Medicinal plants (herbs) are plants that are known to have certain compounds which are nutritious for health. In Indonesia there are 30,000 types of plants and 7000 of them are classified as medicinal plants (herbs). The human body is complex and organic, while chemical medicines contain chemicals that are inorganic and pure. Therefore, chemical medicine are considered not very suitable for consumption by the human body, which if consumed continuously can even be bad for human health. However, some chemical drugs are actually symptomatic (temporary) so they must be taken for life by patients with certain diseases. Therefore a system is needed to be able to help the community to recognize medicinal plants better, in this case the medicinal plants are focused on the introduction of medicinal leaves. In this study identification of medicinal plant leaves was carried out using the Convolutional Neural Network method. This research will build a system of identification of medicinal plant leaves by using Convolutional Neural Networks. Using training data that is carried out in a computer set and then implemented in mobile-based software to recognize the types and benefits of medicinal plant leaves identified.

Coronavirus Disease 2019 (COVID-19) spread quickly and reached epidemic levels worldwide. West Java is Indonesia’s most populous province and has a high susceptibility to the transmission of the disease, resulting in a significant number of COVID-19 cases. Therefore, this research aimed to determine the influencing factors as well as the spatial and temporal distribution of COVID-19 in West Java. Data on COVID-19 cases in West Java obtained from PIKOBAR were used. Spatial distribution was described using a choropleth, while the influencing factors were evaluated with regression analysis. To determine whether COVID-19s policies and events affected its temporal distribution, the cases detected were graphed daily or biweekly with information on those two variables. Furthermore, the cumulative incidence was described in the linear regression analysis model as being significantly influenced by vaccinations and greatly elevated by population density. The biweekly chart had a random pattern with sharp decreases or spikes in cumulative incidence changes. Spatial and temporal analysis helps greatly in understanding distribution patterns and their influencing factors, specifically at the beginning of the pandemic. Plans and strategies for control and assessment programs may be supported by this study material.

Paraphrase extraction is the method of collecting words, phrases or sentences that have same meaning from free text or structured documents. Candidate monolingual parallel corpus was build from scientific papers by clustering techniques. The corpus contain couples of citation sentences that mention same index. The corpus evaluated using weighting techniques and proximity measurements based on the density of each sentence cluster. The results of this research are expected to simplify paraphrase labeling by language and computer science experts.

The paraphrase generator for citation sentences is used to produce several sentence alternatives to avoid plagiarism. Furthermore, the generation results need to pay attention to semantic similarity and lexical divergence standards. This study proposed the StoPGEN model as an algorithm for generating citation paraphrase sentences with stochastic output. The generation process is guided by an objective function using a simulated annealing algorithm to maintain the properties of semantic similarity and lexical divergence. The objective function is created by combining the two factors that maintain these properties. This study combined METEOR and PINC Scores in a linear weighting function that can be adjusted for its value tendency in one of the matrix functions. The dataset of citation sentences that had been labeled with paraphrases was used to test StoPGEN and other models for comparison. The StoPGEN model, with the citation sentences dataset, produced a BLEU score of 55.37, outperforming the bidirectional LSTM method with a value of 28.93. StoPGEN was also tested using Quora data by changing the language source in the architecture section resulting in a BLEU score of 22.37, outperforming UPSA 18.21. In addition, the qualitative evaluation results of the citation sentence generation based on respondents obtained an acceptance value of 50.80.

Recording tax payments is the government’s responsibility. Is urgent to have a sophisticated system that records tax payments. In Indonesia, property taxes are divided on land and buildings. With this form of data, the most appropriate solution for recording the tax is with a geographic information system that is able to describe areas, points, and roads that serve as a reference for tax payments. The government of Cimahi City already has a tax recording system, but the system is independent and separate from the tax map. This research works on integrating these two parts and making it web-based service architecture.