This article presents ‘Poribohon-BD’ dataset for vehicle classification purposes in Bangladesh. The dataset contains 9058 labeled and annotated images of 15 native Bangladeshi vehicles such as bus, motorbike, three-wheeler rickshaw, truck, wheelbarrow.

A machine learning approach is proposed to recognize doctors’ cursive handwriting and create digital prescriptions. The methodology includes Rotating, Shifting, and Stretching (RSS) for data augmentation and Bidirectional LSTM model for recognition.

A transfer learning approach based on CNN has been applied to the popular You Only Look Once (YOLO) framework for vehicle classification. The pre-trained convolutional layers of the YOLO model are resued to detect 15 novel vehicles of Bangladesh.

A proposed prototype for identifying patients having cardiac disease. It consists of different sensor modules to collect data e.g., Heart BPM, Cholesterol, ECG, etc., and uses an ML model to perform the classification based on the collected data.

This paper has applied three encoding techniques (one-hot encoding, label encoding, and frequency encoding) and proposed a new encoding approach to handle categorical variables.

This article has introduced a handwritten dataset from Bangladeshi doctors and applied a proposed data augmentation technique SRP (Stroke Rotation and Parallel shift) using a Bidirectional LSTM model is used for the classification purpose.

An IoT and Machine Learning derived cardiac status prediction method that can collect necessary data from the human body using IoT devices (sensors) and transfer those data to the cloud to store and apply further classification processes.