Person: BİLGİN, METİN
Loading...
Email Address
Birth Date
Research Projects
Organizational Units
Job Title
Last Name
BİLGİN
First Name
METİN
Name
5 results
Search Results
Now showing 1 - 5 of 5
Publication Novel random models of entity mobility models and performance analysis of random entity mobility models(Tubitak Scientific & Technological Research Council Turkey, 2020-01-01) Bilgin, Metin; Bilgin, Metin; BİLGİN, METİN; Bursa Uludağ Üniversitesi/Mühendislik Fakültesi/Bilgisayar Mühendisliği Bölümü.; AAH-2049-2021It has become possible to collect data from geographically large areas with smart devices that are prevalently used today. Sensors that are integrated into smart devices make it possible for these devices to receive and transmit data wirelessly. The most important problem of this model that is known as mobile crowd sensing and that allows inferences on the data obtained from its users is lack of data. The main reason for this problem is the lack of sufficient usage of the sensors on devices by the user. To increase the amount of data collected, while users may be incentivized in various ways, the amount and accuracy of the collected data may be increased by developing random entity mobility models (REMMs). In this study, two new models (random point and random journey) were proposed as alternatives to existing REMMs. In the experiment environment that was created to measure the performances of the proposed models, their performances were compared to those that are currently used prevalently (random waypoint (RWP), random walk (RW), and random direction (RD)). In the experiment environment, the performances were compared in terms of three different metrics (visiting rates of nodes, rates of reaching the basis, and the number of messages they carried to the basis). The greatest increase in differently sized areas and at different numbers of nodes in the RP model in terms of rates of reaching the basis was 2.6% compared to RWP, 7% compared to RW, and 46.34% compared to RD, while these values for the number of nodes that were visited were 3% compared to RWP, 1.5% compared to RW, and 17.67% compared to RD. In the same conditions in terms of the metric on the number of messages, the model collected 1465.4, 2933.46, and 7260.12 more messages than those in respectively RWP, RW, and RD. The greatest increase in differently sized areas and at different numbers of nodes in the RJ model in terms of reaching the basis was 1% compared to RWP, 3.5% compared to RW, and 25% compared to RD, while these values for the number of nodes that were visited were 0.75% compared to RWP, 2% compared to RW, and 21.4% compared to RD. In the same conditions in terms of the metric on the number of messages, the model collected 1109.56, 1534.26, and 4488.5 more messages than those in RWP, RW, and RD, respectively.Publication A new approach to automatically find and fix erroneous labels in dependency parsing treebanks(Zarka Private Univ, 2021-05-01) Bilgin, Metin; BİLGİN, METİN; Bursa Uludağ Üniversitesi/Mühendislik Fakültesi/Bilgisayar Mühendisliği Bölümü; AAH-2049-2021Dependency Parsing (DP) is the existence of sub-term/upper-term relations between the words that make up that sentence for each sentence in the text. DP serves to produce meaningful information for high-level applications. Correct labeling of the text corpus used in DP studies is very important. There will be mistakes in the results of the studies that will be performed with the wrongly-labeled text corpus. If text corpus is labeled manually or automatically by human beings, then faulty cases will occur. As a result of the cases that may arise from human factors or annotations used for labeling, faulty labels will be on freebanks. In order to prevent these errors, detection, and correction of possible faulty labeling is very important in terms of increasing the accuracy of the studies to be carried out. Manual correction of possible faulty labels requires great effort and time. The purpose of this study is to create a model that automatically finds possible faulty labels and offers new label suggestions for faulty labels. With the help of the proposed model, it is aimed to detect and correct possible faulty labels that are included in a text corpus, and to increase consistency among the text corpus of the same language. With the help of the developed model, suggesting new labels for faulty labels by a language expert will be a great convenient for the specialist. Another advantage of the model is that the developed model provides a language-independent structure. It has succeeded in obtaining successful results in finding and correcting potentially faulty labels in experimental studies for Turkish. An increase in accuracy has been detected in studies carried out for languages other than Turkish. In investigating the accuracy of the results obtained by the system, the results were analyzed with the help of 10 different language experts.Publication Research on modeling the thixotropic properties of cementitious systems using regression methods in machine learning(Elsevier Sci Ltd, 2023-12-28) Şahin, Hatice Gizem; Altun, Öznur Biricik; Eser, Murat; Bilgin, Metin; BİLGİN, METİN; Mardani, Ali; MARDANİ, ALİ; Bursa Uludağ Üniversitesi/Mühendislik Fakültesi/İnşaat Mühendisliği Bölümü.; Bursa Uludağ Üniversitesi/Mühendislik Fakültesi/Bilgisayar Mühendisliği Bölümü.; 0000-0002-8915-879X; 0000-0003-0326-5015; C-7860-2015; AAL-2592-2020; JPK-8822-2023; IAQ-9713-2023; AAE-2420-2022; KUD-7264-2024In this study, the rheological properties of cementitious systems were investigated through modeling studies on structural build-up and breakdown area. The area values were calculated using Herschel Bulkley analysis and hysteresis area method. The properties were examined by varying the composition of the cementitious system (cement fineness, C4AF, C3S, C2S, C3A, equivalent alkali and metakaolin ratio) and changes made in the rheological measurement processes (applied shear rate, maximum shear rate and duration). For this purpose, cement paste mixtures were prepared by substituting metakaolin at four different ratios (3%, 6%, 9%, and 12%) into cements with varying C3A content (2.13, 3.60, 6.82, 9.05%). The modeling study of the obtained results was conducted using three different learning methods: Linear Regression Analysis (LR), AdaBoost, and K Nearest Neighbor (KNN), encompassing machine learning and ensemble learning techniques. It was determined that the most dominant parameter affecting the rheology and thixotropic properties of the mixtures is the metakaolin usage ratio. The pre-shear rate was dominant over the duration and maximum shear rate parameters. Effect of the C3A content on dynamic yield stress and viscosity becomes more pronounced with an increase in the applied shear rate. The KNN method has yielded the best results in all experimental modeling studies. Euclidean distance criterion was used in the KNN method. Although the AdaBoost method obtained results close to the KNN method, the opposite situation was observed depending on the number of data. Logcosh, MAE and RMSE metrics were used to evaluate the experimental results. When the results for 3 different metrics in all modeling studies were examined, the success order of the metrics was found to be Logcosh, MAE and RMSE.Publication Classification of Turkish tweets by document vectors and investigation of the effects of parameter changes on classification success(Yıldız Teknik Üniversitesi, 2020-06-13) Bilgin, Metin; BİLGİN, METİN; Bursa Uludağ Üniversitesi/Mühendislik Fakültesi/Bilgisayar Mühendisliği Bölümü.; 0000-0002-4216-0542; AAH-2049-2021Natural language processing is an artificial intelligence field which is gaining in popularity in recent years. To make an emotional deduction from texts related to an issue, or classify documents are of great importance considering the increasing data size in today's world. Understanding and interpreting written texts is a feature that pertains to people. But, it is possible to deduce from texts or classify texts using natural language processing which is a sub-branch of machine learning and artificial intelligence. In this study, both text classification was made on Turkish tweets, and text classification success of method parameter changes was investigated using two different methods of the algorithm mentioned as document vectors in the literature. It was found in the study that as well as higher accuracy values were obtained by the DBoW (Distributed Bag of Words) method than DM (Distributed Memory) method; higher accuracy values were also obtained by DBoW-NS (Negative Sampling) architecture than others.Publication Research on behavior of two new random entity mobility models in 3-D space(Springer, 2021-06-02) Bilgin, Metin; Eser, Murat; BİLGİN, METİN; Bursa Uludağ Üniversitesi; AAH-2049-2021Mobile data collectors that can be used without a central control mechanism currently have common use in many fields. Because they do not need a central unit, each node in a network can move independently. The field literature offers various group- or entity-based models to define the functioning of mobile data collectors. In this study, a random entity mobility model (REMM) research was performed. The study was based on the models random walk (RW) and random waypoint (RWP), used in several former studies mentioned in the literature. Furthermore, the models random point (RP) and random journey (RJ) proposed by Bilgin [1] for two-dimensional (2D) space were transferred to three-dimensional (3D-cubic) to be used in the study. Study findings obtained by defining a various number of fixed nodes in areas of various sizes were analyzed using 4 different metrics. It was observed that 4 different metric values decreased for 4 REMMs when the cubic area was enlarged by increasing the edge lengths (150-200-250 pixel) of the cubic. When the cubic's edge length is 150-200-250 pixel, respectively, connected node ratio (CNR) metric value is 98.04%-95.8%-91.34% for RP and 96.83%-83.23%-70% for RJ. Provided that the cubic area remains constant, the increases in the number of nodes generally tend to increase, although there are slight fluctuations on the results. When the cubic edge is 200 and the node numbers are 4-64-10, the message delay is 13.345-16.566-27.386-40.050 seconds for RW and 6.579-9.124-11.431-13.456 seconds for RWP. In the comparisons made by taking the average of the values obtained according to the size of the cubic area and the number of nodes, the RP model reached the highest values for all metrics. For example, the visited node ratio (VNR) metric average for the cubic edge 200 pixels is 98.76% for RP and 94.68%-87.38%-94.78% for RW-RWP-RJ. The VNR metric for the cubic edge 250 is 96.55%-93.7%-87.45%-51.27% for the RP-RW-RWP-RJ. Similarly, the average values obtained for other metrics prove this situation. In addition, when the results of the study are examined, it has been measured that the RP model can deliver the message to the base with less delay than other models. The average delay for the cubic edge 150 is 2.933-27.667-23.236-5.698 second for the RP-RW-RWP-RJ and 2.846-24.337-10.148-4.293 second when the edge is 200. When the average results obtained were examined, the success ranking in the delay metric was RP-RJ-RWP and RW, while the other metrics were formed as RP-RJ-RW-RWP. Considering all the obtained results, it was seen that the proposed two models achieved better results than the existing models in 3D after 2D.