Yönetim Bilişim Sistemleri Bölümü Koleksiyonu
Bu koleksiyon için kalıcı URI
Güncel Gönderiler
Öğe Analysis of a hypothetical humanitarian supply chain with agent-based simulation: The expected Istanbul earthquake(CRC Press, 2024) Usluer, Furkan Onur; Sezen, Hayrettin Kemal; Şeneras, Arzu ErenAll humanity has tragic memories and experiences of disasters. Disasters are low-probability events. In most cases, it is impossible to predict exactly when and where they will occur and what will be the devastating effects. However, many improvements can be made to reduce losses. According to estimates, as many as 2.5 million people may need emergency shelter after the expected Istanbul earthquake. The focus of this study is a hypothetical humanitarian supply chain to provide food and water to people in need of emergency shelters. An agent-based simulation (ABS) is created for the analysis. Software for the ABS model was developed with the Python programming language. Among agent-oriented software engineering methodologies, situational method engineering was chosen as a programming approach in the software development process. Agents of the model are smart objects that can have behavioral traits such as "parent", "mentally disabled", and "opportunist". The results indicate that panic among people can hinder the success rate of aid efforts, and relief operation plans that overlook individual differences are more likely to be unsuccessful.Öğe Development of a neural network algorithm for estimating the makespan in jobshop production scheduling(Strojarski Facultet, 2023) Yıldız, İncilay; Saygın, Abdülvahap; Çolak, Selçuk; Abut, FatihSince production scheduling is considered a short-term plan for future production planning, the advantages of effective scheduling and control and their contribution to the production process are numerous. Efficient use of resources improves productivity and ensures that customer orders are met on time. Even the simplest scheduling system has a complex solution structure. Long lead times also make it difficult to estimate the demand accurately. Therefore, it is important to solve scheduling problems effectively for such difficult-to-manage production processes. Job shop scheduling (JSS) problems are among the combinatorial problems in the NP-hard problems class. As constraints increase in such problems, the solution space starts to go to infinity, making it increasingly difficult to find the exact optimum solution. For this reason, metaheuristic algorithms have been used to solve such problems in recent years. This study aims to develop an artificial neural network (ANN)-based application to produce an optimal or near-optimal solution for JSS. Using the job shop type production data of Taillard comparison problems, the total processing time (i.e., makespan) has been calculated with the proposed ANN application. The results have been compared with the results of related studies in the literature, and the algorithm's efficiency has been evaluated in detail.Öğe Shortest route application via dynamic programming in the transportation networks(2021) Şahin, İnanç; Şenaras, Arzu Eren; Sezen, Hayrettin Kemal; Şenaras, Onur MesutThe purpose of this study is to develop an application for finding the shortest path in the transportation sector. The application was developed using the dynamic programming method in MS Excel Visual Basic application. These types of problems are also called stagecoach problems. The purpose of the problem is finding the shortest path between the starting point (node) and the destination point. Values are related to the roads in the network to specify the distance between two nodes. In case of a small number of nodes (activities), a solution can be reached by evaluating all options. But the number of possible options to be scanned for real problems is quite large. In such cases, a suitable method is needed for the solution. It can produce effective solutions with the dynamic programming approach.Öğe Price discrimination for Topkapı Palace Museum in Turkey: Vip or regular entrance(Pamukkale University Journal of Social Sciences Institute, 2021) Birişçi, EsmaMuseums, which are our cultural heritage, are a socio-cultural phenomenon but play an active role in terms of economy. The main issue for the operation of museums is the admission-entrance fee. In order to solve the admission-entrance fee problem, there are different ticket types. This study aims to develop a policy for museum’s revenue by setting different access fee values to the museum for only full fare. These access values can be classified into three groups depending on weather conditions; Regular, Exclusive and VIP. In order to attract more customers, museum operation is planning to give a souvenir as a gift to visitors during inclement weather time. This study considers how handing out the souvenir to visitors will affect the profit. Utilizing the optimal price of the Museum operation, yearly average extra revenue is calculated and compared with the other access policies that are applied. We illustrate our approach with an application to empirical data from Topkapı Palace Museum. Monthly data were considered from January 2010 to December 2012. As a result, to make profit of extra revenue of museum operation, regular access demand can be maximum 60% of total visitor and minimum fee of VIP and Exclusive accesses can be 400TL and 200TL.Öğe Türk işletme grubu iştirakleri üst yönetim ekibinde aile üyeleri varlığının işletme performansı üzerine etkileri(2019) Yalçın, Azmi; Aydemir, MuzafferÜlkemiz dâhil pek çok gelişmiş ve gelişmekte olan ülkelerde aile işletmeleri baskın konumdadırlar. Başlangıçta tamamen aile üyeleri tarafından yönetilen aile işletmeleri zamanla profesyonel yöneticiler tarafından yönetilmeye başlanmıştır. Üst yönetimi profesyonel yöneticilere bırakan aile üyeleri yönetim kurulunda yer almayı tercih etmektedirler. Üst yönetim ekiplerinde aile üyelerinin varlığının oluşturduğu heterojen ekiplerin performans üzerine etkileri tartışılan bir konudur. Araştırmamız İMKB kote 44 işletmenin üst yönetim ekiplerinde yapılmıştır. 371 üst yöneticide sadece 12’si aile üyesi olmasına rağmen varlıkları sermaye dönüşüm oranını olumlu yönde etkilemektedir. Ayrıca genç işletmelerin varlıklarının dönüşüm oranı yaşlı işletmelere göre daha yüksek olmaktadır.Öğe Lung cancer classification using data mining and supervised learning algorithms on multi-dimensional data set(International University of Sarajevo, 2019) Ahmed, Saadaldeen Rashid Ahmed; Al-Barazanchi, Israa; Mhana, Ammar; Abdulshaheed, Haider RasheedThese With recent developments in machine learning, data mining and computer vision, there is great potential for improvements in early detection of lung cancer using scans and data available. This paper details the methods and techniques used in our project, where the objective is to develop algorithms to determine whether a patient has or is likely to develop lung cancer using dataset images using data mining and machine learning for the classification and examination. We explore approaches to address the problem. Cancer is the most important cause of death globally. The disease diagnosis is a major process to treat the patients who are affected by cancer disease. The diagnosis process is more difficult comparatively known about the cancer disease detection. Developing a proposed data mining model is useful to diagnose the cancer disease once the cancer detection is accomplished using data mining for the examination and classification of machine learning supervised algorithms. © 2019 International University of Sarajevo.Öğe System dynamics modelling for policy design: A case study in Turkey(IGI Global, 2019) Şenaras, Arzu Eren; Sezen, Hayrettin KemalThe system dynamics model was developed in the Vensim software. The model was developed based on the Yamaguchi study. The construct and behavioral validity of the model were addressed. Construct validity means that the correlations that construct the model, that is, the "rationale" of the model, are consistent with the correlations in the real system. There were five sub-models in the model. These were manufacturers and consumers sub-model, banks sub-model, central bank submodel, balance of payments sub-model, exchange rate market sub-model. Five sub models included in the model developed with the VENSIM software are included in the appendices. © 2020, IGI Global. All rights reserved.Öğe A review on UWB antenna sensor for wireless body area networks(Institute of Electrical and Electronics Engineers Inc., 2020) Alani, Sameer; Zakaria, Zahriladha; Saiedi, Tale; Ahmad, Asmala; Mahmood, Sarmad Nozad; Saad, Mohammed Ayad; Albeyar, Ma'ath Abdulla A. Arabi; Hamdi , Mustafa MaadThe high demand use of Ultra-Wideband (UWB) in wireless body area network (WBAN) based medical applications opens a way for many types of research in the current decade. The continuous health monitoring of the patients during normal daily activities is the primary concentration of the WBAN system. Many studies and analyses are taken into and performance is evaluated. The major sections which are discussed in this paper are UWB technologies, on-off body communication; WBAN ideas are discussed to overcome several research drawbacks. © 2020 IEEE.Öğe Iris detection and recognition by image segmentation using K-means algorithm and artificial neural network(Institute of Electrical and Electronics Engineers Inc., 2020) Alabdullah, Firas Yaqoob Yousif; Ibrahim, Abdullahi AbduSegmentation is one of the most complex and time reliant steps in the Iris recognition process. Using the powerful and fast k-means algorithm alongside Neural Networks, this algorithm manages to isolate the Iris within the image of the eye, not only with high precision, but also with a great reduction in time and computational load our scheme is capable of deciding whether the extraction of characteristics after segmentation can be carried out. Thus, enhancing the IRIS recognition and can be extended to include other Biometrics © 2020 IEEE.Öğe Predicting breast cancer in fine needle aspiration images using machine learning(Institute of Electrical and Electronics Engineers Inc., 2020) Al-Sammarraie, Luay Hani Abbas; Ibrahim, Abdullahi AbduBreast cancer is the second leading cause of cancer death in women in the world. Statistics show that 1, 152, 161 new cases of breast cancer are found worldwide; and with 411, 093 deaths It has been shown that early diagnosis of breast cancer increases the probability of a complete recovery and reduces the mortality of patients suffering from this cancer [1] Cancer is the mutation of genes responsible for cell replication and the regulation of cell growth. These genes are found in the nucleus of cells and act as a control to turn different cells on or off so that old cells die while new ones take over. When a mutation occurs, these cells do not die and begin to divide uncontrollably, creating tumors in this work we have designed and implemented a system whose main purpose is to detect the existence of breast cancer lumps in fine needle aspiration images. We use a clustering and a feature extraction method such as CNN and then we use a classification method to detect the cancer. Early detection of breast cancer is essential to increase patient survival © 2020 IEEE.Öğe Detection of facial features using statistical machine learning(Institute of Electrical and Electronics Engineers Inc., 2020) Nassrullah, Melak Thamer Nassrullah; Abdu, AbdullahiClassification modules can be used in multiple and diverse applications. The general objective of this work is the classification of facial features using statistical learning algorithms, this means being able to detect and classify the largest possible number of features that can be found on a face using only examples of images of these, without using a priori no information of the given characteristics. In the present work, detectors and classifiers of the characteristics that are considered most significant were developed, Excellent results were reported in mouth detection, with detection rates greater than 99% and errors comparable to the error from manual mouth marking. The lens sorter also obtained excellent results, with detection rates of 95% for databases with controlled environments and of the order of 90% for databases with uncontrolled environments. Beard and mustache classifiers after using the mouth detector obtained very good results, with a detection rate of over 95% in databases with uncontrolled environments. © 2020 IEEE.Öğe Robot pathplanning by image segmentation using the fuzzy C-means algoritm and KNN algorithm(Institute of Electrical and Electronics Engineers Inc., 2020) Al-Khayyat, Abdulrahman Tareq Ali; Ibrahim, AbdullahiMobile robotics is a valuable tool for exploring environments inaccessible to humans due to their remoteness, cost or danger, and for performing unpleasant or laborious tasks. It is a relatively new field, until recently experimental, but it is already being applied to real problems with satisfactory results, 3D simulation plays a relevant role in both the design and control of mobile robots. It allows to reflect the situation of the real robot or simulate hypothetical scenarios. At the same time, it provides a graphical interface for robot control, in this paper, we present a scheme for guiding a robot into an uncharted area by using the fuzzy c-means segmentation algorithm and k-NN classification to classify the safe and unsafe areas, our method proves to be fast with satisfactory results in terms of both segmentation, classification, and correct path planning. © 2020 IEEE.Öğe Fingerprint recognition by using convoloutional neurla network and support vector machine classification(Institute of Electrical and Electronics Engineers Inc., 2020) Al-Saedi, Ali Abdulhasan Johni; Ibrahim, Abdullahi AbduBiometrics seeks to solve the problems of traditional verification methods by using certain physiological properties associated with an individual. Among all the biometric indicators, fingerprints have been shown to have good levels of reliability. The most widely used local representation is based on the details (minutiae) of the fingerprints. The pattern of the minutiae on a fingerprint forms a valid representation of the fingerprint. The minutiae that are most used for automatic recognition are branches and endings. However, given fingerprint acquisition techniques, it is common for endings and bifurcations to undergo deformations, which is why they are commonly referred to as minutiae. That is why in this document we will simply refer to these characteristics as minutiae. In this work we describe the results obtained using a methodology proposed for the recognition of minutiae using convolutional neural networks CNN, trained with different databases that contain fingerprints then we use the support vector machine classification to classify newly input images of fingerprints based on the features extracted by the CNN and matched with the dataset, our method proves to have better accuracy and lower MSE than the previous linear methods use for fingerprint recognition. © 2020 IEEE.Öğe Image processing encryption(IOP Publishing Ltd, 2020) Shabeeb, D.M.S.; Ahmed, S.R.A.; Ibrahim, Abdullahi AbduThe aim of this research paper is to develop a new approach of image processing encryption using machine learning techniques in python So that the human cannot understand the images because it is in encrypted form and can be securely transfer to its destination. We also used the computer-generated Holography (CGH) technique to encrypt and decrypt images. We first implement an existing algorithm and verify the claims of the authors. We then investigate higher dimensional Baker maps for image encryption. For this, we first propose a new interpretation for the Baker map in terms of a path function S. We then apply the higher dimensional maps for image encryption and experimentally conclude that 3D Baker map suffices for encryption. That is, there is no perceptible performance gained when using higher dimensional Baker maps. Next, in an attempt to use chaotic maps for the diffusion mechanism in the encryption scheme, we embed the diffusion process into the confusion process. For this, we first propose an alternative view of a 2D image as a 3D structure using the binary representation of the image intensity values. We extend this scheme from grayscale images to color images and show its immense value in color image encryption. Lastly, we propose a Baker map based on random walk of the image. Here, we employ sparse decomposition of images as a method of generating the random paths. Random walk-based Baker maps would be more difficult to break than traditional Baker maps because of the chaotic behavior in the walk itself. The significance of images and their sharing is increasing day by day. Their security is becoming an important issue while transferring over a public network. To protect images from hacker's secret sharing is one of the best techniques. The secret sharing is a way to share a secret with n participants and then setup is made for t or more number of participants who must contribute to revealing the secret. Here t < n is known as a threshold which must be achieved for secret reconstruction. © Published under licence by IOP Publishing Ltd.
