, and 7 started before the California COVID-19 lockdown order. This multimodal dataset included different means of data collection such as Samsung Galaxy Watch, Oura Ring, a Life-logger app named Personicle, a questionnaire mobile app named Personicle Questions, and periodical and personalised surveys. The dataset contains raw data from Photoplethysmogram (PPG), Inertial measurement unit (IMU), and pressure sensors in addition to processed data on heart rate, heart rate variability, sleep (bedtime, sleep stages, quality), and physical activity (step, active calories, type of activity). Ecological momentary assessments were collected from participants on daily and weekly bases containing their Positive and Negative Affect Schedule (PANAS) questionnaire and their emotional responses to COVID-19 and their health. Subjective data was also collected through monthly surveys containing standard mood and mental health surveys such as Beck Depression Inventory II (BDI-II), Brief Symptom Inventory (BSI), GAD-7, Inclusion of Other in the Self Scale (IOS-Partner), Acceptability of Intervention Measure (AIM), Intervention Appropriateness Measure (IAM), Feasibility of Intervention Measure (FIM), Experiences in Close Relationships Scale Short Form (ECR-S), UCLA Three-Item Loneliness Scale (ULS), Multidimensional Scale of Perceived Social Support (MSPSS), Investment Model Scale (IMS), Conflict Management Scale (CMS), etc in addition to their response to important events and COVID-19. This dataset can be used to study emotions, mood, physical activity, and lifestyle of young adults through longitudinal subjective and objective measures. This dataset also contains valuable data regarding adjustment of lifestyle and emotions during the events of 2020 and 2021 including COVID-19 discovery and lockdown, Black Life Matter movement, 2020 US presidential elections, etc. On average, participants engaged in the EMA collection study at a rate of 86% (SD=10, MIN=65, MAX=99). Smartwatch usage saw an average participation rate of 51% (SD=20, MIN=16, MAX=88), while engagement with the Oura ring averaged at 85% (SD=12, MIN=60, MAX=99).

Cover page of ChatDiet: Empowering personalized nutrition-oriented food recommender chatbots through an LLM-augmented framework

ChatDiet: Empowering personalized nutrition-oriented food recommender chatbots through an LLM-augmented framework

(2024)

The profound impact of food on health necessitates advanced nutrition-oriented food recommendation services. Conventional methods often lack the crucial elements of personalization, explainability, and interactivity. While Large Language Models (LLMs) bring interpretability and explainability, their standalone use falls short of achieving true personalization. In this paper, we introduce ChatDiet, a novel LLM-powered framework designed specifically for personalized nutrition-oriented food recommendation chatbots. ChatDiet integrates personal and population models, complemented by an orchestrator, to seamlessly retrieve and process pertinent information. The personal model leverages causal discovery and inference techniques to assess personalized nutritional effects for a specific user, whereas the population model provides generalized information on food nutritional content. The orchestrator retrieves, synergizes and delivers the output of both models to the LLM, providing tailored food recommendations designed to support targeted health outcomes. The result is a dynamic delivery of personalized and explainable food recommendations, tailored to individual user preferences. Our evaluation of ChatDiet includes a compelling case study, where we establish a causal personal model to estimate individual nutrition effects. Our assessments, including a food recommendation test showcasing a 92% effectiveness rate, coupled with illustrative dialogue examples, underscore ChatDiet's strengths in explainability, personalization, and interactivity.

A CMOS Fully Integrated 120-Gbps RF-64QAM F-band Transmitter with an On-Chip Antenna for 6G Wireless Communication

(2024)

This paper presents a single-chip bits-to-antenna transmitter (TX) for >100 Gbps in 45nm CMOS SOI. The construction of the 64QAM constellation is achieved directly in the RF domain by utilizing three QPSK sub-TXs with weighted amplitude. This method significantly reduces the need to address power amplifier nonlinear effects in high-order modulation, thereby creating room for TX enhancements in both bandwidth and output power. To further improve TX performance, multi-step phase alignment strategies, and a local oscillator leakage suppression technique have been incorporated. With 40-GHz RF bandwidth, the RF-64QAM TX prototype is able to achieve a measured data rate of 120 Gbps with 15dBm effective isotropic radiated power (EIRP).

Cover page of Photon-Momentum-Enabled Electronic Raman Scattering in Silicon Glass

Photon-Momentum-Enabled Electronic Raman Scattering in Silicon Glass

(2024)

The nature of enhanced photoemission in disordered and amorphous solids is an intriguing question. A point in case is light emission in porous and nanostructured silicon, a phenomenon that is still not fully understood. In this work, we study structural photoemission in heterogeneous cross-linked silicon glass, a material that represents an intermediate state between the amorphous and crystalline phases, characterized by a narrow distribution of structure sizes. This model system shows a clear dependence of photoemission on size and disorder across a broad range of energies. While phonon-assisted indirect optical transitions are insufficient to describe observable emissions, our experiments suggest these can be understood through electronic Raman scattering instead. This phenomenon, which is not commonly observed in crystalline semiconductors, is driven by structural disorder. We attribute photoemission in this disordered system to the presence of an excess electron density of states within the forbidden gap (Urbach bridge) where electrons occupy trapped states. Transitions from gap states to the conduction band are facilitated through electron-photon momentum matching, which resembles Compton scattering but is observed for visible light and driven by the enhanced momentum of a photon confined within the nanostructured domains. We interpret the light emission in structured silicon glass as resulting from electronic Raman scattering. These findings emphasize the role of photon momentum in the optical response of solids that display disorder on the nanoscale.

Cover page of HyperXite 9

HyperXite 9

(2024)

The overall objective for HyperXite 9 was to design and build a more robust, and reliable pod, capable of proving the feasibility of a high-speed transportation system. We are working to improve a linear induction motor as the pod's propulsion system. We are also designing and implementing a thermal cooling system to actively dissipate the heat generated by this propulsion system. Our team is comprised of the following 7 subteams: Static Structures, Braking & Pneumatics, Dynamic Structures, Propulsion, Power Systems, Control Systems, and Outreach.

Cover page of Long-range optical coherence tomography of pediatric airway during drug induced sleep endoscopy: A preliminary report

Long-range optical coherence tomography of pediatric airway during drug induced sleep endoscopy: A preliminary report

(2024)

Objective

Drug induced sleep endoscopy (DISE) is often performed for pediatric obstructive sleep apnea (OSA) when initial diagnostic studies do not provide adequate information for therapy. However, DISE scoring is subjective and with limitations. This proof-of-concept study demonstrates the use of a novel long-range optical coherence tomography (LR-OCT) system during DISE of two pediatric patients.

Methods

LR-OCT was used to visualize the airway of pediatric patients during DISE. At the conclusion of DISE, the OCT probe was guided in the airway under endoscopic visual guidance, and cross-sectional images were acquired at the four VOTE locations. Data processing involved image resizing and alignment, followed by rendering of three-dimensional (3D) volumetric models of the airways.

Results

Two patients were included in this study. Patient one had 18.4%, 20.9%, 72.3%, and 97.3% maximal obstruction at velum, oropharynx, tongue base, and epiglottis, while patient two had 40.2%, 41.4%, 8.0%, and 17.5% maximal obstruction at these regions, respectively. Three-dimensional reconstructions of patients' airways were also constructed from the OCT images.

Conclusion

This proof-of-concept study demonstrates the successful evaluation of pediatric airway during DISE using LR-OCT, which accurately identified sites and degrees of obstruction with respective 3D airway reconstruction.

Cover page of Understanding the Internet-Wide Vulnerability Landscape for ROS-based Robotic Vehicles

Understanding the Internet-Wide Vulnerability Landscape for ROS-based Robotic Vehicles

(2024)

Due to the cyber-physical nature of robotic vehicles, security is especially crucial, as a compromised system not only. exposes privacy and information leakage risks, but also increases the risk of harm in the physical world. As such, in this paper, we explore the current vulnerability landscape of robotic vehicles exposed to and thus remotely accessible by any party on the public Internet. Focusing particularly on instances of the Robot Operating System (ROS), a commonly used open-source robotic software framework, we performed new Internet-wide scans of the entire IPv4 address space, identifying, categorizing, and analyzing the ROS-based systems we discovered. We further performed the first measurement of ROS scanners in the wild by setting up ROS honeypots, logging traffic, and analyzing the traffic we received. We found over 190 ROS systems on average being regularly exposed to the public Internet and discovered new trends in the exposure of different types of robotic vehicles, suggesting increasing concern regarding the cybersecurity of today’s ROS-based robotic vehicle systems.

Cover page of Ultrafast Q-boosting in semiconductor metasurfaces

Ultrafast Q-boosting in semiconductor metasurfaces

(2024)

All-optical tunability of semiconductor metasurfaces offers unique opportunities for novel time-varying effects, including frequency conversion and light trapping. However, the all-optical processes often induce optical absorption that fundamentally limits the possible dynamic increase of their quality factor (Q-boosting). Here, we propose and numerically demonstrate the concept of large Q-boosting in a single-material metasurface by dynamically reducing its structural anisotropy on a femtosecond timescale. This balance is achieved by excitation with a structured pump and takes advantage of the band-filling effect in a GaAs direct-bandgap semiconductor to eliminate the free-carrier-induced loss. We show that this approach allows a dynamic boosting of the resonance quality factor over orders of magnitude, only limited by the free-carrier relaxation processes. The proposed approach offers complete dynamic control over the resonance bandwidth and opens applications in frequency conversion and light trapping.

Cover page of Early Feasibility Study of a Hybrid Tissue-Engineered Mitral Valve in an Ovine Model

Early Feasibility Study of a Hybrid Tissue-Engineered Mitral Valve in an Ovine Model

(2024)

Tissue engineering aims to overcome the current limitations of heart valves by providing a viable alternative using living tissue. Nevertheless, the valves constructed from either decellularized xenogeneic or purely biologic scaffolds are unable to withstand the hemodynamic loads, particularly in the left ventricle. To address this, we have been developing a hybrid tissue-engineered heart valve (H-TEHV) concept consisting of a nondegradable elastomeric scaffold enclosed in a valve-like living tissue constructed from autologous cells. We developed a 21 mm mitral valve scaffold for implantation in an ovine model. Smooth muscle cells/fibroblasts and endothelial cells were extracted, isolated, and expanded from the animal's jugular vein. Next, the scaffold underwent a sequential coating with the sorted cells mixed with collagen type I. The resulting H-TEHV was then implanted into the mitral position of the same sheep through open-heart surgery. Echocardiography scans following the procedure revealed an acceptable valve performance, with no signs of regurgitation. The valve orifice area, measured by planimetry, was 2.9 cm2, the ejection fraction reached 67%, and the mean transmitral pressure gradient was measured at 8.39 mmHg. The animal successfully recovered from anesthesia and was transferred to the vivarium. Upon autopsy, the examination confirmed the integrity of the H-TEHV, with no evidence of tissue dehiscence. The preliminary results from the animal implantation suggest the feasibility of the H-TEHV.