The gLOWCOST (global low-cost cosmic detector network) developed with support from the RISE initiative, aims to better understand the Earth’s terrestrial and space weather by deploying a low-cost portable cosmic ray detector network worldwide. High energy particles originating from outer galactic space or our sun, interact with the Earth’s atmosphere causing various particles to shower towards the Earth’s surface. Out of these, muons can be detected easily at the surface of the Earth. Since these muon particles carry information about the conditions of the atmosphere it has passed through and about outer space where they originated from, a model for both terrestrial and space weather can be built if there is enough information about the cosmic flux from all around the world. Because of this exciting idea, scientists have already collaborated with the cosmic ray research group at GSU to deploy the detectors in six countries around the world. With the current detector network, we were able to see the detector’s sensitivity to space weather phenomena such as Geomagnetic storms and also,terrestrial weather phenomena such as hurricanes. We are working towards the goal of developing the detector network by addressing the challenges encountered in expanding the network,analyzing data from the current detectors to build models to better understand these terrestrial and space weather phenomena, and using the detector as a tool of STEM education to popularize and engage students in the field of cosmic ray science which will be highly valuable with emerging outer space activities of mankind.

Title: A smart sock-based remote monitoring system to assess the progression of clinical disability and fatigue in people with Multiple Sclerosis. Authors: Julie F. Stowell, DPT1,2, Victory A. Ladipo3, Sujay S. Galen2 and T. Bradley Willingham, PhD1,2 1 Virginia C. Crawford Research Institute, Shepherd Center. Atlanta, GA, USA. 2Georgia State University, Byrdine F. Lewis College of Nursing and Health Professions, Atlanta, GA, USA. 3Georgia Institute of Technology, Department of Biology. Atlanta, GA, USA. The purpose of this cross-sectional study was to determine whether gait metrics derived from a smart sock-based remote monitoring system can identify different disability levels in people with MS (PwMS) and detect changes in gait associated with motor fatigue during prolonged walking. Twenty participants (14F, 6M) were recruited by convenience sampling; mean age was 46.6±15.47 years and mean Patient Determined Disease Steps (PDDS; disability level) score was 4.2±1.74. Participants completed the timed 25-foot walk test (T25FTWT), timed up and go test (TUG), 6-minute walk test (6MWT) while wearing smart socks to measure gait metrics. Fatigue ratings were collected before, after, and during the walk tests using the Visual Analog Scale for Fatigue (VAS‐F). Participants also completed questionnaires related to walking, fatigue, and disability level. Gait metrics derived from smart socks were significantly correlated to disability level (Cadence r=-0.682-0.753, p≤0.001; speed r=-0.59-0.751, p≤0.008; gait cycle r=0.57-0.665, p≤0.011; step time r=0.533-0.661, p≤0.023; single support r=0.519-0.66, p≤0.023; double support r=0.513-0.564, p≤0.025; and stance time r=0.572-0.654, p≤0.010) across all walk tests. Gait metrics (cadence, gait cycle, step time, double support time, stance time; p≤0.05) significantly changed from minute 1 to 6 during the 6MWT. Self-reported fatigue increased 181.3±235.3% during the 6MWT; change from minute 1 to 6 is statistically significant (minute 1 x̄ =2.5±2.3, minute 6 x̄=5.5±3.2; p=0.000). Our results demonstrate the potential for wearable smart sock systems to assess the progression of clinical disability and fatigue in PwMS. Thus, this technology has the potential to enhance diagnostics, treatment, and research strategies for PwMS.

The primary aim of this paper is to delve into the enhancement of body posture during exercise utilizing an innovative AI-based smart system. This system is designed to provide recommendations for improved posture by employing real-time images and video sensing technology. Acknowledging the profound impact of mental health on our daily routines and physical workout regimens, this paper underscores the critical importance of regular physical exercise in maintaining optimal hormone levels and fostering mindfulness. It underscores the the necessity of executing physical practices safely and properly to prevent potential harm to the body. Consequently, continual monitoring and adjustment of exercise techniques are advocated to ensure their effectiveness and safety. The study focuses on exploring AI-based exercise monitoring systems, leveraging various Python modules such as MediaPipe, TensorFlow, Matplotlib, and OpenCV, among others. These modules are instrumental in analyzing input data comprehensively and furnishing precise feedback on body posture, thereby facilitating informed adjustments to exercise routines. Keywords:- Physical exercise, OpenCV, TensorFlow, CNN, Media Pipe.