No abstract

This research aims to design medicine information based on the ontology scheme and to display the relationship between information through chatbot as search media. The diversity of information does not guarantee to gather a relevant search result with user’s needs. A conventional search engine would be substantially beneficial in information searching yet could not able to comprehend meaning of found information and its relationship with other information. However a machine could understand the relationship and the meaning of information through the implementation of semantic technology, which is ontology. Ontology is implemented to represent semantic metadata information. The information designed with the ontology model would be very assistive in searching for data which is relevant to users’ need. The result of implementing ontology as a knowledge base in this research able to display the information of a disease and its relationship with medicine used as the medication for such a particular disease. The evaluation of our system shows that 90% of queries from users generate a valid response from the chatbot. Therefore, this research could be used as a reference in search of medical information and describe its relationship with a particular disease or related to medicine.

An image resulting from a low-resolution (LR) camera on the mobile phone has lower quality than a high-resolution(HR) camera on a DSLR. Meanwhile, the HR camera is pricing if compared with the LR camera. How to achieve a single-image quality on LR camera likewise on HR camera becomes essential research in the past years. Addressing this issue can be done by upscaling a single LR image. Recently, the super-resolution generative adversarial network (SRGAN) model is one of the state-of-the-art super-resolution(SR)models employed on single-image SR. However, implementing a deep learning model like SRGAN on a mobile device is challenging in computation power and resources. This study aims to develop a smaller and lower resources model while preserving single-image SR quality on mobile devices. To meet these objectives, we convert, quantize, and compress the SRGAN model on Snapdragon Neural Processing Engine (SNPE) as an example. We then validate the SRGAN on the DIV2K dataset on which improves the model performances. Besides, we conduct experiments on GPU, DSP environment. The experimental result confirmed that SNPE-SRGAN capable of achieves not only HR images’ quality but also low latency by 0.06 second and smaller model by 1.7 Mb size running on DSP. Also, the SRGAN-DLC-Quantized running on GPU has a smaller size by 1.7 Mb and lower latency by 1.151 seconds compared with Non-quantized SRGAN-TensorFlow by 9.1 Mb and 1.608 seconds latency.

This paper presents the influence of distributed generation (DG) location and capacity for mitigating voltage sag caused by faults. The voltages sags are caused by the faults were simulated on the IEEE 13 bus system for single line to ground close to 650 and three-line phase faults at bus 646 using Alternative Transient Program (ATP) software. The voltages are monitored at every buss system. The DG is installed for one DG, two DG and three DG as the alternative. The DG locations are installed based on trial and error. DG total capacity is 2/3 load total installed in the system. As the alternative DGs installed viz. for one DG at Bus 611 with the capacity of 2.5 MVA; Two DGs at Bus 611 and Bus 680 with their respective capacities of 1.25 MVA; Three DGs are located at Bus 611, Bus 680 and Bus 633 with their respective capacities of 1 MVA. The results show that DG location placement in many locations gives the better results for mitigating voltage sags.

Principal component analysis is to analyze the observation data table into a new data table that has the same correlation. And the aim is to simplify the previously complex observation data so that it is easier to process or analyze. The dataset used is transaction data which is often used by the association method in sales analysis, where the data taken consists of 1397 types of products sold in 1200 transactions. In this data, there are products that have very small sales, which means that the percentage of these products has very little effect on the future process, namely sales analysis with the association method. Therefore the authors try to optimize the data to become ready to use data by reducing products that have a small percentage value that affects research for the dataset. And on this occasion the author uses the main component analysis method to reduce products or form products that can represent the entire dataset without reducing the quality of the data for analysis. From the results of research conducted on transaction data, there was a product decline of 65.21%, where the products totaling 1397 were reduced to 486 products that could represent without reducing their value.