Stream data might make farming more sustainable, efficient, and ecologically friendly at a time when agricultural concerns include feeding a rising population and slowing climate change. This study examines how stream data promotes sustainable farming utilizing three novel methods: Random Forest, CNN, and Reinforcement Learning. Our studies with these approaches revealed how stream data may change things. Random Forest is one of the greatest crop health algorithms because it leverages real-time sensor network data. CNN uses high-resolution images to identify and manage pests. Irrigation optimization demonstrates RL by managing water, avoiding waste, and protecting resources. Comparing the supplied approaches shows they outperform six conventional agricultural methods. These findings demonstrate how real- time data-driven strategies might enhance food health, resource consumption, and environmental impact. These adjustments are necessary for food security and climate change adaptation. Stream data is increasingly essential to healthy farms as we feed everyone and safeguard the planet. Data, algorithms, and agricultural practices that work together build a robust, ecologically responsible farm. To ensure sustainable agriculture, we must continue adopting these cutting-edge approaches. This protects our food supply and global health.

Intrusion detection systems are the primitive elements in safeguarding vital infrastructures, which are able to identify malicious activity on hosts or networks. The efficient IDS must be able to handle a variety of threats is a difficult security cum threat related problems. Numerous strategies have been put out in the literature as of right now to increase intrusion detection efficiency while taking into account some of these restrictions, like mobility and resource limitations. This review paper discusses about the early research works on performed on IDS using Deep Learning and Machine Learning techniques. This paper provides a qualitative assessment of these methods and deeper insights about the analysis as well as a summary of the field's current themes and the methods used to train and implement IDSs. We address the overall limitations of these solutions, namely the types of attacks that these approaches are unable to identify and the setup limitations that are specific to each of these works, even though they offer insightful information and solutions for certain aspects of these constraints.

The necessity for Computer networks' use is expanding quickly, which raises problems with preserving network secrecy, availability, and integrity. Intrusion can be defined as an intentional breach of security rules within a secured network. Such intrusions can be identified by an Intrusion Detection system which searches for any malicious actions and recognized dangers within a secured network. Intrusion detection systems patrol the traffic passing through computer systems and give out notifications when they do. Recently, an immense upsurge in cyber-attack cases on computer networks has imposed the need for an effective Intrusion detection system than ever before. Nowadays, network administrators are utilizing multivarious kinds of Intrusion Detection Systems (IDS), in order to monitor network traffic for malicious and unauthorized activities. This review paper focuses on various research works that has developed an approach for evaluating or identifying IDS using many kinds of Machine Learning (ML) and Deep Learning (DL) techniques.

In today’s life, Traffic sign identification is a significant domain of environment awareness system. This traffic sign identification is becoming a top priority for modern transportation systems as it is highly essential to maintain the road safety nowadays. While detecting the traffic signs using various target detection techniques, many real-time problems are being faced like easy omission, undesirable light, inaccurate positioning for traffic signs (during detection), disorientation, motion blur, color fade, occlusion, rain, and snow. In view of these problems that the traffic signs cannot be recognized well, many novel target detection technologies are emerging, which in-turn solves these problems. This article introduces a reliable traffic sign categorization system, with the help of OpenCV for image enhancement and a five-layered Convolution Neural Network. The significance of sophisticated traffic sign identification for preventing accidents and promoting road safety is emphasized by this research that classifies traffic signs. The proposed CNN model has proved to achieve a remarkable classification accuracy and flexibility in response to changes in sign and environment, as demonstrated by the outcomes of the experiments. The strength of the proposed model has been tested on the German Traffic Sign Dataset and the experimental results have unfolded the fact that this model has recognized German traffic signs, with a better classification accuracy of 97.3%.

An improved elephant herding optimization (EHOI) is proposed for continuous function optimization, financial stress prediction problem and two engineering optimization problems in this work. Elephant Herding Optimization (EHO) is a swarm-based algorithm and was inspired by the social behaviour of elephant clans. In the literature, EHO has received great attention from researchers due to its global optimization capability and ease of implementation. However, it has few limitations like random replacing of worst individual and lack of exploitation, which leads to slow convergence. In this work, EHO was enhanced with the help of the position updating mechanism of sine-cosine algorithm (SCA) and opposition-based learning (OBL). The separating operator in original EHO was replaced by the sine-cosine mechanism and followed by opposition-based learning was introduced to increase the performance of EHO. The proposed EHOI was compared with eight well-known metaheuristic optimization algorithms (MAs) by using 23 classical benchmark functions, 10 modern CEC2019 benchmark test functions and two engineering optimization problems. From the results, it was observed that the proposed EHOI outperformed most of the selected MAs in terms of solution quality. A kernel extreme learning machine (KELM) model was optimized by improved EHO and applied to handle financial stress prediction. The efficiency of the proposed EHOI_KELM model was tested on two popular financial datasets and compared with popular classifiers, EHO_KELM and SCA_KELM models. The results demonstrate that the proposed EHOLKELM model shows excellent performance than the popular classifiers, EHO_KELM & SCA_KELM models and it can also serve as an effective tool for financial prediction.

Recent trend of research is to hybridize two and more metaheuristics algorithms to obtain superior solution in the field of optimization problems. This paper proposes a newly developed wrapper-based feature selection method based on the hybridization of Biogeography Based Optimization (BBO) and Sine Cosine Algorithm (SCA) for handling feature selection problems. The position update mechanism of SCA algorithm is introduced into the BBO algorithm to enhance the diversity among the habitats. In BBO, the mutation operator is got rid of and instead of it, a position update mechanism of SCA algorithm is applied after the migration operator, to enhance the global search ability of Basic BBO. This mechanism tends to produce the highly fit solutions in the upcoming iterations, which results in the improved diversity of habitats. The performance of this Improved BBO (IBBO) algorithm is investigated using fourteen benchmark datasets. Experimental results of IBBO are compared with eight other search algorithms. The results show that IBBO is able to outperform the other algorithms in majority of the datasets. Furthermore, the strength of IBBO is proved through various numerical experiments like statistical analysis, convergence curves, ranking methods, and test functions. The results of the simulation have revealed that IBBO has produced very competitive and promising results, compared to the other search algorithms.

BACKGROUND AND OBJECTIVE:Infant cry signal carries several levels of information about the reason for crying (hunger, pain, sleepiness and discomfort) or the pathological status (asphyxia, deaf, jaundice, premature condition and autism, etc.) of an infant and therefore suited for early diagnosis. In this work, combination of wavelet packet based features and Improved Binary Dragonfly Optimization based feature selection method was proposed to classify the different types of infant cry signals.METHODS:Cry signals from 2 different databases were utilized. First database contains 507 cry samples of normal (N), 340 cry samples of asphyxia (A), 879 cry samples of deaf (D), 350 cry samples of hungry (H) and 192 cry samples of pain (P). Second database contains 513 cry samples of jaundice (J), 531 samples of premature (Prem) and 45 samples of normal (N). Wavelet packet transform based energy and non-linear entropies (496 features), Linear Predictive Coding (LPC) based cepstral features (56 features), Mel-frequency Cepstral Coefficients (MFCCs) were extracted (16 features). The combined feature set consists of 568 features. To overcome the curse of dimensionality issue, improved binary dragonfly optimization algorithm (IBDFO) was proposed to select the most salient attributes or features. Finally, Extreme Learning Machine (ELM) kernel classifier was used to classify the different types of infant cry signals using all the features and highly informative features as well.RESULTS:Several experiments of two-class and multi-class classification of cry signals were conducted. In binary or two-class experiments, maximum accuracy of 90.18% for H Vs P, 100% for A Vs N, 100% for D Vs N and 97.61% J Vs Prem was achieved using the features selected (only 204 features out of 568) by IBDFO. For the classification of multiple cry signals (multi-class problem), the selected features could differentiate between three classes (N, A & D) with the accuracy of 100% and seven classes with the accuracy of 97.62%.CONCLUSION:The experimental results indicated that the proposed combination of feature extraction and selection method offers suitable classification accuracy and may be employed to detect the subtle changes in the cry signals.

Pattern recognition is the task of choosing the pertinent and descriptive features that best describes the target concept during feature selection (FS). Choosing such descriptive features becomes a daunting task in large-volume datasets which have high dimensionality. In such cases, selecting the discriminative features with better classification accuracy is tedious. To overcome this issue, in recent times, many search heuristics have been used to select the best features from these large-volume datasets. In this work, a sine–cosine algorithm (SCA) with Elitism strategy and new best solution update mechanism is proposed to select best features/attributes to improve the classification accuracy. Improved version of SCA is named as improved sine–cosine algorithm (ISCA). Wrapper-based FS approach is used. ELM with radial basis function kernel is used as the learning algorithm. For experimentation, ISCA is tested with ten benchmark datasets. Experimental results have proved the efficiency of ISCA in achieving better classification performance along with less number of features. Both computational and time complexity has been handled by this algorithm in an expedite manner. The potency of this algorithm is proved by comparing its results with three well-known meta-heuristics such as GA, PSO and basic SCA. Finally, it can be seen that pattern classification using ISCA has been commendable in achieving better classification performance.

A novel clinical decision support system is proposed in this paper for evaluating the fetal well-being from the cardiotocogram (CTG) dataset through an Improved Adaptive Genetic Algorithm (IAGA) and Extreme Learning Machine (ELM). IAGA employs a new scaling technique (called sigma scaling) to avoid premature convergence and applies adaptive crossover and mutation techniques with masking concepts to enhance population diversity. Also, this search algorithm utilizes three different fitness functions (two single objective fitness functions and multi-objective fitness function) to assess its performance. The classification results unfold that promising classification accuracy of 94% is obtained with an optimal feature subset using IAGA. Also, the classification results are compared with those of other Feature Reduction techniques to substantiate its exhaustive search towards the global optimum. Besides, five other benchmark datasets are used to gauge the strength of the proposed IAGA algorithm.

Elderly people are commonly affected by Parkinson's disease (PD) which is one of the most common neurodegenerative disorders due to the loss of dopamine-producing brain cells. People with PD's (PWP) may have difficulty in walking, talking or completing other simple tasks. Variety of medications is available to treat PD. Recently, researchers have found that voice signals recorded from the PWP is becoming a useful tool to differentiate them from healthy controls. Several dysphonia features, feature reduction/selection techniques and classification algorithms were proposed by researchers in the literature to detect PD. In this paper, hybrid intelligent system is proposed which includes feature pre-processing using Model-based clustering (Gaussian mixture model), feature reduction/selection using principal component analysis (PCA), linear discriminant analysis (LDA), sequential forward selection (SFS) and sequential backward selection (SBS), and classification using three supervised classifiers such as least-square support vector machine (LS-SVM), probabilistic neural network (PNN) and general regression neural network (GRNN). PD dataset was used from University of California-Irvine (UCI) machine learning database. The strength of the proposed method has been evaluated through several performance measures. The experimental results show that the combination of feature pre-processing, feature reduction/selection methods and classification gives a maximum classification accuracy of 100% for the Parkinson's dataset.

Pathological voice analysis is a challenging task and an important area of research in voice disorder identification. Until now, the long-time acoustic (LTA) parameters are used primitively to classify the disordered voices into pathological and normal. Selection of such optimal LTA features is a disputing task. Previous researchers have used various data projection methods like principle component analysis (PCA), linear discriminant analysis (LDA) and sub-optimal searching techniques like sequential forward selection (SFS), sequential backward selection (SBS), and individual feature selection (IFS) methods for this purpose. But, these methods work efficiently for linearly separable datasets only. In order to overcome these issues, we propose a hybrid expert system in this paper, which includes the optimal selection of LTA parameters using genetic algorithm (GA), followed by non-linear classification algorithms to classify the two classes of voice samples. Nowadays, though many non-linear and high-order spectral parameters of voices have been used in this application, LTA features are scoring more importance because their clinical diagnosis is of more ease. Within this context, the GA-based feature vector quantisation combined with SVM classification is demonstrated to be more reliable, yielding 96.86% of classification accuracy for a feature vector of length 10.

In recent years, various physiological signal based rehabilitation systems have been developed for the physically disabled in which electroencephalographic (EEG) signal is one among them. The efficiency of such a system depends upon the signal processing and classification algorithms. In order to develop an EEG based rehabilitation or assistive system, it is necessary to develop an effective EEG signal processing algorithm. This paper proposes Stockwell transform (ST) based analysis of EEG dynamics during different mental tasks. EEG signals from Keirn and Aunon database were used in this study. Three classifiers were employed such as k-means nearest neighborhood (kNN), linear discriminant analysis (LDA) and support vector machine (SVM) to test the strength of the proposed features. Ten-fold cross validation method was used to demonstrate the consistency of the classification results. Using the proposed method, an average accuracy ranging between 84.72% and 98.95% was achieved for multi-class problems (five mental tasks).

In recent times, vocal fold problems have been increasing dramatically due to unhealthy social habits and voice abuse. Non-invasive methods like acoustic analysis of voice signals can be used to investigate such problems. Various feature extraction techniques are used to classify the voice signals into normal and pathological. Among them, long-time acoustical parameters are used by many researchers. The selection of best long-time acoustical parameters is very important to reduce the computational complexity, as well as to achieve better accuracy with minimum number of features. In order to select best long-time acoustical parameters, different feature reduction methods or feature selection methods are proposed by researchers. In this work, genetic algorithm (GA) based optimal selection of long-time acoustical parameters is proposed to achieve higher accuracy with minimum number of features. The classification is carried out using k-nearest neighbourhood (k-NN) classifier. In comparison with other works in the literature, the simulation results show that a minimum of 5 features are required to classify the voice signals by GA and a better accuracy of 94.29% is achieved.

Acoustical parameters extracted from the recorded voice samples are actively pursued for accurate detection of vocal fold pathology. Most of the system for detection of vocal fold pathology uses high quality voice samples. This paper proposes a hybrid expert system approach to detect vocal fold pathology using the compressed/low quality voice samples which includes feature extraction using wavelet packet transform, clustering based feature weighting and classification. In order to improve the robustness and discrimination ability of the wavelet packet transform based features (raw features), we propose clustering based feature weighting methods including k-means clustering (KMC), fuzzy c-means (FCM) clustering and subtractive clustering (SBC). We have investigated the effectiveness of raw and weighted features (obtained after applying feature weighting methods) using four different classifiers: Least Square Support Vector Machine (LS-SVM) with radial basis kernel, k-means nearest neighbor (kNN) classifier, probabilistic neural network (PNN) and classification and regression tree (CART). The proposed hybrid expert system approach gives a promising classification accuracy of 100% using the feature weighting methods and also it has potential application in remote detection of vocal fold pathology. (C) 2013 Elsevier B. V. All rights reserved.

Dysfluency and stuttering are a break or interruption of normal speech such as repetition, prolongation, interjection of syllables, sounds, words or phrases and involuntary silent pauses or blocks in communication. Stuttering assessment through manual classification of speech dysfluencies is subjective, inconsistent, time consuming and prone to error. This paper proposes an objective evaluation of speech dysfluencies based on the wavelet packet transform with sample entropy features. Dysfluent speech signals are decomposed into six levels by using wavelet packet transform. Sample entropy (SampEn) features are extracted at every level of decomposition and they are used as features to characterize the speech dysfluencies (stuttered events). Three different classifiers such as k-nearest neighbor (kNN), linear discriminant analysis (LDA) based classifier and support vector machine (SVM) are used to investigate the performance of the sample entropy features for the classification of speech dysfluencies. 10-fold cross validation method is used for testing the reliability of the classifier results. The effect of different wavelet families on the classification performance is also performed. Experimental results demonstrate that the proposed features and classification algorithms give very promising classification accuracy of 96.67% with the standard deviation of 0.37 and also that the proposed method can be used to help speech language pathologist in classifying speech dysfluencies.

Crying is the most noticeable behavior of infancy. Infant cry signals can be used to identify physical or psychological status of an infant. Recently, acoustic analysis of infant cry signal has shown promising results and it has been proven to be an excellent tool to investigate the pathological status of an infant. This paper proposes short-time Fourier transform (STFT) based time-frequency analysis of infant cry signals. Few statistical features are derived from the time-frequency plot of infant cry signals and used as features to quantify infant cry signals. General Regression Neural Network (GRNN) is employed as a classifier for discriminating infant cry signals. Two classes of infant cry signals are considered such as normal cry signals and pathological cry signals from deaf infants. To prove the reliability of the proposed features, two neural network models such as Multilayer Perceptron (MLP) and Time-Delay Neural Network (TDNN) trained by scaled conjugate gradient algorithm are also used as classifiers. The experimental results show that the GRNN classifier gives very promising classification accuracy compared to MLP and TDNN and the proposed method can effectively classify normal and pathological infant cries.

The selection of most suitable mother wavelet function is still an open research problem in various signal and image processing applications. This paper presents a comparative study of different wavelet families (Daubechies, Symlets, Coiflets, and Biorthogonal) for analysis of wrist motions from electromyography (EMG) signals. EMG signals are decomposed into three levels using discrete wavelet packet transform. From the decomposed EMG signals, root mean square (RMS) value, autoregressive (AR) model coefficients (4th order) and waveform length (WL) are extracted. Two data projection methods such as principal component analysis (PCA) and linear disciminant analysis (LDA) are used to reduce the dimensionality of the extracted features. Probabilistic neural network (PNN) and general regression neural network (GRNN) are employed to classify the different types of wrist motions, which gives a promising accuracy of above 99%. From the analysis, we inferred that 'Biorthogonal' and 'Coiflets' wavelet families are more suitable for accurate classification of EMG signals of different wrist motions.

A cry is the first verbal communication of infants and it is described as a loud, high-pitched sound made by infants in response to certain situations. Infant cry signals can be used to identify physical or psychological status of an infant. Recently, acoustic analysis of infant cry signal has shown promising results and it has been proven to be an excellent tool to investigate the pathological status of an infant. This paper proposes short-time Fourier transform (STFT) based time-frequency analysis of infant cry signals. Few statistical features are derived from the time-frequency plot of infant cry signals and used as features to quantify infant cry signals. Two types of radial basis neural networks such as Probabilistic Neural Network (PNN) and General Regression Neural Network are employed as classifiers for discriminating infant cry signals. Two classes of infant cry signals are considered such as normal cry signals and pathological cry signals of infants with asphyxia. For comparison, the proposed features are also tested using two neural network models such as Multilayer Perceptron (MLP) and Time-Delay Neural Network (TDNN) trained by scaled conjugate gradient algorithm. The experimental results show that the PNN and GRNN give very promising classification accuracy compared to MLP and TDNN and the proposed methods can effectively classify normal and pathological infant cries of infants with asphyxia.