Anomaly detection in indoor localization using Machine Learning

One of the most concerning topics in smart cities is the internet of things, namely wireless sensor networks in indoor localization. Wi-Fi with received signal strengths (RSSs) is one of the most used indoor localization techniques. It generates signal intensity irregularities in Wi-Fi RSSs owing to reflection, refraction, incursion, and channel noise. RSS values cannot be defined (the location of each unknown node must be accurately stated). Here, Asymmetrical, abnormal circumstances are present in the Wi-Fi indoor localization area. Matplotlib, numpy, pandas, ploty, scipy, seaborn, scikitlearn, wordcloud, statsmodels, and streamlit were utilized in this study.