To assist the visually impaired people to travel independently without external aid and monitoring real-time location information of these individuals, a wearable electronic device is presented in this paper. The system is able to detect the obstacles in front of the user, humps on the ground, moving objects. In addition, the system detects the sudden fall and informs the user’s guardian. The system is comprised of ultrasonic sensors, a PIR motion sensor, an accelerometer, a smartphone application, a microcontroller, and a data transmission device. The microcontroller transmits the data to the user’s smartphone via Bluetooth module. The smartphone application generates audible instructions to navigate the user properly. The application also updates the current location of the user to keep track and notifies the guardians when the user falls down or in distress. The developed system obtained an accuracy of about 98.34% when the obstacle is 50 cm away from the user. The system is proved to be very effective and efficient for users to navigate using precise speech instructions. Overall, the developed system will make the visually impaired people and their guardian’s feel much safer and confident.

Anemia, which is defined by a lack of red blood cells or hemoglobin, is a widespread issue in global health that has far-reaching effects. An accurate and timely diagnosis of Anemia is essential, especially for pregnant women and people with chronic medical conditions as it can result in weakness, exhaustion, deteriorated cognitive function, and other severe problems. Traditional techniques of detecting Anemia often involve invasive blood testing, which can be expensive and inconvenient. This study proposes a non-invasive mHealth application that uses a machine learning and deep learning algorithms to identify Anemia from conjunctiva images. An annotated dataset containing eye conjunctiva images and ground truth masks were prepared for this study. The proposed system uses smartphone to capture image of a person's face with exposed conjunctiva and this image is segmented and region of interest that is eye conjunctiva is separated from the background. Then this segmented region is classified into Anemic and Non-anemic class by a machine learning algorithm. In this study UNet architecture gave 72.05% IOU in segmentation task and Random Forest classifier showed 91.43%±1.06% accuracy.

Word Sense Disambiguation (WSD) refers to the process of finding the appropriate sense of an ambiguous word i.e. a word with multiple senses. It is an important problem in natural language processing that enables a machine to disambiguate and understand human natural language. In this paper, a method for WSD is proposed based on the context of the word using WordNet as a knowledge base. First, the input paragraph is preprocessed before disambiguating operation starts. The disambiguation process determines the appropriate senses of the ambiguous words using context information of each word in the paragraph. The radix tree data structure used to store context information for efficient searching.