Information Gain Model Research Articles

Enhanced data preprocessing with novel window function in Raman spectroscopy: Leveraging feature selection and machine learning for raspberry origin identification

In this study, a simple and accurate approach is proposed for enhancing the origin identification of raspberry samples using a combination of innovative Raman spectral preprocessing techniques, feature selection, and machine learning algorithms. Window function was creatively introduced and combined with baseline removal technique to preprocess the Raman spectral data, reducing the dimensionality of the raw data and ensuring the quality of the processed data. An optimization process was conducted to determine the optimal parameter for the window function, resulting in a binning window width of 5 that yielded the highest accuracy. After applying three feature selection techniques, it was found that the information gain model had the best performance in extracting discriminative spectral features. Finally, ten different machine learning algorithms were employed to construct predictive models, and the optimal models were selected. Linear Support Vector Classifier (LinearSVC), Multi-Layer Perceptron Classifier (MLPClassifier), and Linear Discriminant Analysis (LDA) achieve accuracy, precision, recall, and F1 values above 0.96, while the Random Vector Functional Link Network Classifier (RVFLClassifier) surpasses 0.93 for these performance metrics. These results demonstrate the effectiveness of the proposed approach in identifying the origin of raspberry samples with high accuracy and robustness, providing a valuable tool for agricultural product authentication and quality control.

Lung cancer diagnosis based on weighted convolutional neural network using gene data expression

Lung cancer is thought to be a genetic disease with a variety of unknown origins. Globocan2020 report tells in 2020 new cancer cases identified was 19.3 million and nearly 10.0 million died owed to cancer. GLOBOCAN envisages that the cancer cases will raised to 28.4 million in 2040. This charge is superior to the combined rates of the former generally prevalent malignancies, like breast, colorectal, and prostate cancers. For attribute selection in previous work, the information gain model was applied. Then, for lung cancer prediction, multilayer perceptron, random subspace, and sequential minimal optimization (SMO) are used. However, the total number of parameters in a multilayer perceptron can become extremely large. This is inefficient because of the duplication in such high dimensions, and SMO can become ineffective due to its calculating method and maintaining a single threshold value for prediction. To avoid these difficulties, our research presented a novel technique including Z-score normalization, levy flight cuckoo search optimization, and a weighted convolutional neural network for predicting lung cancer. This result findings show that the proposed technique is effective in precision, recall, and accuracy for the Kent Ridge Bio-Medical Dataset Repository.

An Efficient Robot Exploration Method Based on Heuristics Biased Sampling

Autonomous robot exploration has received widespread attention as a crucial step in constructing maps for unknown environments. Among the research results in the field of robotic exploration, the boundary exploration algorithm based on Rapidly-exploring Random Tree (RRT) performs well in most scenarios, which guides the robot motion by taking the frontier with the maximum revenue value as the target point discretely. However, this discrete target selection scheme ignores the geometric continuity of the environment, and the robot often turns to another area before completing a geometrically continuous area (e.g. a complete room), which results the disorderly motion of the robot and a relatively low exploration efficiency. This work proposes a heuristics biased sampling based robot exploration strategy, which utilizes the semantic information of the environment as the heuristics to guide the robot exploration. Firstly, a lightweight network model is proposed for heuristic object recognition. Secondly, a geometrically continuous region is estimated based on the heuristic object, and frontiers are then extracted in this region by using a biased sampling method. Finally, the heuristic information gain model is designed to determine the target frontier for the exploration, which instructs the robot to select the frontiers in the heuristic region with a higher priority. In this way, the robot can effectively use the heuristic knowledge of the environment to improve the efficiency of exploration. Compared with the RRT based exploration methods in simulations and real-world environmental studies, and the experimental results prove the feasibility and effectiveness of our approach.

Credit Risk Analysis Using Fuzzy Logic with Machine Learning Models

Credit Risk is an important issue in the Banking Industry. Credit risk Prediction and assessment of credit is a difficult task for credit managers. Banking Industry has large amount of data related to the behavior of the customer and their credit history, but this raw data is not useful for making correct judgment in credit decisions. The banking industry is need of a correct credit decision making system, to distinguish between good customers and default customers. The data mining domain is suitable for assessing credit risk and making good decisions on credit. Feature selection is one of the main pre-processing step in the data mining. This paper use FuzzyRoughSetTheory (FRST) for finding feature subset. Four other feature selection methods are used to find the optimal feature subset. The four feature selection methods are Information Gain, Relief, Chi-Squared and Wrapper subset model. These different feature selection methods are compared in terms of accuracy and efficiency.

Intelligent IoT-BOTNET attack detection model with optimized hybrid classification model

The botnet have developed into a severe risk to Internet of Things (IoT) systems as a result of manufacturers ‘insufficient security policies and end users’ lack of security awareness. By default, several ports are open and user credentials are left unmodified. ML and DL strategies have been suggested in numerous latest research for identifying and categorising botnet assaults in the IoT context, but still, it has a few issues like high error susceptibility, working only with a large amount of data, poor quality, and data acquisition. This research provided use of a brand-new IoT botnet detector built on an improved hybrid classifier. The proposed work's main components are "pre-processing, feature extraction, feature selection, and attack detection." Following that, the improved Information Gain (IIG) model is used to choose the most reliable characteristics from the received information. To detect an attack, a hybrid classifier is utilized which can be constructed by integrating the optimized Bi-GRU with the Recurrent Neural Network (RNN). To increase the detection accuracy of IoT-BOTNETS, a novel hybrid optimization approach called SMIE (Slime Mould with Immunity Evolution) is created by conceptually integrating two conventional optimization modes: Coronavirus herd immunity optimizer (CHIO) and the Slime mould algorithm. The final output of the hybrid classifier displays the presence or absence of IoT-BOTNET attacks. The projected model's accuracy is 97%, which is 22.6%, 18.5%, 27.8%, 22.6%, and 24.8% higher than the previous models like GWO+ HC, SSO+ HC, WOA+ HC, SMA+ HC, and CHIO+ HC, respectively.

Intrusion Detection System with a Modified DASO Optimization Algorithm

The Dolphin Atom Search Optimization (DASO) is modified in the proposed work. The Bayesian information gain model has the naïve-bayes classifier centered on the parameters, which include Information Gain (IG), Class-wide Information Gain (CIG), and mutual information. The information is fed to the ID phase for processing at the Deep RNN classifier and the performance is tested with the developed proposed algorithm. An optimization algorithm proposed, is based on the ‘Bayesian information gain model’ to tune the weights in order to generate effective detection decisions through the fitness measure. The updated information at the selection segment is processed. The performance is outlayed on the general metrics including accuracy, sensitivity, and selectivity and it is better than the results with the existing algorithms. Enhancement performance is observed with the machine learning and Deep Recurrent Neural Network techniques. The proposed DASO is developed by integrating the Dolphin Echolocation (DE) with the Atom Search Optimization (ASO).

Epileptic Seizure Prediction Using Exponential Squirrel Atom Search Optimization-Based Deep Recurrent Neural Network

Electroencephalogram (EEG) signal is broadly utilized for monitoring epilepsy and plays a key role to revitalize close loop brain. The classical method introduced to find the seizures relies on EEG signals which is complex as well as costly, if channel count increases. This paper introduces the novel method named exponential-squirrel atom search optimization (Exp-SASO) algorithm in order to train the deep RNN for discovering epileptic seizure. Here, the input EEG signal is given to the pre-processing module for enhancing the quality of image by reducing the noise. Then, the pre-processed image is forwarded to the feature extraction module. The features, like statistical features, spectral features, logarithmic band power, wavelet coefficients, common spatial patterns, along with spectral decrease, pitch chroma, tonal power ratio, and spectral flux, are extracted. Once the features are extracted, the feature selection is carried out using fuzzy information gain model for choosing appropriate features for further processing.

Enhanced Semantic-Aware Multi-Keyword Ranked Search Scheme Over Encrypted Cloud Data

Traditional searchable encryption schemes based on the Term Frequency-Inverse Document Frequency (TF-IDF) model adopt the presence of keywords to measure the relevance of documents to queries, which ignores the latent semantic meanings that are concealed in the context. Latent Dirichlet Allocation (LDA) topic model can be utilized for modeling the semantics among texts to achieve semantic-aware multi-keyword search. However, the LDA topic model treats queries and documents from the perspective of topics, and the keywords information is ignored. In this article, we propose a privacy-preserving searchable encryption scheme based on the LDA topic model and the query likelihood model. We extract the feature keywords from the document using the LDA-based Information Gain (IG) and Topic Frequency-Inverse Topic Frequency (TF-ITF) model. With feature keyword extraction and the query likelihood model, our scheme can achieve a more accurate semantic-aware keyword search. A special index tree is used to enhance search efficiency. The secure inner product operation is utilized to implement the privacy-preserving ranked search. The experiments on real-world datasets demonstrate the effectiveness of our scheme.

The Feature Selection Effect on Missing Value Imputation of Medical Datasets

In practice, many medical domain datasets are incomplete, containing a proportion of incomplete data with missing attribute values. Missing value imputation can be performed to solve the problem of incomplete datasets. To impute missing values, some of the observed data (i.e., complete data) are generally used as the reference or training set, and then the relevant statistical and machine learning techniques are employed to produce estimations to replace the missing values. Since the collected dataset usually contains a certain number of feature dimensions, it is useful to perform feature selection for better pattern recognition. Therefore, the aim of this paper is to examine the effect of performing feature selection on missing value imputation of medical datasets. Experiments are carried out on five different medical domain datasets containing various feature dimensions. In addition, three different types of feature selection methods and imputation techniques are employed for comparison. The results show that combining feature selection and imputation is a better choice for many medical datasets. However, the feature selection algorithm should be carefully chosen in order to produce the best result. Particularly, the genetic algorithm and information gain models are suitable for lower dimensional datasets, whereas the decision tree model is a better choice for higher dimensional datasets.

Improving retrieval framework using information gain models

Content-based image retrieval systems are meant to retrieve the most similar images of a collection to a query image. One of the most well-known models widely applied for this task is the bag of visual words (BoVW) model. In this paper, we introduce a study of different information gain models used for the construction of a visual vocabulary. In the proposed framework, information gain models are used as a discriminative information to index image features and select the ones that have the highest information gain values. We introduce some extensions to further improve the performance of the proposed framework: mixing different vocabularies and extending the BoVW to bag of visual phrases. Exhaustive experiments show the interest of information gain models on our retrieval framework.

Towards a Small Set of Robust Acoustic Features for Emotion Recognition: Challenges

The search of a small acoustic feature set for emotion recognition faces three main challenges. Such a feature set must be robust to large diversity of contexts in real-life applications; model parameters must also be optimized for reduced subsets; finally, the result of feature selection must be evaluated in cross-corpus condition. The goal of the present study is to select a consensual set of acoustic features for valence recognition using classification and non-classification based feature ranking and cross-corpus experiments, and to optimize emotional models simultaneously. Five realistic corpora are used in this study: three of them were collected in the framework of the French project on robotics ROMEO, one is a game corpus (JEMO) and one is the well-known AIBO corpus. Combinations of features found with non-classification based methods (information gain and Gaussian mixture models with Bhattacharyya distance) through multi-corpora experiments are tested under cross-corpus conditions, simultaneously with SVM parameters optimization. Reducing the number of features goes in pair with optimizing model parameters. Experiments carried on randomly selected features from two acoustic feature sets show that a feature space reduction is needed to avoid over-fitting. Since a Grid search tends to find non-standard values with small feature sets, the authors propose a multi-corpus optimization method based on different corpora and acoustic feature subsets which ensures more stability. The results show that acoustic families selected with both feature ranking methods are not relevant in cross-corpus experiments. Promising results have been obtained with a small set of 24 voiced cepstral coefficients while this family was ranked in the 2nd and 5th positions with both ranking methods. The proposed optimization method is more robust than the usual Grid search for cross-corpus experiments with small feature sets.

Short text classification based on strong feature thesaurus

Data sparseness, the evident characteristic of short text, has always been regarded as the main cause of the low accuracy in the classification of short texts using statistical methods. Intensive research has been conducted in this area during the past decade. However, most researchers failed to notice that ignoring the semantic importance of certain feature terms might also contribute to low classification accuracy. In this paper we present a new method to tackle the problem by building a strong feature thesaurus (SFT) based on latent Dirichlet allocation (LDA) and information gain (IG) models. By giving larger weights to feature terms in SFT, the classification accuracy can be improved. Specifically, our method appeared to be more effective with more detailed classification. Experiments in two short text datasets demonstrate that our approach achieved improvement compared with the state-of-the-art methods including support vector machine (SVM) and Naive Bayes Multinomial.

Risk aversion in information seeking

The information gain model argues that participants select alternatives with a larger expected value of information gain. The present study investigated risk aversion in information seeking to examine whether the expected value always determines information-seeking behaviour. For this investigation, we used a scale method selection task in which participants were required to select one of two scales for weighing coins in order to find an underweight coin. Two experiments showed that participants more frequently selected the alternative that provided information gain without risk, although its expected information gain was smaller. This finding indicates the presence of risk aversion in information seeking, suggesting that information-seeking behaviour is affected by risk associated with obtaining information gain.

ON GENE SELECTION AND CLASSIFICATION FOR CANCER MICROARRAY DATA USING MULTI-STEP CLUSTERING AND SPARSE REPRESENTATION

Microarray data profiles gene expression on a whole genome scale, and provides a good way to study associations between gene expression and occurrence or progression of cancer disease. Many researchers realized that microarray data is useful to predict cancer cases. However, the high dimension of gene expressions, which is significantly larger than the sample size, makes this task very difficult. It is very important to identify the significant genes causing cancer. Many feature selection algorithms have been proposed focusing on improving cancer predictive accuracy at the expense of ignoring the correlations between the features. In this work, a novel framework (named by SGS) is presented for significant genes selection and efficient cancer case classification. The proposed framework first performs a clustering algorithm to find the gene groups where genes in each group have higher correlation coefficient, and then selects (1) the significant (2) genes in each group using the Bayesian Lasso method and important gene groups using the group Lasso method, and finally builds a prediction model based on the shrinkage gene space with efficient classification algorithm (such as support vector machine (SVM), 1NN, and regression). Experimental results on public available microarray data show that the proposed framework often outperforms the existing feature selection and prediction methods such as SAM, information gain (IG), and Lasso-type prediction models.

Bayesian inference for the information gain model

One of the most popular paradigms to use for studying human reasoning involves the Wason card selection task. In this task, the participant is presented with four cards and a conditional rule (e.g., “If there is an A on one side of the card, there is always a 2 on the other side”). Participants are asked which cards should be turned to verify whether or not the rule holds. In this simple task, participants consistently provide answers that are incorrect according to formal logic. To account for these errors, several models have been proposed, one of the most prominent being the information gain model (Oaksford & Chater, Psychological Review, 101, 608–631, 1994). This model is based on the assumption that people independently select cards based on the expected information gain of turning a particular card. In this article, we present two estimation methods to fit the information gain model: a maximum likelihood procedure (programmed in R) and a Bayesian procedure (programmed in WinBUGS). We compare the two procedures and illustrate the flexibility of the Bayesian hierarchical procedure by applying it to data from a meta-analysis of the Wason task (Oaksford & Chater, Psychological Review, 101, 608–631, 1994). We also show that the goodness of fit of the information gain model can be assessed by inspecting the posterior predictives of the model. These Bayesian procedures make it easy to apply the information gain model to empirical data. Supplemental materials may be downloaded along with this article from www.springerlink.com.Electronic supplementary materialThe online version of this article (doi:10.3758/s13428-010-0057-5) contains supplementary material, which is available to authorized users.

Information Seeking in a Non-Hypothesis Testing Task

The information gain model (Oaksford and Chater, Psychological Review 101, 608–631, 1994) advocates that participants attempt to achieve a larger expected information gain when they have to test an if-then rule or hypothesis. However, acquisition of larger expected information gain could also be operational when participants do not have to test a hypothesis. This study devised a new task to investigate whether participants would seek larger expected information gain when they were not required to test a hypothesis. The task required participants to select one out of two balance scales for weighing coins in order to detect an underweight coin. We discovered that participants more frequently selected the balance scale that provided smaller expected information gain. This finding suggests that the preference for larger expected information gain may not apply to non-hypothesis testing settings.

Belief Updating and Test Sequences in Hypothesis Testing: An Examination Based on an Information Gain Model

Belief Updating and Test Sequences in Hypothesis Testing: An Examination Based on an Information Gain Model

Popper's Severity of Test as an intuitive probabilistic model of hypothesis testing

AbstractSeverity of Test (SoT) is an alternative to Popper's logical falsification that solves a number of problems of the logical view. It was presented by Popper himself in 1963. SoT is a less sophisticated probabilistic model of hypothesis testing than Oaksford & Chater's (O&C's) information gain model, but it has a number of striking similarities. Moreover, it captures the intuition of everyday hypothesis testing.

How do individuals reason in the Wason card selection task?

AbstractThe probabilistic approach to human reasoning is exemplified by the information gain model for the Wason card selection task. Although the model is elegant and original, several key aspects of the model warrant further discussion, particularly those concerning the scope of the task and the choice process of individuals.

Modelling municipal solid waste generation: A review

The objective of this paper is to review previously published models of municipal solid waste generation and to propose an implementation guideline which will provide a compromise between information gain and cost-efficient model development. The 45 modelling approaches identified in a systematic literature review aim at explaining or estimating the present or future waste generation using economic, socio-demographic or management-orientated data. A classification was developed in order to categorise these highly heterogeneous models according to the following criteria – the regional scale, the modelled waste streams, the hypothesised independent variables and the modelling method. A procedural practice guideline was derived from a discussion of the underlying models in order to propose beneficial design options concerning regional sampling (i.e., number and size of observed areas), waste stream definition and investigation, selection of independent variables and model validation procedures. The practical application of the findings was demonstrated with two case studies performed on different regional scales, i.e., on a household and on a city level. The findings of this review are finally summarised in the form of a relevance tree for methodology selection.