Researchers have been working for a long time to recognize human activities based on sensor-based data. Despite the ongoing advancements in this field, it remains challenging to recognize complex human activities for a specific domain. To bring attention to this issue, the "Third Nurse Care Activity Recognition Challenge" gathered accelerometer data from smartphones to estimate daily nurse care activities. The main challenge was handling the noisy and inconsistent dataset, which is a persistent issue in any real-life data. Also, each activity depends on both the subject and the receiver, making its recognition more complex. Our team, Team Alkaline, used high pass and low pass filters to reduce noise, adopting an overlapping windowing technique. Then we extracted features in multiple domains to derive the necessary information required for classifying the human activities more accurately. Later on, we used a feature selection method to select the most significant features. We applied Random Forest (RF) classifier for training and achieved 99.0% accuracy on the validation set.