BP algorithm is the most widely used supervised training algorithms for multi-layered feedforward neural net works. However, BP takes long time to converge and quite sensitive to the initial weights of a network. In this paper, a modified cuckoo search algorithm is used to get the optimal set of initial weights that will be used by BP algorithm. And changing the value of BP learning rate to improve the error convergence. The performance of the proposed hybrid algorithm is compared with the stan dard BP using simple data sets. The simulation result show that the proposed algorithm has improved the BP training in terms of quick convergence of the solution depending on the slope of the error graph.
Finding a path solution in a dynamic environment represents a challenge for the robotics researchers, furthermore, it is the main issue for autonomous robots and manipulators since nowadays the world is looking forward to this challenge. The collision free path for robot in an environment with moving obstacles such as different objects, humans, animals or other robots is considered as an actual problem that needs to be solved. In addition, the local minima and sharp edges are the most common problems in all path planning algorithms. The main objective of this work is to overcome these problems by demonstrating the robot path planning and obstacle avoidance using D star (D*) algorithm based on Particle Swarm Optimization (PSO)
... Show MoreMost of the Internet of Things (IoT), cell phones, and Radio Frequency Identification (RFID) applications need high speed in the execution and processing of data. this is done by reducing, system energy consumption, latency, throughput, and processing time. Thus, it will affect against security of such devices and may be attacked by malicious programs. Lightweight cryptographic algorithms are one of the most ideal methods Securing these IoT applications. Cryptography obfuscates and removes the ability to capture all key information patterns ensures that all data transfers occur Safe, accurate, verified, legal and undeniable. Fortunately, various lightweight encryption algorithms could be used to increase defense against various at
... Show MoreHepatitis is one of the diseases that has become more developed in recent years in terms of the high number of infections. Hepatitis causes inflammation that destroys liver cells, and it occurs as a result of viruses, bacteria, blood transfusions, and others. There are five types of hepatitis viruses, which are (A, B, C, D, E) according to their severity. The disease varies by type. Accurate and early diagnosis is the best way to prevent disease, as it allows infected people to take preventive steps so that they do not transmit the difference to other people, and diagnosis using artificial intelligence gives an accurate and rapid diagnostic result. Where the analytical method of the data relied on the radial basis network to diagnose the
... Show MoreIn this research was to use the method of classic dynamic programming (CDP) and the method of fuzzy dynamic programming (FDP) to controlling the inventory in N periods and only one substance ,in order to minimize the total cost and determining the required quantity in warehouse rusafa principal of the ministry of commerce . A comparison was made between the two techniques، We found that the value of fuzzy total cost is less than that the value of classic total cost
The research depth and dimensions of the problem of environmental pollution resulting from the combustion of fuel used in electric power generators, especially in the summer and you are the national electric power supplied by almost non-existent state where this problem is a local phenomenon that has serious dimensions to human health, as well as the possibility of using a the tax system tools of b (environmental taxes) to reduce these pollutants, so the search is aimed at the types of gases emitted from burning fuel electric generators operating in the province of Baghdad and then measure the amount of environmental pollution as well as compared to the amount of some of these gases, which is more risk to humans with permitted by the Wor
... Show MoreAbstract
The aim of the present research is to identify the test wisdom and the preoccupation with learning and psychological tension among postgraduate students at the University of Samarra according to the variables of the department, gender, age, and employee or non-employee, and revealing the relationship between the test wisdom and the preoccupation with learning and psychological tension. The research sample consisted of (75) students randomly selected from postgraduate students at the college of Education. The researcher applies test –wisdom of (Mellman & Ebel) and measurement of preoccupation with learning prepared by (Al-zaabi 2013) also, the researcher used the scale of t
... Show MoreThe dye–semiconductor interface between N749 sensitized and zinc semiconductor (ZnSe) has been investigated and studied according to quantum transition theory with focusing on the electron transfer processes from the N749 sensitized (donor) to the ZnSe semiconductor (acceptor). The electron transfer rate constant and the orientation energy were studied and evaluated depended on the polarity of solvents according to refractive index and dielectric constant coefficient of solvents and ZnSe semiconductor. Attention focusing on the influence of orientation energies on the behavior of electron transfer rate constant. Differentdata of rate constant was discussion with orientation energy and effective driving energy for N749-ZnSe system.
... Show MoreData scarcity is a major challenge when training deep learning (DL) models. DL demands a large amount of data to achieve exceptional performance. Unfortunately, many applications have small or inadequate data to train DL frameworks. Usually, manual labeling is needed to provide labeled data, which typically involves human annotators with a vast background of knowledge. This annotation process is costly, time-consuming, and error-prone. Usually, every DL framework is fed by a significant amount of labeled data to automatically learn representations. Ultimately, a larger amount of data would generate a better DL model and its performance is also application dependent. This issue is the main barrier for