Banks Credit Risk Prediction with Optimized ANN Based on Improved Owl Search Algorithm

Credit is one of the most significant elements in banks and financial institutions. It can also be described as unpredicted events, which mainly occur in the form of either assets or liabilities. The risk occurrence is that the facility recipients have no willingness and ability to repay their debt to the bank, which is a default that is synonymous with credit risk. Credit ratings are a way to decrease and measure credit risk and, therefore, manage it appropriately. Credit rating is an approach for estimating the features and recipients of facilities’ performance based on quantitative criteria, including the company’s financial information. The anticipated future performance allows the applicants to obtain facilities with the exact specifications. In this study, due to the need and significance of calculating the credit risk concept, a novel method based on the hybrid method of artificial neural networks and an improved version of Owl search algorithm (IOSA) and forecasting of C5 risk of decision tree credit is done. This algorithm has two major parts. The decision tree runs based on an IOSA to provide the best weighting of the neural network. The weights created along with the problem data are then given as the input to the main network, and the data are classified. The algorithm has the highest level of accuracy, 96% that is much higher than other algorithms. The results also show a precision of 0.885 and a recall of 0.83 for 618 true positive samples. The proposed method has the highest accuracy and reliability toward the other comparative methods. The study is based on actual data noticed in one of the branches of the Bank Melli, Iran.

Designing and Implementing a Method of Data Augmentation Using Machine Learning

Efficiency of neural network (NN) models depend on the parameters given and the input data. Due to the complexity of environmental conditions and limitations the data for NN models, especially for the case of images, can be insufficient. To overcome this problem data augmentation has been used to enlarge the dataset. The task is to generate diverse set of images from a small set of images for NN training. Due to data augmentation transformation, 3105 new images out of 345 input data were created for classification, detection and image segmentation.

Dies Process Performance Improvement Maintenance With e-DMIS Based on Iot Technology

Improvement between departments within the company requires a mutually supportive system so that cooperation occurs between interrelated departments. This requires effort and commitment that needs to be supported by related share holders so that the occurrence of lost time during the production process can be minimized so that the planned time runs effectively and efficiently in increasing productivity. The difficulty in supervising and controlling the production process is the reason for knowing the abnormality in the process of replacing the dies and controlling the process of replacing printing equipment or dies for the Stamping process still using a manual system and the process recording system still using paper that is prone to loss and is engineered irresponsibly . The method used to create an electronic Dies replacement monitoring system by collecting problem data, comparing manual systems with several experiments and testing tools, using IoT in the form of PLC, HDMI as a tool for online communication. The DIMS monitoring system can be used to monitor and provide initial information when there is a request for the Dies replacement process so that replacement requests and needs in the process can be carried out immediately because they can be detected early.

Research Methodology for Selection of Optimum Plant Layout

This paper proposes an efficient and flexible research methodology for selection of plant layout for optimum utilization of resources and deal with future change. It consists of two steps, one for generating the layout alterative and other for selecting the optimum layout, generation of layout with the help of SLP (Systematic Layout Planning) and selection of optimum layout by using MCDM tools and technique by considering weight of each criteria. this research framework consists of define the problem, data collection, generation of alternative, selection of criteria & criteria score, MCDM tools & technique and selection & maintain. this methodology allows flexibility to be incorporated into the design of a new plant layout or provide improvement in exiting one.

Quantity of the inverse problem data for the system of conservation laws

In this paper we study properties of the model, that describes the plane acoustic waves propagation. The model is based on the hyperboliv system of PDE, which is solved numerically by using the finite-volume method, based on Godunov scheme. After studying the direct problem we turn to the inverse one, where our goal is to recover the parameters of the system of PDE by using the initial data, measured in the receivers. We obtain the formula for the gradient of the misfits functional, which allows us to apply gradient-based optimization for recovering the density of the medium. We present the results of numerical experiments for different number of receivers, thus, studying the influence of the quantity of the data of inverse problem on the accuracy of the solution.

Improving Care in Neonatal Intensive Units During the COVID-19 Pandemic: A Survey on Electronic Health Communication

Background A novel virus called severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) started spreading through Italy and the world from February 2020, and the pandemic threatened the family-centred care (FCC) model used in the neonatal intensive care unit (NICU). Teleconferences and video calls were employed to keep parents in contact with their babies. This study aimed to evaluate satisfaction and stress levels between parents in the telematic family-centred care group (T-FCC) versus the FCC group and the no Family-Centred Care (N-FCC) group. Methods A prospective cohort pilot study was carried out from April to May 2020. A parental stressor scale and the NICU satisfaction questionnaire were administered to parents at the time of discharge of their newborns. Parents in T-FCC group could see their newborns via video calls, while those in the FCC and N-FCC groups were extracted from our previously published database. Results Parents in the T-FCC group were more satisfied and less stressed than those in the N-FCC group. Experiences of the mothers and fathers in the T-FCC group were similar. However, the FCC group showed the best results. Conclusion The T-FCC group showed satisfaction with the quality of information received about their babies and felt that their privacy was considered and respected by the medical staff. Parents were also less stressed because they could monitor what happens to the baby through a video, however, they could not intervene if there was a problem. Data support the use of video calls to improve insight into clinical conditions and communication between doctors, nurses, and parents during the pandemic.

Father's Support and Mother's Behavior in Stunting Prevention Efforts

Stunting is the nutritional quality of infants under five years of age according to age compared to the usual benchmarks according to the World Health Organization's Multicentre Growth Reference Study in 2006. The incidence of stunting in infants under five years of age is a problem that exists in Indonesia and is a major nutritional problem. Data from the results of monitoring the quality of nutrition in the previous three years period has the highest prevalence compared to other nutritional problems such as malnutrition, thinness, and obesity. The purpose of this study was to analyze the correlation of the father's support and mother's behavior in Stunting Prevention Efforts in Tuntung 2 Village, Pancur Batu District, Deli Serdang Regency using a cross-sectional design. This study was done on 135 mothers who have infants aged 6-59 months as respondents. The variables in this study were father's support related to stunting prevention and the dependent variable in this study is the behavior of the mother in preventing stunting. The results showed that there was a significant correlation of the father's support and mothers’ behavior in preventing stunting (p <0.038). To increase efforts of prevent stunting, it is hoped that fathers who have not supported their wives should be more concerned about their toddler's growth and health.

Comparison of data augmentation methods for legal document classification

Sorting out the legal documents by their subject matter is an essential and time-consuming task due to the large amount of data. Many machine learning-based text categorization methods exist, which can resolve this problem. However, these algorithms can not perform well if they do not have enough training data for every category. Text augmentation can resolve this problem. Data augmentation is a widely used technique in machine learning applications, especially in computer vision. Textual data has different characteristics than images, so different solutions must be applied when the need for data augmentation arises. However, the type and different characteristics of the textual data or the task itself may reduce the number of methods that could be applied in a certain scenario. This paper focuses on text augmentation methods that could be applied to legal documents when classifying them into specific groups of subject matters.

Aplikasi Penerimaan dan Pengeluaran Kas (ARILUKAS) Menggunakan SDLC Waterfall

Educational institutions are one of the institutions that have a lot of financial transactions in their daily activities, for example new student registration fees, payment of school fees and even grants from the government. Assa'adatul Mahmudiyah, which is our research site, is one of the educational institutions that also has a lot of cash flow transactions. However, problems arise when these transactions are still recorded manually in books or simple spreadsheet files. These problems include rewriting when making reports, calculating and checking funds manually on cash balances and so on. Therefore, making a cash flow application is an alternative to this problem. Data was collected by observing the research site, reference the literature and conducting interviews with the cash manager. While the waterfall method the researchers took as a software development method. With this cash flow application, it can speed up users in making reports and reduce errors when recording cash in and cash out Index Terms— Cash flow application, Cash in and cash out, Waterfall