Bernoulli Time Series Modelling with Application to Accommodation Tourism Demand

In this research, a new uncertainty method has been developed and applied to forecasting the hotel accommodation market. The simulation and training of Time Series data are from January 2001 to December 2018 in the Spanish case. The Log-log BeTSUF method estimated by GMM-HAC-Newey-West is considered as a contribution for measuring uncertainty vs. other prognostic models in the literature. The results of our model present better indicators of the RMSE and Ratio Theil’s for the predictive evaluation period of twelve months. Furthermore, the straightforward interpretation of the model and the high descriptive capacity of the model allow economic agents to make efficient decisions.

Predicting phosphorylation sites using machine learning by integrating the sequence, structure, and functional information of proteins

Background Post-translational modification (PTM) is a biological process that alters proteins and is therefore involved in the regulation of various cellular activities and pathogenesis. Protein phosphorylation is an essential process and one of the most-studied PTMs: it occurs when a phosphate group is added to serine (Ser, S), threonine (Thr, T), or tyrosine (Tyr, Y) residue. Dysregulation of protein phosphorylation can lead to various diseases—most commonly neurological disorders, Alzheimer’s disease, and Parkinson’s disease—thus necessitating the prediction of S/T/Y residues that can be phosphorylated in an uncharacterized amino acid sequence. Despite a surplus of sequencing data, current experimental methods of PTM prediction are time-consuming, costly, and error-prone, so a number of computational methods have been proposed to replace them. However, phosphorylation prediction remains limited, owing to substrate specificity, performance, and the diversity of its features. Methods In the present study we propose machine-learning-based predictors that use the physicochemical, sequence, structural, and functional information of proteins to classify S/T/Y phosphorylation sites. Rigorous feature selection, the minimum redundancy/maximum relevance approach, and the symmetrical uncertainty method were employed to extract the most informative features to train the models. Results The RF and SVM models generated using diverse feature types in the present study were highly accurate as is evident from good values for different statistical measures. Moreover, independent test sets and benchmark validations indicated that the proposed method clearly outperformed the existing methods, demonstrating its ability to accurately predict protein phosphorylation. Conclusions The results obtained in the present work indicate that the proposed computational methodology can be effectively used for predicting putative phosphorylation sites further facilitating discovery of various biological processes mechanisms.

Sistem Pakar Diagnosa Penyakit THT Menggunakan Metode Dempster Shafer

AbstrakBerbagai penyakit pada manusia dapat menimbulkan masalah serius jika tidak cepat ditangani, seperti halnya penyakit THT (Telinga, Hidung, dan Tenggorokan). Penderita penyakit THT di Indonesia cukup tinggi, karena masyarakat sering menganggap remeh penyakit THT dan kurangnya informasi mengenai penyakit tersebut. Perlu adanya sistem yang memberikan informasi mengenai gejala pada penyakit THT dan jenis penyakit apa saja yang diderita, serta solusi apa yang tepat untuk menangani penyakit THT. Subjek dalam penelitian ini adalah sistem pakar untuk mendiagnosa penyakit THT. Pada penelitian ini menggunakan dua metode, yaitu metode ketidakpastian menggunakan Dempster Shafer dan metode penelusuran yaitu Forward Chaining. Langkah pengembangan diawali dari pengumpulan data, lalu pembuatan Rule Based, mengimplementasikan metode, dan melakukan pengujian akurasi pakar. Hasil penelitan ini adalah sistem pakar mendiagnosa penyakit THT sebanyak 7 jenis penyakit dengan gejala sebanyak 24 jenis. Penelitian ini juga menggunakan metode Dempster Shafer untuk mendapatkan nilai kepastian berupa persentase nilai kepastian pada hasil diagnosa penyakitnya. Berdasarkan hasil pengujian pakar, dapat disimpulkan bahwa sistem pakar memiliki tingkat kesamaan dengan pakar sebesar 85% yang berarti bahwa sistem pakar ini layak untuk digunakan.AbstractVarious diseases in humans can cause serious problems if not quickly handled, such as ENT diseases (ear, nose, and throat). People with ENT disease in Indonesia is quite high, because people often consider the condition of ENT disease and lack of information about the disease. There is a system that provides information about the symptoms in ENT diseases and what types of diseases suffered, as well as what is the right solution to handle ENT diseases. The subject in this study is an expert system for diagnosing ENT diseases. The study used two methods, namely the uncertainty method using Putty Shafer and the search method that is Forward Chaining. The development step starts from collecting data, then creating a Rule Based, implementing methods, and conducting expert accuracy testing. The results of this research is a system of experts diagnose ENT diseases as many as 7 types of diseases with the symptoms as much as 24 types. This research also uses the method of putty Shafer to get certainty of the percentage value of certainty in the diagnosis of diseases. Based on expert testing results, it can be concluded that an expert system has a level of similarity with experts at 85% which means that the expert system is worthy of use.