Nowadays, deep learning is playing an important role in the domain of image classification. In this paper, a Python library known as Keras, is used for classification of MNIST dataset, a database with images of handwr...
详细信息
ISBN:
(纸本)9781538641200
Nowadays, deep learning is playing an important role in the domain of image classification. In this paper, a Python library known as Keras, is used for classification of MNIST dataset, a database with images of handwritten images. Two architectures - feed forward neural networks and convolutional neural networks are used for feature extraction and training of model, which is optimized using Stochastic Gradient Descent. This paper gives an overview of multi-class classification of these images using these models, and their performance evaluation in terms of various metrics. It is observed that convolutional neural networks achieve a greater accuracy as compared to feedforward neural networks for classification of handwritten digits.
In this paper, we propose a new enhanced image steganography scheme for color images. The proposed scheme is based on the pixel intensity of the cover image and the similarity in secret message. It can hide the secret...
详细信息
The use of a Predictive Parsing Visualization Tool (PPVT) as a teaching aid in a course on compiler construction offered in the fall of 2015 helped students better understand the predictive parsing as they reported in...
详细信息
Nowadays many biological problems are structured in the form of networks called biological networks. Formation of such large networks helps us in analyzing biological systems extensively and effectively. Although the ...
详细信息
ISBN:
(纸本)9781538663745;9781538663738
Nowadays many biological problems are structured in the form of networks called biological networks. Formation of such large networks helps us in analyzing biological systems extensively and effectively. Although the size and structure of biological networks are very complex and it is difficult to interpret such networks without further processing. In this paper, we discuss the analysis of such systems by forming clusters and analyze the whole arrangement using different types of clusters formed in the network. A cluster is a highly connected group of nodes of the net and cluster analysis is one of the prominent features used for the analysis of the biological systems. Here, we present our study by applying some popular clustering algorithms on multi-layer biological networks to see the changes in the shape, size, and structure of the clusters when multiple interactions among biological entities are included and the behavior of objects in such networks.
This paper presents a novel method of improving image quality using meta-heuristic algorithms such as Bat Algorithm, Cuckoo Search Algorithm and Interior Search Algorithm by contrast enhancement method. The performanc...
详细信息
ISBN:
(数字)9781538624401
ISBN:
(纸本)9781538624418
This paper presents a novel method of improving image quality using meta-heuristic algorithms such as Bat Algorithm, Cuckoo Search Algorithm and Interior Search Algorithm by contrast enhancement method. The performance of these algorithms are compared based on their ability to enhance the contrast, detail and sharpness of the gray scale image. These algorithms are used to generate optimal parameters to reach the global best of a fitness function which is then used to judge the enhancement achieved for the given image.
In this paper, the effect of flux composition on hardness and impact strength of low carbon steel plates welded using submerged arc welding (SAW) was studied. Agglomerated fluxes containing various combinations of CaO...
In this paper, the effect of flux composition on hardness and impact strength of low carbon steel plates welded using submerged arc welding (SAW) was studied. Agglomerated fluxes containing various combinations of CaO, Al 2 O 3 , TiO 2 and MgO were developed. Taguchi L8 orthogonal array was used along with varying voltage at two levels. Taguchi’s robust design approach was used to obtain optimal levels of CaO, Al 2 O 3 , TiO 2 and MgO corresponding to higher is better condition. Furthermore, these results were verified by confirmatory experiments.
For serving traffic in the inter data centers which provide services such as, duplication of data and migration of the virtual machines, it is requisited to transfer voluminous data for which, under guarantee of a fin...
详细信息
Diseased caused through the rapid mediation of Human Papillomavirus (HPV) have surged in the recent decades. While there are a large amount of treatment methods, medical data is often voluminous, high dimensional and ...
详细信息
ISBN:
(纸本)9781538624609;9781538624593
Diseased caused through the rapid mediation of Human Papillomavirus (HPV) have surged in the recent decades. While there are a large amount of treatment methods, medical data is often voluminous, high dimensional and often has redundancy which make selection of a particular method difficult. Wrapper feature selection methods aim to extract a subset of features to improve computability as well as classification accuracy. To address this, we propose a modification to a relatively new evolutionary computation technique, the Binary Dragonfly algorithm (BDFA), by incorporating a penalty function for optimal feature selection. This wrapper based method using BDFA and Random forest classifier is employed on two treatment methods, Immunotherapy and Cryotherapy, showing an increase in both classification accuracy as well as feature reduction as compared to fuzzy rule based systems, genetic algorithms and random forest classifiers.
Due to the multifarious challenges that emerge when developing an artificial intelligent (AI) agent that can compete with human players, the classic game of Othello has received a lot of attention from the Computation...
详细信息
Due to the multifarious challenges that emerge when developing an artificial intelligent (AI) agent that can compete with human players, the classic game of Othello has received a lot of attention from the Computational-Intelligence community. This paper proposes an AI agent that learns a winning strategy for the game of Othello using the eXtended Classifier System (XCS) algorithm which is a popular variant of the Learning Classifier System (LCS) algorithm. Othello has been a favourite in the study of AI due to its simple set of rules, low branching factor and well defined strategic concepts. The LCS system consists of a rule-set which is made to evolve using a combination of Reinforcement Learning (RL) and Genetic Algorithm (GA) such that the evolved rule-set learns an optimal action for each board state. A 6×6 Othello board will be used for this experiment in order to evaluate the applicability of the proposed agent in learning a winning game-playing strategy. The performance of the proposed agent was evaluated against three categories of agents: minimax, human and random agent. The XCS agent was able to outperform the above-mentioned agents showing the effectiveness of rule-based evolutionary learning in Othello. This work demonstrates the possibility of using the XCS algorithm in other strategy-based combinatorial games.
暂无评论