Swarm intelligence is a modern optimization technique, and one of the most promising techniques for solving optimization problems. In this paper, a new swarm intelligence based algorithm namely, Harris’ Hawk Optimizer (HHO) is proposed. The algorithm mimics the cooperative hunting behaviour of Harris’ hawks. The algorithm is analysed for twenty five well known benchmark functions. Performance of HHO is compared with Particle Swarm Optimization (PSO), Differential Evolution (DE), Grey Wolf Optimizer (GWO) and The Whale Optimization Algorithm (WOA). HHO is implemented and results present HHO as one of the efficient optimization methods.
Recent advancement in research and technology has led to the development of various self-adaptive systems like unmanned ground vehicles, unmanned aerial vehicles and robots. The autonomous navigation of these systems is an important area of concern. There exists various node based path planning algorithms that can find a collision free path from an initial location to a destination location avoiding obstacles. In this paper, we provide a comparative study of some node based algorithms based on the time efficiency, solution quality and type of data structure used. In addition, we conduct an applicable analysis of the studied algorithms after considering the merits and demerits.
Cloud has large storage capacity and flexible accessibility. By outsourcing the sensitive data to a cloud server, individuals and enterprises are relieved from the burden of local data management and maintenance. But retrieving the relevant documents and searching semantic query over large database is still challenging. This paper proposes a novel “Clustered Rocchio Search using SemanticLib” framework. The proposed framework will retrieve the relevant document from database the user is searching for. The idea behind this approach is to search semantic query keywords. This paper presents the concept of clustering for efficiently access the relevant information according to domain. To search the information related to keyword query Rocchio Algorithm is used. The result contains required information as semantics-based searching is done with the help of Semantic Library. The proposed framework is simple, efficient and reduces searching time.
Indian Culture exceeds beyond the mere definition of ‘simply how people live’ as it scientifically operates according to specific, detailed knowledge of the eventual aim of life and the means to attain it. Over the years, a lot of work has been done on object recognition and scene recognition but Event Recognition is still one of the fields wherein lies a huge potential for lots of research work and so with this paper, we put forward our best step to preserve the culture of India. More than 150 images of near about 20 cultural events are collected. Results are derived from support vector machine classifier using features extracted by a pre-trained convolutional neural network- Alex Net. In most visual recognition tasks, it strongly suggested that features obtained from deep learning with convolutional nets should be the chief candidate. Our proposed framework has classified images with a comparable accuracy of 77.72 %.
This paper discuss an approach to detect whether a wave file contains speech or not. A frame classifier is trained to classify frames to phones. The inherent biases of the frame classifier, in terms of various aspects of recognition, is captured in terms of probability distributions. Using the distributions of speech and noise, an approach is presented, which scores wave file for the presence or absence of speech. Relevant databases are used to test the detection rate of this approach.
Speech recognition has been one of the key research domains in computational signal processing. Despite high levels of computational complexity associated with achieving speech recognition in real-time, promising progress has been made under the umbrella of voice controlled robotics. This paper proposes an alternate approach to speech recognition for robotics applications, without adding on external hardware. We use a combination of spectrograms, MEL and MFCC features and a neural network based classification which is usually done offline, whereas the proposed method offers a remote real-time control of the robot that can be used to survey terrains that are otherwise impervious for humans, or monitor activities inside huge structures like wind-mills, gas pipelines etc. The trained model occupies lesser than 4MB on the storage medium of the platform and it also displays metrics of confidence and accuracy of prediction. The overall validation accuracy of the algorithm goes as high as 97% while the testing accuracy of the system is 95.4%. Since this is a classification algorithm, results have been presented on custom voice classification datasets.
The ability to predict the aircraft fuel system health/operating condition and possible complications that occur during the long flight of an aircraft helps to improve the performance of aircraft engine. Prognostic and Health Management (PHM) methodology includes fault detection, diagnosis, and prognosis. In this paper, an Artificial Neural Network (ANN) based fault prognosis tool for a typical aircraft fuel system is proposed. Prognostics methods using ANN promises to provide new approach into managing the fuel flow and fuel consumption of aircraft engines more effectively. The proposed method identifies the presence of faults, mitigate them and maintain the proper fuel flow to the engine. Missing the presence of any faults in time could potentially be catastrophic with the loss of pilot, flight crew members, passengers, and aircraft. The ANN works based on the logical rules, which are developed as per the engines fuel consumption and quantity of fuel flow from the tanks. The process and results of using ANN models to predict the health condition of the fuel system of aircraft are discussed.
Copyright © SAI 2018