Search

Son yıllarda çocuk güvenliğinde yaşanan kazaların artması nedeniyle iç mekanlarda çocukların yerini tespit etme çalışmaları önem kazanmıştır. Bu çalışmada kablosuz sinyal gücü ve Destek Vektör Makineleri sınıflandırma algoritması kullanılarak iç mekanlarda farklı odalarda bulunan insanların konumları tespit edilmiştir. Algoritmanın performansının arttırılması için farklı çekirdek fonksiyonları denenmiş ve çekirdek fonksiyonu seçiminin algoritmanın sınıflandırma performansına etkisi incelenmiştir. Performans ölçüm yöntemi olarak 10 kat çapraz doğrulama yöntemi kullanılmıştır. Performans değerlendirmesi, çapraz doğrulama öncesi ve sonrası sınıflandırma performansları karşılaştırılarak yapılmıştır. Yapılan performans değerlendirmesi sonucu iç mekanda konum belirlemede Destek Vektör Makineleri algoritması kullanılırken doğrusal çekirdek fonksiyonunun seçimi uygun görülmüştür.

Microwave spectroscopy method has become widespread in many applications including liquid classification. In this study, a microwave spectroscopy system that can classify liquids without opening the lid of their containers is proposed. Thus, the operators are prevented from being exposed to harmful substances and wasting time. Everyday liquids such as carbonated drinks, fruit juices, shampoo, cream and alcoholic beverages and hazardous liquids were characterized remotely by the microwave spectroscopy method in which spectroscopic signatures of a total of 52 liquids were used. In order to be able to classify liquids with the highest accuracy, it is also important to determine the most suitable measurement system as well as the correct selection of the classification algorithm and algorithm parameters that show the best performance. In this study, Support Vector Machines algorithm, which is a very successful algorithm in separating binary classes, is used. In addition, the effects of the algorithm on the classification performance have been examined using different kernel functions and cross-validation technique has been used for the performance analysis. As a result of the performance analysis, it is seen that up to 100% success can be achieved when linear or polynomial kernel functions have been preferred.

The purpose of occupational health and safety studies is to protect employees from work accidents and occupational diseases and to ensure that they work in a healthy environment. Most of the work accidents happen as a result of wrong storage, transportation and use of chemicals. In order to protect employees from chemical hazards and eliminate their possible risks, a risk assessment should first be carried out. Based on the results of the risk assessment, if not done before, bottles that contain hazardous chemicals must be classified and labelled according to their risk levels. The labels of bottles that contain chemical liquids must be checked and if the labels are worn or unreadable, they must be renewed. After these have been done, hazardous chemical liquids must be classified, stored and transported according to these labels. In this study, a non-contact, liquid measurement system based on microwave data is proposed to detect hazardous liquids. In order to select the most suitable algorithm for use in this measurement system, 3 different classification algorithms have been used and the performance analysis of the algorithms has made. In the study, 3 different classification processes have been applied according to the chemical properties of the liquids. It has been observed that Random Tree algorithm has achieved the best performance while Rep Tree algorithm has done the worst performance. Using this system, hazardous chemical liquids can be detected without opening the cover of the bottles that contain the liquids. Therefore, it can be used to quickly label hazardous liquids for their safe storage and transportation.

Detection of hazardous liquids used in explosive production is important in terms of public safety and health. Because many threats can be prevented by detecting these liquids at security controls points. As existing methods have some disadvantages in terms of accuracy, practicality or reliability, there is a demand for new methods for hazardous liquid detection. In this paper, a circular patch antenna for hazardous liquid detection was designed and by connecting to a vector network analyzer a group of measurements was made. Then, this dataset was used by hierarchical clustering algorithms employed in this study to detect hazardous liquids. The results show that high classification accuracy can be achieved when Ward linkage method is preferred.

Optical burst switching networks are vulnerable to various threats including Burst Header Packet Flooding attack, Circulating Burst Header attack, Address Spoofing, and Replay attack. Therefore, detecting such threats play a key role in taking appropriate security measures. One of the major challenges in identifying the risks of Burst Header Packet flooding attacks is the lack or insufficiency of reliable historical data. In this paper, firstly, Burst Header Packet flooding attacks are classified into four categories, Misbehaving-Block, Behaving-No Block, Misbehaving-No Block and Misbehaving-Wait, using Naive Bayes and K-Nearest Neighbor algorithms. Using performance metrics obtained both after testing on the same set and after applying 10-fold cross validation, the performance of Naive Bayes and K-Nearest Neighbor algorithms is compared based on commonly used performance metrics. As the results show, compared to Naive Bayes, K-Nearest Neighbor algorithm is more suitable for predicting Burst Header Packet Flooding attacks.

Usage of complex words causes significant problems not only in reading but in writing as well and eventually leads to poor academic achievement of students, poorer particularly for hearing impaired children. The dual diagnosis of Autism Spectrum Disorder (ASD) and hearing impairment pose additional challenges mainly due to the difficulties that come with making accurate decisions. Hence, parents must be provided with the information about the signs and symptoms of ASD and deafness or partial hearing loss, as well as appropriate intervention strategies. Although different learning activities can be used to enlarge such children’s vocabulary, if the presented words are difficult to learn, it will be very hard to realize this. Identifying difficult words and replacing them with simple ones both make the readability of a text easier and help such children enhance their vocabulary knowledge in a shorter period of time. Therefore, in this study we propose a classification approach that identifies difficult words among a given set of words in English. The lexical and semantic features of the words in the dataset were extracted based on the language rules specific to hearing impaired children. In the classification approach, five popular classification algorithms were used and the algorithms' performance in identifying difficult words was evaluated using various performance metrics. As the results show, the K-Nearest Neighbors algorithm is the most suitable algorithm for identifying difficult words in English for the target group.

Omuz protezlerinin zamanla farklı nedenlerden dolayı bakımının yapılması ya da değiştirilmesi gerekebilir. Bu bakım işlemleri yine ameliyatlarla yapılır. Farklı türlerde ve farklı üreticiler tarafından üretilmiş omuz protezleri bulunmaktadır ve her birinin çıkarılmasında ve bakımının yapılmasında farklı ekipmanlar kullanılması gereklidir. Protez türü ile ilgili yeterli bilginin sağlanamadığı durumlarda bazı sorunlar ile karşılaşılabilir. Radyografi görüntülerinin görsel muayenesi ve karşılaştırılmasının uzmanlar tarafından yapılması hem yorucudur hem de süreci uzatır. Ameliyattan önce doğru donanım ve prosedürlerin seçilmesi için ameliyatı gerçekleştirecek olan cerraha bilinmeyen protezleri tanımada yardımcı olacak, hızlı ve yüksek doğruluk oranına sahip bir çözüme ihtiyaç duyulmaktadır. Bu çalışmada 3 farklı üreticiye ait omuz protezlerinin radyografi görüntülerinden tanınması için 12 farklı sınıflandırma algoritması kullanılmış ve bu algoritmaların performansları karşılaştırılmıştır. K-En Yakın Komşu algoritmasının diğer algoritmalara göre daha iyi performans sergilediği görülmüştür. Radyografi görüntülerinden protez tanımada bu algoritmanın kullanılmasının doğru tercih olacağı ve diğer protez türlerini tanımada da kullanılabileceği düşünülmektedir.