Jakub Tomczak

Articles

TITLE:Home Health Care Problem with Synchronization Visits and Considering Samples Transferring Time: A Case Study in Tehran, Iran
ABSTRACT: Healthcare facilities have not increased in response to the growing population. Therefore, government and health agencies are constantly seeking cost-effective alternatives so they can provide effective health care to their constituents. Around the world, healthcare organizations provide home health care (HHC) services to patients, especially the elderly, as an efficient alternative to hospital care. In addition, recent pandemics have demonstrated the importance of home health care as a means of preventing infection. This study is the first to simultaneously take into account nurses’ working preferences and skill levels. Since transferring samples from the patient’s home to the laboratory may affect the test results, this study takes into account the time it takes to transfer samples. In order to solve large instances, two metaheuristic algorithms are proposed: Genetic Algorithms and Particle Swarm Optimization. Nurses are assigned tasks according to their time windows and the tasks’ time windows in a three-stage scheduling procedure. Using a case study set in Tehran, Iran, the proposed model is demonstrated. Even in emergencies, models can generate effective strategies. There are significant implications for health service management and health policymakers in countries where home health care services are receiving more attention. Furthermore, they contribute to the growing body of knowledge regarding health system strategies by providing new theoretical and practical insights.
HIGHLIGHTS: [Image 1]

TITLE:Dynamic pricing with demand learning in the uncertain condition using reinforcement learning by considering the customer behavior
ABSTRACT: Dynamic pricing is one of the basic tools to increase revenue in companies. This moving pricing policy allows companies to earn higher revenue by optimally adjusting supply and demand and controlling the pattern of changing demand. One of the most prominent ways to create a strategy is through learning demand. Dynamic pricing through demand learning is the science of optimal pricing that is implemented in uncertain and random environments through collected data. This field of research consists of two branches: statistical learning and optimal pricing. In this research, using the Thomson sampling method and modeling is based on strategic and short-sighted customer behavior; we have tried to select the optimal price so that the seller’s expected income is maximized and compare the results in the presence of strategic and short-sighted customers. At the end of this study, we find that if the seller does the pricing with this approach and by changing his belief based on the observations received from the customer’s behavior, he will earn more income in the long run.
HIGHLIGHTS: [Image 1]

TITLE:Optimization of system costs and waiting time in the queue for donation and receipt Kidney with queuing system modeling approach
ABSTRACT: The use of queuing theory and supply chain systems has a particular place in optimizing the organ transplantation process and the member’s inventory literature as a perishable commodity. Nevertheless, a small volume of articles in this area reviews the policies of supplying members to link to the theory of queue approach, despite the increasing importance of this topic in the health sector[1]. In this paper, the principles of the quadratic theory have been used to optimize the control and vitamins of the donated and received members, and to increase the productivity of the supply chain of perishable goods (living organs) for organ transplantation. People who donate members are logged in as queue system customers based on the Poisson process. Hospitality rates are assumed to give us a queue for the queue. The members who at this stage play the role of the queuing system inputs with the model and group service, enter the with the appropriate vehicle to make the organ transplant there. In, the queuing model is of the type. The resulting work will ultimately be pursued with the goal of minimizing system costs by using a proper solution.
HIGHLIGHTS: [Image 1]

TITLE:Dynamic pricing for online retailers using sponsored search advertising and bundling by considering consumers behavior under inventory level
ABSTRACT: In addition to sponsored search advertising, some online retailers provide information about the stock availability on their websites to attract customers and increase their number of visitors. As people’s access to the internet has been increased, many users prefer to perform their daily tasks online. This encourages retailers to turn towards sponsored search adver- tising. On the other hand, presenting bundle offers is another way that retailers deploy to increase their selling level and sell out the excessive stock of a special product. A bundle offer is the bundle of two or more products provided for the customers such that the offered price is less than the sum of the individual prices of the products in the bundle. In this research, we have studied a customer who aims to sell out a perishable product during a limited period of time by bundling it with a second product priced independently. This retailer uses sponsored search advertising to attract customers to its website. It also shows the stock availability to impress the willingness to pay of the customers. In this research, we have developed a stochastic dynamic programming model to study the strategic decision making about dynamic discount pricing on the bundle as well as the bid to the search engine, which maximizes the revenue. Our results show that when the stock availability is high, or when we approach the end of selling season, the amount of discount on the bundle and bid to the search engine increases. Also, we have found out that discount and bid level increases as the variability and mean of customer’s reservation price declines.
HIGHLIGHTS: [Image 1]

TITLE:Automatic Identification of high-risk riders of shared bicycles using artificial intelligence in geospatial data
ABSTRACT: Due to bike-sharing regulations as well as the rules of insurance companies, users are not allowed to use bicycles on highways, tunnels, and bridges, so identifying those who violate these rules is of particular importance. In this study, we first attempt to identify high-risk users using the spatial join method and identify the effective factors to detect this abuse. Then, by classifying different machine learning methods, it is possible to classify high-risk users according to travel and user characteristics so as to deal with repeat offenders. Finally, after trying several methods based on the accuracy of the model, the best method is selected. The results show, that the best way to classify high-risk users is logistic regression and LDA, which gives us an accuracy of about 85%. Finally, we analyze the travel characteristics and personality of high-risk users and compare these results with those of ordinary users.
HIGHLIGHTS: [Image 1]

Conferences

TITLE:Neural network hyperparameter tuning with bayesian optimization and comparison of its results to traditional machine learning methods (A survey study)
ABSTRACT: Today we are witnessing an increase in the use of machine learning methods in various fields. To fit these methods with different problems, it is necessary to adjust the hyperparameters of each. Choosing the best combination of parameters for machine learning models has a direct impact on model performance. To set up these hyperparameters, in addition to having a deep knowledge of machine learning algorithms, we also need appropriate parameter optimization techniques. Although there are different techniques for optimizing hyperparameters, each has its strengths and weaknesses depending on the issues at hand. In this research, after examining the problem of optimization of hyperparameters, the classification of methods in the literature to solve this problem is presented and different methods are studied in detail. Also, in a separate section, the strengths and weaknesses of each of these methods along with the application of each are discussed. Finally, in a practical example, the Bayesian optimization method is used to adjust the neural network parameters and the results are compared with classical machine learning methods.
HIGHLIGHTS: [Image 1]

TITLE:Investigation of Economic and Social Factors Affecting Population Growth in Iran: An Econometric Approach
ABSTRACT: From the past, the simulation, prediction, and control of a country's population have been of great importance for much macro decision-making. The researchers have applied different methods for simulation and estimate of the growth. Many factors are affecting the population of a country. This article studied the birth and mortality rate in Iran using the multi-step regression method. In addition, various regression tests have been neglected on the model to achieve the best possible result and the least possible error. In the end, the best model with an accuracy of 98 will be proposed, indicating that increasing job opportunities and Declining housing prices have the most significant impact on population growth.
HIGHLIGHTS: [Image 1]

TITLE:Discrete Simulation of Hospital Patient Service System
ABSTRACT: Waiting for time and length of stay have been reported as a factor in decreasing hospital satisfaction, especially in developing countries. This paper describes a model of outpatient hospital workflow in a developing country and optimizes patient waiting time as well as total length of stay. Using discrete event simulation, many alternative scenarios, including adding more work time, changing staffing and staffing responsibilities, are tested to better understand hospital settings. The results show that it is possible to achieve a 9.9% reduction throughout the patient's stay and can be done without adding more resources to the hospital.
HIGHLIGHTS: [Image 1]

TITLE:Bitcoin world price forecasting with time series analysis and machine learning approach
ABSTRACT: The ever-growing attention to Cryptocurrencies highlights the demand for higher academic contributions to the subject. Bitcoin is a kind of Cryptocurrencies, which plays a special role in financial transactions today; hence, price prediction is of great importance. In recent years, a vast body of research has been devoted to bitcoin pricing models, but previous research suffers from high prediction errors due to the fluctuations in the price of bitcoin make room for more research. This research will use SARIMAX, as time series analysis model, XGBOOST, as a gradient method that accelerates model learning by parallelizing decision trees and long short-term memory Neural Network Model (LSTM) to predict Bitcoin price between Late 2012 to early 2021. We considered about two months as test data, which LSTM had the best prediction accuracy, R squared of 81.39 percent for test data.
HIGHLIGHTS: [Image 1]

TITLE:A dynamic model for investigating the role of smoking on the incidence of lung cancer with a social policy approach
ABSTRACT: Nowadays, lung cancer is the deadliest and the most common type of cancer regardless of the gender factor according to global statistics. This has led to the reality that the death rate from lung cancer has risen sharply in recent years. Cigarette smoking is one of the most important causes of lung cancer and the association between cigarettes and lung cancer has been proven by large cohort studies. In this paper, the system dynamics approach is used as the main methodology. We have created a system dynamic model to analyse the relationship between smoking and lung cancer and to study factors such as the rate of smoking, death rate because of lung cancer, lung cancer treatment and costs, the impact of investment and budget allocation in different sectors by government, social welfare level of individuals, etc. Furthermore based on the developed model, some policies suggested to decrease the costs of this problem in society. Proposed policies are based on the impact of several different scenarios, such as increasing the contribution and budget allocation for prevention and advertising to counteract cigarette smoking as well as rising cigarette prices. Based on the model these policies can yield good results in reducing death rates and other costs of this problem. According to the results, in the long run, with a 44 percent increase in the price of cigarettes as well as a 10 percent increase in the smoking prevention budget, the number of smokers will be reduced by 8 percent.
HIGHLIGHTS: [Image 1]

Publications

Articles

Conferences