Decision Tree Classification Method Research Articles

Responding to challenge call for machine learning model development in diagnosing respiratory disease sounds

The normal and abnormal sounds from the respiratory system shed great light on medical science by revealing the quality, diseases and changes in people’s lungs. In medicine, this easy and old method, realized by the stethoscope, facilitates the diagnosis of diseases by specialists. This manual method can sometimes lead to wrong decisions in terms of sound detection due to different audibility. Detailed sound analysis is crucial for accurately detecting lung diseases with high mortality rates. As technology advances, the development of automated approaches based on machine learning is of great interest as they provide modern and highly accurate analysis. In today’s most popular topic, i.e., the COVID-19 disaster, the conflict between early detection of respiratory disease and machine learning for sound signal processing is extremely important. In this study, a machine learning model was developed to detect respiratory system sounds such as sneezing/coughing in disease diagnosis. The automatic model and approach development of breath sounds, which carry valuable information, results in early diagnosis and treatment. A successful machine learning model was developed in this study, which was a strong response to the challenge called the “Pfizer digital medicine challenge” on the “OSFHOME” open access platform. In the database provided in this challenge, which consists of 3 parts, features that effectively showed coughing/sneezing sound analysis were extracted from training, testing and validating samples. Based on the Mel frequency cepstral coefficients (MFCC) feature extraction method, mathematical and statistical features were prepared. The sequential forward selection (SFS) feature selection method was used to select the relevant and dominant variables among the obtained features to represent the model fully and accurately. Three different classification techniques were considered for successful respiratory sound classification in the dataset containing more than 3800 sounds. Support vector machine (SVM) with radial basis function (RBF) kernels, decision tree and ensemble aggregation classification methods were used as classification techniques. In an attempt to classify coughing/sneezing sounds from other sounds, SVM with RBF kernels was achieved with 83% success.

Extracting the winter wheat using the decision tree based on time series dual-polarization SAR feature and NDVI.

Winter wheat is one of the most important crops in the world. It is great significance to obtain the planting area of winter wheat timely and accurately for formulating agricultural policies. Due to the limited resolution of single SAR data and the susceptibility of single optical data to weather conditions, it is difficult to accurately obtain the planting area of winter wheat using only SAR or optical data. To solve the problem of low accuracy of winter wheat extraction only using optical or SAR images, a decision tree classification method combining time series SAR backscattering feature and NDVI (Normalized Difference Vegetation Index) was constructed in this paper. By synergy using of SAR and optical data can compensate for their respective shortcomings. First, winter wheat was distinguished from other vegetation by NDVI at the maturity stage, and then it was extracted by SAR backscattering feature. This approach facilitates the semi-automated extraction of winter wheat. Taking Yucheng City of Shandong Province as study area, 9 Sentinel-1 images and one Sentinel-2 image were taken as the data sources, and the spatial distribution of winter wheat in 2022 was obtained. The results indicate that the overall accuracy (OA) and kappa coefficient (Kappa) of the proposed method are 96.10% and 0.94, respectively. Compared with the supervised classification of multi-temporal composite pseudocolor image and single Sentinel-2 image using Support Vector Machine (SVM) classifier, the OA are improved by 10.69% and 5.66%, respectively. Compared with using only SAR feature for decision tree classification, the producer accuracy (PA) and user accuracy (UA) for extracting the winter wheat are improved by 3.08% and 8.25%, respectively. The method proposed in this paper is rapid and accurate, and provide a new technical method for extracting winter wheat.

A hybrid machine learning with process analytics for predicting customer experience in online insurance services industry

It is essential to innovate and improve service levels by predicting possible process outcomes due to the growth of online service providers. This study estimates the customer satisfaction level based on customer experience analysis. In doing so, we answer recent calls for research about a more thorough exploration of customer behavior using predictive process monitoring techniques. In particular, a hybrid framework of supervised/unsupervised machine learning methods is proposed to predict the outcomes of customers’ experiences while dealing with the problem of high intra-class variance. This problem occurs due to the large dispersion of traces identified in the customer journeys. In this regard, customer journeys are first matched with the event log format aiming to implement a Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering technique based on the similarity between the customer journeys. After summarizing the journeys by removing low-value activities, the multi-class decision tree classification method is applied, and the level of customer satisfaction is predicted. Due to the imbalanced nature of the data, the oversampling for imbalanced classification is applied to achieve good results in accuracy indicators such as recall, precision, and F1-score. Finally, the proposed approach has been evaluated on a real-life event log, BPI Challenge 2016, to investigate unsatisfied customers. The results of the machine learning models on the test data show a high degree of accuracy in predicting customer dissatisfaction.

Deep-Learning-Based Automatic Extraction of Aquatic Vegetation from Sentinel-2 Images—A Case Study of Lake Honghu

Aquatic vegetation is an important component of aquatic ecosystems; therefore, the classification and mapping of aquatic vegetation is an important aspect of lake management. Currently, the decision tree (DT) classification method based on spectral indices has been widely used in the extraction of aquatic vegetation data, but the disadvantage of this method is that it is difficult to fix the threshold value, which, in turn, affects the automatic classification effect. In this study, Sentinel-2 MSI data were used to produce a sample set (about 930 samples) of aquatic vegetation in four inland lakes (Lake Taihu, Lake Caohai, Lake Honghu, and Lake Dongtinghu) using the visual interpretation method, including emergent, floating-leaved, and submerged vegetation. Based on this sample set, a DL model (Res-U-Net) was used to train an automatic aquatic vegetation extraction model. The DL model achieved a higher overall accuracy, relevant error, and kappa coefficient (90%, 8.18%, and 0.86, respectively) compared to the DT method (79%, 23.07%, and 0.77) and random forest (78%,10.62% and 0.77) when utilizing visual interpretation results as the ground truth. When utilizing measured point data as the ground truth, the DL model exhibited accuracies of 59%, 78%, and 91% for submerged, floating-leaved, and emergent vegetation, respectively. In addition, the model still maintains good recognition in the presence of clouds with the influence of water bloom. When applying the model to Lake Honghu from January 2017 to October 2023, the obtained temporal variation patterns in the aquatic vegetation were consistent with other studies. The study in this paper shows that the proposed DL model has good application potential for extracting aquatic vegetation data.

Impact of The Covid-19 Pandemic on Student Learning Styles: Naïve Bayes and Decision Tree Classification in Education

The Covid-19 pandemic significantly changed education with social distancing and changes in the learning environment. In this study, one strong reason for the significance of the research is the urgency of changes in students' learning styles during the Covid-19 pandemic. Investigating differences in learning styles before and during the pandemic not only provides deep insight into students' adaptation to these changes, but also provides a foundation for the development of more inclusive and adaptive learning strategies in the future. This study aims to analyze the effect of the Covid-19 pandemic on students' learning styles in an educational context, focusing on the comparison of two classification methods, Naïve Bayes and Decision Tree. The study was conducted by collecting data on students' learning styles before and during the Covid-19 pandemic, using various relevant indicators. The data was obtained based on school survey results and online platforms, involving student characteristics and learning preferences. The data was then analyzed using Naïve Bayes and Decision Tree classification methods to identify significant changes in students' learning styles. The results showed the prediction accuracy of learning style changes with Naïve Bayes 68.75% and Decision Tree 87.50%. Recommendations for educators and education policy makers are to develop inclusive and adaptive learning strategies to meet diverse learning preferences.

Utilization and Management of Technology in Making Decisions to Assist Owners in First Aid for Dogs

Dogs are one of the pets that have a close relationship with humans, due to various factors including following the word, easy to be a human playmate, and even being docile to live with humans. However, in dog keeping, disease-related problems for dogs are harmful, not only to them but also to their owners. Difficult situations in obtaining treatment also often occur, where due to the distance of the veterinary clinic, the limited number of animal specialist clinics and the owner's desire to carry out the treatment on his own. Therefore, advanced technology needs to be introduced in diagnosing and giving recommendations to dog owners for first aid in providing fast and appropriate treatment to dogs. Therefore, here an expert mobile system-based application is introduced, that uses a decision tree classification method and a forward chaining algorithm. The application was tested for user acceptance using a Likert scale that yielded 94.4% for the ease of understanding the application, 92% for the ease of use of the application, 88% for the accuracy of providing information about symptoms and diseases, 93.6% for the attractiveness of the application display and 92.8% for the benefits for application users.

A new approach to extract the upright maize straw from Sentinel-2 satellite imagery using new straw indices

Unharvested upright maize straw is highly susceptible to burning in winter or in spring of the following year, contributing significantly to air pollution. The rapid and accurate acquisition of the spatial distribution of upright maize straw holds great importance for agricultural and environmental protection departments. This study introduces a new approach that focuses on extracting upright maize straw using Sentinel-2 satellite images. Initially, the Sentinel-2 images from the Botou and Hejian regions underwent preprocessing. To minimize interference during straw extraction, the normalized difference vegetation index (NDVI) was utilized to extract and eliminate built-up land and woodland areas. Subsequently, utilizing the spectral characteristics of maize straw across various bands including short-wave infrared, red edge, and near-infrared, three new indices were proposed and computed: the accumulation infrared straw index (AIRSI), the product near-infrared straw index (PNISI), and the normalized difference short-wave infrared straw index (NDSSI). Finally, the decision tree classification method was implemented to establish classification rules and extract the spatial distribution of upright maize straw. The study results revealed that the proposed new straw indices achieved an extraction accuracy of over 90% for upright maize straw. This new approach effectively enhances the identification accuracy of upright maize straw, providing valuable support for scientific supervision, comprehensive utilization, and prevention and control measures against maize straw burning.

Cost–Benefit Evaluation of Walnut and Jujube Orchards under Fruit Tree–Crop Intercropping Conditions in Southern Xinjiang

Fruit planting plays an essential role in achieving zero hunger, ensuring food security, and increasing the income of local people. As one of China’s principal fruit-planting areas, southern Xinjiang possesses more than 80% of the total fruit-planting areas of Xinjiang. However, the spatial distribution, extent, and types of fruit trees remain unknown, generating uncertainty in calculating the economic benefits of orchards in this area. In this paper, we used walnut and jujube orchards under fruit tree–crop intercropping conditions in the Hotan Oasis in southern Xinjiang as the research object. Walnut and jujube orchards were precisely characterized using object-oriented and decision tree classification methods. Then, the economic benefits for farmers were estimated based on field surveys and statistical data. From 2003 to 2020, the area of jujube orchards rapidly increased from 1.91 × 103 ha to 33.59 × 103 ha, while that of walnut orchards steadily increased from 18.05 × 103 ha to 40.24 × 103 ha. The expansion areas of walnut orchards were mainly transformed from other orchards in the oasis, while the expansion areas of jujube orchards mainly originated from newly cultivated land in the desert. The increases in areas and yields largely offset the increase in planting costs and the decrease in purchase prices, resulting in an increasing trend in the total net income of the orchards. From 2003 to 2020, the total net income of walnut orchards increased by 68.96%, and the total net income of jujube orchards significantly increased by 23.37 times. However, the output/input ratios of walnut orchards under intercropping conditions were approximately two times higher than those of jujube orchards under monocropping conditions. The increase in investment slightly offset the decreases in yields and purchase prices, resulting in increases of 5.24% and 18.64% in the output/input ratios of walnuts and jujubes, respectively, in orchards exhibiting standardized cultivation. In the future, it is necessary to significantly expand the area of orchards involving standardized cultivation and improve the yield and quality of fruits, thereby increasing the yields and income levels of local farmers.

Detection of Broken Rotor Bars in Cage Induction Motors Using Machine Learning Methods.

In this paper, the performance of machine learning methods for squirrel cage induction motor broken rotor bar (BRB) fault detection is evaluated. Decision tree classification (DTC), artificial neural network (ANN), and deep learning (DL) methods are developed, applied, and studied to compare their performance in detecting broken rotor bar faults in squirrel cage induction motors. The training data were collected through experimental measurements. The BRB fault features were extracted from measured line-current signatures through a transformation from the time domain to the frequency domain using discrete Fourier Transform (DFT) of the frequency spectrum of the current signal. Eighty percent of the data were used for training the models, and twenty percent were used for testing. A confusion matrix was used to validate the models' performance using accuracy, precision, recall, and f1-scores. The results evidence that the DTC is less load-dependent, and it has better accuracy and precision for both unloaded and loaded squirrel cage induction motors when compared with the DL and ANN methods. The DTC method achieved higher accuracy in the detection of the magnitudes of the twice-frequency sideband components induced in stator currents by BRB faults when compared with the DL and ANN methods. Although the detection accuracy and precision are higher for the loaded motor than the unloaded motor, the DTC method managed to also exhibit a high accuracy for the unloaded current when compared with the DL and ANN methods. The DTC is, therefore, a suitable candidate to detect broken rotor bar faults on trained data for lightly or thoroughly loaded squirrel cage induction motors using the characteristics of the measured line-current signature.

Satellite-Based Monitoring of Growing Agricultural Water Consumption in Hyper-Arid Regions

Land-use change has a key role in hydrologic processes and biodiversity. Although many satellite-based studies have been conducted to reveal the interaction between land-use changes in hydrological processes worldwide, the land-use change impact on agricultural water consumption in hyper-arid regions is poorly understood. Here, we investigate increased agricultural water consumption in the Qom province, a hyper-arid region in Iran, using derived imageries from Landsat 5 Tm and Landsat 8 OLI during the last three decades. We used maximum likelihood classification (MLC) and decision tree classification (DTC) to analyze the satellite images. The MLC method showed that croplands have increased from 30,547 ha in 1989 to 39,255 ha in 2019 (i.e., a 29% increase). In this period, the total orchard area increased from 3904 ha to 6307 ha, revealing a growth of 61%. In the DTC method, the increases in the cropland and orchard areas were, respectively, 34% and 60%. Although both MLC and DTC satisfied the accuracy criteria, the former was more consistent than the latter concerning ground data and documented statistics. Satellite-based and MLC results showed an increase in agricultural water consumption from 152 million cubic meters (MCM) in 1989 to 209 MCM in 2019, showing a 38% increase (i.e., 1.27% annually). Our findings send an alarming message for policymakers to reduce the water demand through sustainable agricultural practices in the Qom province, where the agricultural sector uses approximately 90% of annual water demand.

IoT Botnet Detection Using Autoencoders and Decision Trees

The use of IoT devices has grown rapidly, leading to an increase in cyber attacks that pose greater security and privacy threats than ever before. One such threat is botnet attacks on IoT devices. An IoT botnet is a group of Internet-connected IoT devices infected with malware and remotely controlled by an attacker. Machine learning techniques can be employed to detect botnet attacks. The use of machine learning-based detection methods has been shown to be effective in identifying cyber attacks. The performance of the detection system in machine learning can be improved by utilizing data reduction methods. The data reduction process in classification is used to overcome the problem of scalability and computation resources in the IoT. This paper proposes a detection system using the Autoencoder reduction method and the Decision tree classification method. The test results demonstrate that the Deep Autoencoder algorithm can reduce data and memory usage from 1.62 GB to 75.9 MB, while also improving the performance of decision tree classification, resulting in a high level of accuracy up to 100%. The Autoencoder approach in conjunction with the Decision Tree exhibits superior capabilities compared to previous studies.

The Latest Desertification Process and Its Driving Force in Alxa League from 2000 to 2020

Alxa League of Inner Mongolia Autonomous Region is a concentrated desert distribution area in China, and the latest desertification process and its driving mechanism under the comprehensive influence of the extreme dry climate and intense human activities has attracted much attention. Landsat data, including ETM+ images obtained in 2000, TM images obtained in 2010, and OLI images obtained in 2020, were used to extract three periods of desertification land information using the classification and regression tree (CART) decision tree classification method in Alxa League. The spatio-temporal variation characteristics of desertification land were analyzed by combining the transfer matrix and barycenter migration model; the effects of climate change and human activities on regional desertification evolution were separated and recombined using the multiple regression residual analysis method and by considering the influence of non-zonal factors. The results showed that from 2000 to 2020, the overall area of desertification land in Alxa League was reduced, the desertification degree was alleviated, the desertification trend was reversed, and the desertification degree in the northern part of the region was more serious than in the southern part. The barycenter of the slight, moderate, and severe desertification land migrated to the southeast, whereas the serious desertification land’s barycenter migrated to the northwest in the period of 2000–2010; however, all of them hardly moved from 2010 to 2020. The degree of desertification reversal in the south was more significant than in the north. Regional desertification reversal was mainly influenced by the combination of human activities and climate change, and the area accounted for 61.5%; meanwhile, the localized desertification development was mainly affected by human activities and accounted for 76.8%.

A Meta-Heuristic Algorithm-Based Feature Selection Approach to Improve Prediction Success for Salmonella Occurrence in Agricultural Waters

The presence of Salmonella in agricultural waters may be a source of produce contamination. Recently, the performance of various algorithms has been tested for the prediction of indicator bacteria population and pathogen occurrence in agricultural water sources. The purpose of this study was to evaluate the effect of meta-heuristic optimization algorithms for feature selection to increase the Salmonella occurrence prediction performance of commonly used algorithms in agricultural waters. Previously collected dataset from six agricultural ponds in Central Florida included the population of indicator microorganisms, physicochemical water attributes, and weather station measurements. Salmonella presence was also reported with PCR-confirmed method in data set. Features were selected by binary meta-heuristic optimization methods including differential evolution optimization (DEO), grey wolf optimization (GWO), Harris hawks optimization (HHO) and particle swarm optimization (PSO). Each meta-heuristic method was run for 100 times for the extraction of features before classification analysis. Selected features after optimization were used in the K-nearest neighbor algorithm (kNN), support vector machine (SVM) and decision tree (DT) classification methods. Microbiological indicators were ranked as the first or second features by all optimization algorithms. Generic Escherichia coli was selected as the first feature 81 and 91 times out of 100 by GWO and DEO, respectively. The meta-heuristic optimization algorithms for the feature selection process followed by machine learning classification methods yielded the prediction accuracy between 93.57 and 95.55%. Meta-heuristic optimization algorithms had a positive effect to improve Salmonella prediction success in agricultural waters despite spatio-temporal variations in agricultural water quality.

Estimation of Hyrcanian forests coverage using ALOS PALSAR and MODIS satellite data (2007–2017)

This study aims to monitor the extent changes of Hyrcanian forests using ALOS-/PALSAR-1 and ALOS/PALSAR-2 (PALSAR) mosaic data with HH and HV polarimetric bands from 2007 to 2017. To date, no comprehensive studies have been conducted on the total cover area of the Hyrcanian forests. This study attempts to provide specific and local threshold values for to extract the Hyrcanian forests cover through careful examination of satellite data over ten years. In this study, the acquired 57 PALSAR images were calibrated and converted to γ0 (dB) for the years 2007, 2010, and 2017. Then, the backscattering value ranges of the Hyrcanian forests were determined using the Decision Tree classification method. The backscattering values range from −14.5 to −7.2 dB and −17.5 to −8.5 dB for the years 2007 and 2010 and −18.5 to −7.5 dB for 2017 in the HV-band and from −7.5 to −14.5 dB for 2007 and 2010 and −6.2 to −12.5 dB for 2017 in the HH band correspond to forest. Finally, the results were compared with Japanese Aerospace Exploration Organization (JAXA) forest and non-forest (F/NF) maps from PALSAR data for validation purposes; the overall accuracies and Kappa coeffitients were 92.55%, 0.82% (2007), 91.14%, 0.79% (2010), and 88.19%, 0.74 (2017), respectively. This result shows that values between −7.2 and −13.5 dB are the best range for the Hyrcanian forests’ extent extraction from PALSAR image in the HV band. The output were further validated using three independent sources: (1) High-Resolution Google Earth (GE) image; (2) F/NF maps from the JAXA; and (3) MOD13Q1 Products (250 m spatial resolution). The results show good consistency with the mentioned datasets.

Comparison of K-Nearest Neighbor, Naive Bayes Classifier, Decision Tree, and Logistic Regression in Classification of Non-Performing Financing

The Non-Performing Financing (NPF) indicator of one of the Islamic Banks in Indonesia in the 1st to 3rd quarter of 2021 in a row of 9.69%; 9.97%; 9.46%. The NPF movement tends to improve slightly from time to time but still exceeds the maximum limit stipulated in Bank Indonesia’s Regulation Number 23/2/PBI/2021, which is no more than 5%. This shows that the Islamic bank has a financing performance that can be said to be less good. Preventive steps that can be taken to reduce the NPF ratio in order to improve the health of the bank is to classify prospective financing customers. This research was conducted using the K-Nearest Neighbor (KNN), Naive Bayes Classifier (NBC), Decision Tree, and Logistics Regression classification methods to predict potential financing customers. The dataset is divided into 80% training and 20% testing. It was found that the best classification result was the Naive Bayes Classifier in the proportion of distribution of 80% training data and 20% testing data with an accuracy value of 84.69%, sensitivity of 58.25%, and specificity of 90.16%.

Comparison of KNN, naive bayes, and decision tree methods in predicting the accuracy of classification of immunotherapy dataset

Health is crucial for humans to carry out daily activities, and cancer is the second leading cause of death worldwide. Maintaining health is essential in minimizing factors associated with cancer. Immunotherapy is a new cancer treatment technique that has s shown a bigger success rate compared with conventional techniques. However, the effectiveness of this method depends on accurate diagnosis, which requires deeper analysis and research on classification methods. This study compares the accuracy of KNN, Naive Bayes, and Decision Tree classification methods in predicting the accuracy of immunotherapy treatment. The goal is to find the most effective classification techniques that can provide more accurate predictive results in treating diseases using immunotherapy. Based on the test results of Naive Bayes, Decision Tree, and K-Nearest Neighbor, the result obtained of accuracy rates are 81.11%, 80.00%, and 74.44%. From the accuracy comparison, it is known that the Naive Bayes algorithm is the most effective algorithm with the highest accuracy value of 81.11%.

Classification of Poisonous and Edible Mushrooms with Optimized Classification Algorithms

Within the scope of this study, it is aimed to classify the mushroom species consumed as a staple food. For this purpose, 8124 mushroom data with 22 different mushroom feature information were used. 5686 of these data were used for training and 2438 for testing. In the study, poisonous and edible mushroom species were classified by random forest, decision tree, and logistic regression classification methods. The parameters used in the random forest and decision tree classification algorithms used in the study were optimized with the GridSearchCV optimization method. With the random forest algorithm, the highest precision, recall, and F1 score values are 0.93, 0.98, and 0.95, respectively. When these values are examined on a class basis, the highest distinctiveness results were obtained in the poisonous class. In the edible class, the highest performance results were measured as 0.97, 0.92, and 0.95 for precision, recall, and F1 score values, respectively. With the decision Tree algorithm, the highest precision, recall, and F1 score values are 0.98, 0.98, and 0.92, respectively. The highest precision, recall, and F1 score values of the best poisonous class are 0.90, 0.98, and 0.92, respectively. The best performance results of the edible class were obtained with the highest precision, recall, and F1 score values of 0.98, 0.89, and 0.90, respectively. The average accuracy rate was 0.9028 with the Logistic Regression algorithm, and the precision, recall, and F1 score values of the poisonous class were obtained as 0.86, 0.97, and 0.91, respectively. Precision, recall, and F1 score values of the Edible class were obtained as 0.96, 0.83, and 0.89, respectively.

A groundwater level-based filtering to improve the accuracy of locating agricultural tile drain and ditch networks

Remote sensing (RS) using satellites circling around the Earth has great potential for monitoring surface processes with reduced cost and greater access. This study uses three approaches to identify possible drainage unit locations: existing benchmark techniques and a novel complementary approach based on groundwater table depth. The study area comprises a site in Ontario, Canada, and the Kleine Nete catchment, Belgium. First, a change detection method based on the interpretation of RS imagery is used to retrieve soil moisture differences. Based on the retrieved soil moisture differences, it is possible to distinguish between drained and undrained fields. Secondly, the decision tree classification (DTC) method based on filtering pixels corresponding to agricultural fields with a slowly draining soil class along with a gentle slope was applied to identify drainage units. Finally, a novel filtering technique based on groundwater table depth is applied as a complementary identification tool to the former approach.The remote sensing method resulted in 87.8% accuracy in the first study area, while the decision tree classification achieved 96.7% accuracy. Although the RS approach was not successful in following the ditch network, the DTC was able to indicate ditch networks with up to 58% accuracy. However, the additional filtering using groundwater level measurements increased the drainage unit identification accuracy in the first study area (corresponds to finding an additional 19.4 km2 area of drains). A final quantitative assessment for the second study area revealed a close follow-up of the ditch network to the shallow groundwater table maps. In general, it can be concluded that both the remote sensing and the DTC method have tremendous potential to identify drainage units, although with limitations in particular cases, such as low accuracy. Moreover, it can be advised that a local visit to the study area is required to investigate what type of drainage system is used. Next, the novel use of groundwater level-based filtering further improves the drainage identification procedure. Finally, combining several data and techniques allows for accurately identifying drainage units, which is ultimately useful for the sustainable management of drained water from agricultural fields.

Feature Selection and Dynamic Network Traffic Congestion Classification based on Machine Learning for Internet of Things

The network traffic congestion classifier is essential for network monitoring systems. Network traffic characterization is a methodology to classify traffic into several classes supporting various attributes. In this paper, payload-based classification is suggested for network traffic characterization. It has a broad scope of utilization like network security assessment, intrusion identification, QoS supplier, et cetera; furthermore, it has significance in investigating different suspicious movements in the network. Numerous supervised classification techniques like Support Vector Machines and unsupervised clustering methods like K-Means connected are used in traffic classification. In current network conditions, minimal supervised data and unfamiliar applications influence the usual classification procedure's performance. This paper implements a methodology for network traffic classification using clustering, feature extraction, and variety for the Internet of Things (IoT). Further, K-Means is used for network traffic clustering datasets, and feature extraction is performed on grouped information. KNN, Naïve Bayes, and Decision Tree classification methods classify network traffic because of extracted features, which presents a performance measurement between these classification algorithms. The results discuss the best machine learning algorithm for network congestion classification. According to the outcome, clustering (k-means) with network classification (Decision Tree) generates a higher accuracy, 86.45 %, than other clustering and network classification

The (Un)Equal Effect of Binary Socialisation on Adolescents’ Exposure to Pornography: Girls’ Empowerment and Boys’ Sexism from a New Representative National Survey

Due to the increasing trend in the use of pornography recorded in recent years, along with the decreasing age of its consumers, many studies have investigated its potential negative effects on adolescents, who are developing their social and sexual identity, often producing inconsistent results. With the present study, which is based on a large representative sample of Italian students attending public upper secondary schools, predictors as well as negative and positive effects of pornography use on adolescents’ attitudes, beliefs and well-being have been identified through a psychosocial approach. To achieve these results, the study involved a two-step analysis: first, the decision tree method for classification was applied to identify the main predictors of different frequencies in pornography consumption; subsequently, multinomial logistic regressions were carried out to detect the effects of pornography use. The results show a large difference between boys and girls in terms of frequency of pornography use, but also in the effects on adherence to gender roles, which is related to a still strongly stereotyped socialisation. Instead, similar negative effects on both girls and boys were found on self-esteem, body satisfaction, negative primary emotions and distress, suggesting the need for adequate sex education provided by both parents and schools to counteract taboos and blind internalisation of models of beauty and sexual behaviours provided by pornography.