Deep learning-based total suspended solids concentration classification of stream water surface images captured by mobile phone

The continuous monitoring of total suspended solids (TSS) in streams plays an important role in the management of hydrological processes, and TSS is also a decisive parameter in the control of pollution in streams. Determination of TSS involves both a costly and time-consuming process. For this reason, there is a need to determine TSS more quickly, easily reliably, and economically. In this study, it is aimed to classify TSS concentration by using stream water surface images recorded with a mobile phone. For this purpose, the sampling studies carried out in the Lower Değirmendere Stream Watershed (Trabzon, northeast of Turkey) between June 2020 and May 2021, and the images of the stream water surface were taken and recorded with a mobile phone simultaneously with the sampling studies. The stream water surface images and TSS concentration were divided into four classification group, namely clear, turbid, very turbid, and extremely turbid and processed with deep learning method. More than 5500 stream water surface images and TSS concentration data were divided into groups as 70% training and the rest of test. This study uses eight convolutional neural network (CNN) models, including a custom CNN model designed for image classification, along with pre-existing architectures such as VGG-16, VGG-19, Inception-V3, Xception, DenseNet-121, MobileNet, and NASNet-mobile. The results revealed that the most effective ensemble model formation strategy was stacking with an accuracy rate of 87%, followed by weighted averaging, averaging, and majority voting. As a result, with the image of the stream water surface via the mobile phone camera, it can be easily determined which class the current TSS concentration belongs to instantly.

The prevalence of diabetes and associated risk factors among adult population in a Turkish population (Trabzon city)

OBJECTIVE

The objectives of this study were to determine the prevalence of diagnosed and undiagnosed diabetes mellitus (DM) and prediabetes, and to evaluate the associated risk factors in a sample of adult Turkish population.

METHODS

A total of 4000 eligible study subjects, aged 20 years or older, chosen by multistage sampling on a field were considered. Of those 3721 subjects (2139 women and 1582 men) participated in the study.

RESULTS

The prevalence of prediabetes and DM were found to be as 6.4% and 10.4% (3.6% being newly diagnosed by this study), respectively. In multivariate logistic regression analysis, advanced age (OR:26.7, p < 0.0005 in the group 70 years and over), marriage (OR:2.05, p = 0.047), housewives (OR:1.34, p = 0.003), family history of diabetes (OR:2.84, p < 0.0005), overweight (OR:1.61, p = 0.026), obesity (OR:2.25, p < 0.0005), hypertension (OR:1.42, p = 0.007) and dyslipidemia (OR:1.38, p = 0.028) were independent risk factors for being diabetic.

CONCLUSIONS

DM is an important health problem in the adult population of Trabzon city. Newly diagnosed diabetic patients who were unaware of their status are at high risk. To control DM and associated risk factors, effective public health education and taking urgent steps are needed.

Evaluation of urban transformation areas in terms of user satisfaction: the case study of Zağnos Valley (Trabzon/Turkey)

Following the Industrial Revolution, rapid urbanization brought about many socio-economic, physical, and cultural problems. The concept of urban transformation has come to the fore as a solution to these emerging troubles. Especially since 1980, in Turkey, like other developing countries, the concept of urban transformation has only been evaluated as an economic standpoint ignoring the social and spatial dimensions of that area and the quality of life of people residing in the area. Therefore, the necessity of these socially accessible areas where individuals can regenerate themselves in spiritual and physical terms has increased even more. However, when the urban transformation projects are put into practice, the needs and demands of the users are not taken into account; moreover, there are no studies showing the satisfaction or dissatisfaction of the users following the implementation. In the current study, satisfaction/dissatisfaction levels of the users were determined by asserting the user profile of Zağnos Valley, which is the first urban transformation area of Trabzon. In the valley, which is an important air corridor and a recreation area for Trabzon, questionnaires were implemented through face-to-face interview technique. Factor analysis was carried out in order to reveal the socio-demographic characteristics, space usage trends, and spatial usage characteristics of the users. In order to measure satisfaction and dissatisfaction levels, the determined criteria were weighted on a 5-point Likert scale and frequency distributions were examined. In this way, solution proposals have been made in order to increase the level of satisfaction and remediate the level of dissatisfaction of users.

Prevalence of gestational diabetes mellitus and associated risk factors in Turkish women: the Trabzon GDM Study

INTRODUCTION

The aim of this study was to investigate the prevalence of gestational diabetes mellitus (GDM) in Turkish pregnant women in the Trabzon Region and further to identify population-specific risk factors for GDM.

MATERIAL AND METHODS

In this prospective cross-sectional survey, universal screening for GDM was performed in 815 pregnant women. Screening was done with a 50-g oral glucose challenge test (GCT) with a 140 mg/dl cut-off point, then a diagnostic 100 g oral glucose tolerance test (OGTT) was performed according to Carpenter and Coustan (CC) criteria.

RESULTS

The GCT was positive in 182 (22.3%) cases. The OGTT was performed on the 182 screen-positive pregnant women. Thirty-five were diagnosed with GDM on the basis of their results for a prevalence of 4.3% (35/815). Of the pregnancies with negative GCT but having high risk factors for GDM (n = 31), 4 were diagnosed with GDM (0.5%). Prevalence of GDM was found to be 4.8% (n = 39) for all pregnant women. Gestational diabetes mellitus was positively associated with advanced maternal age (p < 0.001), prepregnancy body mass index (p < 0.001), cessation of cigarette smoking (p < 0.001), excessive weight gain during pregnancy (p = 0.003), previous history of GDM (p < 0.001), history of selected medical conditions (p = 0.018), family history of diabetes (FHD) (p < 0.001), and existence of at least one high risk factor for GDM (p < 0.001). In multiple logistic regression analysis, independent predictors for GDM were maternal age, cessation of cigarette smoking, increasing prepregnancy body mass index, weight gain of more than 8 kg during pregnancy, GDM history in previous pregnancies and a history of diabetes in first-degree relatives of pregnant women.

CONCLUSIONS

The prevalence of GDM in Trabzon province was found as moderate. Commonly recognized risk factors including older age, prepregnancy obesity, FHD and past history of GDM, are valid for our urban Turkish population. Also, excessive weight gain in pregnancy and cigarette cessation were observed to be nontradional risk factors of GDM. It was concluded that all pregnant women should be screened for GDM if prevalence was not low.