Existing Machine Learning Algorithms Research Articles

A Grey Wolf Optimized XGboost-Multilayer Stacking Approach to Detect XSS Attacks

Life is easier with web applications. However, data stealing has become a serious issue and can have unpleasant effects on human life. This is when attackers try to access sensitive users’ information or acquire illegal rights. Cross-site scripting is the most common attack that steals user information. It is also known as an XSS attack and appears on OWASP’s Top 10 Attacks as well. More than 70 percent of web-based applications are susceptible to XSS attacks. This paper presents a Grey Wolf optimizer based on the XGboost multilayer stacking approach for XSS attack detection. The grey wolf optimizer is also known as the GWO as feature optimization for machine learning. This is superior to FEP, PSO, and GSA algorithms as it overcomes real-world challenges. The proposed techniques categorize XSS and non-XSS with an accuracy of 99.5%, recall rate of 1, false positive rate of 0.004, precision of 98.5%, and F-degree of 99.28%. The proposed methodology also compares with several existing machine learning algorithms and ensemble classifier techniques. It shows that the proposed approach is more accurate than earlier.

Prediction of traditional Chinese medicine prescriptions based on multi-label resampling

PurposeTraditional Chinese medicine (TCM) prescriptions have always relied on the experience of TCM doctors, and machine learning(ML) provides a technical means for learning these experiences and intelligently assists in prescribing. However, in TCM prescription, there are the main (Jun) herb and the auxiliary (Chen, Zuo and Shi) herb collocations. In a prescription, the types of auxiliary herbs are often more than the main herb and the auxiliary herbs often appear in other prescriptions. This leads to different frequencies of different herbs in prescriptions, namely, imbalanced labels (herbs). As a result, the existing ML algorithms are biased, and it is difficult to predict the main herb with less frequency in the actual prediction and poor performance. In order to solve the impact of this problem, this paper proposes a framework for multi-label traditional Chinese medicine (ML-TCM) based on multi-label resampling.Design/methodology/approachIn this work, a multi-label learning framework is proposed that adopts and compares the multi-label random resampling (MLROS), multi-label synthesized resampling (MLSMOTE) and multi-label synthesized resampling based on local label imbalance (MLSOL), three multi-label oversampling techniques to rebalance the TCM data.FindingsThe experimental results show that after resampling, the less frequent but important herbs can be predicted more accurately. The MLSOL method is shown to be the best with over 10% improvements on average because it balances the data by considering both features and labels when resampling.Originality/valueThe authors first systematically analyzed the label imbalance problem of different sampling methods in the field of TCM and provide a solution. And through the experimental results analysis, the authors proved the feasibility of this method, which can improve the performance by 10%−30% compared with the state-of-the-art methods.

Monitoring marine pollution for carbon neutrality through a deep learning method with multi-source data fusion

IntroductionMarine pollution can have a significant impact on the blue carbon, which finally affect the ocean’s ability to sequester carbon and contribute to achieving carbon neutrality. Marine pollution is a complex problem that requires a great deal of time and effort to measure. Existing machine learning algorithms cannot effectively solve the detection time problem and provide limited accuracy. Moreover, marine pollution can come from a variety of sources. However, most of the existing research focused on a single ocean indicator to analyze marine pollution. In this study, two indicators, marine organisms and debris, are used to create a more complete picture of the extent and impact of pollution in the ocean.MethodsTo effectively recognize different marine objects in the complex marine environment, we propose an integrated data fusion approach where deep convolutional neural networks (CNNs) are combined to conduct underwater object recognition. Through this multi-source data fusion approach, the accuracy of object recognition is significantly improved. After feature extraction, four machine and deep learning classifiers’ performances are used to train on features extracted with deep CNNs.ResultsThe results show that VGG-16 achieves better performance than other feature extractors when detecting marine organisms. When detecting marine debris, AlexNet outperforms other deep CNNs. The results also show that the LSTM classifier with VGG-16 for detecting marine organisms outperforms other deep learning models.DiscussionFor detecting marine debris, the best performance was observed with the AlexNet extractor, which obtained the best classification result with an LSTM. This information can be used to develop policies and practices aimed at reducing pollution and protecting marine environments for future generations.

Bone tumor examination based on FCNN-4s and CRF fine segmentation fusion algorithm

Background and objectiveBone tumor is a kind of harmful orthopedic disease, there are benign and malignant points. Aiming at the problem that the accuracy of the existing machine learning algorithm for bone tumor image segmentation is not high, a bone tumor image segmentation algorithm based on improved full convolutional neural network which consists fully convolutional neural network (FCNN-4s) and conditional random field (CRF). MethodologyThe improved fully convolutional neural network (FCNN-4s) was used to perform coarse segmentation on preprocessed images. Batch normalization layers were added after each convolutional layer to accelerate the convergence speed of network training and improve the accuracy of the trained model. Then, a fully connected conditional random field (CRF) was fused to refine the bone tumor boundary in the coarse segmentation results, achieving the fine segmentation effect. ResultsThe experimental results show that compared with the traditional convolutional neural network bone tumor image segmentation algorithm, the algorithm has a great improvement in segmentation accuracy and stability, the average Dice can reach 91.56%, the real-time performance is better. ConclusionCompared with the traditional convolutional neural network segmentation algorithm, the algorithm in this paper has a more refined structure, which can effectively solve the problem of over-segmentation and under-segmentation of bone tumors. The segmentation prediction has better real-time performance, strong stability, and can achieve higher segmentation accuracy.

Denoising and decoding spontaneous vagus nerve recordings with machine learning.

Neural interfaces that electrically stimulate the peripheral nervous system have been shown to successfully improve symptom management for several conditions, such as epilepsy and depression. A crucial part for closing the loop and improving the efficacy of implantable neuromodulation devices is the efficient extraction of meaningful information from nerve recordings, which can have a low Signal-to-Noise ratio (SNR) and non-stationary noise. In recent years, machine learning (ML) models have shown outstanding performance in regression and classification problems, but it is often unclear how to translate and assess these for novel tasks in biomedical engineering. This paper aims to adapt existing ML algorithms to carry out unsupervised denoising of neural recordings instead. This is achieved by applying bandpass filtering and two novel ML algorithms to in-vivo spontaneous, low-SNR vagus nerve recordings. The performance of each approach is compared using the task of extracting respiratory afferent activity and validated using cross-correlation, MSE, and accuracy in terms of extracting the true respiratory rate. A variational autoencoder (VAE) model in particular produces results that show better correlation with respiratory activity compared to bandpass filtering, highlighting that these models have the potential to preserve relevant features in complex neural recordings.

Intelligence system for sentiment classification with deep topic embedding using N-gram based topic modeling

Multi-modal information outbreak is consistently increasing in social media. Classification of tweet sentiments using various information modalities will help the recommender systems to achieve success in digital marketing. Moreover, aspect-level sentiment analysis categorizes a target’s sentiment polarity in a specific environment. Using topic modelling in aspect-level sentiment analysis enables the identification of more accurate aspect-based tweet sentiments. The existing sentiment classification techniques used for the development of recommendation systems do not focus on the aspect-based approach modelled using deep learning classifier with temporal analysis on the social media data. Hence, this paper proposes an efficient sentiment classification model that highlights the impact of topic modelling-based word feature embedding for improvising the classification of Twitter sentiments and product reviews based on temporal reasoning and analysis for performing predictive analysis. For tweets context analysis, Latent Dirichlet Allocation based topic modelling is used in this work which generates the topics. For each topic, the sentiment is calculated separately and the topic guided feature expansion is done using Senti-wordnet. Moreover, an extended deep learning classification algorithm called Long Short-Term Memory (LSTM) with word embedding and temporal reasoning(LSTMWTR) is proposed in this paper for improving the classification accuracy. Finally, the labelled data are classified using the existing machine learning algorithms namely Naïve Bayes, Support Vector Machines and also using the deep learning models such as Convolution Neural Network(CNN),LSTM, Recurrent Neural Networks (RNN) and the transformer model namelyBi-directional Encoder Representation from Transformers (BERT),Convolution Bi-directional Recurrent Neural Network (CBRNN) and the proposed deep learning algorithm namelyLSTMWTR. These sentiment classification algorithms have been evaluated with word embedding for tweet sentiment classification and product review classification. The results obtained from this work show that the proposed LSTMWTR algorithm emerges as the highly accurate model for tweet sentiment and product review classification.

Analysis of Intrusion Detection Systems in UNSW-NB15 and NSL-KDD Datasets with Machine Learning Algorithms

Recently, the need for Network-based systems and smart devices has been increasing rapidly. The use of smart devices in almost every field, the provision of services by private and public institutions over network servers, cloud technologies and database systems are almost completely remotely controlled. Due to these increasing requirements for network systems, malicious software and users, unfortunately, are increasing their interest in these areas. Some organizations are exposed to almost hundreds or even thousands of network attacks daily. Therefore, it is not enough to solve the attacks with a virus program or a firewall. Detection and correct analysis of network attacks is vital for the operation of the entire system. With deep learning and machine learning, attack detection and classification can be done successfully. In this study, a comprehensive attack detection process was performed on UNSW-NB15 and NSL-KDD datasets with existing machine learning algorithms. In the UNSW-NB115 dataset, 98.6% and 98.3% accuracy were obtained for two-class and multi-class, respectively, and 97.8% and 93.4% accuracy in the NSL-KDD dataset. The results prove that machine learning algorithms are lateral to the solution in intrusion detection systems.

Constructing a link between multivariate titanium-based semiconductor band gaps and chemical formulae based on machine learning

Titanium-based semiconductors are wildly recognized as one of the most commonly used photocatalysts for photocatalysis. Energy band modulation is a key aspect of the catalytic activity of photocatalytic semiconductors, but the acquisition of semiconductor energy bands is still a complex and important task. In recent years, machine learning has played an important role in materials prediction, where the crystal structure of a material is usually used as input in energy band prediction. However, existing machine learning algorithms cannot accurately predict the energy bands of materials from structural components. Here, we convert the chemical formula into component descriptors after comparing first principles and ultraviolet-visible spectrophotometry (UV–vis) errors on bandgap values, and the component and bandgap values form a set of labeled data pairs. The chemical formula components are used as input to accurately predict the energy bands of the material. In our evaluation, the model outperforms existing machine learning methods in predicting energy bands, yielding mean absolute value errors of about 0.277 eV, and possesses a significant advantage in component prediction. In particular, this method of predicting the photocatalytic semiconductor energy band gap from chemical formula components provides a new way of thinking about photocatalyst selectivity.

Multiclass classification of environmental chemical stimuli from unbalanced plant electrophysiological data.

Plant electrophysiological response contains useful signature of its environment and health which can be utilized using suitable statistical analysis for developing an inverse model to classify the stimulus applied to the plant. In this paper, we have presented a statistical analysis pipeline to tackle a multiclass environmental stimuli classification problem with unbalanced plant electrophysiological data. The objective here is to classify three different environmental chemical stimuli, using fifteen statistical features, extracted from the plant electrical signals and compare the performance of eight different classification algorithms. A comparison using reduced dimensional projection of the high dimensional features via principal component analysis (PCA) has also been presented. Since the experimental data is highly unbalanced due to varying length of the experiments, we employ a random under-sampling approach for the two majority classes to create an ensemble of confusion matrices to compare the classification performances. Along with this, three other multi-classification performance metrics commonly used for unbalanced data viz. balanced accuracy, F1-score and Matthews correlation coefficient have also been analyzed. From the stacked confusion matrices and the derived performance metrics, we choose the best feature-classifier setting in terms of the classification performances carried out in the original high dimensional vs. the reduced feature space, for this highly unbalanced multiclass problem of plant signal classification due to different chemical stress. Difference in the classification performances in the high vs. reduced dimensions are also quantified using the multivariate analysis of variance (MANOVA) hypothesis testing. Our findings have potential real-world applications in precision agriculture for exploring multiclass classification problems with highly unbalanced datasets, employing a combination of existing machine learning algorithms. This work also advances existing studies on environmental pollution level monitoring using plant electrophysiological data.

Machine learning based prediction for oncologic outcomes of renal cell carcinoma after surgery using Korean Renal Cell Carcinoma (KORCC) database

We developed a novel prediction model for recurrence and survival in patients with localized renal cell carcinoma (RCC) after surgery and a novel statistical method of machine learning (ML) to improve accuracy in predicting outcomes using a large Asian nationwide dataset, updated KOrean Renal Cell Carcinoma (KORCC) database that covered data for a total of 10,068 patients who had received surgery for RCC. After data pre-processing, feature selection was performed with an elastic net. Nine variables for recurrence and 13 variables for survival were extracted from 206 variables. Synthetic minority oversampling technique (SMOTE) was used for the training data set to solve the imbalance problem. We applied the most of existing ML algorithms introduced so far to evaluate the performance. We also performed subgroup analysis according to the histologic type. Diagnostic performances of all prediction models achieved high accuracy (range, 0.77–0.94) and F1-score (range, 0.77–0.97) in all tested metrics. In an external validation set, high accuracy and F1-score were well maintained in both recurrence and survival. In subgroup analysis of both clear and non-clear cell type RCC group, we also found a good prediction performance.

A Review on Fake News Detection using Machine Learning

Fake news, which is defined as material that has been shared with the intention of defrauding people, has been growing quickly and widely recently. This kind of misinformation is dangerous to social cohesion and wellbeing because it exacerbates political polarisation and public mistrust of authority figures. As a result, false news is an issue that has a big impact on our social lives, especially in politics. In order to address this issue, this study suggests brand-new methods based on machine learning (ML) and deep learning (DL) for the fake news identification system. This survey deals with a review of existing machine learning algorithms Naïve Bayes, Convolutional Neural Network, LSTM, Neural Network, Support Vector Machine proposed for detecting and reducing fake news from different social media platforms like Facebook, whatsapp, twitter, etc. This review provides a comprehensive detail including data mining perspective, evaluation metrics, and representative datasheets.

Complex nonlinear neural network prediction with IOWA layer

Neural network methods are widely used in business problems for prediction, clustering, and risk management to improving customer satisfaction and business outcome. The ability of a neural network to learn complex nonlinear relationship is due to its architecture that uses weight parameters to transform input data within the hidden layers. Such methods perform well in many situations where the ordering of inputs is simple. However, for a complex reordering of a decision-maker, the process is not enough to get an optimal prediction result. Moreover, existing machine learning algorithms cannot reduce computational complexity by reducing data size without losing any information. This paper proposes an induced ordered weighted averaging (IOWA) operator for the artificial neural network IOWA-ANN. The operator reorders the data according to the order-inducing variable. The proposed sorting mechanism in the neural network can handle a complex nonlinear relationship of a dataset, which results in reduced computational complexities. The proposed approach deals with the complexity of the neuron, collects the data and allows a degree of customisation of the structure. The application further extended to IGOWA and Quasi-IOWA operators. We present a numerical example in a financial decision-making process to demonstrate the approach's effectiveness in handling complex situations. This paper opens a new research area for various complex nonlinear predictions where the dataset is big enough, such as cloud QoS and IoT sensors data. The approach can be used with different machine learning, neural networks or hybrid fuzzy neural methods with other extensions of the OWA operator.

A semantic-based approach for hepatitis C virus prediction and diagnosis using a fuzzy ontology and a fuzzy Bayesian network

Medical decisions, especially when diagnosing Hepatitis C, are challenging to make as they often have to be based on uncertain and fuzzy information. In most cases, that puts doctors in complex yet uncertain decision-making situations. Therefore, it would be more suitable for doctors to use a semantically intelligent system that mimics the doctor’s thinking and enables fast Hepatitis C diagnosis. Fuzzy ontologies have been used to remedy the shortcomings of classical ontologies by using fuzzy logic, which allows dealing with fuzzy knowledge in ontologies. Moreover, Fuzzy Bayesian networks are well-known and widely used to represent and analyze uncertain medical data. This paper presents a system that combines fuzzy ontologies and Bayesian networks to diagnose Hepatitis C. The system uses a fuzzy ontology to represent sequences of uncertain and fuzzy data about patients and some features relevant to Hepatitis C diagnosis, enabling more reusable and interpretable datasets. In addition, we propose a novel semantic diagnosis process based on a fuzzy Bayesian network as an inference engine. We conducted an experimental study on 615 real cases to validate the proposed system. The experimentation allowed us to compare the results of existing machine learning algorithms for the Hepatitis C diagnosis with the results of our proposed system. Our solution shows promising results and proves effective for fast medical assistance.

A Novel Approach for Prediction of Gestational Diabetes based on Clinical Signs and Risk Factors

Gestational diabetes mellitus occurs due to high glucose levels in the blood. Pregnant women are affected by this type of diabetes. A blood test is to be performed to identify diabetes. The Oral Glucose Tolerance Test (OGTT) is a blood test performed between the 24th and 28th week of pregnancy that is necessary to identify and overcome the side effects of GDM. The main objective of this work is to train a model by utilizing the training data, evaluate the trained model using the test data, and compare existing machine learning algorithms with a Gradient boosting machine (GBM) to achieve a better model for the effective prediction of gestational diabetes. In this work, the analysis was done with a few existing algorithms and the Extreme learning machine and Gradient boosting techniques. The k-fold cross-validation technique is applied with values of k as 3, 5, and 10 to obtain better performance. The existing algorithms implemented are the Naive Bayes classifier, Support Vector Machine, K-Nearest Neighbour, ID3, CART and J48. The proposed algorithms are Gradient boosting and ELM. These algorithms are implemented in R programming. The metrics like accuracy, kappa statistic, sensitivity/Recall, specificity, precision, f-measure and AUC are used to compare all the algorithms. GBM has obtained better performance than existing algorithms. Then finally, GBM is compared with the other proposed robust Machine Learning algorithm, namely the Extreme learning machine, and the GBM performed better. So, It is recommended to use a gradient-boosting algorithm to predict gestational diabetes effectively.

Identifying Potential Students as College Customers Using Machine Learning: A Literature Review

College customers begin with prospective students who are important asset opportunities. Potential prospective students can be identified from academic score data while in SMA / SMK / MAN, achievement data, data on the number of siblings, and data on parents' income. After being a student, their potential can be identified from GPA scores, non-academic achievement data and length of study in college. When becoming an alumnus, college customers can be identified for their potential from the waiting time for alumni to get a job, place of work, and type of alumni work. The use of CRM (Customer Relationship Management) is expected to be able to recognize the potential of college customers to benefit universities. This article contains a systematic literature review of several research themes that have been carried out related to the utilization of machine learning for CRM using several existing machine learning algorithms, The goal of this article is to find new ideas that are better at implementing CRM in college by using machine-based learning methods. The results found turned out that there were only 5 literatures out of 50 that did machine learning method development for CRM or only 5/50 *100% = 10%.

An Ensemble Learning Approach for detection of Chronic Kidney Disease (CKD)

Chronic kidney disease (CKD) is a common and possibly fatal condition affecting billions worldwide. Early detection and accurate diagnosis of CKD are critical for timely intervention and improved patient outcomes. In recent years, machine learning techniques have shown great promise in assisting medical professionals in detecting and diagnosing various diseases. This study aims to develop a novel machine learning (ML) model for detecting CKD using clinical and demographic data. The dataset used in this study comprises a comprehensive collection of patient records, including laboratory test results, medical history, and demographic information. Feature selection is one of the techniques that, combined with the ML approach, select the significant features. Several ML algorithms were implemented to detect CKD in the early stages but identified the issues with existing ML algorithms. The developed models' performance is assessed using precision, accuracy, and recall metrics. Additionally, feature importance analysis is conducted to identify the key factors influencing CKD diagnosis. The strength of the proposed approach shows accurately by identifying the individuals at risk of CKD and distinguishing between different stages of the disease. The dataset used for this research was collected from the UCI repository, which consists of 25 attributes, 550 samples, 400 CKD affected, and 150 standard models. The dataset consists of two folders, training and testing. The training utilizes 1000 samples with detailed patient health conditions. The developed CKD detection model shows promising results, achieving high accuracy of 97.98%. on the test dataset. By leveraging machine learning algorithms, this approach can assist healthcare professionals in making more informed decisions regarding early intervention and personalized treatment plans for patients with CKD. Ultimately, applying machine learning techniques in CKD detection can improve patient outcomes and reduce healthcare costs.

Benchmarking Machine Learning for Sentimental Analysis of Climate Change Tweets in Social Internet of Things

Climate change has become one of the most critical problems threatening our world, gaining increased attention in either academia or industry. Climate change has been demonstrated as the major barrier in the way of sustainable development strategy in the 2030 Agenda. Nowadays, the Social Internet of Things (SIoT) has paved new ways for public deliberations and has transformed the communication of global issues such as climate change. Thus, sentiment analysis of SIoT media streams can offer great help in improving the mitigation and adaptation to climate change. Machine learning (ML) is demonstrating great success in a wide range of SIoT applications. However, training ML algorithms for sentimental analysis of climate change is notoriously hard as it suffers from feature engineering issues, information squashing, unbalancing, and curse-of-dimensionality, which bounds their possible power for modeling social awareness of climate change. Besides, the absence of a standard benchmark with reasonable and dependable experimentations brings a practically intractable difficulty to the evaluation of the efficiency of new solutions. In this regard, this study introduces the first reasonable and reproducible benchmark devoted to evaluating the potential of ML algorithms in identifying users’ opinions about climate change. Moreover, a novel taxonomy is presented for categorizing the existing ML algorithms, exploring their optimal hyperparameter, and unifying their elementary settings. Inclusive experiments are then performed on real Twitter data with different families of ML algorithms. To promote further study, a detailed analysis is provided for the state of the field to uncover the open research challenges and promising future directions.

Multiple correlation based decision tree model for classification of software requirements

Recent research in requirements engineering (RE) includes requirements classification and use of machine learning (ML) algorithms to solve RE problems. The limitation of existing techniques is that they consider only one feature at a time to map the requirements without considering the correlation of two features and are biased. To understand these limitations, our study compares and extends the ML algorithms to classify requirements in terms of precision and accuracy. Our literature survey shows that decision tree (DT) algorithm can identify different requirements and outperforms existing ML algorithms. As the number of features increases, the accuracy using the DT is improved by 1.65%. To overcome the limitations of DT, we propose a multiple correlation coefficient based DT algorithm. When compared to existing ML approaches, the results showed that the proposed algorithm can improve classification performance. The accuracy of the proposed algorithm is improved by 5.49% compared to the DT algorithm.

Detection and Prevention WEB-Service for Fraudulent E-Transaction using APRIORI and SVM

With the increased use of information technology, many financial services are available to users at their fingertips. However, this led to many fraud transactions. Automatic fraud identification and detection could improve the user experience and security of online transactions. Using machine learning algorithms, it is possible to detect fraud transactions. Machine learning algorithms have the ability to find the hidden implicit pattern and data relationships from a large dataset. Hence, using this algorithm is possible to detect the outlier from all transactions, which can help in determining the fraud transaction. In this paper, the APRIORI algorithm and Support Vector Machine are used to detect fraud transactions in credit cards via developing a secure web application service enforced the security by standard metrics. We compare the result with the other existing machine learning algorithms. We observed that the accuracy of fraud transaction detection is higher in the proposed algorithm more than 94.56, and the false fraud transaction detection is less than the fraud detection based on the Hidden Markov Model.

An Overview of Wearable Biosensor Systems for Real-Time Substance Use Detection

Wearable biosensors represent an opportunity to improve treatment and research into a variety of diseases, including substance use disorder. They provide continuous, real-time data about the wearer’s condition in their natural environment in an unobtrusive, increasingly capable, and cost-effective way. However, generating clinically relevant insights from high-velocity, noisy, multidimensional data streams requires new approaches in real-time anomaly machine learning (ML). We present a survey of the existing algorithms for substance use monitoring in wearable biosensor data streams and how the advent of 5G and 6G wireless communications will drive further changes in this field. Our work highlights trends that have emerged among the different efforts published to-date as well as identifying ongoing challenges not adequately addressed by existing ML algorithms.