The integration of Artificial Intelligence (AI) into smart farming, particularly Crop Recommendation System (CRS), has propelled significant advancements but is often hindered by the ‘black box’ nature of models, which limits transparency and trust. This study aims to enhance smart farming by embedding explainable Artificial Intelligence (XAI) techniques – specifically Contrastive Explanation Method (CEM) and Accumulated Local Effects (ALE) – within CRS, empowering farmers to understand AI-generated crop suggestions. Implemented an XAI-driven CRS, utilising Local Interpretable Model-agnostic Explanations (LIME), SHapley Additive exPlanations (SHAP), CEM, and ALE for comprehensive explainability. Notably, CEM provides farmers with actionable contrastive explanations, while ALE details the average influence of environmental factors. To address data scarcity, Generative Adversarial Networks (GANs) were used to augment the dataset with synthetic data, and an interactive, explainable interface was developed using Streamlit. Results show a substantial improvement in system interpretability and user trust, evidenced by clearer, actionable explanations for farmers. Quantitatively, incorporating GAN-augmented data improved the Random Forest model’s Area Under the Receiver Operating Characteristic curve (AUROC) from 0.94 to 0.985 and F1-score from 0.93 to 0.98. This research is the first to integrate CEM and ALE in CRS, establishing a new benchmark for transparent and effective AI-powered agricultural decision-making.

Sign Language (SL) is the only means of communication for the hearing-impaired people. Normal people have difficulty understanding SL, resulting in a communication barrier between hearing impaired people and hearing community. However, the Sign Language Recognition System (SLRS) has helped to bridge the communication gap. Many SLRs are proposed for recognizing SL; however, a limited number of works are reported for Indian Sign Language (ISL). Most of the existing SLRS focus on global features other than the Region of Interest (ROI). Focusing more on the hand region and extracting local features from the ROI improves system accuracy. The attention mechanism is a widely used technique for emphasizing the ROI. However, only a few SLRS used the attention method. They employed the Convolution Block Attention Module and temporal attention but Spatial Attention (SA) is not utilized in previous SLRS. Therefore, a novel SA based SLRS named Spatial Attention-based Sign Language Recognition Module (SASLRM) is proposed to recognize ISL words for emergency situations. SASLRM recognizes ISL words by combining convolution features from a pretrained VGG-19 model and attention features from a SA module. The proposed model accomplished an average accuracy of 95.627% on the ISL dataset. The proposed SASLRM is further validated on LSA64, WLASL, and Cambridge Hand Gesture Recognition datasets where, the proposed model reached an accuracy of 97.84%, 98.86%, and 98.22%, respectively. The results indicate the effectiveness of the proposed SLRS in comparison with the existing SLRS.

To date, there has been relatively little research in the field of credit risk analysis that compares all of the well known statistical, optimization technique (heuristic methods) and machine learning based approaches in a single article. Review on credit risk assessment using sixteen well-known approaches has been conducted in this work. The accuracy of the machine learning approaches in dealing with financial difficulties is superior to that of traditional statistical methods, especially when dealing with nonlinear patterns, according to the findings. Hybrid or Ensemble algorithms, on the other hand have been found to outperform their traditional counterparts – standalone classifiers in the vast majority of situations. Finally, the paper compares the models with nine machine learning classifiers utilizing two benchmark datasets. In this study, we have encountered with 46 datasets, among them 35 datasets have been utilized for once; whereas among the other 11 datasets, Australian, German and Japanese are the three most frequently utilized datasets by the researchers. The study showed that the performance of ensemble classifiers were very much significant. As per the experimental result, for both datasets ensemble classifiers outperformed other standalone classifiers which validate with the prior research also. Although some of these approaches have a high level of accuracy, additional study is required to discover the right parameters and procedures for better outcomes in a transparent manner. Additionally this study is a valuable reference source for analyzing credit risk for both academic and practical domains, since it contains relevant information on the most major machine learning approaches employed so far.

Abstract A system which is transparent and has less decision rules is an efficient, user‐convincing system and moreover convenient and manageable to fields like banking, business, and medical. Decision Tree (DT) is a data mining technique which is transparent and produces a set of production rules for decision‐making. However sometimes it creates some unnecessary and redundant rules which diminish its comprehensibility. Thus a system named Transparent Expert System of Rules (TESR) is proposed in this paper to efficiently improve comprehensibility of the DT by reducing the number of rules drastically without compromising accuracy. The proposed system adopts a Sequential Hill Climbing method with a flexible heuristic function to prune the insignificant rules from decision rules generated by DT. Finally, the proposed TESR system produces a transparent and comprehensible rule set for a decision. The proposed TESR performance is evaluated using 10 datasets and is compared with simple DT (ID3, C4.5, and Classification and Regression Trees) and also two of the existing transparent systems with respect to comprehensibility, accuracy, precision, recall, and F‐measures.

Mortality rate due to fatal heart disease (HD) or cardiovascular disease (CVD) has increased drastically over the world in recent decades. HD is a very hazardous problem prevailing among people which is treatable if detected early. But in most of the cases, the disease is not diagnosed until it becomes severe. Hence, it is requisite to develop an effective system which can accurately diagnosis HD and provide a concise description for the underlying causes [risk factors (RFs)] of the disease, so that in future HD can be controlled only by managing the primary RFs. Recently, researchers are using various machine learning algorithms for HD diagnosis, and neural network (NN) is one among them which has attracted tons of people because of its high performance. But the main obstacle with a NN is its black-box nature, i.e., its incapability in explaining the decisions. So, as a solution to this pitfall, the rule extraction algorithms can be very effective as they can extract explainable decision rules from NNs with high prediction accuracies. Many neural-based rule extraction algorithms have been applied successfully in various medical diagnosis problems. This study assesses the performance of rule extraction algorithms for HD diagnosis, particularly those that construct rules recursively from NNs. Because they subdivide a rule’s subspace until the accuracy improves, recursive algorithms are known for delivering interpretable decisions with high accuracy. The recursive rule extraction algorithms’ efficacy in HD diagnosis is demonstrated by the results. Along with the significant data ranges for the primary RFs, a maximum accuracy of 82.59% is attained.

The issue of class imbalance and its consequences over the conventional learning models is a well-investigated topic, as it highly influences performances of real-life classification tasks. Amongst the available solutions, Synthetic Minority Oversampling Technique (SMOTE) imprints efficacy in balancing the data through synthetic minority instance generation. However, SMOTE suffers from the drawback of redundant data generation owing to uniform oversampling rate in regard to which, SMOTE with a customised oversampling rate has been investigated recently. In parallel to this, ensemble learning approaches are quite effective in improving prediction abilities of a set of weak classifiers through adaptive-weighted training. However, it does not account the imbalanced nature of the data during training. Through this paper, Correlation-based Oversampling aided Cost Sensitive Ensemble learning (CorrOV-CSEn) is proposed by integrating correlation-based oversampling with the AdaBoost ensemble learning model. The correlation-based oversampling entails to define a customised oversampling rate and a suitable oversampling zone while a misclassification ratio-based cost-function is introduced in the AdaBoost model to administer adaptive learning of imbalanced cases. CorrOV-CSEn is evaluated against 13 state-of-the-art methods by using 8 simulation datasets. The experimental results establish CorrOV-CSEn to be effective than the state-of-the-art methods in resolving the concerned issues.

Classification is one of the important tasks in data mining. Over the last few decades, neural networks have proved to be very effective in solving this task. This paper presents a novel algorithm, called Neural Network Boosting (NNBOOST) to improve the classification performance of neural networks using ensembling technique. The ensembling technique proposed here is based on the boosting concept to ensemble classifiers. A boosting algorithm sequentially learns a new model by reassigning pattern weights. NNBOOST algorithm adapts a new technique to assign weights to patterns based on the Euclidean distances of patterns from the centroids of respective classes. It assigns more weight to patterns closest to the centroid. The pattern weights are updated subsequently after building or learning a neural network model, based on the updated centroids to build the next neural network model. Weighted Majority voting scheme is used to combine all the learned neural network models. Weight or confidence of a learned neural network model is calculated as the ratio of correctly classified to misclassified training patterns. The algorithm is validated with six real life data sets taken from UCI repository. Results show the effectiveness of the algorithm in ensembling neural networks.

The class imbalance problem engraves the traditional learning models by degrading performance and yielding erroneous outcomes. It is the scenario where one of the class representation is over-shadowed by other classes in a data space. Presence of class imbalance can cause a grave difficulty as misclassification cost of minority class tends to be very high. Presence of overlapping cases along with the case of imbalanced data, can lead to create grim situation for effective learning. In this study, an in-depth analysis of the effects of class imbalance and class overlapping in conventional learning models has been presented. A data level approach is adapted with one-class SVM-based anomaly detection to detect the cases of data overlapping while an adapted Tomek-link undersampling algorithm is defined to treat both overlapped and imbalanced cases. The proposed model evolves to eliminate borderline, redundant and overlapping cases with the account of Tomek-link pair and sparse neighbourhood. The proposed method has been evaluated with six state-of-the-art models for seven binary and two multiclass datasets, with respect to three standard learning models. The proposed model has been evaluated with cost-sensitive learning and extreme learning based approaches for imbalanced class learning. The proficiency of the proposed method over state-of-the-art models is established through experimental analyses.

Electroencephalogram (EEG) is a highly sensitive instrument and is frequently corrupted with eye blinks. Methods based on adaptive noise cancellation (ANC) and discrete wavelet transform (DWT) have been used as a standard technique for removal of eye blink artefacts. However, these methods often require visual inspection and appropriate thresholding for identifying and removing artefactual components from the EEG signal. The proposed work describes an automated windowed method with a window size of 0.45 s that is slid forward and fed to a support vector machine (SVM) classifier for identification of artefacts, after the identification of artefacts, it is fed to an autoencoder for correction of artefacts. The proposed method is evaluated on the data collected from the project entitled ‘Analysis of Brain Waves and Development of Intelligent Model for Silent Speech Recognition’. From the results it is observed that the proposed method performs better in identifying and removing artefactual components from EEG data than existing wavelet and ANC based methods. The proposed method does not require the application of independent component analysis (ICA) before processing and can be applied to multiple channels in parallel.

Class imbalance can be defined as a span among data mining, machine learning and pattern recognition domains that provides to learn from a data-space having unequal class distribution. Common classifiers when trained by imbalanced data tend to bias towards the class possessing bulk instances causing misclassification of upcoming patterns/instances. The study reveals that presence of redundant borderline instances and outliers in the data-space severely catalyzes the effect of class imbalance. The Condensed Nearest Neighbor and Tomek-link undersampling techniques are used as the baseline systems for the present study, and an improved undersampling algorithm is proposed to be employed in the pre-processing stage by amalgamating aspects of outlier and redundancy detection to the baseline system. The proposed scheme imparts to detect outlier, redundant and noisy instances having least contribution in estimating accurate class labels. Thus, a data-level solution has been offered to the concerned problem with novelty in effective elimination of majority instances without losing valuable information. The proposed scheme is implemented and validated with Back Propagation Neural Network (BPNN), K-Nearest-Neighbor (K-NN), Support Vector Machine (SVM) and Naive Bayes classifiers for 10 real-life datasets. The experimental results obtained clearly manifest the superiority of the proposed scheme over the baseline schemes.