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.
Deep learning techniques are used across a wide range of fields for several applications. In recent years, deep learning-based object detection from aerial or terrestrial photos has gained popularity as a study topic. The goal of object detection in computer vision is to anticipate the presence of one or more objects, along with their classes and bounding boxes. The YOLO (You Only Look Once) modern object detector can detect things in real-time with accuracy and speed. A neural network from the YOLO family of computer vision models makes one-time predictions about the locations of bounding rectangles andclassification probabilities for an image. In layman's terms, it is a technique for instantly identifying and rec
... Show Moresix specimens of the Hg0.5Pb0.5Ba2Ca2Cu3-y
The Pulse Coupled Oscillator (PCO) has attracted substantial attention and widely used in wireless sensor networks (WSNs), where it utilizes firefly synchronization to attract mating partners, similar to artificial occurrences that mimic natural phenomena. However, the PCO model might not be applicable for simultaneous transmission and data reception because of energy constraints. Thus, an energy-efficient pulse coupled oscillator (EEPCO) has been proposed, which employs the self-organizing method by combining biologically and non-biologically inspired network systems and has proven to reduce the transmission delay and energy consumption of sensor nodes. However, the EEPCO method has only been experimented in attack-free networks without
... Show MoreMobile Ad hoc Networks (MANETs) is a wireless technology that plays an important role in several modern applications which include military, civil, health and real-time applications. Providing Quality of Service (QoS) for this application with network characterized by node mobility, infrastructure-less, limitation resource is a critical issue and takes greater attention. However, transport protocols effected influential on the performance of MANET application. This study provides an analysis and evaluation of the performance for TFRC, UDP and TCP transport protocols in MANET environment. In order to achieve high accuracy results, the three transport protocols are implemented and simulated with four different network topology which are 5, 10
... Show MoreElectrocardiogram (ECG) is an important physiological signal for cardiac disease diagnosis. With the increasing use of modern electrocardiogram monitoring devices that generate vast amount of data requiring huge storage capacity. In order to decrease storage costs or make ECG signals suitable and ready for transmission through common communication channels, the ECG data
volume must be reduced. So an effective data compression method is required. This paper presents an efficient technique for the compression of ECG signals. In this technique, different transforms have been used to compress the ECG signals. At first, a 1-D ECG data was segmented and aligned to a 2-D data array, then 2-D mixed transform was implemented to compress the
Predicting permeability is a cornerstone of petroleum reservoir engineering, playing a vital role in optimizing hydrocarbon recovery strategies. This paper explores the application of neural networks to predict permeability in oil reservoirs, underscoring their growing importance in addressing traditional prediction challenges. Conventional techniques often struggle with the complexities of subsurface conditions, making innovative approaches essential. Neural networks, with their ability to uncover complicated patterns within large datasets, emerge as a powerful alternative. The Quanti-Elan model was used in this study to combine several well logs for mineral volumes, porosity and water saturation estimation. This model goes be
... Show MoreDirectional Compact Geographic Forwarding (DCGF) routing protocol promises a minimal overhead generation by utilizing a smart antenna and Quality of Service (QoS) aware aggregation. However, DCGF was tested only in the attack-free scenario without involving the security elements. Therefore, an investigation was conducted to examine the routing protocol algorithm whether it is secure against attack-based networks in the presence of Denial-of-Service (DoS) attack. This analysis on DoS attack was carried out using a single optimal attacker, A1, to investigate the impact of DoS attack on DCGF in a communication link. The study showed that DCGF does not perform efficiently in terms of packet delivery ratio and energy consumption even on a sin
... Show MoreThe approach of the research is to simulate residual chlorine decay through potable water distribution networks of Gukookcity. EPANET software was used for estimating and predicting chlorine concentration at different water network points . Data requiredas program inputs (pipe properties) were taken from the Baghdad Municipality, factors that affect residual chlorine concentrationincluding (pH ,Temperature, pressure ,flow rate) were measured .Twenty five samples were tested from November 2016 to July 2017.The residual chlorine values varied between ( 0.2-2mg/L) , and pH values varied between (7.6 -8.2) and the pressure was very weak inthis region. Statistical analyses were used to evaluated errors. The calculated concentrations by the calib
... Show MoreThe quality of Global Navigation Satellite Systems (GNSS) networks are considerably influenced by the configuration of the observed baselines. Where, this study aims to find an optimal configuration for GNSS baselines in terms of the number and distribution of baselines to improve the quality criteria of the GNSS networks. First order design problem (FOD) was applied in this research to optimize GNSS network baselines configuration, and based on sequential adjustment method to solve its objective functions.
FOD for optimum precision (FOD-p) was the proposed model which based on the design criteria of A-optimality and E-optimality. These design criteria were selected as objective functions of precision, whic
... Show MoreOver the past few decades, the surveying fieldworks were usually carried out based on classical positioning methods for establishing horizontal and vertical geodetic networks. However, these conventional positioning techniques have many drawbacks such as time-consuming, too costly, and require massive effort. Thus, the Global Navigation Satellite System (GNSS) has been invented to fulfill the quickness, increase the accuracy, and overcome all the difficulties inherent in almost every surveying fieldwork. This research assesses the accuracy of local geodetic networks using different Global Navigation Satellite System (GNSS) techniques, such as Static, Precise Point Positioning, Post Processing Kinematic, Session method, a
... Show More