Different signal frequencies from body tissues, muscles fat etc affects the EMG signals. The signal frequencies from body organ can considered as noise which affects the output and hence for better signal output noised should be minimised. Traditional EMG machines supports analogue filtering while residual noises carried by signal channels. For good and better signal aggregation and useful data gathering machine generated noises need to be cleared out for maintaining proper accuracy regardless of signal distortions. In this work, an artifact reduction method is proposed for the EMG machines that can detect noise, randomized trials or points through sequential predictions. Through the proposed prediction method the data points will be reshaped and re-sampled with variance checking. It ensures maximization of SNR of the EMG signals. The reduction method also works with a digital sequence filter which shapes the noisy inputs. The shaped input then merged with a sequential output with less loss of information. Since the noise reduction process is a prediction based filter method, it will be independent of signal frequencies related with body organs like - body tissues, muscles fat etc. It reduces the variance and low discrepancy also.

Most of the appliances that we used in our everyday life are electronic devices, i.e. TV, Air Conditioner, Refrigerator, etc. Excessive voltage, current, temperature, etc. can harm the devices and in extreme cases, the devices can be completely damaged. We proposed a system to monitor the electrical behaviors of the devices in real-time. The system is trained with an unlabeled dataset and capable of identifying outliers. We have used a clustering technique, i.e. Density-Based Spatial Clustering of Applications with Noise (DBSCAN) to learn the label of a dataset and then apply machine learning algorithms, i.e. Support Vector Machine (SVM) and Decision Tree to predict the label of the new data. From the prediction, the system determines whether the device is operating in safe mode or not. In this work, we have achieved the accuracy of 98.61% in detecting outliers using SVM with `rbf' kernel. Hence, if the device operates beyond safe mode, we can shut down the device.