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
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.
Analysis of EEG (Electroencephalography) signals provides an alternative ingenious approach towards Emotion recognition. Nowadays, Gradient Boosting Machines (GBMs) have emerged as state-of-the-art supervised classifi...
ISBN:
(纸本)9781538666791;9781538666784
Analysis of EEG (Electroencephalography) signals provides an alternative ingenious approach towards Emotion recognition. Nowadays, Gradient Boosting Machines (GBMs) have emerged as state-of-the-art supervised classification techniques used for robust modeling of various standard machine learning problems. In this paper, two GBM's (XGBoost and LightGBM) were used for emotion classification on DEAP Dataset. Furthermore, a participant independent model was fabricated by excluding participant number from features. The proposed approach performed well with high accuracies and faster training speed.
With the advancement in the digital technologies, the internet has become major break-through and has been universally acceptable technology by the people of all the ages. They use the internet for the purpose of ente...
详细信息
ISBN:
(纸本)9781538641200
With the advancement in the digital technologies, the internet has become major break-through and has been universally acceptable technology by the people of all the ages. They use the internet for the purpose of entertainment, shopping, gossiping, and playing games and also for harming the other users in the form of promoting fraud, cyberbullying and sometimes terrorism. However, overuse of internet which is often called cyberaddiction results in some negative implications such as health disorders, poor social relationships, poor academic performance, cyberbullying and so on. For this paper, we have surveyed people using questionnaire on the subject related to internet usage and cyberbullying. As a result, this paper shows the analysis of internet usage, cyberbullying and its relationship. Cyberbullying is the most important concept to be considered now a days for the researchers as it is directly linked to the lives of the youth of the world. Earlier research did not focus on the importance of social media, however, this paper discusses linkage of the overuse of social media with cyberbullying.
Scale-Free social network is universally popular among the users of almost all the ages. This scale-free network follows the Power Law that expresses the distribution of data in the form of body and tail. Tail can be ...
详细信息
ISBN:
(纸本)9781538641200
Scale-Free social network is universally popular among the users of almost all the ages. This scale-free network follows the Power Law that expresses the distribution of data in the form of body and tail. Tail can be expressed in two types: heavy and long. Heavy tail also called Pareto distribution means rare or infrequent occurrences of events with high values whereas long tail which is used for Zipf's distributionshows many occurrences of events with small values. In this paper, we employed the concept of long tail to identify the skeptical pattern in the social network as security is the main concern for everyone and become an open research area. Earlier papers on Zipf's Law worked on the concept of constructing the dictionaries or thesaurus on the basis of the frequency of keywords. However, this paper deals with the suspicious pattern on the basis of the frequency of keywords.
Gene Expression Programming, a popular evolutionary paradigm, has acquired great attention from researchers in the domain of mathematical modeling. In view of its insufficiencies arising due to premature convergence, ...
详细信息
Gene Expression Programming, a popular evolutionary paradigm, has acquired great attention from researchers in the domain of mathematical modeling. In view of its insufficiencies arising due to premature convergence, this paper presents an Augmented Gene Expression Programming (AGEP) algorithm. Improvements suggested over classical GEP mechanism are (1) Opposition Based Learning to initialize the population of individuals to speed up convergence, (2) A diversifying clonal selection algorithm to eliminate bias towards fitter individuals, and (3) A population upliftment step to counter stagnancy over generations. A set of experiments related to function finding was conducted using AGEP and the results show a prominent improvement by AGEP over its classical counterpart, GEP and an improved version from authoritative literature (Niche technology of Outbreeding Fusion-OFN-GEP). The results have been used to reason that AGEP gives more accurate solutions at a better convergence rate.
The primary purpose of fingerprint recognition is to make sure that user authentication is reliable. Fully connected Convolutional networks help to attain good performance in classifying a time-series sequence of capt...
详细信息
ISBN:
(纸本)9781538663745;9781538663738
The primary purpose of fingerprint recognition is to make sure that user authentication is reliable. Fully connected Convolutional networks help to attain good performance in classifying a time-series sequence of captured fingerprint images. In this paper, we work on the approach of detecting spoofed fingerprints from these sequences by combining the use of Convolutional Neural Networks and Long Short Term Memory networks. Our proposed model has superior performance, with minimum amount of processing and optimal model size. The experiments, carried out on a dataset [1] of real and spoofed fingerprints, prove that the proposed approach is effective in detecting spoofed fingerprints.
Consuming news via social media is an integral part of our lives. Various news agencies use social media as a medium to spread their content. Popularity prediction of news before publication is a challenging task beca...
ISBN:
(纸本)9781538656587
Consuming news via social media is an integral part of our lives. Various news agencies use social media as a medium to spread their content. Popularity prediction of news before publication is a challenging task because it depends on a very large user base. Popularity of news on social platform can be represented using number of likes, shares. We have used number of likes as a popularity measure. In this paper, we first find out features on social platform which can affect popularity of an article. These features and content metadata are fed to various machine learning models. These models are used to predict whether an article is going to be popular or not. Tree based models achieve best results for prediction. These models also show that hashtags, usermentions and other social features are important factors which affect popularity of news.
Biometric systems are playing an important role in identifying a person, thus contributing to global security. There are many possible biometrics, for example height, DNA, handwriting etc., but computer vision based b...
ISBN:
(纸本)9781538666791;9781538666784
Biometric systems are playing an important role in identifying a person, thus contributing to global security. There are many possible biometrics, for example height, DNA, handwriting etc., but computer vision based biometrics have found an important place in the domain of human identification. computer vision based biometrics include identification of face, fingerprints, iris etc. and using their abilities to create efficient authentication systems. In this paper, we work on a dataset [1] of iris images and make use of deep learning to identify and verify the iris of a person. Hyperparameter tuning for deep networks and optimization techniques have been taken into account in this system. The proposed system is trained using a combination of Convolutional Neural Networks and Softmax classifier to extract features from localized regions of the input iris images. This is followed by classification into one out of 224 classes of the dataset. From the results, we conclude that the choice of hyperparameters and optimizers affects the efficiency of our proposed system. Our proposed approach outperforms existing approaches by attaining a high accuracy of 98 percent.
暂无评论