Metaheuristics under the swarm intelligence (SI) class have proven to be efficient and have become popular methods for solving different optimization problems. Based on the usage of memory, metaheuristics can be classified into algorithms with memory and without memory (memory-less). The absence of memory in some metaheuristics will lead to the loss of the information gained in previous iterations. The metaheuristics tend to divert from promising areas of solutions search spaces which will lead to non-optimal solutions. This paper aims to review memory usage and its effect on the performance of the main SI-based metaheuristics. Investigation has been performed on SI metaheuristics, memory usage and memory-less metaheuristics, memory char

Recently, the environmental isotopes are adopted to figure out the hydrological processes, recharge areas, flow paths, groundwater origin and the interaction between different watery bodies. Currently, five samples of the rainwater have been collected since January to April 2012, as well as December 2011. Those sampling periods have highest amounts of precipitation events. Meantime, 25 samples of groundwater, 5 of the Lesser Zab River and 3 of overland flow have been picked up during the wet period. The dry sampling of groundwater and the Lesser Zab River has been achieved in summer 2011. The Local Meteoric Water Line lies between Global Meteoric Water Line (GMWL) and East Mediterranean Water Line (EMWL). The lowest, highest and

The studied succession is deposited during late Berriasian-Aptian interval, which is represented by the Zubair, Ratawi, Yamama formations. The present study includes stratigraphic development and basin analysis for 21 boreholes (Rachi-1, 2; Rifaei-1, Diwan- 1; Ratawi-1, 2; Halfaia-5; West Qurna 12, 15; Nahr Umr-7,8; Zubair-47,49; North Rumaila- 72, 131, 158; Suba-7; Majnoon-2, 3 and Luhais-2, 12) distributed within 13 oil fields in the southern Iraq. The back-stripping process determined the original direction of basin depocenter for the studied succession. The Yamama basin in the study area stretches from southeast to southwest with single depocenters, it was located in the southeast of the study area near wells Mj-2, Mj-3.NR-8 and

The aim of the current paper is to resolve the non-uniqueness in gravity interpretation through searching for singular points in the gravity field that are coincide with causative body vertices. The Absolute Second Horizontal Gradient (ASHG) method is used to locate the horizontal reference location of the body, while its amplitude could be used to define body corner depth. Intelligent use of the ASHG method could help in differentiating between basin and intrusion structures from their gravity effect and could facilitate the interpretation in forward modeling and constrain inversion modeling to maximum limit. The method is tested by using many synthetic examples with different types of shapes. A real data is used to examine the method a

The middle Cenomanian – early Turonian Mishrif Formation, a major carbonate reservoir unit in southern Iraq, was studied using cuttings and core samples and wireline logs (gamma‐ray, density and sonic) from 66 wells at 15 oilfields. Depositional facies ranging from deep marine to tidal flat were recorded. Microfacies interpretations together with wireline log interpretations show that the formation is composed of transgressive and regressive hemicycles. The regressive hemicycles are interpreted to indicate the progradation of rudist lithosomes (highstand systems tract deposits) towards distal basinal locations such as the Kumait, Luhais and Abu Amood oilfield areas. Transgressive hemicycles (transgressive systems tract deposits)

In this paper, we used four classification methods to classify objects and compareamong these methods, these are K Nearest Neighbor's (KNN), Stochastic Gradient Descentlearning (SGD), Logistic Regression Algorithm(LR), and Multi-Layer Perceptron (MLP). Weused MCOCO dataset for classification and detection the objects, these dataset image wererandomly divided into training and testing datasets at a ratio of 7:3, respectively. In randomlyselect training and testing dataset images, converted the color images to the gray level, thenenhancement these gray images using the histogram equalization method, resize (20 x 20) fordataset image. Principal component analysis (PCA) was used for feature extraction, andfinally apply four classification metho

This paper presents a method to classify colored textural images of skin tissues. Since medical images havehighly heterogeneity, the development of reliable skin-cancer detection process is difficult, and a mono fractaldimension is not sufficient to classify images of this nature. A multifractal-based feature vectors are suggested hereas an alternative and more effective tool. At the same time multiple color channels are used to get more descriptivefeatures.Two multifractal based set of features are suggested here. The first set measures the local roughness property, whilethe second set measure the local contrast property.A combination of all the extracted features from the three colormodels gives a highest classification accuracy with 99.4

Secure data communication across networks is always threatened with intrusion and abuse. Network Intrusion Detection System (IDS) is a valuable tool for in-depth defense of computer networks. Most research and applications in the field of intrusion detection systems was built based on analysing the several datasets that contain the attacks types using the classification of batch learning machine. The present study presents the intrusion detection system based on Data Stream Classification. Several data stream algorithms were applied on CICIDS2017 datasets which contain several new types of attacks. The results were evaluated to choose the best algorithm that satisfies high accuracy and low computation time.

Machine learning (ML) is a key component within the broader field of artificial intelligence (AI) that employs statistical methods to empower computers with the ability to learn and make decisions autonomously, without the need for explicit programming. It is founded on the concept that computers can acquire knowledge from data, identify patterns, and draw conclusions with minimal human intervention. The main categories of ML include supervised learning, unsupervised learning, semisupervised learning, and reinforcement learning. Supervised learning involves training models using labelled datasets and comprises two primary forms: classification and regression. Regression is used for continuous output, while classification is employed