Volume 11, Issue 9, September 2023 Edition - IEEE-SEM Journal Publication
ChatGPT: The next Frontier in Software Project ManagementPDF
Qamar Abbas, Waqas Younus, Shumain Malik, Muhammad Hammad Hassan
This paper investigates the applications of Chat-GPT, a state-of-the-art language model, in the field of applied software project management. Chat-GPT, developed by OpenAI, is a generative AI model that has demonstrated remarkable advancements in natural language processing and generation of text-based output. This paper aims to highlight the potential uses of Chat-GPT in project management, including communication, risk management, resource allocation, and decision-making. By leveraging the capabilities of generative AI in language models, Chat-GPT offers innovative solutions for project management challenges. This paper also discusses the benefits and challenges associated with integrating Chat-GPT into project management workflows. Through this exploration, we shed light on how Chat-GPT can enhance project management practices, streamline communication processes, and improve overall project throughput and outcomes. The research findings provide valuable insights for practitioners and organizations seeking to harness the power of generative AI in applied project management.
Adaptive PID gain-scheduling for 3D smart quadrotor flight controllerPDF
Wassim Arfa/Chiraz Ben Jabeur/Yassine Faleh/Hassene Seddik
In this paper, we present a performance evaluation of PID controller gains for angle control of drones. The primary objective is to optimize the PID gains to enhance the performance of the drone. The proposed solution is named Adaptive PID flight controller for controlling the altitude dynamics of a UAV. This approach is based on three comparisons: Firstly, we compare the use of a single PID controller for all three angles. Secondly, we explore the option of using two PID controllers for the three angles, where the first controller is designed to con-trol the Pitch and Roll angles, while the second controller is dedicated to the Yaw angle. Finally, we use three PID controllers for each angle (Pitch, Roll and Yaw).
Our ultimate aim is to identify the most effective PID controller configuration that optimizes drone angle control, leading to improved sta-bility, responsiveness, and accuracy during flight.
Cyber Security Requirements for Platforms Enhancing AI ReproducibilityPDF
Polra Victor Falade
Scientific research is increasingly reliant on computational methods, posing challenges for ensuring research reproducibility. This study focuses on the field of artificial intelligence (AI) and introduces a new framework for evaluating AI platforms for reproducibility from a cyber security standpoint to address the security challenges associated with AI research. Using this framework, five popular AI reproducibility platforms—Floydhub, BEAT, Codalab, Kaggle, and OpenML—were assessed. The analysis revealed that none of these platforms fully incorporates the necessary cyber security measures essential for robust reproducibility. Kaggle and Codalab, however, performed better in terms of implementing cyber security measures covering aspects like security, privacy, usability, and trust. Consequently, the study provides tailored recommendations for different user scenarios, including individual researchers, small laboratories, and large corporations. It emphasizes the importance of integrating specific cyber security features into AI platforms to address the challenges associated with AI reproducibility, ultimately advancing reproducibility in this field. Moreover, the proposed framework can be applied beyond AI platforms, serving as a versatile tool for evaluating a wide range of systems and applications from a cyber security perspective.
A Modified Firefly Algorithm for Scheduling: Optimization Strategy with Objective Function FilteringPDF
Arcely Perez-Napalit, Melvin A. Ballera
This study evaluates the Modified Firefly Algorithm (MFA), an advanced optimization technique that integrates processes like Constraint Satisfaction, Hamming Distance, objective function filtering, and positional adjustment. The MFAs were assessed based on solution quality, computational efficiency, and performance in complex optimization problems. A meta-optimization process fine-tuned its parameters, improving solution quality. Despite longer computation times, the MFA outperformed other Firefly Algorithm variants in solution quality and adaptability. The study demonstrated the MFA's effectiveness in a real-world staff scheduling scenario, making it promising for similar problems in various domains. Despite challenges in computation time, the study underscores the trade-off for enhanced solution quality and the potential for further refinement highlights the benefits of enhanced solution quality, and recommends exploring varying n values and comparing them with other advanced optimization algorithms for future research.
UTILIZING EDPUZZLE AS PRE-LABORATORY DISCUSSION TOOL TO ENHANCE LABORATORY PERFORMANCE OF GRADE 9 STUDENTS
OF XAVIER UNIVERSITYPDF
MARIA LEAH PAOLA M. ESTACIO, JERECHO GREG R. GETARUELAS, ISIAH STEPHAN RADAZA, ANDREA ALEXA JOAN V. ERMINO RONALD G. KHU, CHRIST ISRAEL A. MILLARE,
This study aimed to determine whether the pre-laboratory discussion video enhances and determines possible indicators of the enhancement of laboratory performance among the actual 27 participants in one Grade 9 class of Xavier University Junior High School. Moreover, the study aims to know how were the experiences of students and teachers with the integration of the EdPuzzle discussion video, and learning how the results of the study help the community to further improve the laboratory procedures enhancement of Grade 9 students in a hybrid mode of learning. This study employed the mixed method design which is the combination of qualitative and quantitative approach to collect and analyze data. As for the sampling procedure, this study uses a purposive sampling, where the respondents of this study were selected on a specific grade level and section. Based on the results, there was an increase in test score results from pretest in which there are those who failed and to the post-test in which all passed. Moreover, there was a “significant difference “ between the pretest and posttest data through the T-test results and the FGD responses through thematic analysis. Through the utilization of the EdPuzzle discussion, students' interests increased in conducting more experiments in order to understand in depth the world around us. In addition to this, students’ test scores have a congruence to the performance rubric results. Prior to performing the experiment, students can be prepared by watching the EdPuzzle pre-laboratory discussion video and learning technical terms, equipment, and laboratory procedures. Hence, pretest and post-test scores improvement, good performance rubric results, rejection of the null hypothesis, and no groups required for experiment repetition, indicates conceptual and procedural knowledge retention of the students. It is recommended that the EdPuzzle pre-laboratory discussion be used in laboratory experiments in Xavier University Junior High School.
