Search results for: algorithms decision tree

Authors: Sıdıka Kaya, Gülay Sain Güven, Seda Karsavuran, Onur Toka

Abstract:

This study is part of an ongoing research project supported by the Scientific and Technological Research Council of Turkey (TUBITAK) under Project Number 114K404, and participation to this conference was supported by Hacettepe University Scientific Research Coordination Unit under Project Number 10243. Evaluation of hospital readmissions is gaining importance in terms of quality and cost, and is becoming the target of national policies. In Turkey, the topic of hospital readmission is relatively new on agenda and very few studies have been conducted on this topic. The aim of this study was to determine 30-day readmission rates and risk factors for readmission. Whether readmission was planned, related to the prior admission and avoidable or not was also assessed. The study was designed as a ‘prospective cohort study.’ 472 patients hospitalized in internal medicine departments of a university hospital in Turkey between February 1, 2015 and April 30, 2015 were followed up. Analyses were conducted using IBM SPSS Statistics version 22.0 and SPSS Modeler 16.0. Average age of the patients was 56 and 56% of the patients were female. Among these patients 95 were readmitted. Overall readmission rate was calculated as 20% (95/472). However, only 31 readmissions were unplanned. Unplanned readmission rate was 6.5% (31/472). Out of 31 unplanned readmission, 24 was related to the prior admission. Only 6 related readmission was avoidable. To determine risk factors for readmission we constructed Chi-square automatic interaction detector (CHAID) decision tree algorithm. CHAID decision trees are nonparametric procedures that make no assumptions of the underlying data. This algorithm determines how independent variables best combine to predict a binary outcome based on ‘if-then’ logic by portioning each independent variable into mutually exclusive subsets based on homogeneity of the data. Independent variables we included in the analysis were: clinic of the department, occupied beds/total number of beds in the clinic at the time of discharge, age, gender, marital status, educational level, distance to residence (km), number of people living with the patient, any person to help his/her care at home after discharge (yes/no), regular source (physician) of care (yes/no), day of discharge, length of stay, ICU utilization (yes/no), total comorbidity score, means for each 3 dimensions of Readiness for Hospital Discharge Scale (patient’s personal status, patient’s knowledge, and patient’s coping ability) and number of daycare admissions within 30 days of discharge. In the analysis, we included all 95 readmitted patients (46.12%), but only 111 (53.88%) non-readmitted patients, although we had 377 non-readmitted patients, to balance data. The risk factors for readmission were found as total comorbidity score, gender, patient’s coping ability, and patient’s knowledge. The strongest identifying factor for readmission was comorbidity score. If patients’ comorbidity score was higher than 1, the risk for readmission increased. The results of this study needs to be validated by other data–sets with more patients. However, we believe that this study will guide further studies of readmission and CHAID is a useful tool for identifying risk factors for readmission.

Keywords: decision tree, hospital, internal medicine, readmission

Procedia PDF Downloads 260

Authors: Yeliz Karaca, Rana Karabudak

Abstract:

Multifractal Denoising techniques are used in the identification of significant attributes by removing the noise of the dataset. Magnetic resonance (MR) image technique is the most sensitive method so as to identify chronic disorders of the nervous system such as Multiple Sclerosis. MRI and Expanded Disability Status Scale (EDSS) data belonging to 120 individuals who have one of the subgroups of MS (Relapsing Remitting MS (RRMS), Secondary Progressive MS (SPMS), Primary Progressive MS (PPMS)) as well as 19 healthy individuals in the control group have been used in this study. The study is comprised of the following stages: (i) L2 Norm Multifractal Denoising technique, one of the multifractal technique, has been used with the application on the MS data (MRI and EDSS). In this way, the new dataset has been obtained. (ii) The new MS dataset obtained from the MS dataset and L2 Multifractal Denoising technique has been applied to the K-Means and Fuzzy C Means clustering algorithms which are among the unsupervised methods. Thus, the clustering performances have been compared. (iii) In the identification of significant attributes in the MS dataset through the Multifractal denoising (L2 Norm) technique using K-Means and FCM algorithms on the MS subgroups and control group of healthy individuals, excellent performance outcome has been yielded. According to the clustering results based on the MS subgroups obtained in the study, successful clustering results have been obtained in the K-Means and FCM algorithms by applying the L2 norm of multifractal denoising technique for the MS dataset. Clustering performance has been more successful with the MS Dataset (L2_Norm MS Data Set) K-Means and FCM in which significant attributes are obtained by applying L2 Norm Denoising technique.

Keywords: clinical decision support, clustering algorithms, multiple sclerosis, multifractal techniques

Procedia PDF Downloads 174

Authors: Ahmed Ouammi

Abstract:

This paper presents an integrated decision framework to support decision makers in the selection and optimal allocation of wind power plants in the electric grid. The developed approach intends to maximize the benefice related to the project investment during the planning period. The proposed decision model considers the main cost components, meteorological data, environmental impacts, operation and regulation constraints, and territorial information. The decision framework is expressed as a stochastic constrained optimization problem with the aim to identify the suitable locations and related optimal wind turbine technology considering the operational constraints and maximizing the benefice. The developed decision support system is applied to a case study to demonstrate and validate its performance.

Keywords: decision support systems, electric power grid, optimization, wind energy

Procedia PDF Downloads 156

Authors: Hitesh Tahbildar

Abstract:

The cost of test data generation for a program is computationally very high. In general case, no algorithm to generate test data for all types of algorithms has been found. The cost of generating test data for different types of algorithm is different. Till date, people are emphasizing the need to generate test data for different types of programming constructs rather than different types of algorithms. The test data generation methods have been implemented to find heuristics for different types of algorithms. Some algorithms that includes divide and conquer, backtracking, greedy approach, dynamic programming to find the minimum cost of test data generation have been tested. Our experimental results say that some of these types of algorithm can be used as a necessary condition for selecting heuristics and programming constructs are sufficient condition for selecting our heuristics. Finally we recommend the different heuristics for test data generation to be selected for different types of algorithms.

Keywords: ongest path, saturation point, lmax, kL, kS

Procedia PDF Downloads 409

Authors: Shokoufeh Abrisham, Seyed Mahmoud Hossieni, Elham Pishbin

Abstract:

In this paper, a hybrid method based on the fault tree analysis (FTA) and Bayesian networks (BNs) are employed to evaluate the team performance quality of advanced cardiac life support (ACLS) procedures in emergency department. According to American Heart Association (AHA) guidelines, a category relying on staff action leading to clinical incidents and also some discussions with emergency medicine experts, a fault tree model for ACLS procedure is obtained based on the human performance. The obtained FTA model is converted into BNs, and some different scenarios are defined to demonstrate the efficiency and flexibility of the presented model of BNs. Also, a sensitivity analysis is conducted to indicate the effects of team leader presence and uncertainty knowledge of experts on the quality of ACLS. The proposed model based on BNs shows that how the results of risk analysis can be closed to reality comparing to the obtained results based on only FTA in medical procedures.

Keywords: advanced cardiac life support, fault tree analysis, Bayesian belief networks, numan performance, healthcare systems

Procedia PDF Downloads 149

Authors: Yitao Lei, Xingxiang Zhai, Burra Venkata Durga Kumar

Abstract:

As the quantity and complexity of computing in large-scale software systems increase, distributed system computing becomes increasingly important. The distributed system realizes high-performance computing by collaboration between different computing resources. If there are no efficient resource scheduling resources, the abuse of distributed computing may cause resource waste and high costs. However, resource scheduling is usually an NP-hard problem, so we cannot find a general solution. However, some optimization algorithms exist like genetic algorithm, ant colony optimization, etc. The large scale of distributed systems makes this traditional optimization algorithm challenging to work with. Heuristic and machine learning algorithms are usually applied in this situation to ease the computing load. As a result, we do a review of traditional resource scheduling optimization algorithms and try to introduce a deep reinforcement learning method that utilizes the perceptual ability of neural networks and the decision-making ability of reinforcement learning. Using the machine learning method, we try to find important factors that influence the performance of distributed system computing and help the distributed system do an efficient computing resource scheduling. This paper surveys the application of deep reinforcement learning on distributed system computing resource scheduling proposes a deep reinforcement learning method that uses a recurrent neural network to optimize the resource scheduling, and proposes the challenges and improvement directions for DRL-based resource scheduling algorithms.

Keywords: resource scheduling, deep reinforcement learning, distributed system, artificial intelligence

Procedia PDF Downloads 116

Authors: Harun Aydilek, Asiye Aydilek, Ali Allahverdi

Abstract:

Our objective is to minimize the total tardiness in an m-machine two-stage assembly flowshop scheduling problem. The objective is an important performance measure because of the fact that the fulfillment of due dates of customers has to be taken into account while making scheduling decisions. In the literature, the problem is considered with zero setup times which may not be realistic and appropriate for some scheduling environments. Considering separate setup times from processing times increases machine utilization by decreasing the idle time and reduces total tardiness. We propose two new algorithms and adapt four existing algorithms in the literature which are different versions of simulated annealing and genetic algorithms. Moreover, a dominance relation is developed based on the mathematical formulation of the problem. The developed dominance relation is incorporated in our proposed algorithms. Computational experiments are conducted to investigate the performance of the newly proposed algorithms. We find that one of the proposed algorithms performs significantly better than the others, i.e., the error of the best algorithm is less than those of the other algorithms by minimum 50%. The newly proposed algorithm is also efficient for the case of zero setup times and performs better than the best existing algorithm in the literature.

Keywords: algorithm, assembly flowshop, scheduling, simulation, total tardiness

Procedia PDF Downloads 334

Authors: Begum Koru, Isik Aybay, Demet Celik Ulusoy

Abstract:

The discipline of law is quite complex and has its own terminology. Apart from written legal rules, there is also living law, which refers to legal practice. Basic legal rules aim at the happiness of individuals in social life and have different characteristics in different branches such as public or private law. On the other hand, law is a national phenomenon. The law of one nation and the legal system applied on the territory of another nation may be completely different. People who are experts in a particular field of law in one country may have insufficient expertise in the law of another country. Today, in addition to the local nature of law, international and even supranational law rules are applied in order to protect basic human values and ensure the protection of human rights around the world. Systems that offer algorithmic solutions to legal problems using artificial intelligence (AI) tools will perhaps serve to produce very meaningful results in terms of human rights. However, algorithms to be used should not be developed by only computer experts, but also need the contribution of people who are familiar with law, values, judicial decisions, and even the social and political culture of the society to which it will provide solutions. Otherwise, even if the algorithm works perfectly, it may not be compatible with the values of the society in which it is applied. The latest developments involving the use of AI techniques in legal systems indicate that artificial law will emerge as a new field in the discipline of law. More AI systems are already being applied in the field of law, with examples such as predicting judicial decisions, text summarization, decision support systems, and classification of documents. Algorithms for legal systems employing AI tools, especially in the field of prediction of judicial decisions and decision support systems, have the capacity to create automatic decisions instead of judges. When the judge is removed from this equation, artificial intelligence-made law created by an intelligent algorithm on its own emerges, whether the domain is national or international law. In this work, the aim is to make a general analysis of this new topic. Such an analysis needs both a literature survey and a perspective from computer experts' and lawyers' point of view. In some societies, the use of prediction or decision support systems may be useful to integrate international human rights safeguards. In this case, artificial law can serve to produce more comprehensive and human rights-protective results than written or living law. In non-democratic countries, it may even be thought that direct decisions and artificial intelligence-made law would be more protective instead of a decision "support" system. Since the values of law are directed towards "human happiness or well-being", it requires that the AI algorithms should always be capable of serving this purpose and based on the rule of law, the principle of justice and equality, and the protection of human rights.

Keywords: AI and law, artificial law, protection of human rights, AI tools for legal systems

Procedia PDF Downloads 78

Authors: Pathinathan Theresanathan, Ajay Minj

Abstract:

Ignatian Discernment Process (IDP) is an intense decision-making tool to decide on life-issues. Decisions are influenced by various factors outside of the decision maker and inclination within. This paper develops IDP in the context of Fuzzy Multi-criteria Decision Making (FMCDM) process. Extended VIKOR method is a decision-making method which encompasses even conflict situations and accommodates weightage to various issues. Various aspects of IDP, namely three ways of decision making and tactics of inner desires, are observed, analyzed and articulated within the frame work of fuzzy rules. The decision-making situations are broadly categorized into two types. The issues outside of the decision maker influence the person. The inner feeling also plays vital role in coming to a conclusion. IDP integrates both the categories using Extended VIKOR method. Case studies are carried out and analyzed with FMCDM process. Finally, IDP is verified with an illustrative case study and results are interpreted. A confused person who could not come to a conclusion is able to take decision on a concrete way of life through IDP. The proposed IDP model recommends an integrated and committed approach to value-based decision making.

Keywords: AHP, FMCDM, IDP, ignatian discernment, MCDM, VIKOR

Procedia PDF Downloads 263

Authors: Mariam Shah

Abstract:

This paper will examine the potential influence and role of unconscious cognition on judicial decision making. The theoretical underpinnings of this paper rest on phenomenological theory grounded predominantly in Schutzian phenomenology. Aspects of Husserlian and Gadamerian phenomenology will be included within the phenomenological framework put forward in this paper, in an attempt to provide a more complete and thorough account of how unconscious cognition can influence judicial decision making. This paper has far reaching implications, as the framework provides a foundation for unconscious cognitive factors which can work to influence decision making more generally.

Keywords: decision making, Gadamer, Gadamerian, Husserl, Husserlian, judicial decision making, phenomenology, Schutz, Schutzian

Procedia PDF Downloads 415

Authors: Valeria Bondarenko

Abstract:

We proposed algorithms for: estimation of parameters fBm (volatility and Hurst exponent) and for the approximation of random time series by functional of fBm. We proved the consistency of the estimators, which constitute the above algorithms, and proved the optimal forecast of approximated time series. The adequacy of estimation algorithms, approximation, and forecasting is proved by numerical experiment. During the process of creating software, the system has been created, which is displayed by the hierarchical structure. The comparative analysis of proposed algorithms with the other methods gives evidence of the advantage of approximation method. The results can be used to develop methods for the analysis and modeling of time series describing the economic, physical, biological and other processes.

Keywords: mathematical model, random process, Wiener process, fractional Brownian motion

Procedia PDF Downloads 359

Authors: Hanieh Tarbiat Khosrowshahi, Mojtaba Shakeri

Abstract:

Wireless Sensor Networks (WSNs) consist of a set of sensor nodes with limited capability. WSNs may suffer from multiple node failures when they are exposed to harsh environments such as military zones or disaster locations and lose connectivity by getting partitioned into disjoint segments. Relay nodes (RNs) are alternatively introduced to restore connectivity. They cost more than sensors as they benefit from mobility, more power and more transmission range, enforcing a minimum number of them to be used. This paper addresses the problem of RN placement in a multiple disjoint network by developing a genetic algorithm (GA). The problem is reintroduced as the Steiner tree problem (which is known to be an NP-hard problem) by the aim of finding the minimum number of Steiner points where RNs are to be placed for restoring connectivity. An upper bound to the number of RNs is first computed to set up the length of initial chromosomes. The GA algorithm then iteratively reduces the number of RNs and determines their location at the same time. Experimental results indicate that the proposed GA is capable of establishing network connectivity using a reasonable number of RNs compared to the best existing work.

Keywords: connectivity restoration, genetic algorithms, multiple-node failure, relay nodes, wireless sensor networks

Procedia PDF Downloads 246

Authors: Hsin-Yi Huang, Ming-Sheng Liu, Jiun-Yan Shiau

Abstract:

Planning the order picking lists of warehouses to achieve when the costs associated with logistics on the operational performance is a significant challenge. In e-commerce era, this task is especially important productive processes are high. Nowadays, many order planning techniques employ supervised machine learning algorithms. However, the definition of which features should be processed by such algorithms is not a simple task, being crucial to the proposed technique’s success. Against this background, we consider whether unsupervised algorithms can enhance the planning of order-picking lists. A Zone2 picking approach, which is based on using clustering algorithms twice, is developed. A simplified example is given to demonstrate the merit of our approach.

Keywords: order picking, warehouse, clustering, unsupervised learning

Procedia PDF Downloads 164

Authors: Aref Aasi, Sahar Ebrahimi Bajgani, Erfan Aasi

Abstract:

Breast cancer (BC) continues to be the most frequent cancer in females and causes the highest number of cancer-related deaths in women worldwide. Inspired by recent advances in studying the relationship between different patient attributes and features and the disease, in this paper, we have tried to investigate the different classification methods for better diagnosis of BC in the early stages. In this regard, datasets from the University Hospital Centre of Coimbra were chosen, and different machine learning (ML)-based and neural network (NN) classifiers have been studied. For this purpose, we have selected favorable features among the nine provided attributes from the clinical dataset by using a random forest algorithm. This dataset consists of both healthy controls and BC patients, and it was noted that glucose, BMI, resistin, and age have the most importance, respectively. Moreover, we have analyzed these features with various ML-based classifier methods, including Decision Tree (DT), K-Nearest Neighbors (KNN), eXtreme Gradient Boosting (XGBoost), Logistic Regression (LR), Naive Bayes (NB), and Support Vector Machine (SVM) along with NN-based Multi-Layer Perceptron (MLP) classifier. The results revealed that among different techniques, the SVM and MLP classifiers have the most accuracy, with amounts of 96% and 92%, respectively. These results divulged that the adopted procedure could be used effectively for the classification of cancer cells, and also it encourages further experimental investigations with more collected data for other types of cancers.

Keywords: breast cancer, diagnosis, machine learning, biomarker classification, neural network

Procedia PDF Downloads 143

Authors: Harun Aydilek, Asiye Aydilek, Ali Allahverdi

Abstract:

The total tardiness is a widely used performance measure in the scheduling literature. This performance measure is particularly important in situations where there is a cost to complete a job beyond its due date. The cost of scheduling increases as the gap between a job's due date and its completion time increases. Such costs may also be penalty costs in contracts, loss of goodwill. This performance measure is important as the fulfillment of due dates of customers has to be taken into account while making scheduling decisions. The problem is addressed in the literature, however, it has been assumed zero setup times. Even though this assumption may be valid for some environments, it is not valid for some other scheduling environments. When setup times are treated as separate from processing times, it is possible to increase machine utilization and to reduce total tardiness. Therefore, non-zero setup times need to be considered as separate. A dominance relation is developed and several algorithms are proposed. The developed dominance relation is utilized in the proposed algorithms. Extensive computational experiments are conducted for the evaluation of the algorithms. The experiments indicated that the developed algorithms perform much better than the existing algorithms in the literature. More specifically, one of the newly proposed algorithms reduces the error of the best existing algorithm in the literature by 40 percent.

Keywords: algorithm, assembly flowshop, dominance relation, total tardiness

Procedia PDF Downloads 358

Authors: Dewi Juliah Ratnaningsih, Imas Sukaesih Sitanggang

Abstract:

Classification is one of data mining techniques that aims to discover a model from training data that distinguishes records into the appropriate category or class. Data mining classification methods can be applied in education, for example, to determine the classification of non-active students in Indonesia Open University. This paper presents a comparison of three methods of classification: Naïve Bayes, Bagging, and C.45. The criteria used to evaluate the performance of three methods of classification are stratified cross-validation, confusion matrix, the value of the area under the ROC Curve (AUC), Recall, Precision, and F-measure. The data used for this paper are from the non-active Indonesia Open University students in registration period of 2004.1 to 2012.2. Target analysis requires that non-active students were divided into 3 groups: C1, C2, and C3. Data analyzed are as many as 4173 students. Results of the study show: (1) Bagging method gave a high degree of classification accuracy than Naïve Bayes and C.45, (2) the Bagging classification accuracy rate is 82.99 %, while the Naïve Bayes and C.45 are 80.04 % and 82.74 % respectively, (3) the result of Bagging classification tree method has a large number of nodes, so it is quite difficult in decision making, (4) classification of non-active Indonesia Open University student characteristics uses algorithms C.45, (5) based on the algorithm C.45, there are 5 interesting rules which can describe the characteristics of non-active Indonesia Open University students.

Keywords: comparative analysis, data mining, clasiffication, Bagging, Naïve Bayes, C.45, non-active students, Indonesia Open University

Procedia PDF Downloads 318

Authors: I. Teotónio, C.O. Cruz, C.M. Silva, M. Manso

Abstract:

Diverse stakeholders show different concerns when choosing green roof systems. Also, green roof solutions vary in their cost and performance. Therefore, decision-makers continually face the difficult task of balancing benefits against green roofs costs. Decision analysis methods, as multicriteria analysis, can be used when the decision‑making process includes different perspectives, multiple objectives, and uncertainty. The present study adopts a multicriteria decision model to evaluate the installation of green roofs in buildings, determining the solution with the best trade-off between costs and benefits in agreement with the preferences of the users/investors. This methodology was applied to a real decision problem, assessing the preferences between different green roof systems in an existing building in Lisbon. This approach supports the decision-making process on green roofs and enables robust and informed decisions on urban planning while optimizing buildings retrofitting.

Keywords: decision making, green roofs, investors preferences, multicriteria analysis, sustainable development

Procedia PDF Downloads 187

Authors: Rimac Smiljanic Ana, Pepur Sandra, Bulog Ivana

Abstract:

Financial decision-making in the household is not simple, and it demands that the decision-maker has proper knowledge and skills. Usually, high uncertainty, risk, and stress surround household financial decision-making since it is extremely important and critical for household wealth accumulation and for the well-being of all household members. Generally, skilful people tend to have higher confidence in certain tasks they perform, and they achieve better results. Therefore, in the household context, the possession of certain skills by the ones who make financial decisions for the household is of particular importance. This paper addresses financial literacy as an important skill for household decision-making. Apart from financial literacy, the paper also considers other factors, such as employment, education, and age, as significant for household financial decision-making. The analysis is based on quantitative individual-level survey data. The data collection was conducted during January and February 2021 in Croatia through an online survey. To reach a wide variety of participants, the snowball sampling method was used. The result revealed interesting and somewhat puzzling results. Our results point to the importance of financial literacy skills for household decision-making.

Keywords: skill, financial literacy, decision-making, household financijal decision making

Procedia PDF Downloads 102

Authors: Doru Anastasiu Popescu, Dan Rădulescu

Abstract:

In this paper, we determine the similarity of two HTML web applications. We are going to use a genetic algorithm in order to determine the most significant web pages of each application (we are not going to use every web page of a site). Using these significant web pages, we will find the similarity value between the two applications. The algorithm is going to be efficient because we are going to use a reduced number of web pages for comparisons but it will return an approximate value of the similarity. The binary trees are used to keep the tags from the significant pages. The algorithm was implemented in Java language.

Keywords: Tag, HTML, web page, genetic algorithm, similarity value, binary tree

Procedia PDF Downloads 357

Authors: H. W. Meerveld, R. H. A. Lindelauf

Abstract:

In contemporary warfare, data science is crucial for the military in achieving information superiority. Yet, to the authors’ knowledge, no extensive literature survey on data science in military decision-making has been conducted so far. In this study, 156 peer-reviewed articles were analysed through an integrative, semi-systematic literature review to gain an overview of the topic. The study examined to what extent literature is focussed on the opportunities or risks of data science in military decision-making, differentiated per level of war (i.e. strategic, operational, and tactical level). A relatively large focus on the risks of data science was observed in social science literature, implying that political and military policymakers are disproportionally influenced by a pessimistic view on the application of data science in the military domain. The perceived risks of data science are, however, hardly addressed in formal science literature. This means that the concerns on the military application of data science are not addressed to the audience that can actually develop and enhance data science models and algorithms. Cross-disciplinary research on both the opportunities and risks of military data science can address the observed research gaps. Considering the levels of war, relatively low attention for the operational level compared to the other two levels was observed, suggesting a research gap with reference to military operational data science. Opportunities for military data science mostly arise at the tactical level. On the contrary, studies examining strategic issues mostly emphasise the risks of military data science. Consequently, domain-specific requirements for military strategic data science applications are hardly expressed. Lacking such applications may ultimately lead to a suboptimal strategic decision in today’s warfare.

Keywords: data science, decision-making, information superiority, literature review, military

Procedia PDF Downloads 176

Authors: Jae-Hyun Ro, Jong-Kwang Kim, Chang-Hee Kang, Hyoung-Kyu Song

Abstract:

In multiple input multiple output-orthogonal frequency division multiplexing (MIMO-OFDM) systems, QR decomposition-M algorithm (QRD-M) has suboptimal error performance. However, the QRD-M has still high complexity due to many calculations at each layer in tree structure. To reduce the complexity of the QRD-M, proposed QRD-M modifies existing tree structure by eliminating unnecessary candidates at almost whole layers. The method of the elimination is discarding the candidates which have accumulated squared Euclidean distances larger than calculated threshold. The simulation results show that the proposed QRD-M has same bit error rate (BER) performance with lower complexity than the conventional QRD-M.

Keywords: complexity, MIMO-OFDM, QRD-M, squared Euclidean distance

Procedia PDF Downloads 337

Authors: Haya Salah, Srinivas Sharan

Abstract:

Healthcare facilities use appointment systems to schedule their appointments and to manage access to their medical services. With the growing demand for outpatient care, it is now imperative to manage physician's time effectively. However, high variation in consultation duration affects the clinical scheduler's ability to estimate the appointment duration and allocate provider time appropriately. Underestimating consultation times can lead to physician's burnout, misdiagnosis, and patient dissatisfaction. On the other hand, appointment durations that are longer than required lead to doctor idle time and fewer patient visits. Therefore, a good estimation of consultation duration has the potential to improve timely access to care, resource utilization, quality of care, and patient satisfaction. Although the literature on factors influencing consultation length abound, little work has done to predict it using based data-driven approaches. Therefore, this study aims to predict consultation duration using supervised machine learning algorithms (ML), which predicts an outcome variable (e.g., consultation) based on potential features that influence the outcome. In particular, ML algorithms learn from a historical dataset without explicitly being programmed and uncover the relationship between the features and outcome variable. A subset of the data used in this study has been obtained from the electronic medical records (EMR) of four different outpatient clinics located in central Pennsylvania, USA. Also, publicly available information on doctor's characteristics such as gender and experience has been extracted from online sources. This research develops three popular ML algorithms (deep learning, random forest, gradient boosting machine) to predict the treatment time required for a patient and conducts a comparative analysis of these algorithms with respect to predictive performance. The findings of this study indicate that ML algorithms have the potential to predict the provider service time with superior accuracy. While the current approach of experience-based appointment duration estimation adopted by the clinic resulted in a mean absolute percentage error of 25.8%, the Deep learning algorithm developed in this study yielded the best performance with a MAPE of 12.24%, followed by gradient boosting machine (13.26%) and random forests (14.71%). Besides, this research also identified the critical variables affecting consultation duration to be patient type (new vs. established), doctor's experience, zip code, appointment day, and doctor's specialty. Moreover, several practical insights are obtained based on the comparative analysis of the ML algorithms. The machine learning approach presented in this study can serve as a decision support tool and could be integrated into the appointment system for effectively managing patient scheduling.

Keywords: clinical decision support system, machine learning algorithms, patient scheduling, prediction models, provider service time

Procedia PDF Downloads 123

Authors: Ehsan Mehryaar

Abstract:

The rate of penetration is (RoP) one of the vital factors in the cost and time of tunnel boring projects; therefore, predicting it can lead to a substantial increase in the efficiency of the project. RoP is heavily dependent geological properties of the project site and TBM properties. In this study, 151-point data from Queen’s water tunnel is collected, which includes unconfined compression strength, peak slope index, angle with weak planes, and distance between planes of weaknesses. Since the size of the data is small, it was observed that it is imbalanced. To solve that problem synthetic minority oversampling technique is utilized. The model based on the model tree is proposed, where each leaf consists of a support vector machine model. Proposed model performance is then compared to existing empirical equations in the literature.

Keywords: Model tree, SMOTE, rate of penetration, TBM(tunnel boring machine), SVM

Procedia PDF Downloads 178

Authors: Olatunde Sunday Eludoyin, Charles Obiechina Olisa

Abstract:

The study examined the spatial interactions between earthworm abundance (EA) and tree growth characteristics in ecological belts of Western Niger Delta, Nigeria. Eight 20m x 20m quadrat were delimited in the natural vegetation in each of the rainforest (RF), mangrove (M), fresh water swamp (FWS), and guinea savanna (GS) ecological belts to gather data about the tree species (TS) characteristics which included individual number of tree species (IN), diversity (Di), density (De) and richness (Ri). Three quadrats of 1m x 1m were delineated in each of the 20m x 20m quadrats to collect earthworm species the topsoil (0-15cm), and subsoil (15-30cm) and were taken to laboratory for further analysis. Descriptive statistics and inferential statistics were used for data analysis. Findings showed that a total of 19 earthworm species was found, with 58.5% individual species recorded in the topsoil and 41.5% recorded in the subsoil. The total population ofEudriliuseugeniae was predominantly highest in both topsoil (38.4%) and subsoil (27.1%). The total population of individual species of earthworm was least in GS in the topsoil (11.9%) and subsoil (8.4%). A total of 40 different species of TS was recorded, of which 55.5% were recorded in FWS, while RF was significantly highest in the species diversity(0.5971). Regression analysis revealed that Ri, IN, DBH, Di, and De of trees explained 65.9% of the variability of EA in the topsoil, while 46.9 % of the variability of earthworm abundance was explained by the floristic parameters in the subsoil.Similarly, correlation statistics revealed that in the topsoil, EA is positively and significantly correlated with Ri (r=0.35; p<0.05), IN (r=0.523; p<0.05) and De (r=0.469; p<0.05) while DBH was negatively and significantly correlated with earthworm abundance (r=-0.437; p<0.05). In the subsoil, only Ri and DBH correlated significantly with EA. The study concluded that EA in the study locations was highly influenced by tree growth species especially Ri, IN, DBH, Di, and De. The study recommended that the TSabundance should be improved in the study locations to ensure the survival of earthworms for ecosystem functions.

Keywords: interactions, earthworm abundance, tree growth, ecological zones, western niger delta

Procedia PDF Downloads 103

Authors: Marinos Xagoraris, Elisavet Lazarou, Eleftherios Alissandrakis, Christos S. Pappas, Petros A. Tarantilis

Abstract:

Strawberry tree (Arbutus unedo L.) and autumn heather (Erica manipuliflora Salisb.) are important beekeeping plants of Greece. Six monofloral honeys (four strawberry tree, two autumn heather) were analyzed by means of Solid Phase Micro-Extraction (SPME, 60 min, 60 oC) followed by Gas Chromatography coupled to Mass Spectrometry (GC-MS) for the purpose of assessing the botanical origin. A Divinylbenzene/Carboxen/Polydimethylsiloxane (DVB/CAR/PDMS) fiber was employed, and benzophenone was used as internal standard. The volatile compounds with higher concentration (μg/ g of honey expressed as benzophenone) from strawberry tree honey samples, were α-isophorone (2.50-8.12); 3,4,5-trimethyl-phenol (0.20-4.62); 2-hydroxy-isophorone (0.06-0.53); 4-oxoisophorone (0.38-0.46); and β-isophorone (0.02-0.43). Regarding heather honey samples, the most abundant compounds were 1-methoxy-4-propyl-benzene (1.22-1.40); p-anisaldehyde (0.97-1.28); p-anisic acid (0.35-0.58); 2-furaldehyde (0.52-0.57); and benzaldehyde (0.41-0.56). Norisoprenoids are potent floral markers for strawberry-tree honey. β-isophorone is found exclusively in the volatile fraction of this type of honey, while also α-isophorone, 4-oxoisophorone and 2-hydroxy-isophorone could be considered as additional marker compounds. The analysis of autumn heather honey revealed that phenolic compounds are the most abundant and p-anisaldehyde; 1-methoxy-4-propyl-benzene; and p-anisic acid could serve as potent marker compounds. In conclusion, marker compounds for the determination of the botanical origin for these honeys could be identified as several norisoprenoids and phenolic components were found exclusively or in higher concentrations compared to common Greek honey varieties.

Keywords: SPME/GC-MS, volatile compounds, heather honey, strawberry tree honey

Procedia PDF Downloads 202

Authors: Raymond Xu, Cindy Jingru Wang

Abstract:

Social media has become a globally connected and influencing platform. Social media data, such as tweets, can help predict the spread of pandemics and provide individuals and healthcare providers early warnings. Public psychological reactions and opinions can be efficiently monitored by AI models on the progression of dominant topics on Twitter. However, statistics show that as the coronavirus spreads, so does an infodemic of misinformation due to pandemic-related factors such as unemployment and lockdowns. Social media algorithms are often biased toward outrage by promoting content that people have an emotional reaction to and are likely to engage with. This can influence users’ attitudes and cause confusion. Therefore, social media is a double-edged sword. Combating fake news and biased content has become one of the essential tasks. This research analyzes the variety of methods used for fake news detection covering random forest, logistic regression, support vector machines, decision tree, naive Bayes, BoW, TF-IDF, LDA, CNN, RNN, LSTM, DeepFake, and hierarchical attention network. The performance of each method is analyzed. Based on these models’ achievements and limitations, a multi-dimensional AI framework is proposed to achieve higher accuracy in infodemic detection, especially pandemic-related news. The model is trained on contextual content, images, and news metadata.

Keywords: artificial intelligence, fake news detection, infodemic detection, image recognition, sentiment analysis

Procedia PDF Downloads 265

Authors: Archana Singh, Jyoti Agarwal, Ajay Rana

Abstract:

Data Mining is an efficient technology to discover patterns in large databases. Association Rule Mining techniques are used to find the correlation between the various item sets in a database, and this co-relation between various item sets are used in decision making and pattern analysis. In recent years, the problem of finding association rules from large datasets has been proposed by many researchers. Various research papers on association rule mining (ARM) are studied and analyzed first to understand the existing algorithms. Apriori algorithm is the basic ARM algorithm, but it requires so many database scans. In DIC algorithm, less amount of database scan is needed but complex data structure lattice is used. The main focus of this paper is to propose a new optimized algorithm (Friendly Algorithm) and compare its performance with the existing algorithms A data set is used to find out frequent itemsets and association rules with the help of existing and proposed (Friendly Algorithm) and it has been observed that the proposed algorithm also finds all the frequent itemsets and essential association rules from databases as compared to existing algorithms in less amount of database scan. In the proposed algorithm, an optimized data structure is used i.e. Graph and Adjacency Matrix.

Keywords: association rules, data mining, dynamic item set counting, FP-growth, friendly algorithm, graph

Procedia PDF Downloads 425

Authors: John Morales, Eduardo Orduña

Abstract:

Currently the Principal Component Analysis (PCA) theory has been used to develop algorithms regarding to Electric Power Systems (EPS). In this context, this paper presents a practical tutorial of this technique detailed their concept, on-line and off-line mathematical foundations, which are necessary and desirables in EPS algorithms. Thus, features of their eigenvectors which are very useful to real-time process are explained, showing how it is possible to select these parameters through a direct optimization. On the other hand, in this work in order to show the application of PCA to off-line and on-line signals, an example step to step using Matlab commands is presented. Finally, a list of different approaches using PCA is presented, and some works which could be analyzed using this tutorial are presented.

Keywords: practical guide; on-line; off-line, algorithms, faults

Procedia PDF Downloads 568

Authors: Ehsan Khademi, Mahdi Jalili

Abstract:

Despite the special features of bipartite networks, they are common in many systems. Real-world bipartite networks may show community structure, similar to what one can find in one-mode networks. However, the interpretation of the community structure in bipartite networks is different as compared to one-mode networks. In this manuscript, we compare a number of available methods that are frequently used to discover community structure of bipartite networks. These networks are categorized into two broad classes. One class is the methods that, first, transfer the network into a one-mode network, and then apply community detection algorithms. The other class is the algorithms that have been developed specifically for bipartite networks. These algorithms are applied on a model network with prescribed community structure.

Keywords: community detection, bipartite networks, co-clustering, modularity, network projection, complex networks

Procedia PDF Downloads 629

Authors: Cristóbal Moënne-Loccoz, Rodrigo C. Vergara, Vladimir López, Domingo Mery, Diego Cosmelli

Abstract:

Our daily interaction with computational interfaces is plagued of situations in which we go from inexperienced users to experts through self-motivated exploration of the same task. In many of these interactions, we must learn to find our way through a sequence of decisions and actions before obtaining the desired result. For instance, when drawing cash from an ATM machine, choices are presented in a step-by-step fashion so that a specific sequence of actions must be performed in order to produce the expected outcome. But, as they become experts in the use of such interfaces, do users adopt specific search and learning strategies? Moreover, if so, can we use this information to follow the process of expertise development and, eventually, predict future actions? This would be a critical step towards building truly adaptive interfaces that can facilitate interaction at different moments of the learning curve. Furthermore, it could provide a window into potential mechanisms underlying decision-making behavior in real world scenarios. Here we tackle this question using a simple game interface that instantiates a 4-level binary decision tree (BDT) sequential decision-making task. Participants have to explore the interface and discover an underlying concept-icon mapping in order to complete the game. We develop a Hidden Markov Model (HMM)-based approach whereby a set of stereotyped, hierarchically related search behaviors act as hidden states. Using this model, we are able to track the decision-making process as participants explore, learn and develop expertise in the use of the interface. Our results show that partitioning the problem space into such stereotyped strategies is sufficient to capture a host of exploratory and learning behaviors. Moreover, using the modular architecture of stereotyped strategies as a Mixture of Experts, we are able to simultaneously ask the experts about the user's most probable future actions. We show that for those participants that learn the task, it becomes possible to predict their next decision, above chance, approximately halfway through the game. Our long-term goal is, on the basis of a better understanding of real-world decision-making processes, to inform the construction of interfaces that can establish dynamic conversations with their users in order to facilitate the development of expertise.

Keywords: behavioral modeling, expertise acquisition, hidden markov models, sequential decision-making

Procedia PDF Downloads 256