Computer-aided diagnosis (CAD) has proved to be an effective and accurate method for diagnostic prediction over the years. This article focuses on the development of an automated CAD system with the intent to perform diagnosis as accurately as possible. Deep learning methods have been able to produce impressive results on medical image datasets. This study employs deep learning methods in conjunction with meta-heuristic algorithms and supervised machine-learning algorithms to perform an accurate diagnosis. Pre-trained convolutional neural networks (CNNs) or auto-encoder are used for feature extraction, whereas feature selection is performed using an ant colony optimization (ACO) algorithm. Ant colony optimization helps to search for the bes

The study showed flow rates and the interaction between the settlements served by applying the model of gravity theory to measure depending on the number of the population between city Najaf and the rest of the other settlements served and using three functions of disability, time and cost, as recorded an increase in the interaction index with some settlements like them Kufa, Abbasid and Manathira, while the indicator contrast was in other settlements, either when the application of the gravity model depending on trips and socio-economic characteristics accuracy rate was more pronounced.

<p>Energy and memory limitations are considerable constraints of sensor nodes in wireless sensor networks (WSNs). The limited energy supplied to network nodes causes WSNs to face crucial functional limitations. Therefore, the problem of limited energy resource on sensor nodes can only be addressed by using them efficiently. In this research work, an energy-balancing routing scheme for in-network data aggregation is presented. This scheme is referred to as Energy-aware and load-Balancing Routing scheme for Data Aggregation (hereinafter referred to as EBR-DA). The EBRDA aims to provide an energy efficient multiple-hop routing to the destination on the basis of the quality of the links between the source and destination. In

Wildfire risk has globally increased during the past few years due to several factors. An efficient and fast response to wildfires is extremely important to reduce the damaging effect on humans and wildlife. This work introduces a methodology for designing an efficient machine learning system to detect wildfires using satellite imagery. A convolutional neural network (CNN) model is optimized to reduce the required computational resources. Due to the limitations of images containing fire and seasonal variations, an image augmentation process is used to develop adequate training samples for the change in the forest’s visual features and the seasonal wind direction at the study area during the fire season. The selected CNN model (Mob

The research aimed to identify smart management capabilities of secondary school principals in education directorates in Baghdad according to the administrative intelligent and leadership competencies. The study used incentives as a descriptive method, by analyzing five main areas of smart management: strategic planning, self-awareness, skills, organization and culture. A purposive sample consisting of 102 secondary school principals from education directorates (Rusafa1) and (Karkh2), was taken to fill questionnaire the latter representing a complete sample of the target population. validated has been built an advanced measurement tool composed of 56 items across the five domains of strategic planning (21%), self-awareness (21%), culture (2

The study addressed the change in the nature of the land cover of the Al-Jadriya Twist area for the period from 1976-2024 with an area of (140 km2)and for a period of (48 years) based on satellite images and their analysis using geographic information systems. The main classifications of the area were reached (water cover, residential areas, vegetation cover, in addition to empty, unused areas). The extracted data indicate a decrease in the water cover and the change rate reached (-14.29) and the residential areas increased with a change rate of (28.26), while the vegetation cover rate was recorded from (45 km2) to (66 km2) and the empty areas had a change rate of (-78.57).

Amplitude variation with offset (AVO) analysis is an 1 efficient tool for hydrocarbon detection and identification of elastic rock properties and fluid types. It has been applied in the present study using reprocessed pre-stack 2D seismic data (1992, Caulerpa) from north-west of the Bonaparte Basin, Australia. The AVO response along the 2D pre-stack seismic data in the Laminaria High NW shelf of Australia was also investigated. Three hypotheses were suggested to investigate the AVO behaviour of the amplitude anomalies in which three different factors; fluid substitution, porosity and thickness (Wedge model) were tested. The AVO models with the synthetic gathers were analysed using log information to find which of these is the

The work reported in this study focusing on the abrasive wear behavior for three types of pipes used in oil industries (Carbone steel, Alloy steel and Stainless steel) using a wear apparatus for dry and wet tests, manufactured according to ASTM G65. Silica sand with
hardness (1000-1100) HV was used as abrasive material. The abrasive wear of these pipes has been measured experimentally by measuring the wear rate for each case under different sliding speeds, applied loads, and sand conditions (dry or wet). All tests have been conducted using sand of particle size (200-425) µm, ambient temperature of 34.5 °C and humidity 22% (Lab conditions).
The results show that the material loss due to abrasive wear increased monotonically with