Conversational AI systems have emerged as key enablers of human-like interactions across diverse sectors. Nevertheless, the balance between linguistic nuance and factual accuracy has proven elusive. In this paper, we first introduce LLMXplorer, a comprehensive tool that provides an in-depth review of over 205 large language models (LLMs), elucidating their practical implications, ranging from social and ethical to regulatory, as well as their applicability across industries. Building on this foundation, we propose a novel functional architecture that seamlessly integrates the structured dynamics of knowledge graphs with the linguistic capabilities of LLMs. Validated using real-world AI news data, our architecture adeptly blends linguistic sophistication with factual rigor and further strengthens data security through role-based access control. This research provides insights into the evolving landscape of conversational AI, emphasizing the imperative for systems that are efficient, transparent, and trustworthy.

Glucose forecasting serves as a backbone for several healthcare applications, including real-time insulin dosing in people with diabetes and physical activity optimization. This paper presents a study on the use of machine learning (ML) and deep learning (DL) methods for predicting glucose variability (GV) in individuals with open-source automated insulin delivery systems (AID). A three-stage experimental framework is employed in this work to systematically implement and evaluate ML/DL methods on a large-scale diabetes dataset collected from individuals with open-source AID. The first stage involves data collection, the second stage involves data preparation and exploratory analysis, and the third stage involves developing, fine-tuning, and evaluating ML/DL models. The performance and resource costs of the models are evaluated alongside relative and proportional errors for 17 GV metrics. Evaluation of fine-tuned ML/DL models shows considerable accuracy in glucose forecasting and variability analysis up to 48 h in advance. The average MAE ranges from 2.50 mg/dL for long short-term memory models (LSTM) to 4.94 mg/dL for autoregressive integrated moving average (ARIMA) models, and the RMSE ranges from 3.7 mg/dL for LSTM to 7.67 mg/dL for ARIMA. Model execution time is proportional to the amount of data used for training, with long short-term memory models having the lowest execution time but the highest memory consumption compared to other models. This work successfully incorporates the use of appropriate programming frameworks, concurrency-enhancing tools, and resource and storage cost estimators to encourage the sustainable use of ML/DL in real-world AID systems.

Deep Learning (DL) based classification of conventional objects using mm-Wave Frequency Modulated Continuous Wave (FMCW) radars is useful for multiple real-world automotive applications. These applications require highly precise and accurate embedded setups to tackle undesirable mishaps. In general adversarial attacks can account for significant degradations in the performance of DL models. Provided a specific hardware setup, the system should be equipped with robust classification algorithms to counter adversarial attacks. The goal of this paper is to present an experimental study regarding the effects of a classical adversarial attack on some of the state-of-the-art DL algorithms. The first phase is to acquire experimental data and construct Range-Angle profile datasets using mm-Wave FMCW radars in real-world situations with and without objects, including a human and car on 5, 10, and 20 meters distances. Afterward, we have developed four DL models, including a self-designed RadarNet using a Convolutional Neural Network (CNN) and transfer learning-based ResNet34, InceptionV3, and GoogleNet2. The models yield an average accuracy of 94% using confusion matrix as a performance parameter. We further applied the Fast Gradient Sign Method (FGSM) adversarial attack on all four models and present a comparative study of its effects on classification accuracy. The results demonstrate that the average accuracy for DL-models degrades to 18.87%, 17.53%, and 16.08% for epsilon values of 0.001, 0.005, and 0.009, respectively. Having a significant degradation in accuracy highlights that adversarial retraining is essential to counter the effects of FGSM adversarial attacks.

Classification of objects using radars can be useful for a wide range of applications including surveillance systems, autonomous vehicles and collision avoidance systems for drones. This paper presents deep neural networks based object classification technique using a 77-81 GHz frequency modulated continuous wave (FMCW) radar. The data is acquired in a variety of real-world scenarios with various objects including humans and cars at various distances between 5 to 20 meters. The work assesses two types of data sets namely range plots and range-angle heat-maps on which Deep Learning Models are developed and trained. Transfer learning is used to incorporate use of multiple pre-trained models including ResNet34, InceptionV3, GoogleNet2 and a less complex self designed Convolutional Neural Network (CNN) is developed for comparison. The proposed technique uses confusion matrix as the performance metric and achieves an overall average classification accuracy of 94% using range-angle heat maps and 93% using range profile for all classes.

Background: Data analysis plays a pivotal role in transforming raw data into findings that are transparent, reproducible, and clinically meaningful and useful, which is critical when analyzing insulin-related data for diabetes studies. Failing to do so will make subsequent analysis of insulin data irrelevant due to inaccuracies. Objective: Describe the end-to-end pre-processing steps used for assessing the T1DEXI dataset and why these steps are necessary before moving to data analysis. Methods: Standardize and harmonize the raw datasets, including comparing devices and adjusting per-device pre-processing steps; mitigating gaps in data; accounting for extended insulin delivery that is articulated as single timestamp records as well as similarly accounting for suspension of insulin delivery, taking into account the periods of time in which insulin was or was not delivered. Results: Insulin-related data is transformed to uniform per-5-minute intervals and is able to be used for subsequent analysis and event-based interpretation. Conclusions: As it relates to insulin delivery, pre-processing should be used to make sure that insulin delivery is uniformly analyzed down to 5-minute intervals so that all insulin delivery event types, whether those be manual up-front boluses; basal or temporary basal rates; and extended bolus events (such as square or dual/square wave boluses) and suspend events are correctly documented as a timeseries such that subsequent analysis will be accurate based on the duration of insulin activity.