The aim of the research is to present an approach of obstacle distance estimation and navigation for smart wheelchair. The smart wheelchair is an electric wheelchair equipped with camera and line laser to navigate and avoid an obstacle. The camera was used to capture images from the environment to sense the pathway condition. The line laser was used in combination with camera to recognize an obstacle in the pathway based on the shape of line laser image in certain angle. A blob method detection was applied on the line laser image to recognize the pattern of the detected obstacles. The line laser projector and camera were mounted in fixed-certain position to make sure a fixed relation between blobs-gaps and obstacle-to-wheelchair distance. A simple linear regression from 16 obtained data was used to represent this relation as the estimated obstacle distance. As a result, the average error between the estimation and actual distance was 1.25 cm from 7 data testing experiments. The experiments result indicates that the proposed method is able to estimate well the distance between wheelchair and obstacle. Later, the smart wheelchair needs to decide further action whether it should turn left, right or just walk straight when facing certain obstacle to avoid it.

The aim of this research is to design a smart medical device that is able to provide an initial diagnosis of lung condition based on body temperature and fingernail color. The presence of smart device is needed because the current lung examination is expensive and requires help from medical personnel. Due to the vital function of the lungs, it is necessary to check the lung condition which can be done independently, real-time and at an affordable cost. So if there is a problem in the lungs, it can be detected early and can be treated immediately before the disease becomes more serious. Based on the WHO, there are two lung diseases that cause millions of deaths, that is pneumonia and tuberculosis. The symptoms of both diseases can be known from the body temperature and fingernail color which indicates the oxygen levels in the blood. Temperature and color sensor was used to acquire data from these two parameters. Classification of lung condition based on the data from both sensors was designed using the Naïve Bayes method. There are three classification classes designed, healthy lung, pneumonia and TB. From the test result, the system provides an accuracy of 84.21% in classifying lung condition.

The arterial blood pressure (ABP) waveform contains essential information concerning the hemodynamic status and its relation to the diagnosis of cardiovascular conditions. Therefore, the continuous monitoring of the ABP waveform has become important. The arterial cannula, considered the gold standard for this monitoring, carries a risk of vascular trauma due to its invasive nature. Consequently, a measurement system that offers a non-invasive approach and maintains high accuracy in detecting morphological details of the ABP waveform is needed. In this study, we introduce a flexible piezoresistive yarn (FPY) pressure sensor for continuous non-invasive ABP waveform measurement. The sensor was experimentally validated using two scenarios: measurements on a hardware simulator and at a radial artery site. The simulator measurement aimed to assess the sensor’s performance in detecting consistent waveforms, while the radial artery site measurements evaluated the sensor’s performance in measuring ABP waveforms corresponding to the cardiovascular cycle. The simulator measurement results showed high repeatability, reproducibility, and accuracy relative to the reference signal at the upper limit of realistic force magnitude, as measured by the Pearson correlation coefficients: 0.9999 ± 0.0002 (10 measurements), 0.9994 ± 0.0002 (3 measurements), and 0.9731 ± 0.0027 (10 measurements), respectively. The correlation value derived from measurements at the radial artery site compared with measurements using a 3D force sensor as a reference sensor was 0.9880 ± 0.0035 (10 measurements from a single subject). Based on our results, the FPY pressure sensor can be used as an innovative solution for monitoring ABP waveforms and has further potential to be developed as a diagnostic device for evaluating cardiovascular conditions.

In Computer Vision, Shape Feature is one of the important features besides color and texture. A Geometric type of Shape Features uses parameters from the Region of Interest as the input such as Area, bounding rectangle's width and length, Axis Length, Centroid, and Perimeter. The Rectangularity, the Eccentricity, and the Elongation rely on the bounding rectangle which is invariant to rotation. The Circularity is invariant to rotation and scale but only captures the general information of the object's area. This research proposes a basic Shape Feature that is rotation and scale invariant. First, it finds the centroid of the Region of Interest using the Moment equation, then it finds the edges using the Sobel operator and calculates the distances between them. The distance uses Euclidian Distance that is invariant to rotation. The distance values are normalized using the Min-Max Normalization to maintain their value due to scale variations. Descriptive Statistics such as Mean, Median, Standard Deviation, Skewness, and Kurtosis are used as the parameter extracted from the normalized distances. The proposed shape feature is tested in common planar shapes with different sizes and rotations such as circle, oval, square, rectangle, triangle, and pentagon and it shows good grouping. The features can cluster the different shapes with a Silhouette Index of 0.578.