Search results for: gaussian selection operator
2641 Movie Genre Preference Prediction Using Machine Learning for Customer-Based Information
Authors: Haifeng Wang, Haili Zhang
Abstract:
Most movie recommendation systems have been developed for customers to find items of interest. This work introduces a predictive model usable by small and medium-sized enterprises (SMEs) who are in need of a data-based and analytical approach to stock proper movies for local audiences and retain more customers. We used classification models to extract features from thousands of customers’ demographic, behavioral and social information to predict their movie genre preference. In the implementation, a Gaussian kernel support vector machine (SVM) classification model and a logistic regression model were established to extract features from sample data and their test error-in-sample were compared. Comparison of error-out-sample was also made under different Vapnik–Chervonenkis (VC) dimensions in the machine learning algorithm to find and prevent overfitting. Gaussian kernel SVM prediction model can correctly predict movie genre preferences in 85% of positive cases. The accuracy of the algorithm increased to 93% with a smaller VC dimension and less overfitting. These findings advance our understanding of how to use machine learning approach to predict customers’ preferences with a small data set and design prediction tools for these enterprises.Keywords: computational social science, movie preference, machine learning, SVM
Procedia PDF Downloads 2522640 Decision Support System for Hospital Selection in Emergency Medical Services: A Discrete Event Simulation Approach
Authors: D. Tedesco, G. Feletti, P. Trucco
Abstract:
The present study aims to develop a Decision Support System (DSS) to support the operational decision of the Emergency Medical Service (EMS) regarding the assignment of medical emergency requests to Emergency Departments (ED). In the literature, this problem is also known as “hospital selection” and concerns the definition of policies for the selection of the ED to which patients who require further treatment are transported by ambulance. The employed research methodology consists of the first phase of revision of the technical-scientific literature concerning DSSs to support the EMS management and, in particular, the hospital selection decision. From the literature analysis, it emerged that current studies are mainly focused on the EMS phases related to the ambulance service and consider a process that ends when the ambulance is available after completing a request. Therefore, all the ED-related issues are excluded and considered as part of a separate process. Indeed, the most studied hospital selection policy turned out to be proximity, thus allowing to minimize the transport time and release the ambulance in the shortest possible time. The purpose of the present study consists in developing an optimization model for assigning medical emergency requests to the EDs, considering information relating to the subsequent phases of the process, such as the case-mix, the expected service throughput times, and the operational capacity of different EDs in hospitals. To this end, a Discrete Event Simulation (DES) model was created to evaluate different hospital selection policies. Therefore, the next steps of the research consisted of the development of a general simulation architecture, its implementation in the AnyLogic software and its validation on a realistic dataset. The hospital selection policy that produced the best results was the minimization of the Time To Provider (TTP), considered as the time from the beginning of the ambulance journey to the ED at the beginning of the clinical evaluation by the doctor. Finally, two approaches were further compared: a static approach, which is based on a retrospective estimate of the TTP, and a dynamic approach, which is based on a predictive estimate of the TTP determined with a constantly updated Winters model. Findings reveal that considering the minimization of TTP as a hospital selection policy raises several benefits. It allows to significantly reduce service throughput times in the ED with a minimum increase in travel time. Furthermore, an immediate view of the saturation state of the ED is produced and the case-mix present in the ED structures (i.e., the different triage codes) is considered, as different severity codes correspond to different service throughput times. Besides, the use of a predictive approach is certainly more reliable in terms of TTP estimation than a retrospective approach but entails a more difficult application. These considerations can support decision-makers in introducing different hospital selection policies to enhance EMSs performance.Keywords: discrete event simulation, emergency medical services, forecast model, hospital selection
Procedia PDF Downloads 842639 Node Pair Selection Scheme in Relay-Aided Communication Based on Stable Marriage Problem
Authors: Tetsuki Taniguchi, Yoshio Karasawa
Abstract:
This paper describes a node pair selection scheme in relay-aided multiple source multiple destination communication system based on stable marriage problem. A general case is assumed in which all of source, relay and destination nodes are equipped with multiantenna and carry out multistream transmission. Based on several metrics introduced from inter-node channel condition, the preference order is determined about all source-relay and relay-destination relations, and then the node pairs are determined using Gale-Shapley algorithm. The computer simulations show that the effectiveness of node pair selection is larger in multihop communication. Some additional aspects which are different from relay-less case are also investigated.Keywords: relay, multiple input multiple output (MIMO), multiuser, amplify and forward, stable marriage problem, Gale-Shapley algorithm
Procedia PDF Downloads 3932638 The Potential Effect of Sexual Selection on the Distal Genitalia Variability of the Simultaneously Hermaphroditic Land Snail Helix aperta in Bejaia/Kabylia/Algeria
Authors: Benbellil-Tafoughalt Saida, Tababouchet Meriem
Abstract:
Sexual selection is the most supported explanation for genital extravagance occurring in animals. In promiscuous species, population density, as well as climate conditions, may act on the sperm competition intensity, one of the most important mechanism of post-copulatory sexual selection. The present study is empirical testing of sexual selection's potential role on genitalia variation in the simultanuously hermaphroditic land snail Helixaperta (Pulmonata, Stylommatophora). The purpose was to detect the patterns as well as the origin of the distal genitalia variability and especially to test the potential effect of sexual selection. The study was performed on four populations, H. aperta, different in habitat humidity regimes and presenting variable densities, which were mostly low. The organs of interest were those involved in spermatophore production, reception, and manipulation. We examined whether the evolution of those organs is connected to sperm competition intensity which is traduced by both population density and microclimate humidity. We also tested the hypothesis that those organs evolve in response to shell size. The results revealed remarkable differences in both snails’ size and organs lengths between populations. In most cases, the length of genitalia correlated positively to snails’ body size. Interestingly, snails from the more humid microclimate presented the highest mean weight and shell dimensions comparing to those from the less humid microclimate. However, we failed to establish any relation between snail densities and any of the measured genitalia traits.Keywords: fertilization pouch, helix aperta, land snails, reproduction, sperm storage, spermatheca
Procedia PDF Downloads 1782637 Globally Attractive Mild Solutions for Non-Local in Time Subdiffusion Equations of Neutral Type
Authors: Jorge Gonzalez Camus, Carlos Lizama
Abstract:
In this work is proved the existence of at least one globally attractive mild solution to the Cauchy problem, for fractional evolution equation of neutral type, involving the fractional derivate in Caputo sense. An almost sectorial operator on a Banach space X and a kernel belonging to a large class appears in the equation, which covers many relevant cases from physics applications, in particular, the important case of time - fractional evolution equations of neutral type. The main tool used in this work was the Hausdorff measure of noncompactness and fixed point theorems, specifically Darbo-type. Initially, the equation is a Cauchy problem, involving a fractional derivate in Caputo sense. Then, is formulated the equivalent integral version, and defining a convenient functional, using the analytic integral resolvent operator, and verifying the hypothesis of the fixed point theorem of Darbo type, give us the existence of mild solution for the initial problem. Furthermore, each mild solution is globally attractive, a property that is desired in asymptotic behavior for that solution.Keywords: attractive mild solutions, integral Volterra equations, neutral type equations, non-local in time equations
Procedia PDF Downloads 1502636 Supervisory Board in the Governance of Cooperatives: Disclosing Power Elements in the Selection of Directors
Authors: Kari Huhtala, Iiro Jussila
Abstract:
The supervisory board is assumed to use power in the governance of a firm, but the actual use of power has been scantly investigated. The research question of the paper is “How does the supervisory board use power in the selection of the board of directors”. The data stem from 11 large Finnish agricultural cooperatives. The research approach was qualitative including semi-structured interviews of the board of directors and supervisory board chairpersons. The results were analyzed and interpreted against theories of social power. As a result, the use of power is approached from two perspectives: (1) formal position-based authority and (2) informal power. Central elements of power were the mandate of the supervisory board, the role of the supervisory board, the supervisory board chair, the nomination committee, collaboration between the supervisory board and the board of directors, the role of regions and the role of the board of directors. The study contributes to the academic discussion on corporate governance in cooperatives and on the supervisory board in the context of the two-tier model. Additional research of the model in other countries and of other types of cooperatives would further academic understanding of supervisory boards.Keywords: board, co-operative, supervisory board, selection, director
Procedia PDF Downloads 1642635 Analysis of Nonlinear Dynamic Systems Excited by Combined Colored and White Noise Excitations
Authors: Siu-Siu Guo, Qingxuan Shi
Abstract:
In this paper, single-degree-of-freedom (SDOF) systems to white noise and colored noise excitations are investigated. By expressing colored noise excitation as a second-order filtered white noise process and introducing colored noise as an additional state variable, the equation of motion for SDOF system under colored noise is then transferred artificially to multi-degree-of-freedom (MDOF) system under white noise excitations. As a consequence, corresponding Fokker-Planck-Kolmogorov (FPK) equation governing the joint probabilistic density function (PDF) of state variables increases to 4-dimension (4-D). Solution procedure and computer programme become much more sophisticated. The exponential-polynomial closure (EPC) method, widely applied for cases of SDOF systems under white noise excitations, is developed and improved for cases of systems under colored noise excitations and for solving the complex 4-D FPK equation. On the other hand, Monte Carlo simulation (MCS) method is performed to test the approximate EPC solutions. Two examples associated with Gaussian and non-Gaussian colored noise excitations are considered. Corresponding band-limited power spectral densities (PSDs) for colored noise excitations are separately given. Numerical studies show that the developed EPC method provides relatively accurate estimates of the stationary probabilistic solutions. Moreover, statistical parameter of mean-up crossing rate (MCR) is taken into account, which is important for reliability and failure analysis.Keywords: filtered noise, narrow-banded noise, nonlinear dynamic, random vibration
Procedia PDF Downloads 2232634 Bayesian Network and Feature Selection for Rank Deficient Inverse Problem
Authors: Kyugneun Lee, Ikjin Lee
Abstract:
Parameter estimation with inverse problem often suffers from unfavorable conditions in the real world. Useless data and many input parameters make the problem complicated or insoluble. Data refinement and reformulation of the problem can solve that kind of difficulties. In this research, a method to solve the rank deficient inverse problem is suggested. A multi-physics system which has rank deficiency caused by response correlation is treated. Impeditive information is removed and the problem is reformulated to sequential estimations using Bayesian network (BN) and subset groups. At first, subset grouping of the responses is performed. Feature selection with singular value decomposition (SVD) is used for the grouping. Next, BN inference is used for sequential conditional estimation according to the group hierarchy. Directed acyclic graph (DAG) structure is organized to maximize the estimation ability. Variance ratio of response to noise is used to pairing the estimable parameters by each response.Keywords: Bayesian network, feature selection, rank deficiency, statistical inverse analysis
Procedia PDF Downloads 3082633 Welding Process Selection for Storage Tank by Integrated Data Envelopment Analysis and Fuzzy Credibility Constrained Programming Approach
Authors: Rahmad Wisnu Wardana, Eakachai Warinsiriruk, Sutep Joy-A-Ka
Abstract:
Selecting the most suitable welding process usually depends on experiences or common application in similar companies. However, this approach generally ignores many criteria that can be affecting the suitable welding process selection. Therefore, knowledge automation through knowledge-based systems will significantly improve the decision-making process. The aims of this research propose integrated data envelopment analysis (DEA) and fuzzy credibility constrained programming approach for identifying the best welding process for stainless steel storage tank in the food and beverage industry. The proposed approach uses fuzzy concept and credibility measure to deal with uncertain data from experts' judgment. Furthermore, 12 parameters are used to determine the most appropriate welding processes among six competitive welding processes.Keywords: welding process selection, data envelopment analysis, fuzzy credibility constrained programming, storage tank
Procedia PDF Downloads 1612632 On-Line Data-Driven Multivariate Statistical Prediction Approach to Production Monitoring
Authors: Hyun-Woo Cho
Abstract:
Detection of incipient abnormal events in production processes is important to improve safety and reliability of manufacturing operations and reduce losses caused by failures. The construction of calibration models for predicting faulty conditions is quite essential in making decisions on when to perform preventive maintenance. This paper presents a multivariate calibration monitoring approach based on the statistical analysis of process measurement data. The calibration model is used to predict faulty conditions from historical reference data. This approach utilizes variable selection techniques, and the predictive performance of several prediction methods are evaluated using real data. The results shows that the calibration model based on supervised probabilistic model yielded best performance in this work. By adopting a proper variable selection scheme in calibration models, the prediction performance can be improved by excluding non-informative variables from their model building steps.Keywords: calibration model, monitoring, quality improvement, feature selection
Procedia PDF Downloads 3492631 Artificial Nesting in Birds at UVAS-Ravi Campus: Punjab-Pakistan
Authors: Fatima Chaudhary, Rehan Ul Haq
Abstract:
Spatial and anthropogenic factors influencing nest-site selection in birds need to be identified for effective conservative practices. Environmental attributes such as food availability, predator density, previous reproductive success, etc., provide information regarding the site's quality. An artificial nest box experiment was carried out to evaluate the effect of various factors on nest-site selection, as it is hard to assess the natural cavities. The experiment was conducted whereby half of the boxes were filled with old nest material. Artificial nest boxes created with different materials and different sizes and colors were installed at different heights. A total of 14 out of 60 nest boxes were occupied and four of them faced predation. The birds explored a total of 32 out of 60 nests, whereas anthropogenic factors destroyed 25 out of 60 nests. Birds chose empty nest boxes at higher rates however, there was no obvious avoidance of sites having high ectoparasites load due to old nest material. It is also possible that the preference towards the artificial nest boxes may differ from year to year because of several climatic factors and the age of old nest material affecting the parasite's survival. These variables may fluctuate from one season to another. Considering these factors, nest-site selection experiments concerning the effectiveness of artificial nest boxes should be carried out over several successive seasons. This topic may stimulate further studies, which could lead to a fully understanding the birds' evolutionary ecology. Precise information on these factors influencing nest-site selection can be essential from an economic point of view as well.Keywords: artificial nesting, nest box, old nest material, birds
Procedia PDF Downloads 832630 Hybrid Temporal Correlation Based on Gaussian Mixture Model Framework for View Synthesis
Authors: Deng Zengming, Wang Mingjiang
Abstract:
As 3D video is explored as a hot research topic in the last few decades, free-viewpoint TV (FTV) is no doubt a promising field for its better visual experience and incomparable interactivity. View synthesis is obviously a crucial technology for FTV; it enables to render images in unlimited numbers of virtual viewpoints with the information from limited numbers of reference view. In this paper, a novel hybrid synthesis framework is proposed and blending priority is explored. In contrast to the commonly used View Synthesis Reference Software (VSRS), the presented synthesis process is driven in consideration of the temporal correlation of image sequences. The temporal correlations will be exploited to produce fine synthesis results even near the foreground boundaries. As for the blending priority, this scheme proposed that one of the two reference views is selected to be the main reference view based on the distance between the reference views and virtual view, another view is chosen as the auxiliary viewpoint, just assist to fill the hole pixel with the help of background information. Significant improvement of the proposed approach over the state-of –the-art pixel-based virtual view synthesis method is presented, the results of the experiments show that subjective gains can be observed, and objective PSNR average gains range from 0.5 to 1.3 dB, while SSIM average gains range from 0.01 to 0.05.Keywords: fusion method, Gaussian mixture model, hybrid framework, view synthesis
Procedia PDF Downloads 2442629 Proposal of a Model Supporting Decision-Making Based on Multi-Objective Optimization Analysis on Information Security Risk Treatment
Authors: Ritsuko Kawasaki (Aiba), Takeshi Hiromatsu
Abstract:
Management is required to understand all information security risks within an organization, and to make decisions on which information security risks should be treated in what level by allocating how much amount of cost. However, such decision-making is not usually easy, because various measures for risk treatment must be selected with the suitable application levels. In addition, some measures may have objectives conflicting with each other. It also makes the selection difficult. Moreover, risks generally have trends and it also should be considered in risk treatment. Therefore, this paper provides the extension of the model proposed in the previous study. The original model supports the selection of measures by applying a combination of weighted average method and goal programming method for multi-objective analysis to find an optimal solution. The extended model includes the notion of weights to the risks, and the larger weight means the priority of the risk.Keywords: information security risk treatment, selection of risk measures, risk acceptance, multi-objective optimization
Procedia PDF Downloads 4582628 Quasistationary States and Mean Field Model
Authors: Sergio Curilef, Boris Atenas
Abstract:
Systems with long-range interactions are very common in nature. They are observed from the atomic scale to the astronomical scale and exhibit anomalies, such as inequivalence of ensembles, negative heat capacity, ergodicity breaking, nonequilibrium phase transitions, quasistationary states, and anomalous diffusion. These anomalies are exacerbated when special initial conditions are imposed; in particular, we use the so-called water bag initial conditions that stand for a uniform distribution. Several theoretical and practical implications are discussed here. A potential energy inspired by dipole-dipole interactions is proposed to build the dipole-type Hamiltonian mean-field model. As expected, the dynamics is novel and general to the behavior of systems with long-range interactions, which is obtained through molecular dynamics technique. Two plateaus sequentially emerge before arriving at equilibrium, which are corresponding to two different quasistationary states. The first plateau is a type of quasistationary state the lifetime of which depends on a power law of N and the second plateau seems to be a true quasistationary state as reported in the literature. The general behavior of the model according to its dynamics and thermodynamics is described. Using numerical simulation we characterize the mean kinetic energy, caloric curve, and the diffusion law through the mean square of displacement. The present challenge is to characterize the distributions in phase space. Certainly, the equilibrium state is well characterized by the Gaussian distribution, but quasistationary states in general depart from any Gaussian function.Keywords: dipole-type interactions, dynamics and thermodynamics, mean field model, quasistationary states
Procedia PDF Downloads 2062627 Estimation of Fragility Curves Using Proposed Ground Motion Selection and Scaling Procedure
Authors: Esra Zengin, Sinan Akkar
Abstract:
Reliable and accurate prediction of nonlinear structural response requires specification of appropriate earthquake ground motions to be used in nonlinear time history analysis. The current research has mainly focused on selection and manipulation of real earthquake records that can be seen as the most critical step in the performance based seismic design and assessment of the structures. Utilizing amplitude scaled ground motions that matches with the target spectra is commonly used technique for the estimation of nonlinear structural response. Representative ground motion ensembles are selected to match target spectrum such as scenario-based spectrum derived from ground motion prediction equations, Uniform Hazard Spectrum (UHS), Conditional Mean Spectrum (CMS) or Conditional Spectrum (CS). Different sets of criteria exist among those developed methodologies to select and scale ground motions with the objective of obtaining robust estimation of the structural performance. This study presents ground motion selection and scaling procedure that considers the spectral variability at target demand with the level of ground motion dispersion. The proposed methodology provides a set of ground motions whose response spectra match target median and corresponding variance within a specified period interval. The efficient and simple algorithm is used to assemble the ground motion sets. The scaling stage is based on the minimization of the error between scaled median and the target spectra where the dispersion of the earthquake shaking is preserved along the period interval. The impact of the spectral variability on nonlinear response distribution is investigated at the level of inelastic single degree of freedom systems. In order to see the effect of different selection and scaling methodologies on fragility curve estimations, results are compared with those obtained by CMS-based scaling methodology. The variability in fragility curves due to the consideration of dispersion in ground motion selection process is also examined.Keywords: ground motion selection, scaling, uncertainty, fragility curve
Procedia PDF Downloads 5812626 Reliability Modeling on Drivers’ Decision during Yellow Phase
Authors: Sabyasachi Biswas, Indrajit Ghosh
Abstract:
The random and heterogeneous behavior of vehicles in India puts up a greater challenge for researchers. Stop-and-go modeling at signalized intersections under heterogeneous traffic conditions has remained one of the most sought-after fields. Vehicles are often caught up in the dilemma zone and are unable to take quick decisions whether to stop or cross the intersection. This hampers the traffic movement and may lead to accidents. The purpose of this work is to develop a stop and go prediction model that depicts the drivers’ decision during the yellow time at signalised intersections. To accomplish this, certain traffic parameters were taken into account to develop surrogate model. This research investigated the Stop and Go behavior of the drivers by collecting data from 4-signalized intersections located in two major Indian cities. Model was developed to predict the drivers’ decision making during the yellow phase of the traffic signal. The parameters used for modeling included distance to stop line, time to stop line, speed, and length of the vehicle. A Kriging base surrogate model has been developed to investigate the drivers’ decision-making behavior in amber phase. It is observed that the proposed approach yields a highly accurate result (97.4 percent) by Gaussian function. It was observed that the accuracy for the crossing probability was 95.45, 90.9 and 86.36.11 percent respectively as predicted by the Kriging models with Gaussian, Exponential and Linear functions.Keywords: decision-making decision, dilemma zone, surrogate model, Kriging
Procedia PDF Downloads 3052625 Competitiveness of a Share Autonomous Electrical Vehicle Fleet Compared to Traditional Means of Transport: A Case Study for Transportation Network Companies
Authors: Maximilian Richter
Abstract:
Implementing shared autonomous electric vehicles (SAEVs) has many advantages. The main advantages are achieved when SAEVs are offered as on-demand services by a fleet operator. However, autonomous mobility on demand (AMoD) will be distributed nationwide only if a fleet operation is economically profitable for the operator. This paper proposes a microscopic approach to modeling two implementation scenarios of an AMoD fleet. The city of Zurich is used as a case study, with the results and findings being generalizable to other similar European and North American cities. The data are based on the traffic model of the canton of Zurich (Gesamtverkehrsmodell des Kantons Zürich (GVM-ZH)). To determine financial profitability, demand is based on the simulation results and combined with analyzing the costs of a SAEV per kilometer. The results demonstrate that depending on the scenario; journeys can be offered profitably to customers for CHF 0.3 up to CHF 0.4 per kilometer. While larger fleets allowed for lower price levels and increased profits in the long term, smaller fleets exhibit elevated efficiency levels and profit opportunities per day. The paper concludes with recommendations for how fleet operators can prepare themselves to maximize profit in the autonomous future.Keywords: autonomous vehicle, mobility on demand, traffic simulation, fleet provider
Procedia PDF Downloads 1212624 Awning: An Unsung Trait in Rice (Oryza Sativa L.)
Authors: Chamin Chimyang
Abstract:
The fast-changing global trend and declining forest region have impacted agricultural lands; animals, especially birds, might become one of the major pests in the near future and go neglected or unreported in many kinds of literature and events, which is mainly because of bird infestation being a pocket-zone problem. This bird infestation can be attributed to the balding of the forest region and the decline in their foraging hotspot due to anthropogenic activity. There are many ways to keep away the birds from agricultural fields, both conventional and non-conventional. But the question here is whether the traditional approach of bird scarring methods such as scare-crows are effective enough. There are many traits in rice that are supposed to keep the birds away from foraging in paddy fields, and the selection of such traits might be rewarding, such as the angle of the flag leaf from the stem, grain size, novelty of any trait in that particular region and also an awning. Awning, as such, is a very particular trait on which negative selection was imposed to such an extent that there has been a decline in the nucleotide responsible for the said trait. Thus, in this particular session, histology, genetics, genes behind the trait and how awns might be one of the solutions to the problem stated above will be discussed in detail.Keywords: bird infestation, awning, negative selection, domestication
Procedia PDF Downloads 132623 EFL Vocabulary Learning Strategies among Students in Greece, Their Preferences and Internet Technology
Authors: Theodorou Kyriaki, Ypsilantis George
Abstract:
Vocabulary learning has attracted a lot of attention in recent years, contrary to the neglected part of the past. Along with the interest in finding successful vocabulary teaching strategies, many scholars focused on locating learning strategies used by language learners. As a result, more and more studies in the area of language pedagogy have been investigating the use of strategies in vocabulary learning by different types of learners. A common instrument in this field is the questionnaire, a tool of work that was enriched by questions involving current technology, and it was further implemented to a sample of 300 Greek students whose age varied from 9 and 17 years. Strategies located were grouped into the three categories of memory, cognitive, and compensatory type and associations between these dependent variables were investigated. In addition, relations between dependent and independent variables (such as age, sex, type of school, cultural background, and grade in English) were pursued to investigate the impact on strategy selection. Finally, results were compared to findings of other studies in the same field to contribute to a hypothesis of ethnic differences in strategy selection. Results initially discuss preferred strategies of all participants and further indicate that: a) technology affects strategy selection while b) differences between ethnic groups are not statistically significant. A number of successful strategies are presented, resulting from correlations of strategy selection and final school grade in English.Keywords: acquisition of English, internet technology, research among Greek students, vocabulary learning strategies
Procedia PDF Downloads 5012622 A Two Tailed Secretary Problem with Multiple Criteria
Authors: Alaka Padhye, S. P. Kane
Abstract:
The following study considers some variations made to the secretary problem (SP). In a multiple criteria secretary problem (MCSP), the selection of a unit is based on two independent characteristics. The units that appear before an observer are known say N, the best rank of a unit being N. A unit is selected, if it is better with respect to either first or second or both the characteristics. When the number of units is large and due to constraints like time and cost, the observer might want to stop earlier instead of inspecting all the available units. Let the process terminate at r2th unit where r12621 The Effect of Initial Sample Size and Increment in Simulation Samples on a Sequential Selection Approach
Authors: Mohammad H. Almomani
Abstract:
In this paper, we argue the effect of the initial sample size, and the increment in simulation samples on the performance of a sequential approach that used in selecting the top m designs when the number of alternative designs is very large. The sequential approach consists of two stages. In the first stage the ordinal optimization is used to select a subset that overlaps with the set of actual best k% designs with high probability. Then in the second stage the optimal computing budget is used to select the top m designs from the selected subset. We apply the selection approach on a generic example under some parameter settings, with a different choice of initial sample size and the increment in simulation samples, to explore the impacts on the performance of this approach. The results show that the choice of initial sample size and the increment in simulation samples does affect the performance of a selection approach.Keywords: Large Scale Problems, Optimal Computing Budget Allocation, ordinal optimization, simulation optimization
Procedia PDF Downloads 3492620 Machine Learning Approach for Yield Prediction in Semiconductor Production
Authors: Heramb Somthankar, Anujoy Chakraborty
Abstract:
This paper presents a classification study on yield prediction in semiconductor production using machine learning approaches. A complicated semiconductor production process is generally monitored continuously by signals acquired from sensors and measurement sites. A monitoring system contains a variety of signals, all of which contain useful information, irrelevant information, and noise. In the case of each signal being considered a feature, "Feature Selection" is used to find the most relevant signals. The open-source UCI SECOM Dataset provides 1567 such samples, out of which 104 fail in quality assurance. Feature extraction and selection are performed on the dataset, and useful signals were considered for further study. Afterward, common machine learning algorithms were employed to predict whether the signal yields pass or fail. The most relevant algorithm is selected for prediction based on the accuracy and loss of the ML model.Keywords: deep learning, feature extraction, feature selection, machine learning classification algorithms, semiconductor production monitoring, signal processing, time-series analysis
Procedia PDF Downloads 1012619 Low Overhead Dynamic Channel Selection with Cluster-Based Spatial-Temporal Station Reporting in Wireless Networks
Authors: Zeyad Abdelmageid, Xianbin Wang
Abstract:
Choosing the operational channel for a WLAN access point (AP) in WLAN networks has been a static channel assignment process initiated by the user during the deployment process of the AP, which fails to cope with the dynamic conditions of the assigned channel at the station side afterward. However, the dramatically growing number of Wi-Fi APs and stations operating in the unlicensed band has led to dynamic, distributed, and often severe interference. This highlights the urgent need for the AP to dynamically select the best overall channel of operation for the basic service set (BSS) by considering the distributed and changing channel conditions at all stations. Consequently, dynamic channel selection algorithms which consider feedback from the station side have been developed. Despite the significant performance improvement, existing channel selection algorithms suffer from very high feedback overhead. Feedback latency from the STAs, due to the high overhead, can cause the eventually selected channel to no longer be optimal for operation due to the dynamic sharing nature of the unlicensed band. This has inspired us to develop our own dynamic channel selection algorithm with reduced overhead through the proposed low-overhead, cluster-based station reporting mechanism. The main idea behind the cluster-based station reporting is the observation that STAs which are very close to each other tend to have very similar channel conditions. Instead of requesting each STA to report on every candidate channel while causing high overhead, the AP divides STAs into clusters then assigns each STA in each cluster one channel to report feedback on. With the proper design of the cluster based reporting, the AP does not lose any information about the channel conditions at the station side while reducing feedback overhead. The simulation results show equal performance and, at times, better performance with a fraction of the overhead. We believe that this algorithm has great potential in designing future dynamic channel selection algorithms with low overhead.Keywords: channel assignment, Wi-Fi networks, clustering, DBSCAN, overhead
Procedia PDF Downloads 1122618 Transport Mode Selection under Lead Time Variability and Emissions Constraint
Authors: Chiranjit Das, Sanjay Jharkharia
Abstract:
This study is focused on transport mode selection under lead time variability and emissions constraint. In order to reduce the carbon emissions generation due to transportation, organization has often faced a dilemmatic choice of transport mode selection since logistic cost and emissions reduction are complementary with each other. Another important aspect of transportation decision is lead-time variability which is least considered in transport mode selection problem. Thus, in this study, we provide a comprehensive mathematical based analytical model to decide transport mode selection under emissions constraint. We also extend our work through analysing the effect of lead time variability in the transport mode selection by a sensitivity analysis. In order to account lead time variability into the model, two identically normally distributed random variables are incorporated in this study including unit lead time variability and lead time demand variability. Therefore, in this study, we are addressing following questions: How the decisions of transport mode selection will be affected by lead time variability? How lead time variability will impact on total supply chain cost under carbon emissions? To accomplish these objectives, a total transportation cost function is developed including unit purchasing cost, unit transportation cost, emissions cost, holding cost during lead time, and penalty cost for stock out due to lead time variability. A set of modes is available to transport each node, in this paper, we consider only four transport modes such as air, road, rail, and water. Transportation cost, distance, emissions level for each transport mode is considered as deterministic and static in this paper. Each mode is having different emissions level depending on the distance and product characteristics. Emissions cost is indirectly affected by the lead time variability if there is any switching of transport mode from lower emissions prone transport mode to higher emissions prone transport mode in order to reduce penalty cost. We provide a numerical analysis in order to study the effectiveness of the mathematical model. We found that chances of stock out during lead time will be higher due to the higher variability of lead time and lad time demand. Numerical results show that penalty cost of air transport mode is negative that means chances of stock out zero, but, having higher holding and emissions cost. Therefore, air transport mode is only selected when there is any emergency order to reduce penalty cost, otherwise, rail and road transport is the most preferred mode of transportation. Thus, this paper is contributing to the literature by a novel approach to decide transport mode under emissions cost and lead time variability. This model can be extended by studying the effect of lead time variability under some other strategic transportation issues such as modal split option, full truck load strategy, and demand consolidation strategy etc.Keywords: carbon emissions, inventory theoretic model, lead time variability, transport mode selection
Procedia PDF Downloads 4232617 A Novel Heuristic for Analysis of Large Datasets by Selecting Wrapper-Based Features
Authors: Bushra Zafar, Usman Qamar
Abstract:
Large data sample size and dimensions render the effectiveness of conventional data mining methodologies. A data mining technique are important tools for collection of knowledgeable information from variety of databases and provides supervised learning in the form of classification to design models to describe vital data classes while structure of the classifier is based on class attribute. Classification efficiency and accuracy are often influenced to great extent by noisy and undesirable features in real application data sets. The inherent natures of data set greatly masks its quality analysis and leave us with quite few practical approaches to use. To our knowledge first time, we present a new approach for investigation of structure and quality of datasets by providing a targeted analysis of localization of noisy and irrelevant features of data sets. Machine learning is based primarily on feature selection as pre-processing step which offers us to select few features from number of features as a subset by reducing the space according to certain evaluation criterion. The primary objective of this study is to trim down the scope of the given data sample by searching a small set of important features which may results into good classification performance. For this purpose, a heuristic for wrapper-based feature selection using genetic algorithm and for discriminative feature selection an external classifier are used. Selection of feature based on its number of occurrence in the chosen chromosomes. Sample dataset has been used to demonstrate proposed idea effectively. A proposed method has improved average accuracy of different datasets is about 95%. Experimental results illustrate that proposed algorithm increases the accuracy of prediction of different diseases.Keywords: data mining, generic algorithm, KNN algorithms, wrapper based feature selection
Procedia PDF Downloads 3112616 Investigating the Glass Ceiling Phenomenon: An Empirical Study of Glass Ceiling's Effects on Selection, Promotion and Female Effectiveness
Authors: Sharjeel Saleem
Abstract:
The glass ceiling has been a burning issue for many researchers. In this research, we examine gender of the BOD, training and development, workforce diversity, positive attitude towards women, and employee acts as antecedents of glass ceiling. Furthermore, we also look for effects of glass ceiling on likelihood of female selection and promotion and on female effectiveness. Multiple linear regression conducted on data drawn from different public and private sector organizations support our hypotheses. The research, however, is limited to Faisalabad city and only females from minority group are targeted here.Keywords: glass ceiling, stereotype attitudes, female effectiveness
Procedia PDF Downloads 2852615 Classification of Political Affiliations by Reduced Number of Features
Authors: Vesile Evrim, Aliyu Awwal
Abstract:
By the evolvement in technology, the way of expressing opinions switched the direction to the digital world. The domain of politics as one of the hottest topics of opinion mining research merged together with the behavior analysis for affiliation determination in text which constitutes the subject of this paper. This study aims to classify the text in news/blogs either as Republican or Democrat with the minimum number of features. As an initial set, 68 features which 64 are constituted by Linguistic Inquiry and Word Count (LIWC) features are tested against 14 benchmark classification algorithms. In the later experiments, the dimensions of the feature vector reduced based on the 7 feature selection algorithms. The results show that Decision Tree, Rule Induction and M5 Rule classifiers when used with SVM and IGR feature selection algorithms performed the best up to 82.5% accuracy on a given dataset. Further tests on a single feature and the linguistic based feature sets showed the similar results. The feature “function” as an aggregate feature of the linguistic category, is obtained as the most differentiating feature among the 68 features with 81% accuracy by itself in classifying articles either as Republican or Democrat.Keywords: feature selection, LIWC, machine learning, politics
Procedia PDF Downloads 3782614 Optimal Portfolio Selection under Treynor Ratio Using Genetic Algorithms
Authors: Imad Zeyad Ramadan
Abstract:
In this paper a genetic algorithm was developed to construct the optimal portfolio based on the Treynor method. The GA maximizes the Treynor ratio under budget constraint to select the best allocation of the budget for the companies in the portfolio. The results show that the GA was able to construct a conservative portfolio which includes companies from the three sectors. This indicates that the GA reduced the risk on the investor as it choose some companies with positive risks (goes with the market) and some with negative risks (goes against the market).Keywords: oOptimization, genetic algorithm, portfolio selection, Treynor method
Procedia PDF Downloads 4382613 A Combination of Anisotropic Diffusion and Sobel Operator to Enhance the Performance of the Morphological Component Analysis for Automatic Crack Detection
Authors: Ankur Dixit, Hiroaki Wagatsuma
Abstract:
The crack detection on a concrete bridge is an important and constant task in civil engineering. Chronically, humans are checking the bridge for inspection of cracks to maintain the quality and reliability of bridge. But this process is very long and costly. To overcome such limitations, we have used a drone with a digital camera, which took some images of bridge deck and these images are processed by morphological component analysis (MCA). MCA technique is a very strong application of sparse coding and it explores the possibility of separation of images. In this paper, MCA has been used to decompose the image into coarse and fine components with the effectiveness of two dictionaries namely anisotropic diffusion and wavelet transform. An anisotropic diffusion is an adaptive smoothing process used to adjust diffusion coefficient by finding gray level and gradient as features. These cracks in image are enhanced by subtracting the diffused coarse image into the original image and the results are treated by Sobel edge detector and binary filtering to exhibit the cracks in a fine way. Our results demonstrated that proposed MCA framework using anisotropic diffusion followed by Sobel operator and binary filtering may contribute to an automation of crack detection even in open field sever conditions such as bridge decks.Keywords: anisotropic diffusion, coarse component, fine component, MCA, Sobel edge detector and wavelet transform
Procedia PDF Downloads 1682612 Frequent Itemset Mining Using Rough-Sets
Authors: Usman Qamar, Younus Javed
Abstract:
Frequent pattern mining is the process of finding a pattern (a set of items, subsequences, substructures, etc.) that occurs frequently in a data set. It was proposed in the context of frequent itemsets and association rule mining. Frequent pattern mining is used to find inherent regularities in data. What products were often purchased together? Its applications include basket data analysis, cross-marketing, catalog design, sale campaign analysis, Web log (click stream) analysis, and DNA sequence analysis. However, one of the bottlenecks of frequent itemset mining is that as the data increase the amount of time and resources required to mining the data increases at an exponential rate. In this investigation a new algorithm is proposed which can be uses as a pre-processor for frequent itemset mining. FASTER (FeAture SelecTion using Entropy and Rough sets) is a hybrid pre-processor algorithm which utilizes entropy and rough-sets to carry out record reduction and feature (attribute) selection respectively. FASTER for frequent itemset mining can produce a speed up of 3.1 times when compared to original algorithm while maintaining an accuracy of 71%.Keywords: rough-sets, classification, feature selection, entropy, outliers, frequent itemset mining
Procedia PDF Downloads 430