Tree Technique Research Articles

Forecasting heating and cooling loads in residential buildings using machine learning: a comparative study of techniques and influential indicators

Residential buildings are a significant source of energy consumption and greenhouse gas emissions, making it crucial to accurately predict their energy demand for reducing their environmental impact. In this study, machine-learning techniques such as linear regression, decision tree classification, logistic regression, and neural networks were applied to forecast the heating and cooling loads of 12 different building types using their area and height attributes. The correlation coefficient was utilized to assign weights to the predictors in linear regression, and the models’ performance was evaluated using metrics such as equations of R2, MAE, and RMSE. The decision tree technique demonstrated the highest accuracy of 98.96% and 93.24% for predicting heating and cooling loads, respectively, among the classification methods. Notably, the cooling load prediction was more accurate than the heating load prediction. The height and area of the roof and floor, along with the relative compactness of the building, were identified as the most influential factors in the heating and cooling loads. These findings have significant implications for optimizing energy efficiency in residential buildings and mitigating their impact on climate change.

IMPLEMENTATION OF C4.5 ALGORITHM FOR ASSESMENT OF COMMUNITY SATISFACTION

This Research applies the C4.5 Algorithm in deciding community satisfaction of sommunity services. Algorithm C4.5 is a classification algorithm with a decision tree technique that is well known and preferred because it has many advantages. These advantages, for example, can process numeric and discrete data, can handle missing attribute values, produce rules that are easy to interpret and the fastest. This research is a classification with the concept of data mining involving 20 community questionnaire data which are categorized as: cheap, expensive, appropriate, inappropriate, fast, long, comfortable, uncomfortable. There are four attributes that affect community satisfaction including: handling costs, service procedures, handling time and convenience. From the results of this research that has been conducted by researchers, it can be concluded. The customer satisfaction of the community services can be predicted and evaluated by utilizing data mining techniques using the C4.5 Algorithm to predict community satisfaction. This research also provided that C4.5 Algorihtm can be used to get high result of accuracy

Two-stage centralised management of Local Energy Market for prosumers integration in a community-based P2P

Centrally managed or community-based P2P Energy Communities are at the forefront of the literature. A collectively shared energy configuration maximises the energy use of local generators. An interesting scenario is energy sharing when residential buildings conform to an Energy Community with tertiary buildings as prosumers. This article introduces a two-stage centralised management of the Local Energy Market for prosumers integration. In the first stage, energy planning is carried out. In this phase, the Local Energy Market Operator optimises the energy dispatch based on energy prosumers’ predictions (previously performed by each participant using Boosting Decision Tree technique) and Mixed Integer Linear Programming. In the second stage, real time management is performed, where energy storage systems (individual Batteries and Central Energy Storage System) are employed to address the energy deviations. To address the viability of the proposed management, in the first place, the community-based P2P is compared to other Low Voltage configurations (Collective Self-Consumption and Full P2P) for one-stage management, where the community-based P2P approach obtains the best results in technical, economic, and environmental aspects. Subsequently, the two-stage management is examined with local Batteries and combining local Batteries with a Central Energy Storage System. The results show that the proposal, integrating local and central storage, significantly improves a local energy community’s techno-economic and environmental indicators regarding other energy management market configurations.

Search for dark photons from Higgs boson decays via ZH production with a photon plus missing transverse momentum signature from pp collisions at sqrt{s} = 13 TeV with the ATLAS detector

This paper describes a search for dark photons (γd) in proton-proton collisions at sqrt{s} = 13 TeV at the Large Hadron Collider (LHC). The dark photons are searched for in the decay of Higgs bosons (H → γγd) produced through the ZH production mode. The transverse mass of the system, made of the photon and the missing transverse momentum from the non-interacting γd, presents a distinctive signature as it peaks near the Higgs boson mass. The results presented use the total Run-2 integrated luminosity of 139 fb−1 recorded by the ATLAS detector at the LHC. The dominant reducible background processes are estimated using data-driven techniques. A Boosted Decision Tree technique is adopted to enhance the sensitivity of the search. As no excess is observed with respect to the Standard Model prediction, an observed (expected) upper limit on the branching ratio BR(H → γγd) of 2.28% ( {2.82}_{-0.84}^{+1.33}% ) is set at 95% CL for massless γd. For massive dark photons up to 40 GeV, the observed (expected) upper limits on BR(H → γγd) at 95% confidence level is found within the [2.19,2.52]% ([2.71,3.11]%) range.

Profiles of University Students Who Graduate on Time: A Cohort Study from the Chilean Context.

Graduating from higher education on time is an important topic, given its relation to students' academic success and the efficiency of the institutions. However, a low percentage of university students finish their studies on time, which poses a challenge that requires the identification of the factors that account for this phenomenon. This study aimed to identify and characterize profiles of students who graduate on time. The population is 514 university students (45% men, 55% women), with an average age of 19.5 years (SD= 1.9) studying business at a university in Chile who belong to four cohorts entering between 2011 and 2014. The results obtained from the Classification and Regression Tree (CART) technique demonstrate eight student profiles constructed considering different variables at the pre-university, transition-motivation, and university levels. As the primary outcome, the profile of the student who graduates on time is characterized by a good performance in the first year of university, enters university right after high school, and takes advantage of institutional support by participating in academic tutoring. These findings suggest that institutions can implement specific strategies from the beginning of the university journey to promote on-time graduation.

Risk Prediction Model of Road Accidents During Long Holiday in Thailand Using Ensemble Learning with Decision Tree Approach

The rate of injury and death from traffic accidents during the New Year and Songkran Festival each year has high and are continuously on the increase. The researchers, therefore, has decided to study and develop a model for predicting the road accident risk during the holiday season with ensemble learning based on decision tree approach. The aim is to help reduce accidents and loss of life caused by road accidents. The dataset used in this research is traffic accidents resulting in injury and death data during the long holiday from 2008 to 2015 from hospitals across the country, accumulatively recorded by the National Institute for Emergency Medicine. Thisresearch compared the efficiency of data classification to find the best ensemble model for predicting traffic accident risk. The methods studied included Adaptive Boosting (AdaBoost), and Random Forest, and the decision tree techniques used in the experiment were J48, ID3, and CART. The results of experiment and comparisons of classification efficiency showed that the Random Forest algorithm with J48 decision tree was the most efficient model, providing an accuracy of up to 93.3%.

LICENSING AND ENFORCEMENTIN MUNICIPAL ENVIRONMENTAL DEPARTMENTS IN THE STATE OF RIO GRANDE DO SUL, BRAZIL

This study evaluated the environmental departments of some municipalities in Rio Grande do Sul, Brazil, regarding their structure and licensing and enforcement processes. Information was collected through online questionnaires sent to municipalities. The questionnaires addressed the staff, the training of the technical staff and the work structure of the environmental departments in the municipalities. Evaluations and classifications were conducted using the classification tree technique based on municipal data on the environmental licenses issued, and additionally the infraction notices issued as response variables. Thus, it was observed that human resources, effective civil servants and the work team composition are the variables that best explain the issuance behavior of the municipal environmental licenses, and in parts the infraction notices. The other variable that most satisfactorily explains the issuance of infraction notices in the municipalities is the use of their own website with environmental software in the environment departments.

Dietry Monitoring System Using Decision Tree to Control Human Obesity

Nowadays, obesity is one of the dangerous diseases in the world. Lack of dietary monitoring system will make it difficult for people with obesity to reduce their weight problems. The main objective of this project is to develop a dietary monitoring system that can be used by everybody especially for obesity’s people. The method used in this study is to identify the strength and weaknesses of the existing system which involves reviewing some articles, journals, magazines, and books. The survey was conducted which involves 10 people answering the questionnaire. Respondent answered was used to improve the quality of the system. Next method is utilizing a waterfall model as a method to develop a dietary monitoring system. The system applied the decision tree technique to a classified food calorie. Therefore, the decision tree technique was used in developing this system. The last method used in this study involves the participation of three respondents to evaluate the usability of the system. Respondents need to answer whether they satisfied with the system or they can give suggestions for future improvement. The results of this study show that obesity is a public health issue that is rapidly increasing and must be addressed seriously by developing the system. Significant by developed this system such as helping obesity’s people to diet by giving them the guideline. In conclusion, this system will help people to diet using the decision tree technique for classifying food calories.

Classification trees as machine learning tool to explore consumers’ purchasing decision pathway. A case-study on parent’s perception of baby food jars

Classification and regression trees are machine learning methods useful to model non-linear and complex relationships. The objective of this study was to use classification tree method to model purchasing parents’ decision of buying or rejecting baby food jars and to identify the different pathways in the decision of consumers that explain the different purchasing patterns. For that, parents (n = 100) of babies (6 to 36 months old) evaluated 16 baby food jar images. For each one, parents indicated their purchase intention but also evaluated other aspects like expected liking, trust, health, and nutritive perception. Three clusters with different purchasing patterns were obtained and classification trees showed the different hierarchy of factors in the pathway toward the purchasing decision. For cluster 1 decision was based mainly on liking but conditioned to trust perception. For cluster 2, the decision was firstly based on healthiness perception and conditioned to liking. Cluster 3, the decision included a more complex pathway initiated by trust and followed by liking, nutritive and healthiness perceptions. The approach combining clustering and classification tree techniques is useful to explore and understand individual differences in consumers purchasing decision.

Efektivitas Teknik Rebozo Shake the Apple (RSTA) Terhadap Intensitas Nyeri Dan Lama Kala 1 Fase Aktif Pada Persalinan Ibu Multigravida

Introduction: Pain during labor if not resolved will result in prolonged labor which is the cause of maternal death by 4,3%. Various efforts have been made to reduce the rate of prolonged labor, one of which is the rebozo shake the apple tree technique. Based on the results of a survey conducted at the Manis Jaya Health Center in April 2022, out of 33 mothers giving birth, 11 mothers experienced prolonged labor. Methods: This study was a quasi-experimental design with a pre-post test control group design. The research sample for multigravida mothers was 30 respondents using a purposive sampling technique. Data were analyzed using the dependent t-test and independent t-test. Results: The results of the univariate analysis revealed that the average pain intensity of the intervention group before was 6,27 after 1,67 and the control group before was 5,93 after 3,33. The average duration of the first active phase of the intervention group was 152,67 minutes and the control group was 215,13 minutes. The results of bivariate analysis of the intensity of labor pain with a value of p = 0,001 <0,005 and the duration of the first stage of the active phase with a value of p = 0,000 <0,005. Discussion: There is the effectiveness of the Rebozo Shake the Apple Tree (RSTA) technique on the intensity of labor pain and the length of the first active phase. It is hoped that health workers can provide the Rebozo Shake the Apple Tree (RSTA) technique to reduce labor pain and speed up the delivery process.

Detection of DDOS Attack using Decision Tree Classifier in SDN Environment

Software Defined Networking (SDN) is a dynamic architecture that employs a variety of applications for making networks more adaptable and centrally controlled. It is easy to attack the entire network in SDN because the control plane and data plane are separated. DDoS attack is major danger to SDN service providers because it can shut down the entire network and stop services to all customers at any time. One of the key flaws of most SDN architectures is lack of susceptibility to DDoS attacks with its types like TCP flooding, UDP flooding, SYN flooding, ICMP flooding and DHCP flooding for detecting those kinds of attacks. The machine learning algorithms are widely used in recent years to identify DDoS attacks. This research utilizes Decision Tree Classifier for detection and classification of DDoS attacks on SDN. The Forward Feature Selection technique is also used in the research to select the best features from the dataset and from that dataset the data are employed to train and test the model by Decision Tree Classifier Algorithm. The decision Tree Classifier technique is a supervised method used to forecast desired values of observations using rudimentary machine learning decision rules derived from training data. Based on the accuracy of decision tree techniques, in future, a hybrid learning model will be designed for detecting the Distributed Denial of Services in an SDN environment with high accuracy and a low false negative rate.

A transportation scheduling management system using decision tree and iterated local search techniques

This paper aimed to develop a delivery truck scheduling management system using a decision tree to support decision-making in selecting a delivery truck. First-in-first-out (FIFO) and decision tree techniques were applied to prioritize loading doors for delivery trucks with the use of iterated local search (ILS) in recommending the route for the transport of goods. Besides, an arrangement of loading doors can be assigned to the door that meets the specified conditions. The experimental results showed that the system was able to assign the job to a delivery truck under the specified conditions that were close to the actual operation at a similarity of 0.80. In addition, the application of ILS suggested the route of the food delivery truck in planning the most effective transportation route with the best total distance.

Employee Attrition System Prediction using Random Forest Classifier

Despite rising unemployment, most job coverage of the COVID-19 outbreak has concentrated on layoffs. Employees have been fired for reasons related to the epidemic, which has been a less prominent issue. COVID-19 is still doing damage to the country's economy. Companies are in the midst of a recession, so they are beginning to fire off unproductive employees. Making critical decisions like laying off employees or cutting an employee's compensation is a challenging undertaking that must be done with extreme attention and accuracy. Adding negligence would harm the employee's career and the company's image in the industry. In this paper, we have predicted employee attrition using Logistic Regression, Random Forest, and Decision Tree techniques. Random Forest Classifier has outperformed other algorithms in this work. After using different machine learning techniques, we can say that Random Forest gives the best performance with a recall of 70%, and also, we have found Precision, Accuracy, and F1- Score.

Forecasting Pesticide Use on Golf Courses by Integration of Deep Learning and Decision Tree Techniques

In the current study, a new hybrid machine learning (ML)-based model was developed by integrating a convolution neural network (CNN) with a random forest (RF) to forecast pesticide use on golf courses in Québec, Canada. Three main groups of independent variables were used to estimate pesticide use on golf courses, expressed as actual active ingredient rate (AAIR): (i) coordinates (i.e., longitude and latitude of the golf course), (ii) characteristics of the golf courses (i.e., pesticide type and the number of holes), and (iii) meteorological variables (i.e., total precipitation, P, and average temperature, T). The meteorological variables were collected from the Google Earth Engine by developing a JavaScript-based Code. On the basis of the different periods of total precipitation and average temperature, four different scenarios were defined. A data bank with more than 40,000 samples was used to calibrate and validate the developed model such that 70% of all samples were randomly selected to calibrate the model, while the remainder of the samples (i.e., 30%) that did not have any role in calibration were employed to validate the model’s generalizability. A comparison of different scenarios indicated that the model that considered the longitude and latitude of the golf course, pesticide type, and the number of holes in golf courses as well as total precipitation and average temperature from May to November as inputs (R = 0.997; NSE = 0.997; RMSE = 0.046; MAE = 0.026; NRMSE = 0.454; and PBIAS (%) = −0.443) outperformed the other models. Moreover, the sensitivity analysis result indicated that the total precipitation was the most critical variable in AAIR forecasting, while the average temperature, pesticide types, and the number of holes were ranked second to fourth, respectively.

Analyzing the Impact of Epidermoid and Adeno Tissue on Cancer Incidence Whit a Data Mining Approach

Early detection is the only way to effectively control diseases whose treatment can be challenging, expensive, and time-consuming. Identifying the influencing factors in the occurrence of disease can, therefore, reduce the time associated with diagnosis and provide a solid foundation for improving the prognosis and preventing patients' deterioration. Applying data mining techniques as a novel approach to the early detection of disease-causing agents can significantly assist the early detection. In this study, an attempt was made to investigate the effect of epidermoid and adeno tissues on the incidence of cancerous diseases such as bone, bone marrow, lung, and neck cancer by conducting a data mining process on cancer patient data sets. Hence, Implementing two data mining techniques, K-nearest neighbor and decision tree, on the data of patients with these four types of cancer, an attempt was made to evaluate their performance using the three criteria of accuracy, error ratio, and negative prediction value. The implementation of data mining techniques and evaluations of their performance indicates that the decision tree technique performed better with an accuracy of 89.10%, an error ratio of 14.04%, and negative prediction value of 77.71%. Also, based on the findings, contamination of epidermoid and adeno tissues does not affect the early detection of any of the four categories of bone, bone marrow, lung, or neck cancer. In other words, the infection of the two epidermoid and adeno tissues cannot be the cause of the four types of bone, bone marrow, lung, and neck cancer

Predicting Willingness to Donate Smartphones as a Reuse Option using Decision Tree Analysis

The increasing number of smartphone users in Indonesia, coupled with the short average usage time of smartphones, has posed a sustainability problem. Smartphone production requires natural resources including rare earth materials and energy, that need to be preserved due to their limited availability and depletion. Circular economy initiatives have become important in the last few decades, and one of them is extending product life by reusing discarded products. On the other hand, triggered by the Covid-19 pandemic, online learning has become an essential part of education. In Indonesia, marginalized communities or low-income societies have limitations in providing online learning tools such as desktop or laptop computers, including smartphones. Therefore, smartphone donation is considered a suitable initiative to help students who need a smartphone to join online learning while at the same time extending the useful life of a smartphone. Using decision tree techniques, we investigate the willingness to donate used smartphones for education in the Indonesian context. The results show that the respondents' willingness-to-donate was influenced by several considerations, which are performance, value (price), type, obsolescence of the used smartphone, and the donators’ age. The resulting parameters and predictions could enhance the effectiveness of the donation mechanism.

Data-Driven Analysis of Stimulation Treatments Using Association Rule Mining

Summary Effective analysis of data collected during the well’s operational cycle is crucial to well performance, economic evaluation, and good decision-making in the upstream oil industry. Generally, the analysis of huge volumes of data stored in databases is beyond the power of traditional methods, such as curve-fitting and statistical hypothesis testing. Data mining is the practice of analyzing large databases to identify patterns, anomalies, and correlations, within the data, leading to new, hidden, and valuable knowledge that would support decisions. This article proposes a data-driven methodology for analyzing the stimulation operations data in oil/gas wells to identify the underlying rules or patterns that lead to successful operations. Association rule mining (ARM) is used in this research for rule induction purposes. The proposed approach aims to mine the frequently occurring rules, within the collected database, that guarantee the success of stimulation operations with a high degree of confidence. Finally, the proposed approach is evaluated against a set of real data from an Iranian oil field. On the basis of past stimulation operations, these extracted rules show the conditions that are most likely to lead to a successful operation. The rules identified by the proposed approach are compared against the rules that can be generated by the decision tree (DT) technique using the same data set. As the reliability of the rules is controlled by setting the minimum thresholds on support and confidence, more significant and useful rules could be derived from ARM compared to the DT technique. Using the identified rules and generated information can support the operational decisions by assisting in the design of due stimulation jobs or in selecting the appropriate candidates for future operations.

Measuring dynamic inefficiency through machine learning techniques

This paper contributes by developing new models for assessing dynamic inefficiency that incorporate machine learning techniques. In particular, the new approaches apply decision trees models for the estimation of dynamic production technologies that account for investment adjustment costs. Methodologically, the new models build on the recently developed techniques of Efficiency Analysis Trees (EAT) and Convexified Efficiency Analysis Trees (CEAT) and extend them even further to a dynamic framework comprising dynamic EAT and CEAT models. The study compares dynamic inefficiency scores estimated assuming the new models against the traditional dynamic free disposal hull (FDH) and dynamic data envelopment analysis (DEA). Our empirical application focuses on dairy manufacturing firms in the main dairy processing countries in the European Union for the years 2014 and 2018. The results show that inefficiency related to the dynamic CEAT or EAT is higher than their corresponding values calculated through the dynamic DEA or FDH. The discriminating power of dynamic DEA (dynamic FDH) drastically improves when switching to dynamic CEAT (dynamic EAT). Finally, the differences between countries are observed regarding the development of dynamic inefficiency in the period associated with milk quota abolition.

Application of data mining techniques for VAT-Registered Business compliance

World Bank recommends that Indonesia lower the turnover threshold required to be a VAT-Registered Business from Rp. 4,8 billion to Rp. 600 million to increase VAT-Registered Businesses numbers which will also increase VAT revenue. The number of VAT-Registered Businesses will be significantly increased, which will push Directorate General of Taxes to determine the correct audit priority because it is impossible to audit all taxpayers. This study aims to form a prediction model for formal compliance of VAT-Registered Businesses in the Sampit Tax Office towards 1270 VAT-registered Businesses as of December 31, 2019, which are classified as low-risk VAT-Registered Businesses. The prediction model will be useful for determining audit priorities for certain taxpayers. This study uses a qualitative method using the RapidMiner application and decision tree technique in making prediction models for VAT-Registered Business compliance. The model made has Prediction Efficiency of 67,9%, reduction in Examination Effort by 63.67%, and Strike Rate of 85.99%. The model made is used to predict new VAT-Registered Business data which registered in 2020 and predicts 76 VAT-Registered Businesses will be compliant and 7 VAT-Registered Businesses will not be compliant

Bidding under uncertainty: Harsh Constructions

Learning outcomes 1. Probabilistic calculations of cost, and profit/loss using standard probability functions 2. Decision tree to find the expected monetary value (EMV) of different options. 3. Monte Carlo simulation for risk analysis. 4. Risk analysis in project management. Learning objectives Learners will be able to understand and apply the following: how to approach uncertainty in business decisions using probabilistic calculations of cost, and profit/loss using standard probability functions; how to address uncertainty in business decisions by looking forward and reasoning backward, using the decision tree technique and the EMV of different decisions; how to analyse the risk inherent in business decisions by incorporating probability distributions for all critical variables in the form of Monte Carlo simulation; and appreciation of strategic considerations in risk analysis as it applies to project management Case overview/synopsis The case describes the challenge facing Vilas Birari, the owner and chief executive of Harsh Constructions, a construction company headquartered in Nasik, India. Birari had to decide on the bid for a construction project in September of 2021, during the COVID-19 (COVID) pandemic. Due to successive waves of the pandemic, the state and federal governments announced lockdowns intermittently, causing uncertainty in costs related to labor, material and project completion. The dilemma before Birari was how to set a bid price that was not so low as to incur a loss and not so high as to lose the bid to competitors. The uncertainty made Birari’s decision-making complex. The case invites students to help Birari find an optimum bid price by using various quantitative techniques, such as Monte Carlo simulation and decision trees. Complexity academic level This case is intended for students of management at a master’s level, in an elective course on management science, which is often also known as decision science. This compact case can be positioned in the second half of the course, when exploring risk management using computer simulation as a tool. The case serves both as an introduction to using simulation to manage uncertainty as well a contrast with simpler methods that are covered earlier in the course. Supplementary material Teaching notes are available for educators only. Subject code CSS 7: Management Science.