IAES International Journal of Artificial Intelligence, Feb 29, 2024
Imbalanced datasets pose a major challenge for the researchers while addressing machine learning ... more Imbalanced datasets pose a major challenge for the researchers while addressing machine learning tasks. In these types of datasets, samples of different classes are not in equal proportion rather the gap between the numbers of individual class samples is significantly large. Classification models perform better for datasets having equal proportion of data tuples in both the classes. But, in reality, the medical image datasets are skewed and hence are not always suitable for a model to achieve improved classification performance. Therefore, various techniques have been suggested in the literature to overcome this challenge. This paper applies oversampling technique on an imbalanced dataset and focuses on a customized convolutional neural network model that classifies the images into two categories: diseased and non-diseased. Outcome of the proposed model can assist the health experts in the detection of oral cancer. The proposed model exhibits 99% accuracy after data augmentation. Performance metrics such as precision, recall and F1-score values are very close to 1. In addition, statistical test is performed to validate the statistical significance of the model. It has been found that the proposed model is an optimised classifier in terms of number of network layers and number of neurons.
Estimation of propagation characteristics of l1 series of LP modes of few-mode W-type fibers using numerical and analytical approach
Optics Communications
Medical Datasets Classification using a Hybrid Genetic Algorithm for Feature Selection based on Pearson Correlation Coefficient
2022 International Conference on Machine Learning, Computer Systems and Security (MLCSS)
IoT for Smart Healthcare: Opportunities, Challenges and Technology
2022 International Conference on Machine Learning, Computer Systems and Security (MLCSS)
Computation of dimensionless propagation parameters of LP11 mode of double clad fibers
Results in Optics
A Collaborative Meta-Heuristic for Exchange Rate Prediction of Different Currencies
Social Science Research Network, 2022
A Collaborative Meta-Heuristic Based Adaptive Forecasting Model for Forex Prediction
SSRN Electronic Journal
IoT-Based Cardiac Arrest Prediction Through Heart Variability Analysis
Advances in Intelligent Systems and Computing, 2020
Current machine learning methods for sudden cardiac arrest have not been tested against physicall... more Current machine learning methods for sudden cardiac arrest have not been tested against physically active heart rates. Developments in wearable technology and advancements in non-intrusive heart rate monitors may allow for a future where people can stream their heart rate readings, with the readings automatically analyzed by robust machine learning algorithms which will alert cardiac arrest risk. This paper presents a new sudden cardiac arrest prediction technique, a random forest classifier implementation, a prospective physical activity heart rate dataset, and an Internet of things solution toward heart rate monitoring and sudden cardiac arrest warning. In this paper, five minutes advance warning is provided with 97.03% accuracy and a 0.9485 F-score for the classification of sudden cardiac arrest prediction. The result shows the efficiency of our method compared to other existing methods.
EAC: Efficient Associative Classifier for Classification
2019 International Conference on Applied Machine Learning (ICAML), 2019
Mining of large datasets which generally leads to the generation of a huge volume of rules and re... more Mining of large datasets which generally leads to the generation of a huge volume of rules and redundancy which Associative Classifiers find very difficult to handle. Thus, most Associative Classification algorithms like CPAR and CMAR, only mine frequent itemsets, which are then processed using additional algorithms in a greedy manner. This adds overhead in running time and makes the process more complex. In this paper, we proposed a new Associative Classification algorithm, called Efficient Associative Classifier (EAC). EAC deals with redundant association rules through an effective and simple pruning technique which also helps in cutting down the number of rules which finally form a part of the classifier. The classifiers are built in a two-phased manner so as to achieve the maximum accuracy and maximum representation of all possible class labels involved in the domain. In the first phase, association rule mining (ARM) is performed globally by taking global values of support and c...
International Journal of Innovative Computing and Applications, 2019
Clustering is one of the important functions of data mining, which is used to analyse a large amo... more Clustering is one of the important functions of data mining, which is used to analyse a large amount of data. It groups these set of data according to some similarity property such that data within the cluster are similar to each other and data between the clusters are dissimilar to each other. To obtain an optimal clustering result with the help of an optimisation algorithm is an emerging trend in data mining. The partitional clustering is one of the popularly used types of clustering algorithm. These algorithms often land in local optimum and number of clusters needs to be predefined. To encounter the above problem, optimisation algorithms such as metaheuristic algorithms are used as a suitable problem-solving paradigm. This paper presents an overview of single-objective metaheuristic algorithms used for partitional clustering problem and their applications. This paper even presents the research issues which can be dealt with in future.
The financial time series is inherently nonlinear and hence cannot be efficiently predicted by us... more The financial time series is inherently nonlinear and hence cannot be efficiently predicted by using linear statistical methods such as regression. Hence, intelligent predictor has been developed and reported which is suitable for nonlinear time series. But such predictors require that the past financial data are available at the location of the predictor which is not the case in many real-life situations. Hence, when the financial data are available at different places and a single intelligent predictor needs to be developed, the task becomes challenging. In the current work, this problem has been addressed and solved using a low-complexity artificial neural network and employing incremental and diffusion learning strategies. In the current study, distributed prediction of three different types of time series such as exchange rates, stock indices and net asset values has been carried using incremental and diffusionbased learning strategies. The results of different days ahead prediction of two proposed low computational complexity-based functional link artificial neural network are compared with those obtained by conventional intelligent method. The results of simulation-based experiments reveal similar or improved prediction performance of the proposed distributed predictors compared to conventional one. In addition, saving in band width, memory and power are achieved in this method.
On the development of cat swarm metaheuristic using distributed learning strategies and the applications
International Journal of Intelligent Computing and Cybernetics, 2019
Purpose The purpose of this paper is to propose distributed learning-based three different metahe... more Purpose The purpose of this paper is to propose distributed learning-based three different metaheuristic algorithms for the identification of nonlinear systems. The proposed algorithms are experimented in this study to address problems for which input data are available at different geographic locations. In addition, the models are tested for nonlinear systems with different noise conditions. In a nutshell, the suggested model aims to handle voluminous data with low communication overhead compared to traditional centralized processing methodologies. Design/methodology/approach Population-based evolutionary algorithms such as genetic algorithm (GA), particle swarm optimization (PSO) and cat swarm optimization (CSO) are implemented in a distributed form to address the system identification problem having distributed input data. Out of different distributed approaches mentioned in the literature, the study has considered incremental and diffusion strategies. Findings Performances of the proposed distributed learning-based algorithms are compared for different noise conditions. The experimental results indicate that CSO performs better compared to GA and PSO at all noise strengths with respect to accuracy and error convergence rate, but incremental CSO is slightly superior to diffusion CSO. Originality/value This paper employs evolutionary algorithms using distributed learning strategies and applies these algorithms for the identification of unknown systems. Very few existing studies have been reported in which these distributed learning strategies are experimented for the parameter estimation task.
Journal of Ambient Intelligence and Humanized Computing, 2018
This paper makes an in depth study on the applications of distributed machine learning based tech... more This paper makes an in depth study on the applications of distributed machine learning based techniques for parameter estimation of infinite impulse response (IIR) systems and as well as inverse modeling of nonlinear systems or sensors. The bio-inspired learning algorithms such as particle swarm optimization (PSO) and differential evolution (DE) are used as incremental and diffusion based distributed learning strategies to estimate the pole-zero parameters of a feed forward-feedback systems. The same distributed learning algorithms are also employed to generate inverse model of nonlinear systems. The performance of these learning algorithms in terms of accuracy of estimation are compared under different additive noise conditions. The ranking based on accuracy of direct estimation demonstrates that the proposed Incremental DE (IDE) based model performs the best than Diffusion DE (DDE) counter part. It is then followed by IPSO, DPSO, ILMS and DLMS based models. The same ranking is also valid for inverse modeling problem. The proposed distributed bioinspired learning can also be applied to various forecasting and classification tasks.
Handbook of Research on Wireless Sensor Network Trends, Technologies, and Applications
Recently the distributed sensor network has achieved more attention than its centralized counterp... more Recently the distributed sensor network has achieved more attention than its centralized counterpart. There are a number of literature that used different evolutionary computing techniques in a distributed way for the task of optimization in several problems of wireless sensor network. Particularly, parameter estimation of FIR filter is carried out using numerous sensor nodes through distributed particle swarm optimization. Differential Evolution (DE) is an evolutionary technique and has been applied in various fields due to its simplicity and faster convergence property in comparison to other algorithms. In this chapter differential evolution is used in two different approaches, namely Incremental DE (IDE) and Diffusion DE (DDE) to estimate the parameters of FIR filter in a distributed manner. The performance is compared with other population based algorithms.
Uploads
Papers by Usha Mohapatra