Optimizing High Energy Physics Experiments With Ai And Iot: A Data-Centric Approach To Particle Detection And Analysis

Main Article Content

Fahad Rasheed, Muhammad Tahir, Rana Muhammad Bilal, Ameer Hamza, Tariq Rafique, Hassan Mumtaz, Dr. Sidra Naz

Abstract

Background: AI and IoT’s inclusion in HEP experiments presents a rich opportunity for particle detection and data analysis improvement. However, it is uncertain just how much these technologies improve experimental speed and precision and what difficulties were experienced while implementing them.


Objective: The goal of this research is to evaluate if employing AI and IoT technologies would work in enhancing the HEP experiments specifically in the areas of particle identification and characterization. The work also presents the case of the challenges that organizational professionals experience in the implementation of these technologies and possible enhancements.


Methods: This paper adopted an exploratory quantitative research design with the use of a survey to gather data from 250 professionals engaged in high-energy physics experiments such as theorists, technologists, and statisticians. This survey established the satisfaction levels of respondents towards AI & IoT; the usage frequency and benefits derived; as well as the challenges experienced. Descriptive analysis, normality tests (Shapiro-Wilk), internal consistency (Cronbach’s Alpha), and Factor analysis.


Results: The mean satisfaction scores of AI and IoT were 2.87 and 2.98 respectively which can be considered a moderate level of satisfaction. The null hypothesis was rejected, and the Shapiro-Wilk test indicated that both the dependent variables AI accuracy (W =,953, p = .0 < .05) and IoT efficiency (W = .954, p = .0 < .05) are not normally distributed. The analysis of results for satisfaction with AI and IoT also showed low internal consistency according to Cronbach’s Alpha coefficient. Challenges of AI are lack of expertise and computational resources and those of IoT include high device costs and issues with network connectivity. Still, in the HEP experiments, IoT terms are used more often than AI terms.


Conclusion: There are lots of prospects in using AI and IoT for tuning the HEP experiments; nonetheless, a wide array of technical and infrastructural challenges prevent their practical use. Issues such as technical skills in doing calculations, computational resources, and IoT devices and platforms can be greatly improved to boost their effectiveness in raising the efficiency of experiments. Futile attempts to further advance the utilization of these technological advances in high-energy physics require more directed approaches.

Article Details

Section
Articles