Sürdürülebilir Kalkınma Amaçları
Yayınlar
- BildiriAçık Erişim2024AN ANALYSIS OF NEIGHBOURHOOD TYPES FOR POINTNET++ IN SEMANTIC SEGMENTATION OF AIRBORNE LASER SCANNING DATA
Akbulut, Z.; Ozdemir, S.; Karsli, F.; Dihkan, M.; Isikdag, U.; Bayram, B.
The objective of the study is to conduct a comprehensive examination of how different neighbourhood types, namely spherical, cylindrical, and k-nearest neighbour (kNN), influence the feature extraction capabilities of the PointNet++ architecture in the semantic segmentation of Airborne Laser Scanning (ALS) point clouds. Two datasets are utilized for semantic segmentation analysis: the Dayton Annotated LiDAR Earth Scan (DALES) and the ISPRS 3D Semantic Labelling Benchmark datasets. In the experiments, the kNN method exhibited approximately 1% higher accuracy in weighted mean F1 and intersection over union (IoU) metrics compared to the spherical and cylindrical neighbourhood types on the DALES dataset. However, in the generalization experiment conducted on the ISPRS dataset, the spherical neighbourhood achieved the best results in these metrics, outperforming the cylindrical neighbourhood by a small margin. Notably, the kNN method was the least accurate, with a decrease in accuracy of approximately 1% in both weighted mean IoU and F1 scores. These findings suggest that the features extracted from spherical and cylindrical neighbourhood types are more generalizable compared to those from the kNN method.
- MakaleAçık Erişim2021Tarragon (Artemisia dracunculus l.) could alleviate negative effects of stocking density in laying hens
Kaya, H.; Karaalp, M.; Kaynar, Ö.; Tekçe, E.; Aksakal, A.; Bayram, B.
The study was conducted to determine the effects of stocking density (SD, 5 or 7 layers/cage) and tarragon (Artemisia dracunculus L.) diet supplementation at four levels (0, 1.2, 6 and 12 g/kg feed) on performance, certain egg characteristics, serum, liver, egg yolk and small intestine bacteria parameters in laying hens. The experiment was carried out over a period of 8 weeks, with 192 Lohman Brown commercial hybrids at 50-w-age. The results showed that an increased SD reduced feed intake (FI; p<0.01) and egg production (p<0.05), but had no effect on the weight gain, feed conversion ratio, damaged egg ratio, egg weight and egg quality (p>0.05) parameters. The supplementation of tarragon to the diet reduced the FI and damaged egg ratio (p<0.01), and improved egg production and FCR (p<0.01). While an increased SD reduced serum total antioxidants (p<0.05), it elevated corticosterone (CORT) and total oxidant serum (TOS) (p<0.05). Tarragon was found to enhance total immunoglobulin (p<0.05), but to decreased the CORT and TOS of the serum (p<0.05). An increased SD raised the malondialdehyde (MDA) in the serum (p<0.001), liver (p<0.05) and yolk (p<0.001). Tarragon supplementation reduced MDA of the serum (p<0.05), liver (p<0.001) and yolk (p<0.001). E. coli and total Mesophilic Aerobic Bacteria counts in the small intestine were raised (p<0.001) with increased SD. Tarragon decreased (p<0.05) mesophilic aerobic bacteria. It was thus found that, tarragon supplementation can be considered generally effective in improving performance parameters, alleviating stress-induced negativities, reducing lipid peroxidation, regulating the immune system and controlling some intestinal microorganisms.
- BildiriAçık Erişim2017THE EFFICIENCY of RANDOM FOREST METHOD for SHORELINE EXTRACTION from LANDSAT-8 and GOKTURK-2 IMAGERIES
Bayram, B.; Erdem, F.; Akpinar, B.; Ince, A.K.; Bozkurt, S.; Catal Reis, H.; Seker, D.Z.; Karas, I.R.; Rahman, A.A.; Isikdag, U.
Coastal monitoring plays a vital role in environmental planning and hazard management related issues. Since shorelines are fundamental data for environment management, disaster management, coastal erosion studies, modelling of sediment transport and coastal morphodynamics, various techniques have been developed to extract shorelines. Random Forest is one of these techniques which is used in this study for shoreline extraction.. This algorithm is a machine learning method based on decision trees. Decision trees analyse classes of training data creates rules for classification. In this study, Terkos region has been chosen for the proposed method within the scope of "TUBITAK Project (Project No: 115Y718) titled "Integration of Unmanned Aerial Vehicles for Sustainable Coastal Zone Monitoring Model – Three-Dimensional Automatic Coastline Extraction and Analysis: Istanbul-Terkos Example". Random Forest algorithm has been implemented to extract the shoreline of the Black Sea where near the lake from LANDSAT-8 and GOKTURK-2 satellite imageries taken in 2015. The MATLAB environment was used for classification. To obtain land and water-body classes, the Random Forest method has been applied to NIR bands of LANDSAT-8 (5th band) and GOKTURK-2 (4th band) imageries. Each image has been digitized manually and shorelines obtained for accuracy assessment. According to accuracy assessment results, Random Forest method is efficient for both medium and high resolution images for shoreline extraction studies.
- BildiriYalnız künye2016Automatic segmentation of plaque and four-dimensional analysis of magnetic resonance images used in the diagnosis and disease monitoring of multiple sclerosis
Demir, S.; Bayram, B.; Demir, N.; Catal, H.; Togrol, R. E.; Kafadar, C.; Ozdag, M. F.
- MakaleYalnız künye2012EFFECT OF THE BODY CONDITION SCORE ON SOME REPRODUCTION AND MILK YIELD TRAITS OF SWEDISH RED AND WHITE COWS
Bayram, B.; Aksakal, V.; Akbulut, O.
This study examined the effect of body condition score (BCS) at calving and during the first month of lactation on some reproduction and milk yield traits of Swedish Red and White (SRW) cows organically raised in Turkey. For this purpose, SRW cows divided two groups, named as thin (BCS <3.00) and moderate (BCS >= 3.00). The actual milk yield (815 kg) and 305 day daily milk yield (736 kg) of cows with low condition score at calving were significantly (P<0.01) higher than those with moderate condition score. The BCS at calving did not have an effect on the lactation length, peak daily milk yield and days to attain peak milk yield. The condition score obtained in the first month of lactation only affected the peak daily milk yield (P<0.05), while its impact on the other characteristics was non-significant. The service period of the cows with low condition score at calving was significantly longer (19.9 day) and their number of services per conception was significantly lower (0.37 units) (P<0.05) than moderate group. The condition loss was calculated as 0.0137 units in the thin group and 0.2290 units in the moderate group and this differences were significant (P<0.01) during the first 30 day period of lactation. The phenotypic correlation between BCS at calving and milk yield traits were negative and significant (P<0.01). According to this relationship, actual milk yield (r=-0.208), 305 day milk yield (r=-0.248) and peak daily milk yield (r=-0.251) decreased significantly (P<0.01) with the increase in the BCS at calving. The service periods of cows with low condition scores at calving were significantly longer (P<0.01).
- MakaleYalnız künye2012Estimation of variance components and heritability of birth weight through different methods in Swedish Red and White cattle
Aksakal, V.; Bayram, B.; Yanar, M.; Akbulut, O.
Data on 368 birth records of Swedish Red and White cattle herd raised organically at Dogan Organic Dairy Cattle Farm for a period of 2006 and 2009 (4 years) were used to estimate the effects of different environmental factors on birth weight. Additionally, a comparison of four methods for variance component estimation to compute heritability of birth weight was performed using ML (Maximum likelihood), MINQUE (Minimum variance quadratic unbiased estimation), REML (Restricted maximum likelihood) and Henderson's Method III. Average abortion rate, stillbirth rate, twin and single birth rates of Swedish Red and White cattle were as 4.5%, 4.3%, 3.2% and 87.7% respectively. The least squares mean for birth weight was 37.4±0.70 kg. While effects of calving year (P<0.01), calving season (P<0.05) and sex of calve (P<0.01) were significant, and the effect of age of dam was not significant (P>0.05). Sire and error variance components and standard error of the heritability obtained by using ML method were lower than those obtained by the other three methods. Heritability estimates for birth weight obtained by ML, REML, MINQUE and Henderson Method III were 0.57±0.22, 0.62±0.24, 0.65±0.25 and 0.59±0.24, respectively. It is concluded that the ML procedure was superior for estimating variance components and heritability of birth weight of Swedish Red and White cattle and non-genetic factors influencing the birth weight should also be considered in selection and an adjustment for the significant environmental factors should be made.
- MakaleYalnız künye2010An analysis of the factors affecting birth weight and actual milk yield in swedish red cattle using regression tree analysis
Topal, M.; Aksakal, V.; Bayram, B.; Yaǧanoǧlu, M.
Performance records (birth weight and actual milk yield) on 206 Swedish Red cattle maintained at private organic diary cattle enterprise in Kelkit district of Gümüşhane province, in Turkey, were analyzed through regression tree method to determine the effects of some factors affecting birth weight and actual milk yield. The birth weight of calves averaged as 41.034±4.218 kg. Out of total calves born, twin born calves were 2.9%. Single born calves were heavier (41.185±3.840 kg) than twin born (36.000±10.545 kg). The results revealed that the most significant variable affecting birth weight was birth type, followed by birth season, sex and body condition score (BCS2) of the dam during birth. Lactation period and peak milk yield were important variables affecting the actual milk yield in the dairy herd under investigation.
- MakaleYalnız künye2009The effect of average daily gain and age at first calving on reproductive and milk production traits of brown swiss and holstein friesian cattle
Bayram, B.; Yanar, M.; Akbulut, O.
The purpose of the study was to determine the effects of average daily gain and age at first calving on the reproductive and milk production traits of Brown Swiss (BS) a.d Holstein Friesian (HF) cattle. For this purpose, daily gains and ages at first calving were divided into two groups which were below the average called as the "slow" or "early" groups and above the average named as "moderate" or "late" groups respectively. BS heifers in the moderate group reached the first insemination age and first calving age 103.7 and 101.7 days earlier (P>0.01) than these in the slow group respectively. The corresponding values for HF heifers were 37.8 and 29.5 days respectively and were not significant. While the average daily gain had negative effects on reproduction traits following the first calving, the daily gain of BS had no effect on the milk production traits in all parities. HF heifers in the moderate group had higher (P>0.05) actual (585 kg) and 305 days milk yield (324 kg) in the second parity. Early calving in both breeds resulted in a significant (P>0.05) reduction in the actual and 305-days milk yield in the first parity. Early calving caused a significant decrease (P>0.05) in the actual milk yield, 305-days milk yield, actual milk fat and 305-days milk fat yield of BS cows in the first parity. Either early or late calving in BS didn't affect on milk traits in second and third parities. The early calving in HF lowered significantly (P>0.05) the actual and 305-days milk yield in first lactation. However, late calving in HF resulted in lower actual milk yield, 305-days milk yield, actual milk fat yield and 305-days milk fat yield in third parity.
- MakaleYalnız künye2006Performance and health of dairy calves fed limited amounts of acidified milk replacer
Güler, O.; Yanar, M.; Bayram, B.; Metin, J.
To compare growth performance of Brown Swiss calves fed acidified milk replacer (AMR) at 8% of birth weight, 20 newborn calves were reared under a new calf-feeding programme. Body weights, total weight gains and gains in body measurements, feed intake and feed efficiency values determined at different stages of growth of AMR-fed calves were comparable to those of calves fed sweet milk replacer (SMR). Faecal consistency scores and percent days with diarrhoea of calves offered AMR from four to 35 days of age were respectively 0.4 and 19.1% lower than those fed SMR. Most of the bebavioural parameters studied were not unfavourably influenced by acidification of the replacer. In conclusion, growth, feed intake and feed efficiency characteristics of Brown Swiss calves fed AMR or SMR were not different from each other. However, incidence of diarrhoea of the young calves was decreased and health status of the calves was improved with the feeding of acidified milk.