Search

Many machine-learning-enabled approaches towards anomaly detection depend on the availability of vast training data. Our data are formed from power readings of cycles from domestic appliances, such as dishwashers or washing machines, and contain no known examples of anomalous behaviour. Moreover, we are limited to the machine’s voltage, amperage, and current readings, drawn from a retrofitted power outlet in 60-s samples. No rich sensor data or previous insights are available as a training basis, limiting our ability to leverage the existing work. We design a system to monitor the behaviour of electrical appliances. This system requires special consideration as different power cycles from the same machine can exhibit different behaviours, and it accounts for this by clustering unseen cycle patterns into siloed training datasets and corresponding learned parameters. They are then passed in real-time to an autoencoder ensemble for reconstruction-based anomaly detection, using the error in reconstruction as a means to flag anomalous points in time. The system correctly identifies and trains appropriate cycle clusters of data streams on a real-world machine dataset injected with stochastic, proportionate anomalies.

Indoor air quality typically encompasses the ambient conditions inside buildings and public facilities that may affect both the mental and respiratory health of an individual. Until the COVID-19 outbreak, indoor air quality monitoring was not a focus area for public facilities such as shopping complexes, hospitals, banks, restaurants, educational institutes, and so forth. However, the rapid spread of this virus and its consequent detrimental impacts have brought indoor air quality into the spotlight. In contrast to outdoor air, indoor air is recycled constantly causing it to trap and build up pollutants, which may facilitate the transmission of virus. There are several monitoring solutions which are available commercially, a typical system monitors the air quality using gas and particle sensors. These sensor readings are compared against well known thresholds, subsequently generating alarms when thresholds are violated. However, these systems do not predict the quality of air for future instances, which holds paramount importance for taking timely preemptive actions, especially for COVID-19 actual and potential patients as well as people suffering from acute pulmonary disorders and other health problems. In this regard, we have proposed an indoor air quality monitoring and prediction solution based on the latest Internet of Things (IoT) sensors and machine learning capabilities, providing a platform to measure numerous indoor contaminants. For this purpose, an IoT node consisting of several sensors for 8 pollutants including NH3, CO, NO2, CH4, CO2, PM 2.5 along with the ambient temperature &amp, air humidity is developed. For proof of concept and research purposes, the IoT node is deployed inside a research lab to acquire indoor air data. The proposed system has the capability of reporting the air conditions in real-time to a web portal and mobile app through GSM/WiFi technology and generates alerts after detecting anomalies in the air quality. In order to classify the indoor air quality, several machine learning algorithms have been applied to the recorded data, where the Neural Network (NN) model outperformed all others with an accuracy of 99.1%. For predicting the concentration of each air pollutant and thereafter predicting the overall quality of an indoor environment, Long and Short Term Memory (LSTM) model is applied. This model has shown promising results for predicting the air pollutants&rsquo, concentration as well as the overall air quality with an accuracy of 99.37%, precision of 99%, recall of 98%, and F1-score of 99%. The proposed solution offers several advantages including remote monitoring, ease of scalability, real-time status of ambient conditions, and portable hardware, and so forth.

Urban centers across the globe are under immense environmental distress due to an increase in air pollution, industrialization, and elevated living standards. The unmanageable and mushroom growth of industries and an exponential soar in population has made the ascent of air pollution intractable. To this end, the solutions that are based on the latest technologies, such as the Internet of things (IoT) and Artificial Intelligence (AI) are becoming increasingly popular and they have capabilities to monitor the extent and scale of air contaminants and would be subsequently useful for containing them. With centralized cloud-based IoT platforms, the ubiquitous and continuous monitoring of air quality and data processing can be facilitated for the identification of air pollution hot spots. However, owing to the inherent characteristics of cloud, such as large end-to-end delay and bandwidth constraint, handling the high velocity and large volume of data that are generated by distributed IoT sensors would not be feasible in the longer run. To address these issues, fog computing is a powerful paradigm, where the data are processed and filtered near the end of the IoT nodes and it is useful for improving the quality of service (QoS) of IoT network. To further improve the QoS, a conceptual model of distributed fog computing and a machine learning based data processing and analysis model is proposed for the optimal utilization of cloud resources. The proposed model provides a classification accuracy of 99% while using a Support Vector Machines (SVM) classifier. This model is also simulated in iFogSim toolkit. It affords many advantages, such as reduced load on the central server by locally processing the data and reporting the quality of air. Additionally, it would offer the scalability of the system by integrating more air quality monitoring nodes in the IoT network.