Turkish Journal of Forecasting最新文献_第2页

Topic Modelling and Artificial Intelligence Based Method Using Online Employee Assessments to Analyze Job Satisfaction 基于主题建模和人工智能的在线员工评估工作满意度分析方法

Turkish Journal of Forecasting Pub Date : 2022-10-12 DOI: 10.34110/forecasting.1173063

A. Özdemir, Aytuğ Onan, Vildan ÇINARLI ERGENE

引用次数: 0

YOLOv5-based Vehicle Objects Detection Using UAV Images 基于yolov5的无人机图像车辆目标检测

Turkish Journal of Forecasting Pub Date : 2022-08-25 DOI: 10.34110/forecasting.1145381

Zeynep Nur Duman, Müzeyyen Büşra Çulcu, Oğuzhan Katar

{"title":"YOLOv5-based Vehicle Objects Detection Using UAV Images","authors":"Zeynep Nur Duman, Müzeyyen Büşra Çulcu, Oğuzhan Katar","doi":"10.34110/forecasting.1145381","DOIUrl":"https://doi.org/10.34110/forecasting.1145381","url":null,"abstract":"Traffic is the situation and movement of pedestrians, animals, and vehicles on highways. The regulation of these movements and situations is also a basic problem of traffic engineering. It is necessary to collect data about traffic in order to produce suitable solutions to problems by traffic engineers. Traffic data can be collected with equipment such as cameras and sensors. However, these data need to be analyzed in order to transform them into meaningful information. For a difficult task such as calculating and optimizing traffic density, traffic engineers need information on the number of vehicles to be obtained from the image data they have collected. In this process, artificial intelligence-based computer systems can help researchers. This study proposes a deep learning-based system to detect vehicle objects using YOLOv5 model. A public dataset containing 15,474 high-resolution UAV images was used in the training of the model. Dataset samples were cropped to 640×640px sub-images, and sub-images that did not contain vehicle objects were filtered out. The filtered dataset samples were divided into 70% training, 20% validation, and 10% testing. The YOLOv5 model reached 99.66% precision, 99.44% recall, 99.66% mAP@0.5, and 89.35% mAP@0.5-0.95% during the training phase. When the determinations made by the model on the images reserved for the test phase are examined, it is seen that it has achieved quite successful results. By using the proposed approach in daily life, the detection of vehicle objects from high-resolution images can be automated with high success rates.","PeriodicalId":141932,"journal":{"name":"Turkish Journal of Forecasting","volume":"211 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133785332","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

Orientation Determination in IMU Sensor with Complementary Filter 互补滤波器在IMU传感器中的定位

Turkish Journal of Forecasting Pub Date : 2022-06-21 DOI: 10.34110/forecasting.1126184

M. Öz, Serkan Budak, Ender Kurnaz, Akif Durdu

{"title":"Orientation Determination in IMU Sensor with Complementary Filter","authors":"M. Öz, Serkan Budak, Ender Kurnaz, Akif Durdu","doi":"10.34110/forecasting.1126184","DOIUrl":"https://doi.org/10.34110/forecasting.1126184","url":null,"abstract":"The use of unmanned aerial vehicles (UAV) systems has increased in recent years. Therefore,studies on UAVs have increased today. In this direction, the production of UAV systems with domestic resources has gained importance. In this study, it is desired to develop a domestic and national flight control card and software. In the flight control board designed for the UAV, it is aimed to keep the vehicle in balance in the air. Accurate measurement of platform orientation plays an important role in many applications such as aerospace, robotics, navigation, marine, machine interaction [1]. Inertial Measurement Unit (IMU) sensor was used to accurately measure the orientation of the UAV. IMU sensor is widely used in UAVs due to its light weight and low energy consumption. In this direction, the need for a filter has emerged in the IMU sensor, which is used to accurately measure the orientation of the unmanned aerial vehicle. In this study, a complementary filter was applied on the IMU sensor. Thanks to this filter, it has been observed that the accuracy of the data received from the IMU sensor has increased. Based on the data obtained, a Proportional Integral Derivative (PID) algorithm was developed, and the vehicle was kept in balance. In this study, ARMCortex-M4 based STM32F407VG microcontroller and MPU6050 as IMU sensor were used. Keil-uVision5 compiler is preferred for software. As a result, high accuracy in the orientation detection of unmanned aerial vehicles was obtained by applying a complementary filter on the IMU sensor.","PeriodicalId":141932,"journal":{"name":"Turkish Journal of Forecasting","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131283393","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

Kalman Filter and PID Application on Underwater Vehicles 卡尔曼滤波与PID在水下航行器中的应用

Turkish Journal of Forecasting Pub Date : 2022-06-09 DOI: 10.34110/forecasting.1125559

Serkan Budak, Muhammet Tekin, Akif Durdu, Cemil Sungur

引用次数: 0

Enhancing the Yearly Profit of a Wind Farm Using a Novel Transfer Function for Binary Particle Swarm Optimization Algorithm 利用新型传递函数的二元粒子群优化算法提高风电场年收益

Turkish Journal of Forecasting Pub Date : 2022-04-22 DOI: 10.34110/forecasting.1104066

P. Bhattacharjee

引用次数: 0

Probabilistic Approach to the Future Course of Fiscal Stability in Turkey: 1958 – 2025 土耳其财政稳定未来进程的概率方法:1958 - 2025

Turkish Journal of Forecasting Pub Date : 2022-04-19 DOI: 10.34110/forecasting.1055932

Cansın Kemal Can

引用次数: 0

A mathematical analysis of the relationship between the vaccination rate and COVID-19 pandemic in Turkey 土耳其疫苗接种率与COVID-19大流行关系的数学分析

Turkish Journal of Forecasting Pub Date : 2022-03-30 DOI: 10.34110/forecasting.1077416

O. Dalkılıç, Naime Demirtaş

引用次数: 2

Estimating CO2 Emission Time Series with Support Vector, Artificial Neural Networks and Classic Time Series Analysis 基于支持向量、人工神经网络和经典时间序列分析的CO2排放时间序列估计

Turkish Journal of Forecasting Pub Date : 2021-12-28 DOI: 10.34110/forecasting.1035912

Fatih Cemrek, Özge Güneş

引用次数: 0

A Poisson-Regression, Support Vector Machine and Grey Prediction Based Combined Forecasting Model Proposal: A Case Study in Distribution Business 一种基于泊松回归、支持向量机和灰色预测的组合预测模型的提出:以分销业务为例

Turkish Journal of Forecasting Pub Date : 2021-09-06 DOI: 10.34110/forecasting.957494

F. Yiğit, Şakir Esnaf, Bahar Yalcin

引用次数: 0

Forecasting of Unemployment and Economic Growth for Turkey: ARIMA Model Application 土耳其失业与经济增长预测:ARIMA模型的应用

Turkish Journal of Forecasting Pub Date : 2021-06-07 DOI: 10.34110/forecasting.917300

Uğurcan Ayik, Gökhan Erkal

引用次数: 0