ABSTRACT

Nineveh province in Iraq has experienced a process of land cover conversion and vegetation loss especially in last decades. It is important to get accurate information on vegetation loss and changes in areas that are used for agriculture. Among the most effective methods to study and get information about this phenomenon is remote sensing technology.Since classical approaches lack of accuracy, artificial intelligence has been introduced to strengthen feature detection which leads to better classification. This paper uses ant colony algorithm to study and classify part of Nineveh province land into six classes. These are Agriculture land/flood plane, Water, Outcrop, Origin of early sand sheet, Desertable area, and Sand dunes. The variation in these six classes from 1987 to 2009 is shown. Results show that agriculture region and flood plain decreased from around 31% in 1987 to 11.2% of total area in 2009 while origin of early sand sheet and desertable area increased from 42.7% to around 49%. Beside that sand dune appears in 2009 to form about 26.47% of total area under study.

One of the key elements of the 5G system is network slicing which is a talented technique to create adapted end-to-end logic network path including dedicated and shared resources. Resources scheduling and distribution of network slices show an essential effect on network performance, resource deployment, and load balancing. This paper compares many resources scheduling schemes in the 5G system with network slicing. We first compare many resource scheduling algorithms, best CQI (BCQI), Round Robin (RR), proportional fair (PF), to assess each scheme performance. Moreover, this paper proposes an adaptive scheduling scheme that dynamically chooses the scheduling algorithm among mentioned schemes to optimize the traffic, user throughput, and cell capacity. Finally, results anticipated assessed and concluded.

Abstract� This paper investigates the use of neural networks to detect and locate early breast cancer using a simple feed-forward back-propagation neural network. In order to test the proposed algorithm, an electromagnetic simulator is used to build a three dimensional breast model. Spherical tumors of radii 1 mm, 2 mm,4 mm, and 5 mm are assumed to be at different locations in the breast model. An ultra-wideband pulse is transmitted towards the breast model and four probes are located around the breast to capture the scattered signals. The collected signals are then analyzed using the neural networks to get useful information concerning the presence or otherwise of the tumor and its location if it does exist. The obtained results from using the proposed method are promising with 100% success in the detection and 95% success in the localization.

This paper presents the effect of rain rate, humidity, and temperature at multiple frequencies in the millimeter-wave band in Mosul city. The fifth-generation has several candidate frequencies above 10 GHz, such as 28, 37, 60, and 73 GHz. The results show that the attenuation due to weather factors does not represent a problem for short distances but Losses increase with frequency, and at a large distance (1 km), they become very large.