This paper introduces a novel parameter automation strategy for the particle swarm algorithm and two further extensions to improve its performance after predefined number of generations. Initially, efficiently control local search convergence global optimum solution, time-varying acceleration coefficients (TVAC) are introduced in addition inertia weight factor optimization (PSO). From basis TVAC, new strategies discussed PSO. First, concept "mutation" is along with TVAC (MPSO-TVAC), by...

Accurate weather forecasts are essential for various human activities. Weather forecasting is a complex process that can exhaust the resources of many computational devices. Out numerous techniques Artificial Neural Networks (ANN) methodology one most widely used techniques. In this study application Network Ensembles in Rainfall Forecasting investigated by using an Ensemble (ENN) to forecast rainfall Colombo, Sri Lanka. The ensemble consist combination Multi Layer Feed Forward with Back...

Rainfall is a complex process and forecasting rainfall complicated because it involves lot of parameters but precise necessary for many human activities. Even though considerable research work has been done in prediction, comparatively fewer efforts have made on Sri Lankan monsoon prediction using large scale climatic teleconnections. In this paper, results study investigating the appropriateness artificial neural networks Lanka climate teleconnections presented.

Localization, navigation, and mapping using vision-based algorithms are an active topic in underwater robotic applications. Although many developed recent years, especially the ground areal communities, directly applying those methods navigation remain challenging due to visual degradation induced by medium. In this paper, we proposed UW-SLAM (Underwater SLAM), a new monocular SLAM algorithm focused on environment which addresses turbidity dynamism. The method was evaluated with several...

Abstract Underwater simultaneous localization and mapping (SLAM) poses significant challenges for modern visual SLAM systems. The integration of deep learning networks within computer vision offers promising potential addressing these difficulties. Our research draws inspiration from approaches applied to interest point detection matching, single image depth prediction underwater enhancement. In response, we propose 3D-Net, a learning-assisted network designed tackle three tasks...

A STEP-NC or ISO 14649 compliant machine controller is developed, using Open Architecture Control technology for a three-axis Computer Numerical milling in this research. The developed on Raspberry Pi single-board computer, C++ language. This new development proposed as low-cost alternative to ISO6983 standard, ensuring continuous integration the CAD/CAM/CNC chain machining; thus, it broadens spectrum of problems handled by conventional CNC systems. intelligent enough extract geometrical and...

The best combination of valve timing events along with three dominant engine operating parameters was observed for optimum performance an internal combustion spark ignition (ICSI) particle swarm optimisation (PSO) method. A thermodynamics simulation programme is considered to evaluate the fitness each individual. Engine power output and thermal efficiency are independently. Seven parameters, including all major events, used as inputs knock limit maximum lift=10 mm constraints. Five different...

Weather forecasting is a widely researched area in time series due to the necessity of accurate weather forecasts various human activities. Out numerous techniques Artificial Neural Networks (ANN) methodology one most used techniques. In this study application Network Ensembles Rainfall Forecasting investigated by using types Ensemble (ENN) forecast rainfall Colombo, Sri Lanka. are generated changing network architecture, initial weights ANN and type. Two ensembles consisting collection...

Artificial Neural Network (ANN) is a widely used technique in forecasting applications. An ensemble of ANNs can produce more accurate forecasts than single ANN. The performance the depends on its' member Member selection for an complicated task that need balancing conflicting conditions. This paper presents method to optimize members ANN using Genetic Algorithms approach. To develop models daily weather data are used. Rainfall Colombo, Sri Lanka and test rainfall Katugastota, validate...

A non linear relationship between an internal combustion engine and its parameters such as vibration signals/ exhaust gas is expected to be available. Under various fault conditions, signals were collected using a test-bed prove this. Fourier transformed mapped their corresponding faults back propagation neural network. The network consists with about 250 input nodes 150 hidden nodes; resilient back-propagation was used deal the complexity created by high number of nodes. dataset divided for...

This research presents a real-time visibility enhancement algorithm for effective underwater visual navigation. Unlike an aerial environment, environment is poor as light travels in the water and resulting scenes are poorly contrasted hazy. At present, several vision-based navigation algorithms were introduced by ground robotic communities. However, most of them fail due to image degradation. But, there possibility use same vision methods with preprocessing which addresses Presented paper...

In this study we present attitude stabilization using a vehicle-fixed-frame adaptive controller and an intrinsic nonlinear PID for low-speed Autonomous Underwater Vehicle (AUV), of complex shape. Controlling AUV poses huge challenge because the non-linearity, time variance unpredictable external disturbance, as well its dynamics hydrodynamic parameters are difficult to identify due geometry. First, is implemented stabilize attitudes given. The stability desired state-dependent, regressor,...

"ENGINEER", established in 1973 by The Institution of Engineers, is a Journal for dissemination Engineering knowledge, published quarterly.If you are interested contributing an Original Technical Paper based on research the author(s) (intended Section I) or Article Professional interest related to Engineering. (Section II) this journal please go through publication checklist which can be downloaded from here.Cover DescriptionCover images show few views Stage II Central Expressway Mirigama...