Machine Learning Based Classification Methods Research Articles

Raman spectroscopy for esophageal tumor diagnosis and delineation using machine learning and the portable Raman spectrometer

Esophageal cancer is one of the leading causes of cancer-related deaths worldwide. The identification of residual tumor tissues in the surgical margin of esophageal cancer is essential for the treatment and prognosis of cancer patients. But the current diagnostic methods, either pathological frozen section or paraffin section examination, are laborious, time-consuming, and inconvenient. Raman spectroscopy is a label-free and non-invasive analytical technique that provides molecular information with high specificity. Here, we report the use of a portable Raman system and machine learning algorithms to achieve accurate diagnosis of esophageal tumor tissue in surgically resected specimens. We tested five machine learning-based classification methods, including k-Nearest Neighbors, Adaptive Boosting, Random Forest, Principal Component Analysis-Linear Discriminant Analysis, and Support Vector Machine (SVM). Among them, SVM shows the highest accuracy (88.61 %) in classifying the esophageal tumor and normal tissues. The portable Raman system demonstrates robust measurements with an acceptable focal plane shift of up to 3 mm, which enables large-area Raman mapping on resected tissues. Based on this, we finally achieve successful Raman visualization of tumor boundaries on surgical margin specimens, and the Raman measurement time is less than 5 min. This work provides a robust, convenient, accurate, and cost-effective tool for the diagnosis of esophageal cancer tumors, advancing toward Raman-based clinical intraoperative applications.

Identification of cloud-to-ground lightning and intra-cloud lightning based on their radiated electric field signatures using different types of neural networks and machine learning classifiers

The scope of this paper is to test the efficiency of three different neural networks in the area of cloud-to-ground/intra-cloud lightning classification using a not very large data set of electric field data. Effective neural network learning verified for a small lightning event dataset but with whole 2-seconds particular record length is an important feature of fast and efficient procedures implemented into lightning location systems among which discrimination between cloud-to-ground and intra-cloud lightning is one of the most important task. Measurement data obtained at the Lightning Observatory in Rzeszow were used for the analysis. About 100 extremely low/medium frequency bandwidth electric field of cloud-to ground lightning registrations and the same number of intra-cloud lightning events were taken into account. During the study 81% of those registrations were dedicated for learning of neural networks while the remaining 19% were put into the testing set. All data were preselected manually with consideration of the electric field variation and information from the lightning location system database. Lightning events were selected uniformly with the well-pronounced presence of their basic components and reported distance to the registration station which ensured a wide variation of expected lightning electric field signatures. The multilayer perceptron neural network, the radial basis function neural network and the convolutional neural network were tested and compared in different configurations while distinguishing lightning. The results were compared with other conventional classification approaches, such as traditional machine learning methods as well as one a little more contemporary architecture, the long short-term memory neural network. The multilayer perceptron neural network achieved the best detection accuracy overall. Presented research is an extension of lightning identification studies available so far mainly based on the convolutional neural network by the results achieved using the multilayer perceptron neural network, the radial basis function neural network, the long short-term memory neural network and several machine learning-based classification methods.

Automated Classification of Manual Exploratory Behaviors Using Sensorized Objects and Machine Learning: A Preliminary Proof-of-Concept Study

Manual exploratory behaviors during object interaction that form the basis of tool use behavior, are mostly qualitatively characterized in terms of their frequency and duration of occurrence. To fully understand their functional and clinical significance, quantitative movement characterization is needed alongside their qualitative analysis. However, there are two challenges in quantifying them—(a) reliably classifying the type of movement and (b) performing this classification on a time series automatically. Here, we propose a machine learning-based classification method to address these challenges. We measured three common exploratory behaviors (object rotation, fingering, and throwing) in college-aged adults using “sensorized objects” that had wireless Inertial Measurement Units embedded in them. We then calculated several statistical features based on linear acceleration and angular velocity data to train machine learning classifiers to identify these behaviors. All classifiers identified the behaviors with a substantially higher accuracy (average accuracy = 84.95 ± 4.16%) than chance level (33.33%). Of all models tested, Support Vector Machine Quadratic, Support Vector Machine Medium Gaussian, and Narrow Neural Network were the best models in classifying the three behaviors (average accuracy = 89.34 ± 0.12%). This classification method shows potential for automating movement characterization of exploratory behaviors, thereby may aid early assessment of neurodevelopmental disorders.

Optimizing Seagrass Detection in Lampung Selatan: Leveraging Machine Learning Algorithms and Sentinel-2A Imagery

Seagrass beds are one of the coastal ecosystems that play an important role in maintaining the stability of blue carbon. However, high community activities threaten the existence of seagrass beds themselves. South Lampung Regency is one of the areas with considerable seagrass potential but the availability of distribution and density data is still minimal. This research aims to identify and map seagrass density as a first step for seagrass management. The data used in this research is Sentinel 2A multispectral image. Machine learning-based classification methods used are random forest (RF) and support vector machine (SVM) because these algorithms have a good ability to distinguish objects based on their features. This study uses a 2-level classification scheme, where level 1 consists of land, shallow sea, and deep-sea classes. Level 2 is the shallow marine bottom benthic habitat class. The type of seagrass found in this area is Enhalus acoroides. Based on the results of the analysis, low, medium, and high-density classes were obtained with an area of low around 20.12 ha, medium around 34.67 ha and high around 320.12ha with a total area of 374.91ha. RF has a higher overall accuracy of 88.00% while SVM accuracy is 84.00% so it can be concluded that Sentinel 2A images can be used to detect seagrass meadows.

Predicting the Distribution of Mangrove Forests through Random Forest Algorithm by Combining Spectral Features and DEM Data

Using satellite data and machine learning-based classification methods for mangrove forest identification has gained popularity due to their effectiveness in producing high accuracy. Therefore, this research developed a random forest classification model using various dataset combinations representing spectral and topographical aspects to identify mangrove forests in Segara Anakan, Cilacap. We used the Sentinel-2 imagery acquired in 2022. Two types of digital elevation model (DEM) data were utilized, namely the National Digital Elevation Model (DEMNAS) and Multi-Error-Removed Improved-Terrain DEM (MERIT DEM). Another critical dataset used is the Normalized Difference Moisture Index (NDMI), derived from the ratio between near-infrared (NIR) and shortwave-infrared (SWIR) bands. The classification method used is the random forest algorithm on six different dataset combinations, including IMAGE, IMAGE+NDMI, IMAGE+DEMNAS, IMAGE+MERIT DEM, IMAGE+NDMI+DEMNAS, and IMAGE+NDMI+ MERIT DEM. The results showed that the combination of Image+DEMNAS and Image+NDMI+DEMNAS datasets was able to identify the mangrove forests more optimally. Incorporating DEM data alongside IMAGE and NDMI datasets resulted in a remarkable level of accuracy in mangrove forest mapping, exceeding 90%. DEM data has a very important role in increasing the classification accuracy of mangrove forests using the random forest algorithm.

Photometric Classification of Evolved Massive Stars: Spectroscopic Verification and Validation

Dorn-Wallenstein et al. utilized a novel machine-learning technique to classify a large sample of evolved massive stars. This resulted in new classifications for ∼2550 objects. We wish to validate the efficiency of the Dorn-Wallenstein et al. machine classifier. To this end we obtained new observations of four stars identified by Dorn-Wallenstein et al., with a focus on verifying newly identified emission-line objects and evolved supergiants. We identified a previously unconfirmed Be star, TYC 3740-1791-1, using these data. We assigned spectral types to the two stars in our sample with sufficient signal-to-noise data. We then used Gaia DR3 BP/RP spectra to validate an additional 73 stars from Dorn-Wallenstein et al. Our classifications support the completeness and contamination reported by the authors and confirm the validity of using machine learning-based classification methods on massive stars in the era of big data.

Application of Machine Learning to Performance Assessment for a Class of PID-Based Control Systems

In this paper, a novel machine learning derived control performance assessment (CPA) classification system is proposed. It is dedicated for a wide class of PID-based control industrial loops with processes exhibiting dynamical properties close to second order plus delay time (SOPDT). The proposed concept is very general and easy to configure to distinguish between acceptable and poor closed loop performance. This approach allows for determining the best (but also robust and practically achievable) closed loop performance based on very popular and intuitive closed loop quality factors. Training set can be automatically derived off-line using a number of different, diverse control performance indices (CPIs) used as discriminative features of the assessed control system. The proposed extended set of CPIs is discussed with comprehensive performance assessment of different machine learning based classification methods and practical application of the suggested solution. As a result, a general-purpose CPA system is derived that can be immediately applied in practice without any preliminary or additional learning stage during normal closed loop operation. It is verified by practical application to assess the control system for a laboratory heat exchange and distribution setup.

A Combined Model for Customer Credit Scoring Using Machine Learning-based Classification Methods

A Combined Model for Customer Credit Scoring Using Machine Learning-based Classification Methods

Healthcare Monitoring System for Diabetic Patients Using Machine Learning

Abstract: Present-day technology provides quite an efficient way of monitoring an individual’s health. Bluetooth Low Energy (BLE)-based sensors can be considered as one of the solutions for checking personal vital signs data such as blood pressure, heart rate, weight, and blood glucose (BG). In this study, we propose a personalized healthcare monitoring system by utilizing a BLE-based sensor device dataset, data processing, and machine learning-based algorithms to help diabetic patients to better self-manage their chronic condition. The proposed real-time data processing system utilizes machine Learning algorithms to train the model. Machine learning–based classification methods were tested on a diabetes dataset in order to show that a Multilayer Perceptron can provide early prediction of diabetes given the user’s sensor data as input. Furthermore, the proposed diabetes classification and prediction might be integrated with individualized diet and physical activity recommendations to improve patients' health quality and avert severe circumstances in the future.

Machine Learning-Based Species Classification Methods Using DART-TOF-MS Data for Five Coniferous Wood Species

Various problems worldwide are caused by illegal production and distribution of timber, such as deception about timber species and origin and illegal logging. Numerous studies on wood tracking are being conducted around the world to demonstrate the legitimacy of timber. Tree species identification is the most basic element of wood tracking research because the quality of wood varies greatly from species to species and is consistent with the botanical origin of commercially distributed wood. Although many recent studies have combined machine learning-based classification methods with various analytical methods to identify tree species, it is unclear which classification model is most effective. The purpose of this work is to examine and compare the performance of three supervised machine learning classification models, support vector machine (SVM), random forest (RF), and artificial neural network (ANN), in identifying five conifer species and propose an optimal model. Using direct analysis in real-time ionization combined with time-of-flight mass spectrometry (DART-TOF-MS), metabolic fingerprints of 250 individual specimens representing five species were collected three times. When the machine learning models were applied to classify the wood species, ANN outperformed SVM and RF. All three models showed 100% prediction accuracy for genus classification. For species classification, the ANN model had the highest prediction accuracy of 98.22%. The RF model had an accuracy of 94.22%, and the SVM had the lowest accuracy of 92.89%. These findings demonstrate the practicality of authenticating wood species by combining DART-TOF-MS with machine learning, and they indicate that ANN is the best model for wood species identification.

Orman Zararlılarının Verdiği Zararın Google Earth Engine Kullanılarak İzlenmesi

Forests tend to disappear for various reasons. Insects have problems such as very high reproduction and spread rates, unpredictable distribution directions, and inability to intervene quickly in the fight against insects. For this reason, harmful insects are at the beginning of many factors that cause forest loss. For the study, Bursa-İnegöl Tahtaköprü location, which was affected by the red-tailed beech caterpillar (Calliteara pudibunda) affecting beech trees, was determined as the study area. This study was carried out on the Google Earth Engine (GEE) interface. For the study area, using Sentinel-2A and Landsat-8 satellite data for the period 2017-2021, 6 different plant indexes; NDVI, EVI, SAVI, RVI, TVI, NPCRI were calculated and it was determined that the most affected period from pests was October 2019. These indices were also calculated for October 2019, and classification was made for four different data combinations in 5 different classes (diseased, healthy, road, power line, settlement) using the Random Forest Classification Algorithm and Support Vector Machines methods, which are machine learning-based classification methods. The classification result was compared for Landsat-8 and Sentine-2A, and the best result was the combination including all plant indices for Sentinel-2A satellite data, and the overall accuracy was calculated as 98.48 and the kappa coefficient as 97.68.

Machine Learning-Based Classification and Evaluation of Regional Ethnic Traditional Sports Tourism Resources

Traditional sports in ethnic minority regions are a valuable cultural heritage. Regional ethnic traditional sports are not only a sports business but also a tourism resource. The construction of a reasonable regional sports tourism resource classification model is fundamental to the development of sports tourism resources. However, the existing sports tourism resources classification is mostly constructed manually based on the national standard tourism resources classification system. The efficiency and accuracy of the traditional manual classification are poor and cannot reflect the characteristics of regional ethnic traditional sports tourism. In order to solve the above problems, a machine learning-based classification method for regional ethnic traditional sports tourism resources is proposed. Firstly, the relevant concepts and characteristics of traditional sports tourism resources are introduced. Then, taking the development of traditional sports of ethnic minorities in Yunnan Province as the research object, SWOT analysis, literature, interview, questionnaire, and mathematical statistics are used to investigate and analyse the overall status of the development of regional ethnic traditional sports. Secondly, a classification evaluation method based on an optimised back-propagation (BP) neural network is proposed. Finally, the optimised BP neural network model is applied to the classification of traditional sports tourism resources. The experimental results show that the optimised BP model performs well in the classification of traditional sports tourism resources, verifying its effectiveness.

Machine learning identifies liquids employing a simple fiber-optic tip sensor.

We proposed an extremely simple fiber-optic tip sensor system to identify liquids by combining their corresponding droplet evaporation events with analyses using machine learning techniques. Pendant liquid droplets were suspended from the cleaved endface of a single-mode fiber during the experiment. The optical fiber-droplet interface and the droplet-air interface served as two partial reflectors of an extrinsic Fabry-Perot interferometer (EFPI) with a liquid droplet cavity. As the liquid pendant droplet evaporated, its length diminished. A light source can be used to observe the effective change in the net reflectivity of the optical fiber sensor system by observing the resulting optical interference phenomenon of the reflected waves. Using a single-wavelength probing light source, the entire evaporation event of the liquid droplet was precisely captured. The measured time transient response from the fiber-optic tip sensor to an evaporation event of a liquid droplet of interest was then transformed into image data using a continuous wavelet transform. The obtained image data was used to fine-tune pre-trained convolution neural networks (CNNs) for the given task. The results demonstrated that machine learning-based classification methods achieved greater than 98% accuracy in classifying different liquids based on their corresponding droplet evaporation processes, measured by the fiber-optic tip sensor.

Automatic body part and pose detection in medical infrared thermal images

ABSTRACT Automatisation and standardisation of the diagnosis process in medical infrared thermal imaging (MITI) is crucial because the number of medical experts in this area is highly limited.The current studies generally need manual intervention. One of the manual operations requires physician’s determination of the body part and orientation. In this study automatic pose and body part detection on medical thermal images is investigated. The database (957 thermal images - 59 patients) was divided into four classes upper-lower body parts with back-front views. First, histogram equalization (HE) method was applied on the pixels only within the body determined using Otsu’sthresholding approach. Secondly, DarkNet-19 architecture was used for feature extraction, and principal component analysis (PCA) and t-distributed stochastic neighbour embedding (t-SNE) approaches for feature selection. Finally, the performances of various machine learning based classification methods were examined. Upper vs. lower body parts and back vs. front of upper body were classified with 100% accuracy, and back vs. front classification of lower body part success rate was 93.38%. This approach will improve the automatisation process of thermal images to group them for comparing one image with the others and to perform queries on the labeled images in a more user-friendly manner.

Accurate classification of fresh and charred grape seeds to the varietal level, using machine learning based classification method

Grapevine (Vitis vinifera L.) currently includes thousands of cultivars. Discrimination between these varieties, historically done by ampelography, is done in recent decades mostly by genetic analysis. However, when aiming to identify archaeobotanical remains, which are mostly charred with extremely low genomic preservation, the application of the genomic approach is rarely successful. As a result, variety-level identification of most grape remains is currently prevented. Because grape pips are highly polymorphic, several attempts were made to utilize their morphological diversity as a classification tool, mostly using 2D image analysis technics. Here, we present a highly accurate varietal classification tool using an innovative and accessible 3D seed scanning approach. The suggested classification methodology is machine-learning-based, applied with the Iterative Closest Point (ICP) registration algorithm and the Linear Discriminant Analysis (LDA) technique. This methodology achieved classification results of 91% to 93% accuracy in average when trained by fresh or charred seeds to test fresh or charred seeds, respectively. We show that when classifying 8 groups, enhanced accuracy levels can be achieved using a "tournament" approach. Future development of this new methodology can lead to an effective seed classification tool, significantly improving the fields of archaeobotany, as well as general taxonomy.

Class Imbalanced Fault Diagnosis via Combining K-Means Clustering Algorithm with Generative Adversarial Networks

Recent advancements in machine learning and communication technologies have enabled new approaches to automated fault diagnosis and detection in industrial systems. Given wide variation in occurrence frequencies of different classes of faults, the class distribution of real-world industrial fault data is usually imbalanced. However, most prior machine learning-based classification methods do not take this imbalance into consideration, and thus tend to be biased toward recognizing the majority classes and result in poor accuracy for minority ones. To solve such problems, we propose a k-means clustering generative adversarial network (KM-GAN)-based fault diagnosis approach able to reduce imbalance in fault data and improve diagnostic accuracy for minority classes. First, we design a new k-means clustering algorithm and GAN-based oversampling method to generate diverse minority-class samples obeying the similar distribution to the original minority data. The k-means clustering algorithm is adopted to divide minority-class samples into k clusters, while a GAN is applied to learn the data distribution of the resulting clusters and generate a given number of minority-class samples as a supplement to the original dataset. Then, we construct a deep neural network (DNN) and deep belief network (DBN)-based heterogeneous ensemble model as a fault classifier to improve generalization, in which DNN and DBN models are trained separately on the resulting dataset, and then the outputs from both are averaged as the final diagnostic result. A series of comparative experiments are conducted to verify the effectiveness of our proposed method, and the experimental results show that our method can improve diagnostic accuracy for minority-class samples.

An Intelligent and Energy-Efficient Wireless Body Area Network to Control Coronavirus Outbreak.

The coronaviruses are a deadly family of epidemic viruses that can spread from one individual to another very quickly, infecting masses. The literature on epidemics indicates that the early diagnosis of a coronavirus infection can lead to a reduction in mortality rates. To prevent coronavirus disease 2019 (COVID-19) from spreading, the regular identification and monitoring of infected patients are needed. In this regard, wireless body area networks (WBANs) can be used in conjunction with machine learning and the Internet of Things (IoT) to identify and monitor the human body for health-related information, which in turn can aid in the early diagnosis of diseases. This paper proposes a novel coronavirus-body area network (CoV-BAN) model based on IoT technology as a real-time health monitoring system for the detection of the early stages of coronavirus infection using a number of wearable biosensors to examine the health status of the patient. The proposed CoV-BAN model is tested with five machine learning-based classification methods, including random forest, logistic regression, Naive Bayes, support vector machine and multi-layer perceptron classifiers, to optimize the accuracy of the diagnosis of COVID-19. For the long-term sustainability of the sensor devices, the development of energy-efficient WBAN is critical. To address this issue, a long-range (LoRa)-based IoT program is used to receive biosensor signals from the patient and transmit them to the cloud directly for monitoring. The experimental results indicate that the proposed model using the random forest classifier outperforms models using the other classifiers, with an average accuracy of 88.6%. In addition, power consumption is reduced when LoRa technology is used as a relay node.

Image processing and machine learning‐based classification method for hyperspectral images

Hyperspectral images are used to produce effective solutions in many areas due to the number of information they have. However, the number of information they provide may not bring an advantage always, in contrast, it may cause confusion sometimes. In this study, we propose a machine learning-based classification method on the reduced bands using median and mean filters. The proposed method is tested on Indian Pines, Pavia University and Salinas datasets. After applying normalization, median filter and mathematical morphology for each band in an image, a feature matrix with only one band is achieved. Then, the most significant features are selected by using relief feature selection algorithm. The selected features are used for classification with support vector machine and K nearest neighbourhood. For all methods and datasets, a success rate above 99% in terms of accuracy is achieved. The proposed method has two significant contributions. First, when the proposed method is compared with the similar studies in the literature, it is clearly seen that the features selected by relief algorithm significantly increase the success rate of classification algorithms. Second significant contribution of using relief algorithm is obtaining faster methods by reducing the number of hyperspectral bands.

Machine Learning Methods for Quality Prediction in Production

The rising popularity of smart factories and Industry 4.0 has made it possible to collect large amounts of data from production stages. Thus, supervised machine learning methods such as classification can viably predict product compliance quality using manufacturing data collected during production. Elimination of uncertainty via accurate prediction provides significant benefits at any stage in a supply chain. Thus, early knowledge of product batch quality can save costs associated with recalls, packaging, and transportation. While there has been thorough research on predicting the quality of specific manufacturing processes, the adoption of classification methods to predict the overall compliance of production batches has not been extensively investigated. This paper aims to design machine learning based classification methods for quality compliance and validate the models via case study of a multi-model appliance production line. The proposed classification model could achieve an accuracy of 0.99 and Cohen’s Kappa of 0.91 for the compliance quality of unit batches. Thus, the proposed method would enable implementation of a predictive model for compliance quality. The case study also highlights the importance of feature construction and dataset knowledge in training classification models.

A Machine Learning Based Classification Method for Customer Experience Survey Analysis

Customer Experience (CX) is monitored through market research surveys, based on metrics like the Net Promoter Score (NPS) and the customer satisfaction for certain experience attributes (e.g., call center, website, billing, service quality, tariff plan). The objective of companies is to maximize NPS through the improvement of the most important CX attributes. However, statistical analysis suggests that there is a lack of clear and accurate association between NPS and the CX attributes’ scores. In this paper, we address the aforementioned deficiency using a novel classification approach, which was developed based on logistic regression and tested with several state-of-the-art machine learning (ML) algorithms. The proposed method was applied on an extended data set from the telecommunication sector and the results were quite promising, showing a significant improvement in most statistical metrics.