Abstract: Hierarchical classification is a special type of classification task where the class labels are organised into a hierarchy, with more generic class labels being ancestors of more specific ones. Meta-learning for classification-algorithm recommendation consists of recommending to the user a classification algorithm, from a pool of candidate algorithms, for a dataset, based on the past performance of the candidate algorithms in other datasets. Meta-learning is normally used in conventional, non-hierarchical classification. By contrast, this paper proposes a meta-learning approach for more challenging task of hierarchical classification, and evaluates it in a large number of bioinformatics datasets. Hierarchical classification is especially relevant for bioinformatics problems, as protein and gene functions tend to be organised into a hierarchy of class labels. This work proposes meta-learning approach for
recommending the best hierarchical classification algorithm to a
hierarchical classification dataset. This work’s contributions are: 1)
proposing an algorithm for splitting hierarchical datasets into
new datasets to increase the number of meta-instances, 2) proposing
meta-features for hierarchical classification, and 3) interpreting
decision-tree meta-models for hierarchical classification algorithm
recommendation.
Abstract: In this paper, we report how to acquire serious victims’ locations in the Acute Stage of Large-scale Disasters, in an Emergency Information Network System designed by us. The background of our concept is based on the Great East Japan Earthquake occurred on March 11th, 2011. Through many experiences of national crises caused by earthquakes and tsunamis, we have established advanced communication systems and advanced disaster medical response systems. However, Japan was devastated by huge tsunamis swept a vast area of Tohoku causing a complete breakdown of all the infrastructures including telecommunications. Therefore, we noticed that we need interdisciplinary collaboration between science of disaster medicine, regional administrative sociology, satellite communication technology and systems engineering experts. Communication of emergency information was limited causing a serious delay in the initial rescue and medical operation. For the emergency rescue and medical operations, the most important thing is to identify the number of casualties, their locations and status and to dispatch doctors and rescue workers from multiple organizations. In the case of the Tohoku earthquake, the dispatching mechanism and/or decision support system did not exist to allocate the appropriate number of doctors and locate disaster victims. Even though the doctors and rescue workers from multiple government organizations have their own dedicated communication system, the systems are not interoperable.
Abstract: The emerging approaches to sustainable manufacturing are considered to be solution-oriented with the aim of addressing the environmental, economic and social issues holistically. However, the analysis of the interdependencies amongst the three sustainability dimensions has not been fully captured in the literature. In a recent review of approaches to sustainable manufacturing, two categories of techniques are identified: 1) Sustainable Product Development (SPD), and 2) Sustainability Performance Assessment (SPA) techniques. The challenges of the approaches are not only related to the arguments and misconceptions of the relationships between the techniques and sustainable development but also to the inability to capture and integrate the three sustainability dimensions. This requires a clear definition of some of the approaches and a road-map to the development of a holistic approach that supports sustainability decision-making. In this context, eco-innovation, social impact assessment, and life cycle sustainability analysis play an important role. This paper deployed an integrative approach that enabled amalgamation of sustainable manufacturing approaches and the theories of reciprocity and motivation into a holistic simulation-based impact analysis framework. The findings in this research have the potential to guide sustainability analysts to capture the aspects of the three sustainability dimensions into an analytical model. Additionally, the research findings presented can aid the construction of a holistic simulation model of a sustainable manufacturing and support effective decision-making.
Abstract: Municipal solid waste (MSW) generation is among the most significant sources which threaten the global environmental health. Solid Waste Management has been an important environmental problem in developing countries because of the difficulties in finding sustainable solutions for solid wastes. Therefore, more efforts are needed to be implemented to overcome this problem. Lebanon has suffered a severe solid waste management problem in 2015, and a new landfill site was proposed to solve the existing problem. The study aims to identify and locate the most suitable area to construct a landfill taking into consideration the sustainable development to overcome the present situation and protect the future demands. Throughout the article, a landfill site selection methodology was discussed using Geographic Information System (GIS) and Multi Criteria Decision Analysis (MCDA). Several environmental, economic and social factors were taken as criterion for selection of a landfill. Soil, geology, and LUC (Land Use and Land Cover) indices with the Sustainable Development Index were main inputs to create the final map of Environmentally Sensitive Area (ESA) for landfill site. Different factors were determined to define each index. Input data of each factor was managed, visualized and analyzed using GIS. GIS was used as an important tool to identify suitable areas for landfill. Spatial Analysis (SA), Analysis and Management GIS tools were implemented to produce input maps capable of identifying suitable areas related to each index. Weight has been assigned to each factor in the same index, and the main weights were assigned to each index used. The combination of the different indices map generates the final output map of ESA. The output map was reclassified into three suitability classes of low, moderate, and high suitability. Results showed different locations suitable for the construction of a landfill. Results also reflected the importance of GIS and MCDA in helping decision makers finding a solution of solid wastes by a sanitary landfill.
Abstract: One challenge faced by procurement decision-maker during the acquisition process is how to compare similar products from different suppliers and allocate orders among different products or services. This work focuses on allocating orders among multiple suppliers considering rebate. The objective function is to minimize the total acquisition cost including purchasing cost and rebate benefit. Rebate benefit is complex and difficult to estimate at the ordering step. Rebate rules vary for different suppliers and usually change over time. In this work, we developed a system to collect the rebate policies, standardized the rebate policies and developed two-stage optimization models for ordering allocation. Rebate policy with multi-tiers is considered in modeling. The discontinuous cost function of rebate benefit is formulated for different scenarios. A piecewise linear function is used to approximate the discontinuous cost function of rebate benefit. And a Mixed Integer Programing (MIP) model is built for order allocation problem with multi-tier rebate. A case study is presented and it shows that our optimization model can reduce the total acquisition cost by considering rebate rules.
Abstract: In this research, a multidimensional compromise optimization method is proposed for multidimensional decision making analysis in the development ranking of the Gulf Cooperation Council Countries and Turkey. The proposed approach presents ranking solutions resulting from different multicriteria decision analyses, which yield different ranking orders for the same ranking problem, consisting of a set of alternatives in terms of numerous competing criteria when they are applied with the same numerical data. The multiobjective optimization decision making problem is considered in three sequential steps. In the first step, five different criteria related to the development ranking are gathered from the research field. In the second step, identified evaluation criteria are, objectively, weighted using standard deviation procedure. In the third step, a country selection problem is illustrated with a numerical example as an application of the proposed multidimensional compromise optimization model. Finally, multidimensional compromise optimization approach is applied to rank the Gulf Cooperation Council Countries and Turkey.
Abstract: Integrated resilience engineering (IRE) is capable of returning banking systems to the normal state in extensive economic circumstances. In this study, information system of a large bank (with several branches) is assessed and optimized under severe economic conditions. Data envelopment analysis (DEA) models are employed to achieve the objective of this study. Nine IRE factors are considered to be the outputs, and a dummy variable is defined as the input of the DEA models. A standard questionnaire is designed and distributed among executive managers to be considered as the decision-making units (DMUs). Reliability and validity of the questionnaire is examined based on Cronbach's alpha and t-test. The most appropriate DEA model is determined based on average efficiency and normality test. It is shown that the proposed integrated design provides higher efficiency than the conventional RE design. Results of sensitivity and perturbation analysis indicate that self-organization, fault tolerance, and reporting culture respectively compose about 50 percent of total weight.
Abstract: Intrusion detection systems (IDS) are the main components of network security. These systems analyze the network events for intrusion detection. The design of an IDS is through the training of normal traffic data or attack. The methods of machine learning are the best ways to design IDSs. In the method presented in this article, the pruning algorithm of C5.0 decision tree is being used to reduce the features of traffic data used and training IDS by the least square vector algorithm (LS-SVM). Then, the remaining features are arranged according to the predictor importance criterion. The least important features are eliminated in the order. The remaining features of this stage, which have created the highest level of accuracy in LS-SVM, are selected as the final features. The features obtained, compared to other similar articles which have examined the selected features in the least squared support vector machine model, are better in the accuracy, true positive rate, and false positive. The results are tested by the UNSW-NB15 dataset.
Abstract: Electricity prices have sophisticated features such as
high volatility, nonlinearity and high frequency that make forecasting
quite difficult. Electricity price has a volatile and non-random
character so that, it is possible to identify the patterns based on the
historical data. Intelligent decision-making requires accurate price
forecasting for market traders, retailers, and generation companies.
So far, many shallow-ANN (artificial neural networks) models have
been published in the literature and showed adequate forecasting
results. During the last years, neural networks with many hidden
layers, which are referred to as DNN (deep neural networks) have
been using in the machine learning community. The goal of this
study is to investigate electricity price forecasting performance of the
shallow-ANN and DNN models for the Turkish day-ahead electricity
market. The forecasting accuracy of the models has been evaluated
with publicly available data from the Turkish day-ahead electricity
market. Both shallow-ANN and DNN approach would give successful
result in forecasting problems. Historical load, price and weather
temperature data are used as the input variables for the models.
The data set includes power consumption measurements gathered
between January 2016 and December 2017 with one-hour resolution.
In this regard, forecasting studies have been carried out comparatively
with shallow-ANN and DNN models for Turkish electricity markets
in the related time period. The main contribution of this study
is the investigation of different shallow-ANN and DNN models
in the field of electricity price forecast. All models are compared
regarding their MAE (Mean Absolute Error) and MSE (Mean Square)
results. DNN models give better forecasting performance compare to
shallow-ANN. Best five MAE results for DNN models are 0.346,
0.372, 0.392, 0,402 and 0.409.
Abstract: Load forecasting has become crucial in recent years
and become popular in forecasting area. Many different power
forecasting models have been tried out for this purpose. Electricity
load forecasting is necessary for energy policies, healthy and reliable
grid systems. Effective power forecasting of renewable energy load
leads the decision makers to minimize the costs of electric utilities
and power plants. Forecasting tools are required that can be used
to predict how much renewable energy can be utilized. The purpose
of this study is to explore the effectiveness of LSTM-based neural
networks for estimating renewable energy loads. In this study, we
present models for predicting renewable energy loads based on
deep neural networks, especially the Long Term Memory (LSTM)
algorithms. Deep learning allows multiple layers of models to learn
representation of data. LSTM algorithms are able to store information
for long periods of time. Deep learning models have recently been
used to forecast the renewable energy sources such as predicting
wind and solar energy power. Historical load and weather information
represent the most important variables for the inputs within the
power forecasting models. The dataset contained power consumption
measurements are gathered between January 2016 and December
2017 with one-hour resolution. Models use publicly available data
from the Turkish Renewable Energy Resources Support Mechanism.
Forecasting studies have been carried out with these data via deep
neural networks approach including LSTM technique for Turkish
electricity markets. 432 different models are created by changing
layers cell count and dropout. The adaptive moment estimation
(ADAM) algorithm is used for training as a gradient-based optimizer
instead of SGD (stochastic gradient). ADAM performed better than
SGD in terms of faster convergence and lower error rates. Models
performance is compared according to MAE (Mean Absolute Error)
and MSE (Mean Squared Error). Best five MAE results out of
432 tested models are 0.66, 0.74, 0.85 and 1.09. The forecasting
performance of the proposed LSTM models gives successful results
compared to literature searches.
Abstract: In this paper, we propose a condition-based
maintenance policy for multi-unit systems considering the
existence of economic dependency among units. We consider a
system composed of N identical units, where each unit deteriorates
independently. Deterioration process of each unit is modeled as a
three-state continuous time homogeneous Markov chain with two
working states and a failure state. The average production rate of
units varies in different working states and demand rate of the
system is constant. Units are inspected at equidistant time epochs,
and decision regarding performing maintenance is determined by the
number of units in the failure state. If the total number of units in the
failure state exceeds a critical level, maintenance is initiated, where
units in failed state are replaced correctively and deteriorated state
units are maintained preventively. Our objective is to determine the
optimal number of failed units to initiate maintenance minimizing
the long run expected average cost per unit time. The problem is
formulated and solved in the semi-Markov decision process (SMDP)
framework. A numerical example is developed to demonstrate the
proposed policy and the comparison with the corrective maintenance
policy is presented.
Abstract: Due to the emergence of the Internet, it has extended the traditional Word-of-Mouth (WOM) to a new form called “Electronic Word-of-Mouth (eWOM).” Unlike traditional WOM, eWOM is able to present information in various ways by applying different components. Each eWOM component generates different effects on online consumer behavior. This research investigates the effects of Webcare (responding message) from product/ service providers on negative eWOM by applying two types of products (search and experience). The proposed conceptual model was developed based on the combination of the stages in consumer decision-making process, theory of reasoned action (TRA), theory of planned behavior (TPB), the technology acceptance model (TAM), the information integration theory and the elaboration likelihood model. The methodology techniques used in this study included multivariate analysis of variance (MANOVA) and multiple regression analysis. The results suggest that Webcare does slightly increase Thai online consumer’s perceptions on perceived eWOM trustworthiness, information diagnosticity and quality. For negative eWOM, we also found that perceived eWOM Trustworthiness, perceived eWOM diagnosticity and quality have a positive relationship with eWOM influence whereas perceived valence has a negative relationship with eWOM influence in Thai online consumers.
Abstract: In Dynamic Data Envelopment Analysis (DDEA), which is a subfield of Data Envelopment Analysis (DEA), the productivity of Decision Making Units (DMUs) is considered in relation to time. In this case, as it is accepted by the most of the researchers, there are outputs, which are produced by a DMU to be used as inputs in a future time. Those outputs are known as intermediates. The common models, in DDEA, do not take into account the shape of the distribution of those inputs, outputs or intermediates data, assuming that the distribution of the virtual value of them does not deviate from linearity. This weakness causes the limitation of the accuracy of the analytical power of the traditional DDEA models. In this paper, the authors, using the concept of piecewise linear inputs and outputs, propose an extended DDEA model. The proposed model increases the flexibility of the traditional DDEA models and improves the measurement of the dynamic performance of DMUs.
Abstract: Achieving environmental sustainability is one of the important issues considered in many countries’ vision. Green/Sustainable building is widely used terminology for describing a friendly environmental construction. Applying sustainable practices has a significant importance in various fields, including construction field that consumes an enormous amount of resource and causes a considerable amount of waste. The need for sustainability is increased in the regions that suffering from the limitation of natural resource and extreme weather conditions such as Saudi Arabia. Since buildings designs are getting sophisticated, the need for tools, which support decision-making for sustainability issues, is increasing, especially in the design and preconstruction stages. In this context, Building Information Modeling (BIM) can aid in performing complex building performance analyses to ensure an optimized sustainable building design. Accordingly, this paper introduces a roadmap towards developing a systematic approach for presenting the sustainability of buildings using BIM. The approach includes set of main processes including; identifying the sustainability parameters that can be used for sustainability assessment in Saudi Arabia, developing sustainability assessment method that fits the special circumstances in the Kingdom, identifying the sustainability requirements and BIM functions that can be used for satisfying these requirements, and integrating these requirements with identified functions. As a result, the sustainability-BIM approach can be developed which helps designers in assessing the sustainability and exploring different design alternatives at the early stage of the construction project.
Abstract: Buying decision making is a complicated process, in which consumer’s decision is under the impact of others. The buying decision making is directed in a way that they have to act as customers in the society. Media and family are key socialising agents for adolescents’. Moreover, changes in the socio-cultural environment in India necessitate that adolescents’ influence in family’s buying decision-making should be investigated. In comparison to Western society, Indian is quite different, when compared in terms of family composition and structure, behaviour, values and norms which effect adolescents’ buying decision-making.
Abstract: To assist medical diagnosis, we propose a federation
of several existing and open medical ontologies and terminologies.
The goal is to merge the strengths of all these resources to provide
clinicians the access to a variety of shared knowledges that can
facilitate identification and association of human diseases and all of
their available characteristic signs such as symptoms and clinical
signs. This work results to an integration model loaded from target
known ontologies of the bioportal platform such as DOID, MESH,
and SNOMED for diseases selection, SYMP, and CSSO for all
existing signs.
Abstract: Requirement Engineering (RE) is a part being created for programming structure during the software development lifecycle. Software product line development is a new topic area within the domain of software engineering. It also plays important role in decision making and it is ultimately helpful in rising business environment for productive programming headway. Decisions are central to engineering processes and they hold them together. It is argued that better decisions will lead to better engineering. To achieve better decisions requires that they are understood in detail. In order to address the issues, companies are moving towards Software Product Line Engineering (SPLE) which helps in providing large varieties of products with minimum development effort and cost. This paper proposed a new framework for software product line and compared with other models. The results can help to understand the needs in SPL testing, by identifying points that still require additional investigation. In our future scenario, we will combine this model in a controlled environment with industrial SPL projects which will be the new horizon for SPL process management testing strategies.
Abstract: The global trend indicates that more and more people live and will continue to live in urban areas. Today cities are expanding both in physical size and number due to the rapid population growth along with sprawl development, which caused the cities to expand beyond the growth boundary and exerting intense pressure on environmental resources specially farmlands to accommodate new housing and urban facilities. Also noticeable is the increase in urban decay along with the increase of slum dwellers present another challenge that most cities in developed and developing countries have to deal with. Today urban practitioners, researchers, planners, and decision-makers are seeking for alternative development and growth management policies to house the rising urban population and also cure the urban decay and slum issues turn to Smart Growth to achieve their goals. Many cities across the globe have adopted smart growth as an alternative growth management tool to deal with patterns and forms of development and to cure the rising urban and environmental problems. The method used in this study is a literature analysis method through reviewing various resources to highlight the potential benefits of Smart Growth in both developed and developing countries and analyze, to what extent it can be a strategic alternative for Afghanistan’s cities, especially the capital city. Hence a comparative analysis is carried on three countries, namely the USA, China, and India to identify the potential benefits of smart growth likely to serve as an achievable broad base for recommendations in different urban contexts.
Abstract: In this study, a model, together with a software tool that implements it, has been developed to determine the performance ratings of employees in an organization operating in the information technology sector using the indicators obtained from employees' online study data. Weighted Sum (WS) Method and Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method based on multidimensional decision making approach were used in the study. WS and TOPSIS methods provide multidimensional decision making (MDDM) methods that allow all dimensions to be evaluated together considering specific weights, allowing employees to objectively evaluate the problem of online performance tracking. The application of WS and TOPSIS mathematical methods, which can combine alternatives with a large number of dimensions and reach simultaneous solution, has been implemented through an online performance tracking software. In the application of WS and TOPSIS methods, objective dimension weights were calculated by using entropy information (EI) and standard deviation (SD) methods from the data obtained by employees' online performance tracking method, decision matrix was formed by using performance scores for each employee, and a single performance score was calculated for each employee. Based on the calculated performance score, employees were given a performance evaluation decision. The results of Pareto set evidence and comparative mathematical analysis validate that employees' performance preference rankings in WS and TOPSIS methods are closely related. This suggests the compatibility, applicability, and validity of the proposed method to the MDDM problems in which a large number of alternative and dimension types are taken into account. With this study, an objective, realistic, feasible and understandable mathematical method, together with a software tool that implements it has been demonstrated. This is considered to be preferable because of the subjectivity, limitations and high cost of the methods traditionally used in the measurement and performance appraisal in the information technology sector.
Abstract: Open Multiagent Systems (MASs) are societies in
which heterogeneous and independently designed entities (agents)
work towards similar, or different ends. Software agents are
autonomous and the diversity of interests among different members
living in the same society is a fact. In order to deal with this
autonomy, these open systems use mechanisms of social control
(norms) to ensure a desirable social order. This paper considers the
following types of norms: (i) obligation — agents must accomplish
a specific outcome; (ii) permission — agents may act in a particular
way, and (iii) prohibition — agents must not act in a specific way. All
of these characteristics mean to encourage the fulfillment of norms
through rewards and to discourage norm violation by pointing out the
punishments. Once the software agent decides that its priority is the
satisfaction of its own desires and goals, each agent must evaluate
the effects associated to the fulfillment of one or more norms before
choosing which one should be fulfilled. The same applies when agents
decide to violate a norm. This paper also introduces a framework
for the development of MASs that provide support mechanisms
to the agent’s decision-making, using norm-based reasoning. The
applicability and validation of this approach is demonstrated applying
a traffic intersection scenario.