Yazar "Basciftci, Fatih" seçeneğine göre listele
Listeleniyor 1 - 20 / 24
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Design of Web-Based Fuzzy Input Expert System for the Analysis of Serology Laboratory Tests(SPRINGER, 2012) Basciftci, Fatih; Incekara, HayriIn this study, it is aimed, using the Web-based Expert System with Fuzzy Input (WESFI), to convert the patients' (users') Serology Laboratory Tests (SLT) results to linguistic statements (low, normal, high) and analyzing those, give a feedback to the user (patient) of the potential signs of disease. The feedbacks given to the patients are the existing interpretations in the database, which were prepared by doctors before. Furthermore, the SLT terms (Brucella Coombs, Ama, P-Protein etc.) are explained in a way that the user can understand. The WESFI is published with an interface on the web environment. In order to determine the rate of the success of the WESFI, users evaluated the system answering the "How do you find the evaluation?" question. The question has been answered by 461 users. As a result it is observed that 90% of female users, 92% of male users and 91% of all users found the system useful.Öğe Designing medical expert system based on logical reduced rule for basic malaria diagnosis from malaria signs and symptoms(EMERALD GROUP PUBLISHING LTD, 2017) Selek, Murat; Basciftci, Fatih; Orucu, SerkanPurpose - Malaria is one of the most sinister life-threatening disease and generally transmitted by the bite of an Anopheles mosquito which was infected. These mosquitoes carry the Plasmodium parasite. Worldwide risk of malaria thread is very hard to deal, because of extreme temperature and climate changes which lead to uncontrolled changes in the mosquito population, as many deaths from malaria occur outside the healthcare system and other infections might be misdiagnosed as malaria unless a diagnostic test is done. The purpose of this study is creating a system which is early diagnosing malaria for settlements adequate healthcare units and non-immune travellers. Design/methodology/approach - In this study's system, the authors developed a new medical expert system (MES) process using the decreased rule base to detect malaria. The authors' purpose was to successfully identify the illness by taking all symptoms of malaria into consideration in the MES (six basic signs, 64 different conditions). In the proposed MES process, in place of inspecting all the malaria-related signs, the authors used the decreased rule bases. Findings - So as to take the lessen decreased bases, Boolean functions are used in a two-level simplification method. Using this method, decreased cases were evaluated by taking six symptoms of malaria into account instead of assessing 64 individual conditions. Research limitations/implications - The system can be used in diagnosis of asthma and chronic obstructive respiratory disease. Practical implications - The system can be used in absence of adequate healthcare units. Thus, malaria can be diagnosed early. Originality/value - The authors hope that the system they have developed will be useful for settlements in the absence of adequate healthcare units and non-immune travellers.Öğe Determination age and gender with developed a novel algorithm in image processing techniques by implementing to dental X-ray images(ROMANIAN LEGAL MED SOC, 2018) Avuclu, Emre; Basciftci, FatihAge determination process is very important in legal medicine and forensic sciences. After a massive disaster or a legal situation, identification may be required. Age determination process is requested from the forensic medicine institute for live or dead body. In such cases, age determination process must be done correctly. In this study, a database was created with a total of 1313 panoramic dental images to determine age and gender. The images in this database are stored in different 6 folders (M1, M2, M3, M4, M5, M6) by preprocessing with image processing techniques. The calculation of the morphological properties of teeth in this folder (height, area, perimeter, similarity, center of gravity, radius of teeth) are stored separately in XML files (XML1, XML2, XML3, XML4, XML5, XML6). In order to obtain better results in determining age and gender, a novel and originally developed algorithm has been applied to the trapezoidal images in the database. Morphological measurement comparisons were made by testing the teeth with height, area, perimeter, radius, similarity ratio, center of gravity information separately. Thanks to the new and originally developed algorithms, the age determination process was performed with an error of +-1 years in general. In addition to the age determination process, gender determination was also performed. In this study, a multi-disciplinary study was performed to determine the age and gender from dental x-ray images.Öğe Face to Recognize and Position Reporting System Design(Selçuk Üniversitesi, 2015) Avuclu, Emre; Basciftci, FatihThe This study is designed to find lost on a system. There are two main components in the system. The first application on the computer, the second robot swims in the outside world. Pictures of missing persons will be saved in the application. WiFi camera on the robot is put into application in the image center. Application matches the registered face images with a face in the coming images. A result of the pairing, alerts application. The location information of the robot can be learned.Öğe Fast computation of the prime implicants by exact direct-cover algorithm based on the new partial ordering operation rule(ELSEVIER SCI LTD, 2011) Basciftci, Fatih; Kahramanli, SirzatIn this study, a novel OFF-set based direct-cover Exact Minimization Algorithm (EMA) is proposed for single-output Boolean functions represented in a sum-of-products form. To obtain the complete set of prime implicants covering the given Target Minterm (ON-minterm), the proposed method uses OFF-cubes (OFF-minterms) expanded by this Target Minterm. The amount of temporary results produced by this method does not exceed the size of the OFF-set. In order to achieve the goal of this study, which is to make faster computations, logic operations were used instead of the standard operations. Expansion OFF-cubes, commutative absorption operations and intersection operations are realized by logic operations for fast computation. The proposed minimization method is tested on several classes of benchmarks and then compared with the ESPRESSO algorithm. The results show that the proposed algorithm obtains more accurate and faster results than ESPRESSO does. (C) 2011 Elsevier Ltd. All rights reserved.Öğe An interactive and multi-functional refreshable Braille device for the visually impaired(ELSEVIER, 2016) Basciftci, Fatih; Eldem, AyseAlthough visually impaired people are generally considered to be dependent and helpless people, they actually share the same characteristics as other people. Thanks to the Braille alphabet, which has been developed to reduce inequality of opportunity to minimum, their lives become a little bit easier. Besides Braille alphabet, there are many devices and software developed for visually impaired people. In this study, a readable, vocalized and refreshable Braille device, which can ease the lives of visually impaired people, has been developed. The results of the tests on this device with 20 visually-impaired people whose ages ranged between 5 and 15 and who do not know the Braille alphabet indicated the usability rate of this device to be 81.8%. The usability rate of the device was found to be 97.16% in the tests with 30 visually-impaired people whose ages ranged between 10 and 33 and who know the Braille alphabet. The durability test of the device indicated that Braille cells worked with 100% efficiency in the trials from 50 characters to 4000 characters. The device was superior both in terms of features and 35% cheaper compared to the ones available on the market. Besides, it was determined that USB connection transmitted data faster compared to the Bluetooth connection. (C) 2015 Elsevier B.V. All rights reserved.Öğe A logic method for efficient reduction of the space complexity of the attribute reduction problem(TUBITAK SCIENTIFIC & TECHNICAL RESEARCH COUNCIL TURKEY, 2011) Hacibeyoglu, Mehmet; Basciftci, Fatih; Kahramanli, SirzatThe goal of attribute reduction is to find a minimal subset (MS) R of the condition attribute set C of a dataset such that R has the same classification power as C. It was proved that the number of MSs for a dataset with n attributes may be as large as ((n)(n/2)) and the generation of all of them is an NP-hard problem. The main reason for this is the intractable space complexity of the conversion of the discernibility function (DF) of a dataset to the disjunctive normal form (DNF). Our analysis of many DF-to-DNF conversion processes showed that approximately (1 - 2/((n)(n/2)) x 100) % of the implicants generated in the DF-to-DNF process are redundant ones. We prevented their generation based on the Boolean inverse distribution law. Due to this property, the proposed method generates 0.5 x ((n)(n/2)) times fewer implicants than other Boolean logic-based attribute reduction methods. Hence, it can process most of the datasets that cannot be processed by other attribute reduction methods.Öğe A Logic Simplification Based on Expert System Application for TBC Diagnosis(SPRINGER, 2011) Sumbul, Harun; Basciftci, FatihTuberculosis (TBC), caused by the bacterium My tuberculosis (Mtb), is a growing international health crisis [1]. TBC is one of the main causes of death produced by infectious illness and is responsible for almost 3 millions deaths every year [2]. In this study, a controlled Expert System (ES) have designed to diagnosis of TBC and truth table have created by considering the probabilities of TBC (12 symptom, 2(12)=4096 different cases). According to the probabilities of TBC, 6 different cases have accepted as output values and reduced rule bases have obtained. These output values have been processed by an ES and have tried to diagnosis of TBC with help to ES. We obtained very good results and the results of analyses carried out indicated that controls performed with ES provide less time, less probability, reliable and consistent diagnosis and that are feasible in real life.Öğe Meeting a dwelling's energy need with solar energy: An application study from Turkey(ELSEVIER SCIENCE BV, 2014) Karaca, Celal; Basciftci, FatihElectricity generation and having energy resources are one of the most important issue for societies from past to these days. Fossil fuels that providing three quarters of world's basic energy needs cause global warming with greenhouse gases becomes progressively smaller as well. Energy consumption is constantly increasing in parallel with population growth in the world, urbanization, industrialization and expansion of technology. While fossil fuels are quickly running out, energy demand is increasing rapidly. It is assumed that Petroleum is getting run out 2050 years. Natural gas and coal will have reserve until 2050 and 2150. In addition, the uses of fossil fuels have many negative effects to our environment. Cities are covered with black exhalations and sometimes it is hard to breathe because of air pollution. The Ozone layer has pierced and has became unable to fulfill the task of filtering. We have started to feel the effects of global warming strongly with each passing day. In such an environment, electricity generation with solar energy is becoming really important which is an endless source of clean energy. However, Dwellings to fulfill their own electricity need contribute significantly to environmental pollution and energy production. In this study, meeting a dwelling's energy need with clean energy that is one of the future energy generation methods has been examined. A system which generates electricity from solar energy was designed for this purpose. In this study we want to show the applicability of solar energy system at houses and make a practice about cost and productivity analyses. (C) 2013 The Authors. Published by Elsevier Ltd.Öğe A new approach to minimize the loss of life after natural hazards by using Android operating system(SPRINGER, 2018) Avuclu, Emre; Basciftci, FatihNowadays, the usage rates of smartphones are increasing rapidly. With the versatility of its features, smartphones have succeeded in attracting users. Performing this study has also affected the usage rate of smartphones every day. It is possible to determine the position with GPS (Global Positioning System) technology which is located in smartphones. In this study, smartphone location notification was used to detect the locations of the people who were under debris after the earthquake by means of the phones on them. People who cannot be reached for any reason will be immediately identified, and emergency interventions will be possible. Thus, the survival rate of the injured will be high with early intervention. In this study, it was aimed to minimize the loss of life after the earthquake and all the negativities that would be experienced in society due to this loss. The developed application has been tested in the external world, and the obtained data are given in results section.Öğe New approaches to determine age and gender in image processing techniques using multilayer perceptron neural network(ELSEVIER, 2018) Avuclu, Emre; Basciftci, FatihAs a result of some events (disasters, inheritance, disappearances etc.), age and gender determination can be vital for people. Forensic medical institutions make the determination of age by examining the structures such as teeth and bones. Procedures for forensic science are currently estimated manually according to certain morphological findings on the tooth. In this study, 1313 panoramic dental images were used automatically to estimate age. Image preprocessing is applied on these images. Trapezoidal teeth are corrected in the coordinate plane to obtain more accurate and standard results. In the study, the correction process is done with original and novel developed algorithm. Dental images are automatically and dynamically segmented and feature vectors are created by extracting their features. The generated feature vectors are dynamic and presented as inputs to the Multilayer Perceptron Neural Network. Depending on the request, the number of input count reduction process can be performed. In this study, age and gender were determined from dental x-ray images with novel and originally developed algorithm. The application is written in C # programming language. In some tooth groups, the highest classification rate of 100% and age determination with 0 error were performed. With this study, age determination in forensic science will be more accurate. (C) 2018 Elsevier B.V. All rights reserved.Öğe A new method based on cube algebra for the simplification of logic functions(SPRINGER HEIDELBERG, 2007) Kahramanli, Sirzat; Guenes, Salih; Sahan, Seral; Basciftci, FatihIn this study an Off-set based direct-cover minimization method for single-output logic functions is proposed represented in a sum-of-products form. To find the sufficient set of prime implicants including the given On-cube with the existing direct-cover minimization methods, this cube is expanded for one coordinate at a time. The correctness of each expansion is controlled by the way in which the cube being expanded intersects with all of K < 2(n) Off-cubes. If we take into consideration that the expanding of one cube has a polynomial complexity, then the total complexity of this approach can be expressed as O(n(p))O(2(n)), that is, the product of polynomial and exponential complexities. To obtain the complete set of prime implicants including the given On-cube, the proposed method uses Off-cubes expanded by this On-cube. The complexity of this operation is approximately equivalent to the complexity of an intersection of one On-cube expanded by existing methods for one coordinate. Therefore, the complexity of the process of calculating of the complete set of prime implicants including given On-cube is reduced approximately to O(n(p)) times. The method is tested on several different kinds of problems and on standard MCNC benchmarks, results of which are compared with ESPRESSO.Öğe A new suggestion for an irrigation schedule with an artificial neural network(TAYLOR & FRANCIS LTD, 2013) Karasekreter, Naim; Basciftci, Fatih; Fidan, UgurThis study used artificial neural networks (ANNs) to propose a new system of irrigation ratios and time intervals. Data on soil moisture, soil type, product type and time interval were used as input parameters for the ANN and the network was trained through the Levenberg-Marquardt learning algorithm. The outputs of the model determined the water requirement of the plant and the irrigation time intervals. The aim of this study is to perform irrigation at night, to reduce water losses from evaporation and thereby promote water conservation. In addition, the study aimed to save on energy, as less irrigation would be provided compared to daytime irrigation. The system was tested in a strawberry orchard of 1000 m(2) in the Serik district of Antalya, Turkey. The trial achieved a 20.46% water saving and 23.9% energy saving.Öğe A NOVEL APPROACH FOR FAST COVERING THE BOOLEAN SETS(WORLD SCIENTIFIC AND ENGINEERING ACAD AND SOC, 2008) Basciftci, Fatih; Kahramanli, SirzatIn this study we propose a new method for iteratively covering given Boolean data set by its prime implicants identified one at a time. In contrast to existing set covering methods of NP time complexity in the size of the set, our method is realized by procedures of linear complexity and therefore its efficiency is rapidly increased by increasing the size of the set. Our method can be useful in all fields related to Boolean data sets processing such as logic synthesis, image processing, data compressing, artificial intelligence and many others.Öğe An off-cubes expanding approach to the problem of separate determination of the essential prime implicants of the single-output Boolean functions(IEEE, 2007) Basciftci, Fatih; Kahramanli, SirzatThe goal of this study is the avoidance of excessive amount of temporary results produced during the minimization process of the two-level single-output Boolean functions of many variables. In this paper we have proposed an Off-set based-direct cover minimization method that uses a single On-cube oriented expanding of the Off-cubes on which the essential prime implicants are identified in a one by one manner and are used for iterative covering the function being minimized. The amount of temporary results produced by this method does not exceed the size of the Offset. The proposed algorithm is up to 3 times faster and uses significantly less amount of memory than well known ESPRESSO.Öğe A REDUCED OFFSET BASED METHOD FOR FAST COMPUTATION OF THE PRIME IMPLICANTS COVERING A GIVEN CUBE(ICIC INTERNATIONAL, 2012) Basciftci, Fatih; Kahramanli, Sirzat; Selek, MuratIn order to generate prime implicants for a cube of a logic function, most logic minimization methods expand this cube by one at a time removing the literals from it. However, there is an intractable problem of determining the order of literals to be removed from the cube and checking whether a tentative literal removal is acceptable. In order to avoid this problem, the reduced offset method was developed. This method uses the positional-cube notation where every reduced off-cube of an n-variable function is represented by two n-bit strings. However, unfortunately, the conversion of such reduced cubes to the associated prime implicants has the time complexity worse than exponential. To avoid this problem, in this study, the method representing every reduced cube by a single n-bit string and a set of bitwise operations to be performed on such strings are proposed. The theoretical and experimental estimations show that this approach can significantly improve the quality of results and reduce the space and time complexities of the logic minimization process 2 times and up to 3.5 times, respectively.Öğe A reduced rule-based expert system by the simplification of logic functions for determining the life expectancy of intensive care patients(EMERALD GROUP PUBLISHING LTD, 2017) Cizmeci, Inayet Hakki; Basciftci, FatihPurpose - Specialist physicians, specialist nurses and personnel in the intensive care unit (ICU) work to treat patients. Compared with other hospital units, ICUs are full-fledged and provide 24-h services. However, patients are admitted to this unit because of conditions such as severe trauma, organ failure or dysfunction and poisoning. The life expectancy of such patients is considerably low. Design/methodology/approach - This study developed a reduced rule-based expert system to determine life expectancy. The purpose of this study is to determine the life expectancy of patients using ten variables. The rules were determined by evaluating 210 = 1,024 results. These rules were minimized using Boolean rules for simplification. Findings - Conclusions were drawn by evaluating the minimized cases rather than evaluating 1,024 different cases. ICU patients were evaluated using this method, and the mean success rate was 63.75 per cent. Originality/value - No rule-based expert system has been designed to determine the death risks of patients in the ICU.Öğe Reduced-rule based expert system by the simplification of logic functions for the diagnosis of diabetes(PERGAMON-ELSEVIER SCIENCE LTD, 2011) Basciftci, Fatih; Hatay, Omer FarukDiabetes is a chronic and complex endocrine disease with metabolic disorders caused by the imbalance between secreted and needed insulin levels. In the present study, all probabilities were examined considering ten (10) indications (2(10)=1024 different cases) of diabetes using medical expert system (MES), and accordingly, a truth table was established. This table was simplified by the simplification method of logic functions. 15 main rules were obtained using minimization method for Boolean Functions (BFs). These rules established rules base of ES. Subsequently, the parameters of 768 patients were compared with this ES. Accuracy rate of the estimations of MES, created as a result these comparisons, was determined as 97.13% in diabetes patients, 97% in non-diabetes patients, 96.5% in Type 1 patients, 98.26% in Type 2 patients and 97.44% in pregnant patients. (C) 2011 Elsevier Ltd. All rights reserved.Öğe REST API Based Image Processing Interactive Person Tracking Application(IEEE, 2017) Balga, Mevlut Kagan; Basciftci, FatihIn today's conditions, parents have to work for home economics. For this reason, it is not always possible for parents to meet their children's needs, to protect them from dangers and to help them. Parents agree with a fee-paying caregiver to ensure that their children's needs are provided. Looking after a child by a caregiver can create a variety of security problems for the mother and the father. In addition, because of the child's development levels, there is always the possibility of encountering an extreme situation everywhere. This project has been developed for observing Alzheimer's patients as well as children. Alzheimer's disease is a disorder of phases. The individual with this disorder is in need of care after a certain level. For this reason, observation of the individuals with this disease and their caregivers is also important for safety. In this completed project, Raspberry Pi microcomputer has been used. A camera has been placed on the chest line. An image is taken every 5 minutes by the camera. This image is transferred to the REST API based web service. In addition, facial analysis has been performed on the photographs using image processing techniques. The faces found have been stored in a separate directory on the REST API based web service. The SIM808 GSM / GPS module has been used to enable the system to be active everywhere. Family members can follow the images transferred by the module with the help of the user panel in the web service.Öğe Simplification of single-output Boolean functions by exact direct cover algorithm based on cube algebra(IEEE, 2007) Basciftci, FatihDue to the nature of the exact two-level Boolean functions minimization methods most of practical applications rely on heuristic ones that are generally realized by a three step cyclic algorithm. First, the algorithm selects an On-minterm and it generates the set of prime implicants for this On-minterm; second, it determinates the essential prime implicant from among the generated prime implicants; and third, it performs a covering operation. The goal of this study, if the determination of the essential prime implicant is impossible, postponed the selection of essential prime implicant for this On-minterm and save it for a status word. When a new essential prime implicant determined, retrieve the status word. The proposed minimization algorithm is tested on several different kinds of problems and on standard MCNC benchmarks results of which are compared with ESPRESSO. The results show that proposed algorithm obtains exact results and faster than ESPRESSO.
