Application of the Spatial Autoregressive (SAR) Method in Analyzing Poverty in Indonesia and the Self Organizing Map (SOM) Method in Grouping Provinces Based on Factors Affecting Poverty

The economy is a benchmark to determine the extent of the development of a country. Indonesia, which is now a developing country, is ranked 5th as the poorest country in Southeast Asia. Of course, the government must pay attention because until now, poverty has become one of Indonesia's main problems. Ending poverty everywhere and in all its forms is goal 01 of the Sustainable Development Goals (SDGs) program. One of the efforts that can be done is by planning as part of the implementation of the target, namely eliminating poverty and appropriate social protection for all levels of society so that the SDGs are achieved. Therefore, it is important to do a spatial analysis by making a model of poverty estimation in Indonesia and grouping to identify areas in Indonesia that have the highest poverty mission. The clustering method used in this grouping is Self Organizing Map (SOM). In this study, Spatial Autoregressive (SAR) analysis was used to create a predictive model. This is because poverty is very likely to have a spatial influence or be influenced by location to other areas in the vicinity. The results of the SAR model that can be formed are . Furthermore, the region with the highest mission is grouped using the Self Organizing Map (SOM) clustering based on variables that significantly affect the amount of poverty in Indonesia. From the results of the analysis obtained four clusters, each of which has its characteristics to classify 34 provinces in Indonesia. The clusters formed include cluster 1 consisting of 17 provinces, cluster 2 consisting of 9 provinces, cluster 3 consisting of 1 province, and cluster 4 consisting of 7 provinces.

Multivariate Analysis Applied to Aquifer Hydrogeochemical Evaluation: A Case Study in the Coastal Significant Subterranean Water Body between “Cecina River and San Vincenzo”, Tuscany (Italy)

The hydrogeochemical characteristics of the significant subterranean water body between “Cecina River and San Vincenzo” (Italy) was evaluated using multivariate statistical analysis methods, like principal component analysis and self-organizing maps (SOMs), with the objective to study the spatiotemporal relationships of the aquifer. The dataset used consisted of the chemical composition of groundwater samples collected between 2010 and 2018 at 16 wells distributed across the whole aquifer. For these wells, all major ions were determined. A self-organizing map of 4 × 8 was constructed to evaluate spatiotemporal changes in the water body. After SOM clustering, we obtained three clusters that successfully grouped all data with similar chemical characteristics. These clusters can be viewed to reflect the presence of three water types: (i) Cluster 1: low salinity/mixed waters; (ii) Cluster 2: high salinity waters; and (iii) Cluster 3: low salinity/fresh waters. Results showed that the major ions had the greater influence over the groundwater chemistry, and the difference in their concentrations allowed the definition of three clusters among the obtained SOM. Temporal changes in cluster assignment were only observed in two wells, located in areas more susceptible to changes in the water table levels, and therefore, hydrodynamic conditions. The result of the SOM clustering was also displayed using the classical hydrochemical approach of the Piper plot. It was observed that these changes were not as easily identified when the raw data were used. The spatial display of the clustering results, allowed the evaluation in a hydrogeological context in a quick and cost-effective way. Thus, our approach can be used to quickly analyze large datasets, suggest recharge areas, and recognize spatiotemporal patterns.

Implementasi Kombinasi Algoritme Self-Organizing Map dan Fuzzy C-Means untuk Pengelompokan Performa Belajar Siswa pada Media Pembelajaran Digital

<p>Media pembelajaran digital mampu menyimpan data dalam bentuk log data yang dapat digunakan untuk melihat perbedaan performa siswa yang tentu saja berbeda-beda antara satu siswa dengan siswa yang lainnya. Perbedaan performa siswa tersebut menyebabkan dibutuhkannya sebuah tahapan yang berfungsi untuk mempermudah proses evaluasi dengan cara menempatkan siswa kedalam kelompok yang sesuai agar dapat membantu tenaga pengajar dalam menangani serta memberikan umpan balik yang tepat pada siswanya. Penelitian ini bertujuan memanfaatkan log data dari sebuah media pembelajaran digital dengan menggunakan kombinasi dari algoritme S<em>elf-Organizing Map</em> dan <em>Fuzzy C-Means </em>untuk mengelompokan siswa berdasarkan aktivitas mereka selama belajar dengan media tersebut. Data akan melalui sebuah proses reduksi dimensi dengan menggunakan algoritme SOM, lalu dikelompokkan dengan menggunakan algoritme FCM. Selanjutnya, data dievaluasi dengan menggunakan nilai <em>silhouette coefficient </em>dan dibandingkan dengan algoritme SOM <em>clustering </em>konvensional. Berdasarkan hasil implementasi yang telah dilakukan menggunakan 12 data <em>assignment </em>pada media pembelajaran <em>Monsakun</em>, dihasilkan parameter-parameter optimal seperti ukuran <em>map </em>atau jumlah <em>output neuron </em>sejumlah 25x25 dengan nilai <em>learning rate </em>yang berbeda-beda disetiap <em>assignment</em>. Selain itu, diperoleh pula 2 kelompok siswa pada setiap <em>assignment </em>berdasarkan nilai <em>silhouette coefficient </em>tertinggi yang mencapai lebih dari 0.8 di beberapa <em>assignment</em>. Melalui serangkaian pengujian yang telah dilakukan, penerapan kombinasi algoritme SOM dan FCM secara signifikan menghasilkan <em>cluster </em>yang lebih baik dibandingkan dengan algoritme SOM <em>clustering </em>konvensional.</p><p> </p><p><strong><em>Abstract</em></strong></p><p> <em>Digital learning media is able to store data in the form of log data that can be used to see differences in student performance. The difference in student performance causes the need for a stage that functions to simplify the evaluation process by placing students into appropriate groups in order to assist the teaching staff in handling and providing appropriate feedback to students. This study aims to utilize log data from a digital learning media using a combination of the Self-Organizing Map algorithm and Fuzzy C-Means to classify students based on their activities while learning with these media. The data will go through a dimensional reduction process using the SOM algorithm, then grouped using the FCM algorithm. Furthermore, the data were evaluated using the silhouette coefficient value and compared with the conventional SOM clustering algorithm. Based on the results of the implementation that has been carried out using 12 data assignments on the Monsakun learning media, optimal parameters such as map size or the number of neuron outputs are 25x25 with different learning rate values in each assignment. In addition, 2 groups of students were obtained for each assignment based on the highest silhouette coefficient score which reached more than 0.8 in several assignments. Through a series of tests that have been carried out, the implementation of a combination of the SOM and FCM algorithms has significantly better clusters than the conventional SOM clustering algorithm.</em></p>

The Spread of the COVID-19 Outbreak in Brazil: An Overview by Kohonen Self-Organizing Map Networks

Background and objective: In the current pandemic scenario, data mining tools are fundamental to evaluate the measures adopted to contain the spread of COVID-19. In this study, unsupervised neural networks of the Self-Organizing Maps (SOM) type were used to assess the spatial and temporal spread of COVID-19 in Brazil, according to the number of cases and deaths in regions, states, and cities. Materials and methods: The SOM applied in this context does not evaluate which measures applied have helped contain the spread of the disease, but these datasets represent the repercussions of the country’s measures, which were implemented to contain the virus’ spread. Results: This approach demonstrated that the spread of the disease in Brazil does not have a standard behavior, changing according to the region, state, or city. The analyses showed that cities and states in the north and northeast regions of the country were the most affected by the disease, with the highest number of cases and deaths registered per 100,000 inhabitants. Conclusions: The SOM clustering was able to spatially group cities, states, and regions according to their coronavirus cases, with similar behavior. Thus, it is possible to benefit from the use of similar strategies to deal with the virus’ spread in these cities, states, and regions.

RNA-Seq identifies condition-specific biological signatures of ischemia-reperfusion injury in the human kidney

Background Acute kidney injury (AKI) is defined as a sudden event of kidney failure or kidney damage within a short period. Ischemia-reperfusion injury (IRI) is a critical factor associated with severe AKI and end-stage kidney disease (ESKD). However, the biological mechanisms underlying ischemia and reperfusion are incompletely understood, owing to the complexity of these pathophysiological processes. We aimed to investigate the key biological pathways individually affected by ischemia and reperfusion at the transcriptome level. Results We analyzed the steady-state gene expression pattern of human kidney tissues from normal (pre-ischemia), ischemia, and reperfusion conditions using RNA-sequencing. Conventional differential expression and self-organizing map (SOM) clustering analyses followed by pathway analysis were performed. Differential expression analysis revealed the metabolic pathways dysregulated in ischemia. Cellular assembly, development and migration, and immune response-related pathways were dysregulated in reperfusion. SOM clustering analysis highlighted the ischemia-mediated significant dysregulation in metabolism, apoptosis, and fibrosis-related pathways, while cell growth, migration, and immune response-related pathways were highly dysregulated by reperfusion after ischemia. The expression of pro-apoptotic genes and death receptors was downregulated during ischemia, indicating the existence of a protective mechanism against ischemic injury. Reperfusion induced alterations in the expression of the genes associated with immune response such as inflammasome and antigen representing genes. Further, the genes related to cell growth and migration, such as AKT, KRAS, and those related to Rho signaling, were downregulated, suggestive of injury responses during reperfusion. Semaphorin 4D and plexin B1 levels were also downregulated. Conclusions We show that specific biological pathways were distinctively involved in ischemia and reperfusion during IRI, indicating that condition-specific therapeutic strategies may be imperative to prevent severe kidney damage after IRI in the clinical setting.

Deep Learning Assisted Buildings Energy Consumption Profiling Using Smart Meter Data

The exponential growth in population and their overall reliance on the usage of electrical and electronic devices have increased the demand for energy production. It needs precise energy management systems that can forecast the usage of the consumers for future policymaking. Embedded smart sensors attached to electricity meters and home appliances enable power suppliers to effectively analyze the energy usage to generate and distribute electricity into residential areas based on their level of energy consumption. Therefore, this paper proposes a clustering-based analysis of energy consumption to categorize the consumers’ electricity usage into different levels. First, a deep autoencoder that transfers the low-dimensional energy consumption data to high-level representations was trained. Second, the high-level representations were fed into an adaptive self-organizing map (SOM) clustering algorithm. Afterward, the levels of electricity energy consumption were established by conducting the statistical analysis on the obtained clustered data. Finally, the results were visualized in graphs and calendar views, and the predicted levels of energy consumption were plotted over the city map, providing a compact overview to the providers for energy utilization analysis.