Department of Computer Engineering

Human or pedestrian detection is an attractive headline and has been proposed in computer vision and machine learning fields. Real time detection and low power system is a critical challenges. Support Vector Machine algorithm with Histograms of oriented gradients (HOG) feature descriptor is given a high successful result, fast and reliable, for human detection. Therefore, this paper demonstrates how to implement HOG feature descriptor with Support Vector Machine (SVM) using FPGA and presents a report that includes FPGA's resource utilization, time consuming, power consumption and SVM accuracy results.

Changes and progresses in information technologies have played an important role in the development of intelligent vehicle systems in recent years. Driver fatigue is an important factor in vehicle accidents. For this reason, traffic accidents involving driver fatigue and driver carelessness have been followed by researchers. In this article, a Multi-tasking Convulational Neural Network (ConNN *) model is proposed to detect driver drowsiness/fatigue. Eye and mouth characteristics are utilized for driver's behavior model. Changes to these characteristics are used to monitor driver fatigue. With the proposed Multi-task ConNN model, unlike the studies in the literature, both mouth and eye information are classified into a single model at the same time. Driver fatigue is determined by calculating eyes' closure duration/Percentage of eye closure (PERCLOS) and yawning frequency/frequency of mouth (FOM). In this study, the fatigue degree of the driver is divided into 3 classes. The proposed model achieved 98.81% fatigue detection on YawdDD and NthuDDD dataset. The success of the model is presented comparatively.

In this study, linear programming and integer programming methods and their application areas are discussed, and these methods are implemented to stock cutting problem. In the application a new approach is used on solution of two dimensional stock cutting problem and performance of new method is compared to the other methods. The aim of application is to obtain minimal leakage with fastest solution by using sizes, quantities of resource and target stocks, plotting the layout on screen.

Employing CAN in distributed real-time control applications sometimes critically requires increasing the size of distributed area, and communication with both other LANs and independent CAN segments. An interworking device with wireless support to extend CAN segments, utilizing an IEEE 802.11b WLAN is a practical solution for such an industrial environment. A key objective of this research work is to design and implement an interworking device called Wireless Interworking Unit (WIU) enabling remote CAN2.0A nodes to communicate over IEEE 802.11b WLAN using encapsulation method. Computer modeling and simulations of the proposed WIU are carried out using OPNET Modeler. The SAE Benchmark has been utilized in the networking models to evaluate the simulation results obtained. Considering the total end-to-end delay results of especially remote CAN messages for above 40 kbit/s bus rates, effect of the designed WIU is proved not causing to exceed the required arrival time deadline set by the SAE Benchmark.

TDMA Directional antennas MAC QoS WATM With the ever-increasing demand for wireless real-time services and continuing emergence of new multimedia applications especially for mobile users, it is necessary for the network to support various levels of quality of service (QoS) while maximizing the utilization of scarce and expensive wireless channel resources. Considering this fact, a new TDMA/FDD MAC protocol integrating a novel QoS management algorithm and multi-beam Directional Antennas (DAs) to efficiently exploit wireless resources has been developed and presented in this paper. It supports all ATM CBR, VBR, ABR and UBR service classes by adopting a well-managed dynamic guarantee-based QoS scheduling algorithm. The work mainly aims at increasing the wireless system throughput as well as improving the call-blocking ratios and end-to-end delays for real-time applications. This seamless communication enables both handling real-time multimedia traffics in a fair manner and granting call requests on the basis of the connection types. The system has been developed, modeled and simulated using OPNET Modeler. The simulation results show that the QoS-aware TDMA/FDD MAC with multi-beam DAs has substantially increased the system throughput and that the callblocking ratio has been reduced from 86% to 18%, when the proposed MAC with 8-Beam antennas is employed instead of the regular MAC.

Handoff decision making is one of the most important topics in wireless heterogeneous networks architecture as there are many parameters which have to be considered when triggering handoff and selecting suitable access point. More intelligent approaches which reckon user profiles, application requirements, and network conditions must be improved so that desired performance results for both user and network could be provided. In this paper we introduce a new adaptive vertical handoff decision making algorithm in which fuzzy membership functions are optimized by means of genetic algorithm. Genetic algorithm is an adaptive search technique based on natural selection and genetic rules. In addition to that, it takes places in various scientific applications and can be used to adjust the membership functions in fuzzy systems. The purpose of the study is to adjust the shape of fuzzy membership functions, properly, using genetic algorithm in order to achieve optimum handoff performance. The results show that, compared to the several different algorithms performance of the proposed approach with genetic algorithm is significantly improved for both user and network in terms of number of handoff while the other requirements are still satisfied.

Desktop Grids use the computing, network and storage resources from idle desktop PCs distributed over multiple-LANs or the Internet to compute a large variety of resource-demanding distributed applications. While these applications need to access, compute, store and circulate large volumes of data, little attention has been paid to data management in such large-scale, dynamic, heterogeneous, volatile and highly distributed Grids. In most cases, data management relies on ad hoc solutions, and providing a general approach is still a challenging issue. A new class of data management service is desirable to deal with such a variety of file transfer protocols than client/server, P2P or the new and emerging Cloud storage service.

Current wireless networking infrastructure is inadequate for multimedia applications each requiring a different quality of service support. This paper presents recently introduced Wireless ATM technology and its application for transferring data and voice traffic. An example model simulated using a commercial simulation tool followed by the performance analysis of the proposed scheme is also given.

Özet. Bu çalışmanın amacı Ulusal Yazılım Mühendisliği Sempozyumları’nda 2003-2014 yılları arasında yaklaşık on yıllık bir zaman aralığında sunulan bildirilere dayalı olarak Türkiye’deki yazılım mühendisliği alanındaki araştırmaların özelliklerini, yöntemlerini ve genel eğilimlerini belirlemektir. 2003 yılından beri Türkiye’deki yazılım alanındaki araştırmacıları ve organizasyonları bir araya getiren ulusal ölçekteki bu sempozyumda sunulan toplamda 356 bildiri sistematik eşleme yöntemi ile incelenmiştir. En fazla araştırma sunulan yazılım mühendisliği alanları olarak yazılım mühendisliği araç ve yöntemleri, yazılım kalitesi, yazılım mühendisliği süreci ve yazılım tasarımı belirlenmekte, konu olarak da yazılım yaşam döngüsü/mühendisliği, metodlar/teknikler, ürün kalitesi ve süreç yönetimi konuları ile eşleşme görülmektedir. Gerçekleştirilen çalışmalar araştırma yöntemi olarak çoğunlukla durum çalışması, araç geliştirme ve eylem araştırmasını kullanmakta ve kişisel deneyim makalesi ya ...