DSpace@ATÜ (Adana Alparslan Türkeş Bilim ve Teknoloji Universiti)
Not a member yet
3463 research outputs found
Sort by
Multivariable Air-Quality Prediction and Modelling via Hybrid Machine Learning: A Case Study for Craiova, Romania
No full textInadequate air quality has adverse impacts on human well-being and contributes to the progression of climate change, leading to fluctuations in temperature. Therefore, gaining a localized comprehension of the interplay between climate variations and air pollution holds great significance in alleviating the health repercussions of air pollution. This study uses a holistic approach to make air quality predictions and multivariate modelling. It investigates the associations between meteorological factors, encompassing temperature, relative humidity, air pressure, and three particulate matter concentrations (PM10, PM2.5, and PM1), and the correlation between PM concentrations and noise levels, volatile organic compounds, and carbon dioxide emissions. Five hybrid machine learning models were employed to predict PM concentrations and then the Air Quality Index (AQI). Twelve PM sensors evenly distributed in Craiova City, Romania, provided the dataset for five months (22 September 2021-17 February 2022). The sensors transmitted data each minute. The prediction accuracy of the models was evaluated and the results revealed that, in general, the coefficient of determination (R2) values exceeded 0.96 (interval of confidence is 0.95) and, in most instances, approached 0.99. Relative humidity emerged as the least influential variable on PM concentrations, while the most accurate predictions were achieved by combining pressure with temperature. PM10 (less than 10 mu m in diameter) concentrations exhibited a notable correlation with PM2.5 (less than 2.5 mu m in diameter) concentrations and a moderate correlation with PM1 (less than 1 mu m in diameter). Nevertheless, other findings indicated that PM concentrations were not strongly related to NOISE, CO2, and VOC, and these last variables should be combined with another meteorological variable to enhance the prediction accuracy. Ultimately, this study established novel relationships for predicting PM concentrations and AQI based on the most effective combinations of predictor variables identified
Balıkesir Balya Pb-Zn cevherinden hidrometalurjik yöntemlerle Zn kazanımının araştırılması
No full textIn this study, the recovery of Zn from Bal & imath;kesir-Balya Pb-Zn ores by acid leaching method was investigated. H2SO4, HCl and HNO3 were used as solvent reagents in leaching processes. According to the results obtained, optimum conditions were defined for each acid and the most suitable acid for the leaching methodwas determined considering its dissolution efficiency (Table A). In addition, temperature-dependent kinetic analyzes were performed for all three acids in this study. In this context, in order to determine the kinetic model controlling the total reaction rate, the situations under the chemical controlled model, diffusion controlled model, and film diffusion model were examined separately and appropriate kinetic models were determined for each acid
Examining the Involvement Level of People who Practise Karate
No full textThis study aims to determine the participants’ level of involvement who are engaged in karate in Adana and whether this involvement differs according to the demographic variables of the people. The data were collected from karate clubs in Adana via a survey. Analyses were carried out on 268 valid surveys. According to the analysis results, the participants' involvement in karate shows significant differences according to marital status, age, how many years karate has been practised, how often karate is practised and going out of province for karate purposes. Besides, while the dimension with the highest mean of the scale of involvement in karate sport is \"Attraction\" (x?=4,54), the dimension with the lowest average is \"Identity Expression\" (x?=3.57). Lastly, the general average of the scale items is x?=4,01. Based on this, it can be interpreted that the participants' interest in karate is generally high. These results highlight the positive tendencies of individuals involved in karate and underline the attractiveness and importance of the activity in their lives
HistSegNet: Histogram Layered Segmentation Network for SAR Image-Based Flood Segmentation
No full textFloods are one of the most common natural disasters, causing fatalities and severe economic and environmental impacts, directly affecting agriculture, urban infrastructure, and transportation networks. Hence, it is of utmost importance that flooded areas are efficiently and effectively identified in the aftermath. Synthetic aperture radar (SAR) images are invaluable to this end, since the amount of microwave energy reflected from water is less than that from land, due to its low surface roughness and lack of apparent texture. In this study, we explore the combination of histograms with deep neural networks for the purpose of flood mapping. The proposed histogram extraction layers, specifically designed for SAR content, are integrated into deep segmentation neural networks and are tested on two real SAR datasets. Experimental results have shown that histogram layers integrated into deep segmentation neural networks improve the performance up to 6% in terms of intersection over union (IoU) with a negligible increase in the number of learnable parameters. The code of the work will be available at https://github.com/ilterturkmenli/HistSegNet.Scientific and Technological Research Council of Turkey (TUBITAK) [123R108]This work was supported by the Scientific and Technological Research Council of Turkey (TUBITAK) under Project 123R108
Human activity recognition from multiple sensors data using deep CNNs
No full textSmart devices with sensors now enable continuous measurement of activities of daily living. Accordingly, various human activity recognition (HAR) experiments have been carried out, aiming to convert the measures taken from smart devices into physical activity types. HAR can be applied in many research areas, such as health assessment, environmentally supported living systems, sports, exercise, and security systems. The HAR process can also detect activity-based anomalies in daily life for elderly people. Thus, this study focused on sensor-based activity recognition, and we developed a new 1D-CNN-based deep learning approach to detect human activities. We evaluated our model using raw accelerometer and gyroscope sensor data on three public datasets: UCI-HAPT, WISDM, and PAMAP2. Parameter optimization was employed to define the model's architecture and fine-tune the final design's hyper-parameters. We applied 6, 7, and 12 classes of activity recognition to the UCI-HAPT dataset and obtained accuracy rates of 98%, 96.9%, and 94.8%, respectively. We also achieved an accuracy rate of 97.8% and 90.27% on the WISDM and PAMAP2 datasets, respectively. Moreover, we investigated the impact of using each sensor data individually, and the results show that our model achieved better results using both sensor data concurrently
Evaluating the Performance of Railway Transportation Companies Using Multi-Criteria Decision-Making Methods
No full textThe purpose of performance evaluation is to generate measurable data on an organization's performance, with the goal of assisting managerial decision-making and enhancing overall performance. In this study, the key performance indicators (KPIs) for railway transportation companies are identified based on expert opinions and previous frameworks. The operational performance of various railway freight transport companies was evaluated using multi-criteria decision-making methods (MCDM). Among the MCDM approaches, the Evaluation Based on Distance from Average Solution (EDAS) method was applied as the main method. In addition to the EDAS method, alternative MCDM methods such as TOPSIS, PROMETHEE II, and COPRAS were used to highlight potential deviations when compared to the results obtained with the EDAS method. Based on the research findings, three out of the seven KPIs, namely safety, have the highest weight at 38%, followed by punctuality at 19%, and journey time at 12%. Subsequently, companies were ranked according to their performance based on all KPIs. Furthermore, a sensitivity analysis was conducted to demonstrate how changes in the relative weights of KPIs can affect the results
Metallization of 3D Printed Polylactic Acid Polymer Structures via Radio-Frequency Sputtering
No full textThe metallization of polymer structures eliminates disadvantages such as low electrical conductivity, undesirable mechanical properties, degradation under different environmental conditions such as UV radiation and humidity, and poor thermal properties, thereby enabling the achievement of more functional polymer structures. 3D printing provides production flexibility by allowing the manufacture of polymer, ceramic, metal, and composite materials with any level of complexity and intricacy. This study aims to investigate the improvement of the drawbacks associated with polymers, by combining the advantages of polymers and metals through 3D printing and surface modification. The newly acquired features will offer researchers and users significant freedom in various applications. Polylactic acid was used to additively manufacture the polymer structures by using fused deposition modeling. Subsequently, the surfaces of polymer structures were subjected to surface treatment methods: as-printed, dichloromethane dipping, dichloromethane vapor, cold oxygen plasma, and sandpaper. The metallization process was completed using the RF sputtering technique with aluminum as the target material. To examine the morphological, structural, optical, and electrical properties of the metalized structures, various analyses were conducted, including scanning electron microscopy, energy-dispersive spectroscopy analysis, atomic force microscopy, x-ray diffraction (XRD), Fourier transform infrared spectroscopy (FT-IR) analysis, ultraviolet-visible-near-infrared (UV-VIS-NIR) analysis, contact angle measurement, ellipsometry analysis, and electrical resistance measurement. The results showed improvements in surface roughness due to the applied surface treatments. EDX and XRD analyses confirmed the presence of aluminum in the polymer structure. Electrical conductivity values of 0.32 x 106 S m-1 were achieved at a thickness of 1000 nm. Contact angles increased up to 91.728 degrees.Cukurova University, Scientific Research Projects Coordination Unit, Turkey [FDK-2021-14089]The authors are grateful to Cukurova University, Scientific Research Projects Coordination Unit, Turkey, for its financial support of this research (Project Number: FDK-2021-14089)
Organik gıda tüketimini etkileyen faktörlerin belirlenmesine yönelik bir çalışma: Adana ili örneği
No full textLisansüstü Eğitim Enstitüsü, İşletme (İngilizce) Ana Bilim DalıOrganik gıda tüketimi son yıllarda tüm dünyada olduğu gibi ülkemizde de hızla yayılmaktadır. Bu çalışma, Adana il merkezindeki tüketicilerin organik ürünlere yönelik tutumlarını ve organik ürünleri satın alma davranışları üzerindeki etkili olan faktörleri belirlemeyi amaçlamaktadır. Araştırmada materyal olarak, Adana ili merkezinde seçilmiş bireyler ile yapılan anket çalışmasından elde edilen verileri kullanılmıştır. Çalışma, katılımcıların demografik özelliklerinin detaylı bir analizini içermekte ve cinsiyet, yaş, gelir, medeni durum, meslek gibi değişkenlerin etkisini aydınlatmaktadır. Mesleki olarak, eğitim sektöründe çalışanlar ve gıda sektörü profesyonelleri, organik gıda endişeleri üzerinde belirgin etkiler sergilemektedir. Çalışma sonuçlarına göre tüketicilerin demografik özellikleri, yaş, cinsiyet, medeni durum ve gelir gibi, organik gıda tercihlerini ve davranışlarını şekillendirmede önemli bir rol oynamaktadır. Genç bireylerin organik gıda tüketimine daha fazla bir eğilimi olduğu belirlenirken, cinsiyet ve medeni durum tüketicilerin tutumlarında minimal farklılıklar göstermiştir. Ancak, gelir düzeyleri, organik gıdaların yaygın olarak benimsenmesine engel olan maliyet endişelerinin önemli bir belirleyicisi olarak ortaya çıkmaktadır. Bulgular, demografik, bilgi ve ekonomik faktörlerin yanı sıra kişisel tercihler ve yaşam tarzının organik gıdaya karşı tutumları şekillendirmedeki kritik rollerini ortaya koymaktadır. Organik ürün tükettiğini ifade eden tüketicilerin %11.5'i yaş sebze-meyve ürün grubunu tüketirken, bunu sırasıyla yumurta (%11.3), zeytinyağı (%10.9), süt ürünleri (%8.9) ve balın (%8.7) izlediği belirlenmiştir. Bu araştırma sonucunda elde edilen bulguların, Adana ilinde tüketicilerin organik ürünlerle ilgili tutumlarının ortaya konması ve organik ürün tüketme tercihlerini etkileyen faktörlerin ayrıntılı olarak belirlenmesi açısından önemli olduğu düşünülmektedir.Organic food consumption is rapidly spreading in our country, as it is worldwide. This study aims to determine the attitudes of consumers in the city center of Adana towards organic products and the factors influencing their purchasing behavior. Data obtained from a survey conducted with selected individuals in the city center of Adana were used as the material for the research. The study includes a detailed analysis of the participants' demographic characteristics and sheds light on the impact of variables such as gender, age, income, marital status, and occupation. Professionally, individuals working in the education sector and food industry professionals exhibit significant effects on organic food concerns. According to the study results, consumers' demographic characteristics, such as age, gender, marital status, and income, play a significant role in shaping their preferences and behaviors regarding organic food. While younger individuals exhibit a greater inclination towards organic food consumption, gender and marital status show minimal differences in consumer attitudes. However, income levels emerge as a significant determinant, posing a barrier to widespread adoption of organic foods due to cost concerns. The findings reveal the critical roles of demographic, knowledge and economic factors, as well as personal preferences and lifestyle, in shaping attitudes towards organic food. It was determined that 11.5% of the consumers who stated that they consumed organic products consumed the fresh fruit and vegetables product group, followed by eggs (11.3%), olive oil (10.9%), dairy products (8.9%) and honey (8.7%). The findings obtained as a result of this research are thought to be important in terms of revealing consumers' attitudes towards organic products in Adana and determining in detail the factors affecting their preferences for consuming organic products
The Applications of Lime (Citrus aurantifolia) Essential Oil as a Functional Ingredient in Gelatin/Kappa-Carrageenan Composite Films for Active Packaging
No full textGelatin and kappa-carrageenan (GEKC) composite films were developed by incorporating lime essential oil (LEO). GCMS analysis revealed the primary constituents within the LEO, which included limonene, gamma-terpinene, cyclohexene, terpineol, beta-pinene, and geranyl acetate. The oil-loaded films exhibited antimicrobial activity against foodborne pathogens such as Candida albicans and Staphylococcus aureus. DPPH and ABTS assays confirmed the enhanced antioxidant properties of the films. It was observed that the inclusion of LEO led to an increase in film thickness and water permeation, while the mechanical characteristics including tensile strength and elongation decreased with LEO addition. The compatibility of LEO with the film matrix was confirmed via scanning electron microscopy (SEM) and Fourier transform infrared spectroscopy (FTIR). Furthermore, the films exhibited improved thermal resistance upon the addition of LEO. This research highlights the potential of LEO as a natural and sustainable antimicrobial and antioxidant agent, paving the way for its application in active packaging.The Research Council; Natural and Medical Sciences Research Center, University of Nizwa, OmanThe Authors are thankful to the Natural and Medical Sciences Research Center, University of Nizwa, Oman, for providing research facilities to conduct the current study
Siber zorbalığın tespiti için hibrit bir yaklaşım
No full textLisansüstü Eğitim Enstitüsü, Bilgisayar Mühendisliği Ana Bilim Dalı, Bilgisayar Bilimi ve Mühendisliği Bilim DalıSiber zorbalık 2000'li yılların başından beri dünyada yaygınlaşmaya başlayan ve yıllar geçtikçe modern toplumun büyük sorunlarından biri haline gelen bir baskı türü olmuştur. Sosyal medyanın yaygın kullanımı siber zorbalık verilerinin gün geçtikçe artmasına sebep olmuştur. Bulgular arttıkça veri miktarı artmış ve siber zorbalık tespiti için otomatize edilmiş yöntemler aranmaya başlamıştır. Literatürde makine öğrenmesi, doğal dil işleme, derin öğrenme ve öznitelik seçimi gibi birçok yöntem ile siber zorbalığın tespit edilebilmesi için çalışmalar yapılmıştır. Bu çalışma son yıllarda bilgisayar bilimlerinde birçok problemin çözümünde büyük başarılar elde edilmesini sağlayan Genetik Algoritma(GA) ve doğadan esinlenilen sürü optimizasyon algoritmalarından biri olan Balina Optimizasyonu Algoritması'nın(BOA) hibrit bir şekilde öznitelik seçiminde kullanılmasının siber zorbalık verisinin sınıflandırılmasında etkili bir yöntem olabileceğini ortaya koyar. Çalışmada sunulan Genetik Balina Optimizasyonu tek başına GA ve BOA'dan doğruluk (accuracy) ve F1-Score bakımından daha iyi sonuç vermiştir.Cyberbullying has been a type of oppression that has become widespread in the world since the early 2000s and has become one of the major problems of modern society over the years. The widespread use of social media has led to an increase in cyberbullying data. As the findings increased, the amount of data increased and automated methods for cyberbullying detection began to be sought. In the literature, studies have been carried out to detect cyberbullying with many methods such as machine learning, natural language processing, deep learning and feature selection. This study reveals that the use of the Genetic Algorithm (GA) which has achieved great success in solving many problems in computer science in recent years, and the Whale Optimization Algorithm (WOA) which is one of the swarm optimization algorithms inspired by nature, in a hybrid way in feature selection can be an effective method in the classification of cyberbullying data. The Genetic Whale Optimization (GWOA) presented in the study gave better results in accuracy and F1-Score than GA and WOA alone