No abstract

The kidney is organ that plays an important role in the body’s metabolism, especially the process of filtration and reabsorption of food waste. Currently the determination of kidney parts through kidney histology is still done manually by experts based on experience and knowledge. Therefore, to make it easier to determine the parts of the kidney, a histological image segmentation of the kidney was carried out. In the segmentation process, it is necessary to extract the color features of the parts of the kidney, namely the glomerulus and proximal tubule. The color features used are Hue, saturation, value (HSV) color space. The hue means the representation of color type. The saturation defines the amount of white color is mixed with hue. The value in HSV color space denotes the intensity or lightness or brightness of the color. The method consists of three steps such as pre-processing step, extraction feature HSV and statistical analysis. The result of statistical analysis showed that the hue and value features, glomerulus and proximal tubule had different ranges of values. However, the features of saturation, glomerulus and proximal tubule is overlap.

Indonesia is a country with a very prominent marine charm, and it is the largest archipelago in the world, covering about 50% of the coral triangle area, providing marine tourist resorts. Therefore tourism development is quite promising. For that purpose, simple boats are of necessity for tourists to enjoy the beauty of such marine tourism. One solution to support such marine tourism sector is the availability of Autonomous Surface Vehicle (ASV). This vehicle will be the interest of this paper. This study used Touristant ASV with dimensions of 1.5 m in diameter, 4 meters in length and 1.3 meters in height. The purpose of this paper is to conduct a study with a focus on the estimation of ASV position with ASV motion influenced by wind speed and wave height by applying the H-infinity method. The position error generated from the simulation shows that the position error has an accuracy of about 96%.

Weather prediction expecially in predicting sunlight intensityhas important role in energy usage. As effort for controlling petrol-based fuel usage, government manage energy usage by converting solar energy from sunlight intensity to electric through solar cell.Sunlight intensity depends on air temperature and humidity. Two methods on prediction process will be applied : Neural Network (NN) and Adaptive Neuro Fuzzy Inference System (ANFIS). Type of NN used in prediction process is Backpropagation. Backpropagation consists of forward propagation, backward propagation, and update weight matrices. ANFIS uses hybrid method to train consequent parameters and premise parameters. In this research, NN will be compared with ANFIS. From five trials of NN simulations, the number of maximum epoch for making the root of mean square error(RMSE) in training data is very large so that the computation time is very long. From the comparison result of two methods, we can see that ANFIS can make faster prediction than NN with the number of maximum epoches is smaller than NN so that computation time is faster.

Currently a low cost security system is needed and easy to apply especially at educational institutions that willimplement smart school and industry 4.0. Needed devices are raspberry pi and web camera. Raspberry pi willonly save moving images taken from the web camera. Because by storing an image whose file size is not toolarge will ease the performance of the server. In this study, a design for the raspberry pi based motion detectionsystem will be applied at SMK PGRI Sukodadi Lamongan Regency which has not have security system. Thissystem will save the file in the form of an image that will be put together into a moving image that looks like avideo that will displayed in a LED monitor.Keywords: smart school, motion detection, moving image.