Yazar "Ugurlu, Bora" seçeneğine göre listele

Listeleniyor 1 - 8 / 8
  • [ X ]
    Öğe
    A novel model for mood changes on a critical event using emotional state and trait analysis and handwriting features
    (Computers and Industrial Engineering, 2014) Ugurlu, Bora; Güçlü Kandemir, Rembiye; Carus, Aydin; Abay, Ercan
    Our brain and sub consciousness actually form our character as a result of our habits. Handwriting which is the significant part of our personality is unique. It contains so much knowledge about us. It is possible to get a comprehension about an individual mood by examining handwriting. In the industry, some real-world applications are frequently used to determine personal identifications, to support employment in business, and to perform document transaction management and e-signature, which is a type of handwriting. The researches done to explore the relation between anxiety and handwriting are rarely computerized. Visual assessments of handwriting analysis for anxiety are common in the literature. According to visual assessments, there are so many debates. In this study, we investigated the relationship between exam anxiety of university students and handwriting in a computerized way. These students often have anxiety based on emotional state and trait. We recommend a novel model for mood changes, which is able to determine whether a student is anxious or not. Collaborative work of two distinct disciplines (i.e., computer science and medical science) makes results much more valuable. Our study is an important preliminary step of a complex mood change assessment system for industrial applications when a critical event occurs. The experimental results show that the proposed model is consistent and statistically significant, and also, is applicable to different fields of business area.
  • [ X ]
    Öğe
    A Query Evaluation Approach using Opinions of Turkish Financial Market Professionals
    (Assoc Information Communication Technology Education & Science, 2015) Ugurlu, Bora; Yenisari, Esma; Karasulu, Bahadir; Ayan, Ozcan Zafer
    People who do not have expertise in the financial area may not see the relationship between the numerical and linguistic data. In our study, a knowledge discovery approach using Turkish natural language processing is recommended in order to respond to meaningful queries and classify them with high accuracy. Query corpus consists of randomly selected unique keywords. Quantitative evaluation is done in order to measure the classification performance. Experimental results indicate that our proposed approach is sufficiently consistent with and able to make categorical classifications correctly. The approach highlights the relationship between numerical and linguistic data obtained from Turkish financial market.
  • [ X ]
    Öğe
    An Expert System for Determining the Emotional Change on a Critical Event Using Handwriting Features
    (Uikten - Assoc Information Communication Technology Education & Science, 2016) Ugurlu, Bora; Kandemir, Rembiye; Carus, Aydin; Abay, Ercan
    An individual may sometimes feel anxious when a critical event happens. Job interview, wedding, moving in a new city/country can result this occurrence. Examinations taken in school are also that kind of events. Since our handwriting is controlled by brain, it is possible to see clear changes in handwriting style during examinations. In our study, an expert system is developed which considers handwriting features to predict student's exam anxiety state. 210 handwriting samples are collected and classification is made by using J48 decision tree algorithm. The average of Precision, Recall and F-Measure metrics are 71%, 66% and 67%, respectively.
  • [ X ]
    Öğe
    An overview on case-based reasoning and its synergetic applications with hybrid reasoning
    (Computers and Industrial Engineering, 2014) Ugurlu, Bora; Karasulu, Bahadir
    A variety of applications in quality management, health care, intelligent manufacturing and communication areas involves the systems based on case-based reasoning with an inference mechanism. The main aim of case-based reasoning is to solve a given problem defined in a specified experience area. A case-base or a case memory is used to make a decision for a problem. The base covers previously solved problem's solutions. For a hybridization, there are a lot of studies using synergism approach so as to combine different knowledge presentation models or reasoning methodologies. It fills possible knowledge gaps or existing lacks for individual systems. There are many advantages, such as simplifying the knowledge acquisition, obtaining an automatic explanation ability, building a cost-effective system and increasing the quality of problem solutions. In this study, we systematically reviewed remarkable studies based on case-based reasoning or its synergetic applications with hybrid reasoning in the literature. They are selected from the years between 1998 and 2013, and involve expert systems or similar mechanisms used in medical, industrial and business fields. The results are discussed.
  • [ X ]
    Öğe
    Instant Information Support and Notification System for Emergency
    (IEEE, 2017) Ugurlu, Bora; Kaynak, Lutfullah
    When an emergency happens in a rural area, accessing the patient's basic medical record, such as age, blood type, and drug allergy if any, via mobile network may sometimes not possible. It is up most important to access quickly the medical records of the patient would be vital when the passing time is considered. Most of the time, this saves lives. Another issue is the notification of survivor's close relatives. They are needed to be informed as soon as the emergency happens. Sharing some information with them such as accident location, hospital name would make them less worried. In this study, we have developed an instant information support and notification software system. Our goal is to provide the survivor's basic medical record to first aid team as well as to notify his/her close relatives as quickly as possible.
  • [ X ]
    Öğe
    Instant information support and notification system for emergency
    (Institute of Electrical and Electronics Engineers Inc., 2017) Ugurlu, Bora; Kaynak, Lutfullah
    When an emergency happens in a rural area, accessing the patient's basic medical record, such as age, blood type, and drug allergy if any, via mobile network may sometimes not possible. It is up most important to access quickly the medical records of the patient would be vital when the passing time is considered. Most of the time, this saves lives. Another issue is the notification of survivor's close relatives. They are needed to be informed as soon as the emergency happens. Sharing some information with them such as accident location, hospital name would make them less worried. In this study, we have developed an instant information support and notification software system. Our goal is to provide the survivor's basic medical record to first aid team as well as to notify his/her close relatives as quickly as possible. © 2017 IEEE.
  • [ X ]
    Öğe
    Reliable Address Translation for Instructions
    (IEEE, 2015) Kadayif, Ismail; Ugurlu, Bora
    As a result of technology scaling, spatial multi-bit soft errors have been becoming a big concern for SRAM-based storage structures, such as caches, buffers, and register files, in the design of reliable computer systems. Conventional techniques, such as bit interleaving or stronger coding, cannot provide the designers with effective solutions to the problem of reliable address generation in instruction translation lookaside buffers (iTLB) because of high power and/or latency overheads. In this study, we aim to generate reliable address translation for instructions without compromising either on performance or on power consumption. To do so, we propose to use a pair of identical registers storing the last address translation, which are referred to as context frame registers (CFR). As long as the control flow of programs stays in the same page, address translations are supplied by these two registers, instead of the iTLB. Since two CFRs keep the same address translation, spatial multi-bit errors are detected by comparing their contents. If their contents do not match, we obtain the address translation from the iTLB as usual, which uses strong coding for error detection and correction.
  • [ X ]
    Öğe
    Reliable address translation for instructions
    (Institute of Electrical and Electronics Engineers Inc., 2016) Kadayif, Ismail; Ugurlu, Bora
    As a result of technology scaling, spatial multi-bit soft errors have been becoming a big concern for SRAM-based storage structures, such as caches, buffers, and register files, in the design of reliable computer systems. Conventional techniques, such as bit interleaving or stronger coding, cannot provide the designers with effective solutions to the problem of reliable address generation in instruction translation lookaside buffers (iTLB) because of high power and/or latency overheads. In this study, we aim to generate reliable address translation for instructions without compromising either on performance or on power consumption. To do so, we propose to use a pair of identical registers storing the last address translation, which are referred to as context frame registers (CFR). As long as the control flow of programs stays in the same page, address translations are supplied by these two registers, instead of the iTLB. Since two CFRs keep the same address translation, spatial multi-bit errors are detected by comparing their contents. If their contents do not match, we obtain the address translation from the iTLB as usual, which uses strong coding for error detection and correction. © 2015 Chamber of Electrical Engineers of Turkey.