Large Language Models (LLMs) have been applied to build several automation and personalized question-answering prototypes so far. However, scaling such prototypes to robust products with minimized hallucinations or fake responses still remains an open challenge, especially in niche data-table heavy domains such as financial decision making. In this work, we present a novel Langchain-based framework that transforms data tables into hierarchical textual "data chunks" to enable a wide variety of actionable question answering. First, the user-queries are classified by intention followed by automated retrieval of the most relevant data chunks to generate customized LLM prompts per query. Next, the custom prompts and their responses undergo multi-metric scoring to assess for hallucinations and response confidence. The proposed system is optimized with user-query intention classification, advanced prompting, data scaling capabilities and it achieves over $ 90\%$ confidence scores for a variety of user-queries responses ranging from {What, Where, Why, How, predict, trend, anomalies, exceptions} that are crucial for financial decision making applications. The proposed data to answers framework can be extended to other analytical domains such as sales and payroll to ensure optimal hallucination control guardrails.

Temperature sensing and control systems are widely used in the closed-loop control of critical processes such as maintaining the thermal stability of patients, or in alarm systems for detecting temperature-related hazards. However, the security of these systems has yet to be completely explored, leaving potential attack surfaces that can be exploited to take control over critical systems.

The objective of this paper is to instill in students motivation and interest for what they are studying a little bit further of the theory they learn in classroom. Sometimes students prefer more interactive classes and want to know why the material given in class is helpful in their career. Do we have a solution for this? Autonomous Robotic Vehicle (ARV) projects can be the solution to this problem. This type of project are interdisciplinary and offer students varieties of challenges, while involving different areas of interest like programming, design, assembling and testing. One of the best ARV project is the Micromouse. The Micromouse is a small robot that solves mazes. The basic idea is that the student makes his own Micromouse from scratch using knowledge acquired from different classes and the research done. This project also helps the student to develop teamwork skills and creativity to complete the different challenges and objectives that appear when building a Micromouse. The student learns the importance of working with students from other engineering concentrations, which allows him to experience how a career in engineer will be.

This paper presents an efficient conflict resolution method for multiple aerial vehicles based on speed planning. The problem is assigning a speed profile to each aerial vehicle in real time such that the separation between them is greater than a minimum safety value and the total deviation from the initial planned trajectories is minimized. Also, the arrival time of each aerial vehicle at the end waypoint of the trajectory is taken into account to solve the conflicts. The proposed method involves the use of appropriate airspace discretization. The method consists of two steps: a search tree step, which finds if it exists a solution; and an optimization step by solving a QP-problem, which minimizes a cost function. The paper also presents simulations for several scenarios and experiments that have been carried out in the multivehicle aerial testbed of the Center for Advanced Aerospace Technologies (CATEC).