Time series modeling is a commonly used approach in exchange for studying and analyzing the data to support decision-making in companies based on historical data and thereby help them to save costs. This work introduces a forecasting framework that utilizes a seasonal autoregressive integrated moving average with exogenous variables (SARIMAX) model to forecast the number of people expected to enter a building within a short period. We applied the model to forecast the abovementioned value at California University Irvine's main door using an open-source dataset that comprised data spanning four months. The experimental results demonstrate that the SARIMAX model exhibits encouraging performance in classification andevaluation, as evidenced by the promising results. The RMSE values for one,two, three, and four prediction weeks are 24.6, 40.4, 36, and 38.7, respectively, accompanied by corresponding percentage errors of 2%, 4.8%,4.76%, and 1.01%. These metrics highlight the model's ability to predict outcomes accurately and indicate its effectiveness in forecasting over various time horizons. Furthermore, the proposed model addresses the issue of inadequate future planning and analyzes foot traffic to provide a reliable forecasting technique, which is essential for modern building facilities management.

Real-time people counting is a beneficial system that covers many levels of use cases. It can help keep track of the number of people entering buildings, buses, stores, and other facilities. Knowing such information can be helpful in case of fire emergencies, preventing overcrowding in public transportation and facilities, helping people with social anxiety, and more. The use cases of such a device are endless and can significantly help society’s development. This thesis will provide research and a solution for accurate real-time people counting using two devices. Having multiple devices count the number of people passing through with good accuracy would benefit facilities with multiple exits. Two Coral Dev Boards will be used, each with its web camera. With the help of machine learning, the device will recognize the top of the head of people passing through and count them, which will later be sent to a server that counts the total amount from each device. The results varied between66.7 % and 100 % accuracy, depending on the walking speed. A fast-paced walking speed, almost running, resulted in 66.7 % accuracy. Meanwhile, a regular walking speed resulted in 80-100 % accuracy.