Güncel Gönderiler: Fen Bilimleri Enstitüsü / Graduate School for Science and Engineering
Toplam kayıt 188, listelenen: 61-80
-
Big data storage and automated text summarization in Turkish text
(Işık Üniversitesi, 2018-06-19)The subject of this study is storing the large datasets in accordance with Big Data ecosystem and to extract the summary sentences of a text in Turkish, apply the automatic text summarization process which is a subtopic ... -
Markdown optimization in apparel retail sector
(Işık Üniversitesi, 2018-01-16)Over last decades, rapidly growing textile and apparel industry has become an important sector. The branding and ever-changing fashion sense have been a trigger for a major competition environment. Nowadays, increasing ... -
Data compression for smart grid infrastructure
(Işık Üniversitesi, 2018-01-15)Embedded systems, which work with large data sets, need larger memory and consume much more data traffc when compared to other IOT (Interne Of Things) devices. In this study, Human's Lossless Compression Algorithm is ... -
Improvement of credit evaluation process in commercial banking
(Işık Üniversitesi, 2018-01-16)Loans constitute the largest sources of revenue in banking industry thus effecting the Turkish economical environment extensively. Credits in the banking sector can be categorized as corporate, medium and large scale, and ... -
Automatic comment generation using the source code
(Işık Üniversitesi, 2018-01-23)In this study, automatic comment generation for Java methods is described. It is sufficient that the codes conform to the syntax rules of the Java programming language, and it is not expected to be runnable. In order to ... -
Sense distinction using computational methods in Turkish dictionaries
(Işık Üniversitesi, 2018-01-25)NLP(Natural Language Processing) refers to general name of the study elds related with processing languages by using computer-based systems. In NLP studies, dictionaries are required as lexical and semantic resources. ... -
Morphological analyser for Turkish
(Işık Üniversitesi, 2018-01-25)Natural Language Processing is one one the fields of work in computer science and specializes in text summarization, machine translation and many various topics. Morphology is one of the Natural Language Processing features ... -
Evaluation of feature selection and encoding methods fpr superpixel image parsing
(Işık Üniversitesi, 2017-12-14)This thesis is about image parsing which is one of the important problems in computer vision. The goal of image parsing is segmentation of object and labeling of each object. Recently, a popular way of image segmentation ... -
Graph clustering approach to sentiment analysis
(Işık Üniversitesi, 2018-01-24)In this thesis, we aim at automatically predicting Turkish movie review scores using adjective clustering. We also measured the reliability of the two popular sentiment lexicons. In order to measure the agreement between ... -
Co-training using prosodic, lexical and morphological information for automatic sentence segmentation of Turkish spoken language
(Işık Üniversitesi, 2018-01-15)Sentence segmentation of speech aims detecting sentence boundaries in a stream of words output by the speech recognizer. Sentence segmentation is a preliminary step toward speech understanding. It is of particular importance ... -
Short term load forecasting in electricity markets in Turkey
(Işık Üniversitesi, 2017-08-16)As energy consumption rises, forecasting electricity parameters becomes a signi?cant advantage on e?cient power system applications, planning and decision making in deregulated power markets. An accurate short term load ... -
Prediction of final football league standings by dynamic frontier estimation
(Işık Üniversitesi, 2017-07-13)Data Envelopment Analysis (DEA) is a commonly used method for efficiency assessment of teams in many sports including football. In this work, we investigate how estimations of final league standings with DEA efficiency ... -
Optimal project duration for resource leveling
(Işık Üniversitesi, 2017-07-13)Resource leveling is important in project management as resource fluctuations are costly and undesired. Typically, schedules with better resource profiles are obtained using the schedule found by Critical Path Method and ... -
Biometric recognition using bio-signals
(Işık Üniversitesi, 2017-04-14)The main objective of the project is to increase the recognition rate by establishing a multimodal biometric recognition system that uses two di_erent biometric characteristics, as bio-signals. Today, institutions use ... -
Enhancement of the coded speech using filtering
(Işık Üniversitesi, 2017-04-14)The processing and storage of speech signals are widely implemented in modern communication systems. Decreasing the amount of information for modeling the reconstruction of speech signal enhances the transmission and storage ... -
Optimization of fertile land usage and agricultural production of Turkey
(Işık Üniversitesi, 2017-01-18)Turkey has a large amount of land which is suitable for agriculture. On the other hand, agricultural activities gradually decrease every year. Moreover, the fertile lands are not used effectively. As a result, production ... -
An assortment planning problem with an empirical demand model
(Işık Üniversitesi, 2017-01-18)In retail industry, although the product range increases with a great pace year by year, the shelf space that products are displayed on does not expand with the same pace. Accordingly, in recent years, placing products ... -
Turkish electricity sector: a bottom-up approach
(Işık Üniversitesi, 2017-01-17)The importance of this study, roots from being the first attempt to model and examine Turkish energy system specific to electricity sector using TIMES modelling methodology to assess the future pathways of the system under ... -
Compression of the mammography images using quadtree based energy and pattern blocks
(Işık Üniversitesi, 2017-01-16)Medical images, like any other digital data, require compression in order to reduce disk space needed for storage and time needed for transmission. This thesis offers , a novel image compression method based on generation ... -
Fabric defect detection in frequency domain using fourier analysis
(Işık Üniversitesi, 2016)An overwhelming majority of image processing based defect detection approaches rely on machine learning methods to train a model for comparison of test examples. This requires a training phase for each item to be learned ...