No abstract

No abstract

Image recognition-based automated disease detection systems play an important role in the early detection of plant leaf diseases. In this study, an apple leaf disease detection system was proposed using Faster Region-Based Convolutional Neural Network (Faster R-CNN) with Inception v2 architecture. Applications for the detection of diseases were carried out in apple orchards in Yalova, Turkey. Leaf images were obtained from different apple orchards for two years. In our observations, it was determined that apple trees of Yalova had black spot (venturia inaequalis) disease. The proposed system in the study detects a large number of leaves in an image, then successfully classifies diseased and healthy ones. The disease detection system trained has achieved an average of 84.5% accuracy.

No abstract

Özetçe-KÇAA'lar farklı aciliyet ve servis kalitesi (Quality of Service, QoS) gereksinimine sahip heterojen trafik taşımaktadır. Kablosuz Algılayıcı Ağlarda (KAA) enerji tüketiminin en aza indirilmesi ihtiyacı önemli olmakla birlikte çoklu ortam uygulamaları için QoS önermekdesteği sunmak; algılayıcı düğümlerin kaynak kısıtları, güvenilir olmayan ortam ve durumu kestirilemez çevre koşullarından dolayı zorluk içermektedir. KÇAA'lar için servis kalitesi farkındalıklı ve öncelik temelli Ortam Erişim Kontrolü (OEK) protokollerine ihtiyaç duyulmaktadır. Bu bildiride önerilen yeni iki aşamalı servis farklılaştırma mekanizması her trafik sınıfı için daha düşük uçtan uca gecikme sağlamakla birlikte acil olan gerçek zamanlı görüntü trafiğine acil olmayan diğer veri trafikğe türlerine kıyaslagöre 4 kat daha düşük ortalama uçtan uca gecikme sağlamaktadır. Önerilen mekanizma özellikle askeri uygulamalarda aciliyet içeren trafiğe KÇAA OEK katmanında QoS desteği sağlamaya odaklanmıştır. Anahtar Kelimeler -KAA, KÇAA, katmanlar arası, servis kalitesi desteği etkileşim, öncelik temelli, OEK, servis farklılaştırma, aciliyet.Abstract-WMSNs carry heterogeneous traffic with different urgency and Qquality of Sservice (QoS) requirements. While the need to minimize the energy consumption is important in wireless sensor networksWSNs, offering QoS support for especially real-time multimedia transmission is a challenging issue due to resource constrained nature structure of sensor nodes, unreliable wireless links and unpredictable environmentals conditions. Currently, there is an emeriging need for new QoS-aware, priority-based Medium Access Control (MAC) protocols on to be employed in WMSNs. The pProposed new two tiered service differentiation mechanism provides about 4 times lower end -to -end latency for urgent real-time video traffic compared to the other data traffic types while as well as providing it can achieve lower better end-to-end latency for each traffic class. Proposed Its mechanism has been fundamentally focused on QoS provisioning at MAC layer for urgent real-time data traffic on especially military applications.

No abstract

Sleep stages are determined firstly for the evaluation of sleep quality and the diagnosis of sleep diseases. The signals, recorded from sensors connected to various parts of the body, such as electroencephalogram (EEG), electrocardiogram (ECG), electrooculogram (EOG) and electromyogram (EMG) are used for this purpose. After the production of affordable wearable EEG devices for individual use, studies have begun to detect sleep stages from a single channel EEG signal. This paper presents an automated system that can perform sleep staging using a single-channel raw EEG signal. A Convolutional Neural Network (CNN) model was trained with the raw EEG signal for sleep stage detection. The use of CNN does not require any feature extraction. The developed CNN model classifies the sleep data sampled at 250 Hz, divided into 30-second segments according to the 5-class sleep staging system. According to the test results, the performance of the proposed system was found to be 93% macro F1 score and 92% accuracy.

A computer system's one of the slowest operation is disk seek operation. Sending out read and write requests to the block devices such as disks as soon as the request arrives results in poor performance. After performing sorting and merging operations, the operating system kernel issues block I/O requests to a disk for improving the overall system performance. The kernel subsystem to perform scheduling the block I/O requests is named as the I/O scheduler. This paper introduces performance comparison and detailed analyses of Deadline, CFQ, Noop and BFQ block I/O schedulers that are contained in the Linux 4.1x kernel. The tests have been carried out on an SSD block device that is common in hardware combinations of both personal and professional use-case scenarios. The performance of the schedulers has been evaluated in terms of throughput. Each scheduler has advantages in different use-case scenarios and provides better throughput in a suitable environment.