2020 Cilt 25 Sayı 3

Permanent URI for this collectionhttps://hdl.handle.net/11452/20110

Browse

Now showing 1 - 7 of 7

Classification of epileptic eeg signals based on finite impulse response filter and artificial neural networks training algorithms
(Bursa Uludağ Üniversitesi, 2020-09-20) Bayrak, Şengül; Yücel, Eylem; Şamlı, Rüya
The electroencephalogram is a powerful tool for understanding the electrical activities of the brain. The automatic and accurate classification of extracranial and intracranial electroencephalogram signals are significant for the evaluation of epilepsy. Electroencephalogram signals contain significant characteristic information about epileptic brain waves. However, the electroencephalogram signals are easily disrupted by the artifacts polluting. This study proposed a clinical decision support system to extract significant epilepsy-related spectral features from the electroencephalogram signal. The artifact-free electroencephalogram signals features were obtained from the Kaiser window based on Finite Impulse Filter. The extracted features were modelled by the Artificial Neural Networks Back Propagation training algorithms which are Levenberg-Marquardt, Bayesian Regularization, and Scaled Conjugate Gradient. The algorithms' classification performances were compared by the accuracy rates. The experiment results show that compared with the Artificial Neural Networks Back Propagation training algorithms, the performance of the Levenberg-Marquardt is better from the point of accuracy rate which achieves a satisfying classification accuracy of 83.01% for extracranial and intracranial electroencephalogram signals.
Comparison of reality types
(Bursa Uludağ Üniversitesi, 2020-10-28) Irıqat, Sanaa; Vatansever, Fahri; Mühendislik Fakültesi; Elektrik Elektronik Mühendisliği Bölümü; 0000-0002-8360-1500; 0000-0002-3885-8622
Rapid developments in technology reflect and directly affect all areas of life. One of these areas is reality technology. With this technology that combines the physical world with the digital world, changes can be created in humans' "reality" perception. This study presents information and detailed comparisons about the fundamentals, principles, and applications of augmented, virtual, and mixed reality technologies that have become popular recently.
Digital transformation to university 4.0: A roadmap
(Bursa Uludağ Üniversitesi, 2020-10-25) Çubukçu, Ceren; Akturk, Cemal
The required skills and knowledge expected from human capital is affected by Industry 4.0. In order to keep up with this movement and graduate qualified human resources, universities need to update themselves and transform to University 4.0. In this study, research was conducted on the sample selected from large and small universities with different characteristics. In this research, first, the structural characteristics of the universities and the information management systems used which concern all the stakeholders in that institution were examined. Also, a roadmap is proposed to help the digital transformation process of universities. The flow of the elements in this model is logically determined to form a basis for the whole transformation process. This study contributes to the literature by introducing a new model to the researchers in this field and to all employees who will endeavor in this transformation process.
Effects of acid and high-temperature treatments on durability of bacterial concrete
(Bursa Uludağ Üniversitesi, 2020-12-04) Özhan, Hacer Bilir; Yıldırım, Musa
Bacterial concrete specimens were produced in this study to investigate the effects of microbially induced calcium carbonate precipitation (MICP) mechanism on concrete durability. Bacterial concrete (BC) samples were produced through supplementation of Bacillus megaterium bacteria into concrete mixture and curing water. However, control concrete (CC) samples were produced without bacteria. BC and CC were exposed to acid (HCl) and high temperature (400C) treatments. In the first phase of the study, 100×100×100 mm cube specimens were immersed into HCl solution for 10 days and compressive strengths and weight losses were determined. Compressive strength of acid-treated samples was measured as 25.08 MPa for BC samples and as 17.90 MPa for CC samples. Such values revealed that BC samples yielded 40.11% greater compressive strength. When CC samples lost 10.99% weight due to acid attack, BC samples lost 8.74% weight. In the second phase of the study, concrete specimens were exposed to 400℃ temperature and compressive strength of heat-treated samples was determined. As the result of high temperature, bacterial samples yielded 13.76% greater compressive strength against high temperature. Present findings revealed that CaCO3 formation on concrete improved concrete durability against attacks and high temperatures.
Effects of yarn spinning systems and twist direction on some properties of viscose interlock fabrics
(Bursa Uludağ Üniversitesi, 2020-10-22) Duru, Sena Cimilli
In this study, it was intended to investigate the effects of yarn spinning systems as well as yarn twist direction on some comfort and spirality performance properties of the fabrics. For this aim, interlock knitted fabrics made of 100% viscose yarns were produced with different spinning systems namely, ring, compact and siro at two twist directions; S and Z. The results indicate that the fabrics made of compact yarn possessed high water vapor and high air permeability values, but lesser vertical wicking values than ring yarn fabrics. However, both of the permeability values of the compact yarn fabrics markedly reduced when yarn twist direction was S. Generally, irrespective of yarn twist direction, the siro yarn fabrics exhibited better permeability but lesser wickability values as compared to ring yarn fabrics. Ring yarn fabrics displayed relatively highest wickability values and spirality percentages as compared to made from siro and compact yarns. In addition, samples produced from Z-twist yarn had higher air permeability values as well as water vapor permeability values but their vertical wicking values and spirality percentages were lesser than that of S-twisted ones. To sum up, it can be inferred that the spinning system has a profound influence on structural parameters of spun yarns.
Front-end module development for a light commercial vehicle
(Bursa Uludağ Üniversitesi, 2020-11-05) Küçükoğlu, Ayça; Bağrıyanık, Ali Ozan; Bahar, İlker; Sirkeci, Fatma; Yağcı, Yavuz Emre
CO2 emission targets became a crucial obstacle for vehicle producers. In order to overcome this problem, weight reduction potentials are getting more and more critical. In this study, for a light commercial vehicle, a glass fiber reinforced thermoplastic front-end structure has been analyzed. At first, a fully plastic draft design is analyzed and compared with the current metal structure. After that, a topology volume is extracted from the existing vehicle structure, and topology optimizations have been carried out according to the modal and static loading performance targets. Different optimization parameters have been investigated to decide the best solution in terms of performance and weight. Load paths and optimum design are calculated by topology results. Due to the packaging problems with the radiator and headlamp, optimization volume is modified, and the new topology volume and optimizations are completed. Based on the topology results, a feasible design is prepared, and detailed non-linear analyses are started. After the non-linear analyses, free size optimization is applied to the ribs of the part. In this study, a feasible preliminary design at the same performance with less weight respect to the current metal version is completed.
Probabilistic runoff modeling approach in mountainous basins based on satellite snow data and wavelet neural network
(Bursa Uludağ Üniversitesi, 2020-11-12) Uysal, Gökçen; Şensoy, Aynur
Streamflow prediction is often a challenging issue for snow dominated basins where proper in-situ snow data might be limited and the snow physics is highly complex. The main aim of this study is to propose an alternative modeling solution by considering both accessibility of the inputs and simplicity of the model structure. We propose Wavelet Neural Network (WNN) model approach which takes probabilistic snow cover area in order to produce probabilistic streamflow in the mountainous basins. For the sake of the accessibility of the input data, snow probability maps are produced from cloud-free images of MODIS. The WNN model is trained and tested with observed hydro-meteorological data. Also, Multi Layer Perceptron Model (MLP) is used as a benchmark model. The approach is tested in a snow-dominated headwater (in altitude from 1559 to 3508 m) of Murat River which has a great importance as being one of the main tributaries of Euphrates River. According to the results, the approach is capable of detecting snow distribution in the area of interest and WNN is promising to generate probabilistic streamflow predictions.

Browse

Browsing by Language "en"