Multiple Class Classification Research Articles

Sentiment Analysis Based on Travelers’ Reviews Using the SVM Model with Enhanced Conjunction Rule-Based Approach

Abstract: It is a tough task for tourism management to identify their user reviews and come up with solutions to the advancement of their tourism organizations. There are many social media reviews, and Tourism organizations face the challenge of evaluating numerous social media reviews to find solutions for advancing their organizations. It can be tough to physically assess all those reviews, social media has become a huge trend these days. People are constantly sharing their experiences and opinions on tourist places. By analyzing the sentiment of reviews, it may obtain useful information about the popularity of different tourist destinations. It's a great way to understand what people love about certain places. Sentiment classification is indeed a valuable tool in classifying reviews into different categories, aiding in decision-making. However, it's important to note that reviews often contain noisy content like typos and emoticons, which can affect the accuracy of the algorithms. Taking these aspects into consideration is crucial for achieving more accurate results. Decision-making and multiple class classification of reviews are possible with the application of sentiment classification. Sentiment analysis plays a crucial role in helping tourists make informed decisions about their travel destinations. In this particular paper, Using an Enhanced Conjunction Rule-Based Approach and Support Vector Machine (SVM) machine learning technique, the authors conducted sentiment analysis. They collected the dataset from different tourism review websites to train and evaluate their model. The findings of this paper are significant as they not only provide valuable insights in the field of tourism but also help in identifying the most appropriate algorithm for tourism-related analysis. The findings of this paper are significant as they not only provide valuable insights in the field of tourism but also help in identifying the most appropriate algorithm for tourism-related analysis. This information can greatly contribute to the development and improvement of tourism strategies and decision-making processes.

Analysis of EEG signals with the use of wavelet transform for accurate classification of Alzheimer Disease, Frontotemporal Dementia and healthy subjects using Machine Learning Models

Dementia is a brain disorder, if not prevented; takes the form of various types of diseases that have no cure yet. Accurate classification of multiple types of dementia diseases is required to provide proper medication to the patient so that growth of that disease can be delayed. This study analyzes EEG signal for the classification of multiple dementia diseases such as Alzheimer’s disease (AD), Fronto-temporal dementia (FTD) and control normal (CN) subjects using machine learning (ML) algorithms. Each of the 19 channels of EEG dataset is analyzed separately in this work to perform the classification. Combination of parameters like Hjorth Activity, Mobility and Complexity along with kurtosis value of the data has been extracted in time-frequency domain for each EEG frequency band (Delta, Theta, Alpha, Beta and Gamma) is applied to the machine learning algorithms. This research is focused on classification of multiple dementia classes (ADvsFTD) as well as three-way (ADvsFTDvsCN) classification. This research is validated using public EEG dataset with 23 participants of each category. Best classification result is achieved using random forest classifier and leave-one-subject-out (LOSO) cross validation method. The three-way classification i.e., ADvsCNvsFTD achieved best accuracy of 75.29%, whereas binary classifications i.e. ADvsCN, ADvsFTD and CNvsFTD achieved best accuracy of 88.90%, 88.44% and 84.10% respectively. The proposed framework shows better results than existing work on dementia classification using machine learning. The results obtained from proposed framework showed that combination of EEG frequency band features can be utilized for the classification of multiple dementia diseases with greater accuracy.

Automatic epileptic seizure detection using MSA-DCNN and LSTM techniques with EEG signals

To identify epilepsy, Electroencephalography (EEG) is an important and common tool used to study the electrical activity of the human brain. The machine learning-based classifier is utilized to detect the seizure by manually extracting the features from the EEG signals in previous works. Though, these effective benefits have been proved already with automatic feature extraction, they are unable to achieve the classification of multiple classes. Meanwhile, real-time epileptic seizure detection is unable to keep the capacity because the identifiable EGG is too long. Hence, this paper is decided to develop an enhanced deep learning architecture with EEG signal for performing automatic epileptic seizure detection. The EEG signal is collected from the standard datasets. The Fourier-Bessel Series Expansion-Based Empirical Wavelet Transform (FBSE-EWT) method is used to decompose the signal from the gathered data. In feature extraction, the decomposed signals are used and while extracting the signal features, the autoencoder is involved in that process. To reduce the computational overload, the relief-F feature ranking method is used for choosing the important signal features. The Long Short Term Memory (LSTM) and Multi-Scale Atrous-based Deep Convolutional Neural Networks (MSA-DCNN) are used that is named as Hybrid Deep Scheme (HDS) to detect epileptic seizures with the top-ranked features for epileptic seizure classification. The Black Widow Optimization (BWO) and the Spider Monkey Optimization (SMO) are combined to generate Adaptive Spider Monkey Black Widow Optimization (ASMBWO) that is employed to perform the parameter tuning into a classification technique. Using different measures, the experimental analysis is done between the conventional epileptic seizure detection and the proposed model to establish an enhanced performance of the proposed model.

A Lightweight Model for DDoS Attack Detection Using Machine Learning Techniques

The study in this paper characterizes lightweight IoT networks as being established by devices with few computer resources, such as reduced battery life, processing power, memory, and, more critically, minimal security and protection, which are easily vulnerable to DDoS attacks and propagating malware. A DDoS attack detection model is crucial for attacks in various industries, ensuring the availability and reliability of their networks and systems. The model distinguishes between legitimate and malicious traffic by analyzing network traffic patterns and identifying anomalies. This safeguards critical infrastructure, preserves business continuity, and protects the user experience, minimizing the impact of DDoS attacks. Numerous scholars have studied the notion that protecting lightweight IoT networks essentially requires improving intrusion detection systems. This research is valuable, as it follows a tailored pre-processing methodology specific to IoT network challenges, addressing a pressing need in cybersecurity by focusing on a growing concern related to IoT devices and DDoS attacks, enhancing the security of essential network systems in various industries by effectively detecting DDoS attacks, and developing a lightweight intrusion detection system that aligns with the limited resources of IoT devices. This manuscript proposes a compact and lightweight intrusion detection system that blends machine learning classifiers with a fresh approach to data pre-processing. The handling of missing values, data standardization using Standard Scalar, feature selection using ExtraTreeClassifier wherein only the 15 best features are extracted, and anomaly detection using a classifier are performed. The network dataset of TON-IOT and BOT-IOT datasets is used for experiments, specifically binary classifications and multiple-class classification for the experiment with DDoS and all attacks, respectively. There is an imbalance between the TON-IOT and BOT-IOT attack classes. In trials using the TON-IOT and BOT-IOT datasets, the classes were balanced using several iterations of the SMOTE approach. This research provides a number of classifier types, namely logistic regression, random forest, naïve bayes, artificial neural network, and k nearest neighbor algorithms, which are used to build a lightweight intrusion detection system that is ideally suited for protecting against DDoS attacks in IoT networks. The time taken to train and predict the DDoS attacks is also implemented. Random forest performed well under TON-IOT and naïve bayes performed well under BOT-IOT under binary and multiple-class classification, achieving an accuracy of 100% with less training and prediction time.

Deep convolution neural network for machine health monitoring using spectrograms of vibration signal and its EMD-intrinsic mode functions

A spectrum-image based representation of machine vibration signals with deep convolution neural network is proposed for machine fault classification in which the convolution layer is used for automatic feature extraction as an alternate to the conventional feature-based methods. Two different forms of spectrum representations are proposed, one based on the short time Fourier transform of the original signals and the other based on the short time Fourier transform of the intrinsic mode functions acquired by empirical mode decomposition. Empirical mode decomposition has its own merits in discriminating non stationary signals and the novelty of the work is to use the short time Fourier transform of intrinsic mode functions with deep convolution neural network model. The classification and validation accuracy of the model are investigated with respect to epochs. It is demonstrated that both spectrum-based techniques perform good with 100% model accuracies in a numerical experiment of binary classification on a bearing dataset that comprises of normal and faulty signals. In another experiment using milling data set, short time Fourier transform of intrinsic mode functions representation performs better with 100% training accuracy, F1 score of 0.8933 which is better than that of using short time Fourier transform of raw signals whose training accuracy is 64% and F1 score of 0.7486. The numerical study shows that the empirical mode decomposition based spectrum representation delivers the highest accuracy in the learning model obviating the necessity for independent feature extraction, feature selection, and dimension reduction. The numerical experiment is extended using empirical mode decomposition based spectrums for multiple class classification problems in bearing dataset. The confusion matrix obtained for 10 classes, shows that validation accuracy is 100% for all classes. The performance comparison throws light on the merits of empirical mode decomposition spectrum method over other state of the art methods.

A training pipeline of an arrhythmia classifier for atrial fibrillation detection using Photoplethysmography signal.

Photoplethysmography (PPG) signal is potentially suitable in atrial fibrillation (AF) detection for its convenience in use and similarity in physiological origin to electrocardiogram (ECG). There are a few preceding studies that have shown the possibility of using the peak-to-peak interval of the PPG signal (PPIp) in AF detection. However, as a generalized model, the accuracy of an AF detector should be pursued on the one hand; on the other hand, its generalizability should be paid attention to in view of the individual differences in PPG manifestation of even the same arrhythmia and the existence of sub-types. Moreover, a binary classifier for atrial fibrillation and normal sinus rhythm is not convincing enough for the similarity between AF and ectopic beats. In this study, we project the atrial fibrillation detection as a multiple-class classification and try to propose a training pipeline that is advantageous both to the accuracy and generalizability of the classifier by designing and determining the configurable options of the pipeline, in terms of input format, deep learning model (with hyperparameter optimization), and scheme of transfer learning. With a rigorous comparison of the possible combinations of the configurable components in the pipeline, we confirmed that first-order difference of heartbeat sequence as the input format, a 2-layer CNN-1-layer Transformer hybridR model as the learning model and the whole model fine-tuning as the implementing scheme of transfer learning is the best combination for the pipeline (F1 value: 0.80, overall accuracy: 0.87)R.

An Extension Network of Dendritic Neurons.

Deep learning (DL) has achieved breakthrough successes in various tasks, owing to its layer-by-layer information processing and sufficient model complexity. However, DL suffers from the issues of both redundant model complexity and low interpretability, which are mainly because of its oversimplified basic McCulloch-Pitts neuron unit. A widely recognized biologically plausible dendritic neuron model (DNM) has demonstrated its effectiveness in alleviating the aforementioned issues, but it can only solve binary classification tasks, which significantly limits its applicability. In this study, a novel extended network based on the dendritic structure is innovatively proposed, thereby enabling it to solve multiple-class classification problems. Also, for the first time, an efficient error-back-propagation learning algorithm is derived. In the extensive experimental results, the effectiveness and superiority of the proposed method in comparison with other nine state-of-the-art classifiers on ten datasets are demonstrated, including a real-world quality of web service application. The experimental results suggest that the proposed learning algorithm is competent and reliable in terms of classification performance and stability and has a notable advantage in small-scale disequilibrium data. Additionally, aspects of network structure constrained by scale are examined.

Comparison of common classification strategies for large-scale vegetation mapping over the Google Earth Engine platform

• We assessed the effect of various sample properties on classification performance. • The use of pixel time series from fusion data achieved optimal results. • Target class proportions and sample time frames affected accuracy. • Suboptimal methods had a larger impact on the accuracy of minority classes. • The combined use of Sentinel MSI and SAR data provided accurate vegetation maps. Vegetation resources have an essential role in sustainable development due to their close relationship with natural resource management and environmental protection. The monitoring of land use and cover is key for a more sustainable management of these resources, and Earth Observation satellites have provided an increasingly powerful platform for performing this task. To date, numerous classification algorithms have been developed for vegetation mapping, but a comparative evaluation of the strategies commonly used in large-scale applications (50000 km 2 and above) is lacking. We developed a classification framework based on random forests and Sentinel data within the Google Earth Engine platform to assess the performance of various strategies over a complex landscape with a wide range of vegetation classes, plot configurations, and agricultural practices. These strategies differed in key aspects related to the characteristics of the classifier and the sample, and were evaluated by class-specific and general accuracy metrics. We found that the use of pixel time series features from fusion data, class-balanced labels, and multi-season time frames enhanced overall performance by 1.3%–14.1% over alternative approaches, but in some cases also generated tradeoffs of 1.6%–8.5% between recall and precision. In general, suboptimal strategies were particularly ineffective for the detection of infrequent classes. Finally, the different parameter values used in the random forests did not have a significant influence over the results. Our results demonstrate the importance of algorithm design in the effective classification of multiple vegetation classes, corroborate the usefulness of Sentinel data to generate mapping products of high resolution and accuracy, and highlight the importance of cloud computing tools for the development of vegetation mapping tools in large-scale applications. These findings provide general guidelines for the design of future classification frameworks, which are necessary for facilitating a sustainable management of natural resources worldwide.

Transfer Learning in Brain Tumor Detection: from AlexNet to Hyb-DCNN-ResNet

Detecting abnormalities in the human body with magnetic resonance imaging has long been a challenge in medical computer-aided diagnosis (CAD). This paper presents a comprehensive review of research focusing on transfer learning (TL) in brain tumor detection. Each work starts from collecting MR images and substantial strategies are applied when preprocessing data including data augmentation and image segmentation. Multiple pre-trained models from AlexNet to Hyb-DCNN-ResNet in the latest work are focused. And the results of binary and multiple class classification are compared chronologically. Three pre-trained models which are frequently used to attain a good performance in brain tumor detection are illustrated in detail. And these pre-trained models, GoogLeNet, VGG and ResNet, all are capable to help the proposed systems reach the accuracy of 99%. The challenges even after transferring apposite knowledge to the target domain still exist in pluralistic forms. But the essence of transfer learning can support interdisciplinary research to get better performance.

An aggregate method for thorax diseases classification

A common problem found in real-word medical image classification is the inherent imbalance of the positive and negative patterns in the dataset where positive patterns are usually rare. Moreover, in the classification of multiple classes with neural network, a training pattern is treated as a positive pattern in one output node and negative in all the remaining output nodes. In this paper, the weights of a training pattern in the loss function are designed based not only on the number of the training patterns in the class but also on the different nodes where one of them treats this training pattern as positive and the others treat it as negative. We propose a combined approach of weights calculation algorithm for deep network training and the training optimization from the state-of-the-art deep network architecture for thorax diseases classification problem. Experimental results on the Chest X-Ray image dataset demonstrate that this new weighting scheme improves classification performances, also the training optimization from the EfficientNet improves the performance furthermore. We compare the aggregate method with several performances from the previous study of thorax diseases classifications to provide the fair comparisons against the proposed method.

Classification of malware for self-driving systems

Classification and distinguishing of malware is key to predict the malicious attack, which is essential in self-driving systems. In order to handle large number of malware variants, many machine learning methods have been proposed. However, the accuracy and efficiency of multiple class classification of malware still remained inadequate to meet demand. In this paper, we propose a 4-LFE method to deal with the issues above. We extract multi-features from malicious programs by combining pixel and n-gram features. In the process of feature selection, we apply L1-L2 penalty into the Logistic Regression, then use LDA to reduce dimensions of malware features. Based on the selected features, we study the performance of classification on ten machine learning algorithms. We assess our approach’s precision on a public dataset consisting 10,868 malware samples. Experimental results show our method could classify malware to their family with accuracy of 99.99%.

The Use of Ensemble Models for Multiple Class and Binary Class Classification for Improving Intrusion Detection Systems.

The pursuit to spot abnormal behaviors in and out of a network system is what led to a system known as intrusion detection systems for soft computing besides many researchers have applied machine learning around this area. Obviously, a single classifier alone in the classifications seems impossible to control network intruders. This limitation is what led us to perform dimensionality reduction by means of correlation-based feature selection approach (CFS approach) in addition to a refined ensemble model. The paper aims to improve the Intrusion Detection System (IDS) by proposing a CFS + Ensemble Classifiers (Bagging and Adaboost) which has high accuracy, high packet detection rate, and low false alarm rate. Machine Learning Ensemble Models with base classifiers (J48, Random Forest, and Reptree) were built. Binary classification, as well as Multiclass classification for KDD99 and NSLKDD datasets, was done while all the attacks were named as an anomaly and normal traffic. Class labels consisted of five major attacks, namely Denial of Service (DoS), Probe, User-to-Root (U2R), Root to Local attacks (R2L), and Normal class attacks. Results from the experiment showed that our proposed model produces 0 false alarm rate (FAR) and 99.90% detection rate (DR) for the KDD99 dataset, and 0.5% FAR and 98.60% DR for NSLKDD dataset when working with 6 and 13 selected features.

Fusing multi-scale context-aware information representation for automatic in-field pest detection and recognition

Automatic in-field pest detection and recognition using mobile vision technique is a hot topic in modern intelligent agriculture, but suffers from serious challenges including complexity of wild environment, detection of tiny size pest and classification of multiple classes of pests. While recent deep learning based mobile vision techniques have shown some success in overcoming above issues, one key problem is that towards large-scale multiple species of pest data, imbalanced classes significantly reduce their detection and recognition accuracy. In this paper, we propose a novel two-stages mobile vision based cascading pest detection approach (DeepPest) towards large-scale multiple species of pest data. This approach firstly extracts multi-scale contextual information of the images as prior knowledge to build up a context-aware attention network for initial classification of pest images into crop categories. Then, a multi-projection pest detection model (MDM) is proposed and trained by crop-related pest images. The role of MDM can combine pest contextual information from low-level convolutional layers with these in high-level convolutional layers for generating the super-resolved feature. Finally, we utilize the attention mechanism and data augmentation to improve the effectiveness of in-field pest detection. We evaluate our method on our newly established large-scale dataset In-Field Pest in Food Crop (IPFC) and sufficient experimental results show that DeepPest proposed in this paper outperforms state-of-the-art object detection methods in detecting in-field pest.

Active learning in multiple-class classification problems via individualized binary models

We propose a unified algorithm for both categorical and ordinal labeled data in multiclass classification problems, where each subject belongs to one class only. In training an effective classification rule, it is critical that one have and rely on a sufficient amount of reliably labeled data. As information on the training sample sizes needed to obtain satisfactory performance is lacking, we adopt an adaptive subject recruiting scheme with an experimental design criterion to shorten the training process. Because this kind of active learning method is naturally conducted in a sequential manner, we adopt sequential analysis to control the required sample size and ensure the performance of the final classifier. Additionally, we report its statistical properties and numerical results from using synthesized and real data.

ESSN: Enhanced Semantic Segmentation Network by Residual Concatenation of Feature Maps

Semantic segmentation performs pixel-level classification of multiple classes in the input image. Previous studies on semantic segmentation have used various methods such as multi-scale image, encoder-decoder, attention, spatial pyramid pooling, conditional random field, and generative models. However, the contexts of various sizes and types in diverse environments make their performance limited in robustly detecting and classifying objects. To address this problem, we propose an enhanced semantic segmentation network (ESSN) robust to various objects, contexts, and environments. The ESSN can extract multi-scale information well by concatenating the residual feature maps with various receptive fields extracted from sequential convolution blocks, and it can improve the performance of semantic segmentation without additional modules such as loss or attention during the training process. We performed the experiments with two open databases, the Stanford background dataset (SBD) and Cambridge-driving labeled video database (CamVid). Experimental results demonstrated the pixel acc. of 92.74%, class acc. of 79.66%, and mIoU of 71.67% with CamVid, and pixel acc. of 87.46%, class acc. of 81.51%, and mIoU of 71.56% with SBD, which are higher than those of the existing state-of-the-art methods. In addition, the average processing time were 31.12 ms and 92.46 ms on the desktop computer and Jetson TX2 embedded system, respectively, which confirmed that ESSN is applicable to both the desktop computer and Jetson TX2 embedded system which is widely used in autonomous vehicles.

Deep C-LSTM Neural Network for Epileptic Seizure and Tumor Detection Using High-Dimension EEG Signals

Electroencephalography (EEG) is a common and significant tool for aiding in the diagnosis of epilepsy and studying the human brain electrical activity. Previously, the traditional machine learning (ML)-based classifier are used to identify the seizure by extracting features from the EEG signals manually. Although the effectiveness of these contributions have already been proved, they cannot achieve multiple class classification with automatic feature extraction. Meanwhile, the identifiable EEG segment is too long to limit the capability of real-time epileptic seizure detection. In this paper, a novel deep convolutional long short-term memory (C-LSTM) model is proposed for detecting seizure and tumor in human brain and identifying two eyes statuses (open and close). It achieves to predict a result in every 0.006 seconds with a short detection duration (one second). By comparing with other two types deep learning approaches (DCNN and LSTM), the presented deep C-LSTM obtains the best performance for classifying these five classes. All of the obtained total accuracy are over 98.80%.

Deep Neural Network with Dropout for Anomaly Detection in Software Defined Networking

A novel anomaly detection-based NIDS is main demand in the computer networking security for discriminating malicious software attack at the early stage. It monitors and analyzes network traffics, checking abnormal behaviors or attack signatures. The detection rate or accuracy is the prerequisite in the network intrusion detection models, also, developing adaptive and flexible model is a critical challenge regarding to unseen attack. This search paper included the deep neural network (DNN) as anomaly detection model can be used within software defined networking (SDN). Dropout technique is used to prevent DNN model from overfitting. Six features have information about the flow were chosen from NSL-KDD dataset to fit and evaluate this model, these data features could be matched to packet-in message header values, also, these features enable the model to be a good generative, and well perform on intrusion recognition issue with a subset of the data. Cross entropy loss function with SoftMax output layer were used for getting the differences between the two different distribution and mapping to multiple class classification covered five class labels, one is normal and the others are attacks (Dos, R2L, U2L and Probe). Accuracy is a comparative metric utilized for assessing the model performance. The results are promising, where accuracy achieved 92.65%.

Non-destructive image processing based system for assessment of rice quality and defects for classification according to inferred commercial value

Rice is among the three most consumed grains in the world, which makes its quality assessment an important task. Conventional methods based on manual inspection need specialized manpower, are time-consuming, error-prone, and at times, destructive. This paper presents an automatic, real-time and cost-effective image processing based system for classification of rice grains into various categories according to their inferred commercial value. The mechanism involves automatic segmentation of rice grains from background of image for discriminative feature extraction. Geometrical features are extracted in spatial domain, which aptly model the appearance characteristics of the grains. The feature sets are fed to an SVM (support vector machine) for multiple-class classification. The experimental results obtained using the proposed method indicate that the selected features have discriminatory properties for categorization of grain samples into different classes. Further milling defect grades are allotted to the samples based on proportion of broken kernels present in them proving a comprehensive grading of the quality of rice.

Neural Network Approach for Multiple-Class Classification

Classification is a very important problem-solving technique. Given a set of attribute values about an object, a classifier determines which category the object belongs to. A classification task can be a binary or multiple classification; it can also be a single-label or multiple-label classification. Neural networks are an effective technique in the field of artificial intelligence. In this paper, we develop different schemes of neural networks for solving binary, multiple, single-label, and multiple-label classification problems. The ideas behind them are described in detail.

Binary Output Layer of Feedforward Neural Networks for Solving Multi-Class Classification Problems

Considered in this short note is the design of output layer nodes of feedforward neural networks for solving multiple-class classification problems with $r$ ( $r\geq 3$ ) classes of samples. The common and conventional setting of the output layer called “ $one - to - one~approach$ ” in this paper, is as follows: The output layer contains $r$ output nodes corresponding to the $r$ classes. And for an input sample of the $i$ -th class ( $1\leq i\leq r$ ), the ideal output is 1 for the $i$ -th output node, and 0 for all the other output nodes. We propose in this paper a new “ $binary~approach$ ”: Suppose $2^{q-1} with $q\geq 2$ , then we let the output layer contain $q$ output nodes, and let the ideal outputs for the $r$ classes be designed in a binary manner. This idea of binary output is also applied for other classifiers, such as support vector machines and associative pulsing neural networks. Numerical simulations are carried out on eight real-world data sets, showing that our binary approach performs as well as, but uses less output nodes and hidden-output weights than, the traditional one-to-one approach.