Sakarya University Journal of Computer and Information Sciences最新文献_第3页

Sector-Based Stock Price Prediction with Machine Learning Models 基于行业的股票价格预测与机器学习模型

Sakarya University Journal of Computer and Information Sciences Pub Date : 2022-11-30 DOI: 10.35377/saucis...1200151

Doğangün Kocaoğlu, Korhan Turgut, M. Z. Konyar

{"title":"Sector-Based Stock Price Prediction with Machine Learning Models","authors":"Doğangün Kocaoğlu, Korhan Turgut, M. Z. Konyar","doi":"10.35377/saucis...1200151","DOIUrl":"https://doi.org/10.35377/saucis...1200151","url":null,"abstract":"Stock price prediction is an important topic for investors and companies. The increasing effect of machine learning methods in every field also applies to stock forecasting. In this study, it is aimed to predict the future prices of the stocks of companies in different sectors traded on the Borsa Istanbul (BIST) 30 Index. For the study, the data of two companies selected as examples from each of the holding, white goods, petrochemical, iron and steel, transportation and communication sectors were analyzed. In the study, in addition to the share analysis of the sectors, the price prediction performances of the machine learning algorithm on a sectoral basis were examined. For these tests, XGBoost, Support Vector Machines (SVM), K-nearest neighbors (KNN) and Random Forest (RF) algorithms were used. The obtained results were analyzed with mean absolute error (MAE), mean absolute percent error (MAPE), mean squared error (MSE), and R2 correlation metrics. The best estimations on a sectoral basis were made for companies in the Iron and Steel and Petroleum field. One of the most important innovations in the study is the examination of the effect of current macro changes on the forecasting model. As an example, the effect of the changes in the Central Bank Governors, which took place three times in the 5-year period, on the forecast was investigated. The results showed that the unpredictable effects on the policies after the change of Governors also negatively affected the forecast performance","PeriodicalId":257636,"journal":{"name":"Sakarya University Journal of Computer and Information Sciences","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115121788","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Deep Transfer Learning-Based Comparative Study for Detection of Malaria Disease 基于深度迁移学习的疟疾疾病检测比较研究

Sakarya University Journal of Computer and Information Sciences Pub Date : 2022-11-30 DOI: 10.35377/saucis...1197119

Emel Soylu

{"title":"A Deep Transfer Learning-Based Comparative Study for Detection of Malaria Disease","authors":"Emel Soylu","doi":"10.35377/saucis...1197119","DOIUrl":"https://doi.org/10.35377/saucis...1197119","url":null,"abstract":"Malaria is a disease caused by a parasite. The parasite is transmitted to humans through the bite of infected mosquitoes. Thousands of people die every year due to malaria. When this disease is diagnosed early, it can be fully treated with medication. Diagnosis of malaria can be made according to the presence of parasites in the blood taken from the patient. In this study, malaria detection and diagnosis study were performed using The Malaria dataset containing a total of 27,558 cell images with samples of equally parasitized and uninfected cells from thin blood smear slide images of segmented cells. It is possible to detect malaria from microscopic blood smear images via modern deep learning techniques. In this study, 5 of the popular convolutional neural network architectures for malaria detection from cell images were retrained to find the best combination of architecture and learning algorithm. AlexNet, GoogLeNet, ResNet-50, MobileNet-v2, VGG-16 architectures from pre-trained networks were used, their hyperparameters were adjusted and their performances were compared. In this study, a maximum 96.53% accuracy rate was achieved with MobileNet-v2 architecture using the adam learning algorithm","PeriodicalId":257636,"journal":{"name":"Sakarya University Journal of Computer and Information Sciences","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130565519","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Simulation of Cargo Unloading Problem: A Case study on estimating the optimal number of trucks and cranes 货物卸载问题的仿真:以汽车和起重机最优数量估算为例

Sakarya University Journal of Computer and Information Sciences Pub Date : 2022-11-22 DOI: 10.35377/saucis...1173791

A. Zengin, Waseem Hamdoon

引用次数: 0

Pseudo-Supervised Defect Detection Using Robust Deep Convolutional Autoencoders 基于鲁棒深度卷积自编码器的伪监督缺陷检测

Sakarya University Journal of Computer and Information Sciences Pub Date : 2022-11-22 DOI: 10.35377/saucis...1196381

Mahmut Nedim Alpdemi̇r

{"title":"Pseudo-Supervised Defect Detection Using Robust Deep Convolutional Autoencoders","authors":"Mahmut Nedim Alpdemi̇r","doi":"10.35377/saucis...1196381","DOIUrl":"https://doi.org/10.35377/saucis...1196381","url":null,"abstract":"Robust Autoencoders separate the input image into a Signal(L) and a Noise(S) part which, intuitively speaking, roughly corresponds to a more stable background scene (L) and an undesired anomaly (or defect) (S). This property of the method provides a convenient theoretical basis for divorcing intermittent anomalies that happen to clutter a relatively consistent background image. In this paper, we illustrate the use of Robust Deep Convolutional Autoencoders (RDCAE) for defect detection, via a pseudo-supervised training process. Our method introduces synthetic simulated defects (or structured noise) to the training process, that alleviates the scarcity of true (real-life) anomalous samples. As such, we offer a pseudo-supervised training process to devise a well-defined mechanism for deciding that the defect-normal discrimination capability of the autoencoders has reached to an acceptable point at training time. The experiment results illustrate that pseudo supervised Robust Deep Convolutional Autoencoders are very effective in identifying surface defects in an efficient way, compared to state of the art anomaly detection methods.","PeriodicalId":257636,"journal":{"name":"Sakarya University Journal of Computer and Information Sciences","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116817552","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Using Multi-Label Classification Methods to Analyze Complaints Against Cargo Services During the COVID-19 Outbreak: Comparing Survey-Based and Word-Based Labeling 基于多标签分类方法的新冠肺炎疫情期间货物服务投诉分析——基于调查和基于文字标注的比较

Sakarya University Journal of Computer and Information Sciences Pub Date : 2022-11-21 DOI: 10.35377/saucis...1121830

Tolga Kuyucuk, Levent Çallı

引用次数: 2

Software Development for the Use of Generalized Parabolic Blending in Data Prediction Processes 数据预测过程中使用广义抛物混合的软件开发

Sakarya University Journal of Computer and Information Sciences Pub Date : 2022-11-18 DOI: 10.35377/saucis...1122506

Hakan Üstünel

引用次数: 0

Process Mining in Manufacturing: A Literature Review 制造业过程挖掘:文献综述

Sakarya University Journal of Computer and Information Sciences Pub Date : 2022-11-17 DOI: 10.35377/saucis...1134293

Yuksel Yurtay

{"title":"Process Mining in Manufacturing: A Literature Review","authors":"Yuksel Yurtay","doi":"10.35377/saucis...1134293","DOIUrl":"https://doi.org/10.35377/saucis...1134293","url":null,"abstract":"Process mining in manufacturing is a newly expanding field of research in the application of data mining and machine learning techniques and the focus of business processes. Although it is an exciting subject of the recent past and business processes, sufficient research has not been done. Decision support systems such as enterprise resource planning, customer relationship management, and management information systems store the most valuable resource data of process details and event logs. In the advanced information systems of tomorrow, the process management, analysis, and modelling functions of modern enterprises will take their place as a necessity. As a requirement, the fundamental purpose of process mining in production is to refine data from event logs, automatically create process models, compare models with event logs, and improve and make development continuous. Our work is to contribute to application and research studies by drawing attention to process mining in the context of production. It is based on the literature review and primary stages of business process mining publications in the last decade with a production focus. An overview is discussed as a roadmap for future research with meaningful results.","PeriodicalId":257636,"journal":{"name":"Sakarya University Journal of Computer and Information Sciences","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128210443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

The Effect of Numerical Mapping Techniques on Performance in Genomic Research 数字制图技术对基因组研究绩效的影响

Sakarya University Journal of Computer and Information Sciences Pub Date : 2022-11-01 DOI: 10.35377/saucis...1191850

Seda Nur Gülocak, Bihter Das

引用次数: 0

FA-AODV: Flooding Attacks Detection Based Ad Hoc On-Demand Distance Vector Routing Protocol for VANET FA-AODV:基于泛洪攻击检测的VANET自组织按需距离矢量路由协议

Sakarya University Journal of Computer and Information Sciences Pub Date : 2022-10-24 DOI: 10.35377/saucis...1175613

B. A. Tosunoglu, C. Koçak

引用次数: 1

A Review of Recent Developments on Secure Authentication Using RF Fingerprints Techniques 射频指纹技术安全认证研究进展综述

Sakarya University Journal of Computer and Information Sciences Pub Date : 2022-10-11 DOI: 10.35377/saucis...1084024

Huseyin Parmaksiz, C. Karakuzu

{"title":"A Review of Recent Developments on Secure Authentication Using RF Fingerprints Techniques","authors":"Huseyin Parmaksiz, C. Karakuzu","doi":"10.35377/saucis...1084024","DOIUrl":"https://doi.org/10.35377/saucis...1084024","url":null,"abstract":"The Internet of Things (IoT) concept is widely used today. As IoT becomes more widely adopted, the number of devices communicating wirelessly (using various communication standards) grows. Due to resource constraints, customized security measures are not possible on IoT devices. As a result, security is becoming increasingly important in IoT. It is proposed in this study to use the physical layer properties of wireless signals as an effective method of increasing IoT security. According to the literature, radio frequency (RF) fingerprinting (RFF) techniques are used as an additional layer of security for wireless devices. To prevent spoofing or spoofing attacks, unique fingerprints appear to be used to identify wireless devices for security purposes (due to manufacturing defects in the devices' analog components). To overcome the difficulties in RFF, different parts of the transmitted signals (transient/preamble/steady-state) are used. \u0000This review provides an overview of the most recent RFF technique developments. It discusses various solution methods as well as the challenges that researchers face when developing effective RFFs. It takes a step towards the discovery of the wireless world in this context by drawing attention to the existence of software-defined radios (SDR) for signal capture. It also demonstrates how and what features can be extracted from captured RF signals from various wireless communication devices. All of these approaches' methodologies, classification algorithms, and feature classification are explained. \u0000In addition, this study discusses how deep learning, neural networks, and machine learning algorithms, in addition to traditional classifiers, can be used. Furthermore, the review gives researchers easy access to sample datasets in this field.","PeriodicalId":257636,"journal":{"name":"Sakarya University Journal of Computer and Information Sciences","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130785361","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2