Search results for: spatial temporal data mining

Authors: Pascal Rey, Anaïs Weber

Abstract:

Many mining projects are being developed in Africa the last decades. Due to the economic opportunities they offer, these projects result in a massive and rapid influx of migrants to the surrounding area. In areas where central government representation is low and local administration lack financial resources, urban development is often anarchical, beyond all public control. It leads to socio-spatial segregation, insecurity and the risk of social conflicts rising. Aware that their economic development is very correlated with local situation, mining companies get more and more involved in regional planning in setting up tools and Strategic Directions document. One of the commonly used tools in this regard is the “Influx Management Plan”. It consists in looking at the region’s absorption capacities in order to ensure its coherent development and by developing several urban centers than one macrocephalic city. It includes many other measures such as urban governance support, skills transfer, creation of strategic guidelines, financial support (local taxes, mining taxes, development funds etc.) local development projects. Through various examples of mining projects in Guinea, A country that is host to many large mining projects, we will look at the implications of regional and urban planning of which mining companies are key playor as well as public authorities. While their investment capacity offers advantages and accelerates development, their actions raise questions of the unilaterality of interests and local governance. By interfering in public affairs are mining companies not increasing the risk of central and local government shirking their responsibilities in terms of regional development, or even calling their legitimacy into question? Is such public-private collaboration really sustainable for the region as a whole and for all stakeholders?

Keywords: Africa, guinea, mine, urban planning

Procedia PDF Downloads 465

Authors: H. S. Saini, K. Vijayalakshmi, Rishi Sayal

Abstract:

Network-based education has been growing rapidly in size and quality. Knowledge clustering becomes more important in personalized information retrieval for web-learning. A personalized-Learning service after the learners’ knowledge has been classified with clustering. Through automatic analysis of learners’ behaviors, their partition with similar data level and interests may be discovered so as to produce learners with contents that best match educational needs for collaborative learning. We present a specific mining tool and a recommender engine that we have integrated in the online learning in order to help the teacher to carry out the whole e-learning process. We propose to use sequential pattern mining algorithms to discover the most used path by the students and from this information can recommend links to the new students automatically meanwhile they browse in the course. We have Developed a specific author tool in order to help the teacher to apply all the data mining process. We tend to report on many experiments with real knowledge so as to indicate the quality of using both clustering and sequential pattern mining algorithms together for discovering personalized e-learning systems.

Keywords: e-learning, cluster, personalization, sequence, pattern

Procedia PDF Downloads 400

Authors: Nada Jasim Habeeb, Rana Saad Mohammed, Muntaha Khudair Abbass

Abstract:

For more efficient and fast video summarization, this paper presents a surveillance video summarization method. The presented method works to improve video summarization technique. This method depends on temporal differencing to extract most important data from large video stream. This method uses histogram differencing and Sum Conditional Variance which is robust against to illumination variations in order to extract motion objects. The experimental results showed that the presented method gives better output compared with temporal differencing based summarization techniques.

Keywords: temporal differencing, video summarization, histogram differencing, sum conditional variance

Procedia PDF Downloads 320

Authors: S. J. Kim, Y. J. Yoo

Abstract:

Slack-tide sampling was carried out at seven stations at high and low tides for a tidal cycle, in summer (7, 8, 9) and fall (10), 2016 to determine the differences of water quality according to tides in Masan Bay. The data were analyzed by Pearson correlation and factor analysis. The mixing state of all the water quality components investigated is well explained by the correlation with salinity (SAL). Turbidity (TURB), dissolved silica (DSi), nitrite and nitrate nitrogen (NNN) and total nitrogen (TN), which find their way into the bay from the streams and have no internal source and sink reaction, showed a strong negative correlation with SAL at low tide, indicating the property of conservative mixing. On the contrary, in summer and fall, dissolved oxygen (DO), hydrogen sulfide (H2S) and chemical oxygen demand with KMnO4 (CODMn) of the surface and bottom water, which were sensitive to an internal source and sink reaction, showed no significant correlation with SAL at high and low tides. The remaining water quality parameters showed a conservative or a non-conservative mixing pattern depending on the mixing characteristics at high and low tides, determined by the functional relationship between the changes of the flushing time and the changes of the characteristics of water quality components of the end-members in the bay. Factor analysis performed on the concentration difference data sets between high and low tides helped in identifying the principal latent variables for them. The concentration differences varied spatially and temporally. Principal factors (PFs) scores plots for each monitoring situation showed high associations of the variations to the monitoring sites. At sampling station 1 (ST1), temperature (TEMP), SAL, DSi, TURB, NNN and TN of the surface water in summer, TEMP, SAL, DSi, DO, TURB, NNN, TN, reactive soluble phosphorus (RSP) and total phosphorus (TP) of the bottom water in summer, TEMP, pH, SAL, DSi, DO, TURB, CODMn, particulate organic carbon (POC), ammonia nitrogen (AMN), NNN, TN and fecal coliform (FC) of the surface water in fall, TEMP, pH, SAL, DSi, H2S, TURB, CODMn, AMN, NNN and TN of the bottom water in fall commonly showed up as the most significant parameters and the large concentration differences between high and low tides. At other stations, the significant parameters showed differently according to the spatial and temporal variations of mixing pattern in the bay. In fact, there is no estuary that always maintains steady-state flow conditions. The mixing regime of an estuary might be changed at any time from linear to non-linear, due to the change of flushing time according to the combination of hydrogeometric properties, inflow of freshwater and tidal action, And furthermore the change of end-member conditions due to the internal sinks and sources makes the occurrence of concentration difference inevitable. Therefore, when investigating the water quality of the estuary, it is necessary to take a sampling method considering the tide to obtain average water quality data.

Keywords: conservative mixing, end-member, factor analysis, flushing time, high and low tide, latent variables, non-conservative mixing, slack-tide sampling, spatial and temporal variations, surface and bottom water

Procedia PDF Downloads 101

Authors: Ana Paula Camelo, Keila Sanches

Abstract:

The Geographically Weighted Regression (GWR) was proposed in geography literature to allow relationship in a regression model to vary over space. In Brazil, the agricultural exploitation of the Cerrado Biome is the main cause of deforestation. In this study, we propose a methodology using geostatistical methods to characterize the spatial dependence of deforestation in the Cerrado based on agricultural production indicators. Therefore, it was used the set of exploratory spatial data analysis tools (ESDA) and confirmatory analysis using GWR. It was made the calibration a non-spatial model, evaluation the nature of the regression curve, election of the variables by stepwise process and multicollinearity analysis. After the evaluation of the non-spatial model was processed the spatial-regression model, statistic evaluation of the intercept and verification of its effect on calibration. In an analysis of Spearman’s correlation the results between deforestation and livestock was +0.783 and with soybeans +0.405. The model presented R²=0.936 and showed a strong spatial dependence of agricultural activity of soybeans associated to maize and cotton crops. The GWR is a very effective tool presenting results closer to the reality of deforestation in the Cerrado when compared with other analysis.

Keywords: deforestation, geographically weighted regression, land use, spatial analysis

Procedia PDF Downloads 328

Authors: Rashi Bhalla, Russel Pears, M. Asif Naeem

Abstract:

In this 'Information Explosion Era' analyzing data 'a critical commodity' and mining knowledge from vertically distributed data stream incurs huge communication cost. However, an effort to decrease the communication in the distributed environment has an adverse influence on the classification accuracy; therefore, a research challenge lies in maintaining a balance between transmission cost and accuracy. This paper proposes a method based on Bayesian inference to reduce the communication volume in a heterogeneous distributed environment while retaining prediction accuracy. Our experimental evaluation reveals that a significant reduction in communication can be achieved across a diverse range of dataset types.

Keywords: big data, bayesian inference, distributed data stream mining, heterogeneous-distributed data

Procedia PDF Downloads 128

Authors: Marc Sango, Olimpia Hoinaru, Christophe Gransart, Laurence Duchien

Abstract:

Ontologies offer a means for representing and sharing information in many domains, particularly in complex domains. For example, it can be used for representing and sharing information of System Requirement Specification (SRS) of complex systems like the SRS of ERTMS/ETCS written in natural language. Since this system is a real-time and critical system, generic ontologies, such as OWL and generic ERTMS ontologies provide minimal support for modeling temporal information omnipresent in these SRS documents. To support the modeling of temporal information, one of the challenges is to enable representation of dynamic features evolving in time within a generic ontology with a minimal redesign of it. The separation of temporal information from other information can help to predict system runtime operation and to properly design and implement them. In addition, it is helpful to provide a reasoning and querying techniques to reason and query temporal information represented in the ontology in order to detect potential temporal inconsistencies. Indeed, a user operation, such as adding a new constraint on existing planning constraints can cause temporal inconsistencies, which can lead to system failures. To address this challenge, we propose a lightweight 3-layer temporal Quality of Service (QoS) ontology for representing, reasoning and querying over temporal and non-temporal information in a complex domain ontology. Representing QoS entities in separated layers can clarify the distinction between the non QoS entities and the QoS entities in an ontology. The upper generic layer of the proposed ontology provides an intuitive knowledge of domain components, specially ERTMS/ETCS components. The separation of the intermediate QoS layer from the lower QoS layer allows us to focus on specific QoS Characteristics, such as temporal or integrity characteristics. In this paper, we focus on temporal information that can be used to predict system runtime operation. To evaluate our approach, an example of the proposed domain ontology for handover operation, as well as a reasoning rule over temporal relations in this domain-specific ontology, are given.

Keywords: system requirement specification, ERTMS/ETCS, temporal ontologies, domain ontologies

Procedia PDF Downloads 385

Authors: Yu Zhang, Pedro Desouza

Abstract:

Since big data has become substantially more accessible and manageable due to the development of powerful tools for dealing with unstructured data, people are eager to mine information from social media resources that could not be handled in the past. Sentiment analysis, as a novel branch of text mining, has in the last decade become increasingly important in marketing analysis, customer risk prediction and other fields. Scientists and researchers have undertaken significant work in creating and improving their sentiment models. In this paper, we present a concept of selecting appropriate classifiers based on the features and qualities of data sources by comparing the performances of five classifiers with three popular social media data sources: Twitter, Amazon Customer Reviews, and Movie Reviews. We introduced a couple of innovative models that outperform traditional sentiment classifiers for these data sources, and provide insights on how to further improve the predictive power of sentiment analysis. The modelling and testing work was done in R and Greenplum in-database analytic tools.

Keywords: sentiment analysis, social media, Twitter, Amazon, data mining, machine learning, text mining

Procedia PDF Downloads 325

Authors: A. Er-Raki, D. Hartmann, J. P. Belaud, S. Negny

Abstract:

This paper has a double purpose: firstly, a literature review of the life cycle analysis (LCA) and secondly a comparison between conventional (static) LCA and multi-level dynamic LCA on the following items: (i) inventories evolution with time (ii) temporal evolution of the databases. The first part of the paper summarizes the state of the art of the static LCA approach. The different static LCA limits have been identified and especially the non-consideration of the spatial and temporal evolution in the inventory, for the characterization factors (FCs) and into the databases. Then a description of the different levels of integration of the notion of temporality in life cycle analysis studies was made. In the second part, the dynamic inventory has been evaluated firstly for a single nuclear plant and secondly for the entire French nuclear power fleet by taking into account the construction durations of all the plants. In addition, the databases have been adapted by integrating the temporal variability of the French energy mix. Several iterations were used to converge towards the real environmental impact of the energy mix. Another adaptation of the databases to take into account the temporal evolution of the market data of the raw material was made. An identification of the energy mix of the time studied was based on an extrapolation of the production reference values of each means of production. An application to the construction of the French nuclear power plants from 1971 to 2000 has been performed, in which a dynamic inventory of raw material has been evaluated. Then the impacts were characterized by the ILCD 2011 characterization method. In order to compare with a purely static approach, a static impact assessment was made with the V 3.4 Ecoinvent data sheets without adaptation and a static inventory considering that all the power stations would have been built at the same time. Finally, a comparison between static and dynamic LCA approaches was set up to determine the gap between them for each of the two levels of integration. The results were analyzed to identify the contribution of the evolving nuclear power fleet construction to the total environmental impacts of the French energy mix during the same period. An equivalent strategy using a dynamic approach will further be applied to identify the environmental impacts that different scenarios of the energy transition could bring, allowing to choose the best energy mix from an environmental viewpoint.

Keywords: LCA, static, dynamic, inventory, construction, nuclear energy, energy mix, energy transition

Procedia PDF Downloads 80

Authors: Jiahao Tian, Michael D. Porter

Abstract:

Law enforcement agencies are tasked with crime prevention and crime reduction under limited resources. Having an accurate temporal estimate of the crime rate would be valuable to achieve such a goal. However, estimation is usually complicated by the interval-censored nature of crime data. We cast the problem of intensity estimation as a Poisson regression using an EM algorithm to estimate the parameters. Two special penalties are added that provide smoothness over the time of day and day of the week. This approach presented here provides accurate intensity estimates and can also uncover day-of-week clusters that share the same intensity patterns. Anticipating where and when crimes might occur is a key element to successful policing strategies. However, this task is complicated by the presence of interval-censored data. The censored data refers to the type of data that the event time is only known to lie within an interval instead of being observed exactly. This type of data is prevailing in the field of criminology because of the absence of victims for certain types of crime. Despite its importance, the research in temporal analysis of crime has lagged behind the spatial component. Inspired by the success of solving crime-related problems with a statistical approach, we propose a statistical model for the temporal intensity estimation of crime with censored data. The model is built on Poisson regression and has special penalty terms added to the likelihood. An EM algorithm was derived to obtain maximum likelihood estimates, and the resulting model shows superior performance to the competing model. Our research is in line with the smart policing initiative (SPI) proposed by the Bureau Justice of Assistance (BJA) as an effort to support law enforcement agencies in building evidence-based, data-driven law enforcement tactics. The goal is to identify strategic approaches that are effective in crime prevention and reduction. In our case, we allow agencies to deploy their resources for a relatively short period of time to achieve the maximum level of crime reduction. By analyzing a particular area within cities where data are available, our proposed approach could not only provide an accurate estimate of intensities for the time unit considered but a time-variation crime incidence pattern. Both will be helpful in the allocation of limited resources by either improving the existing patrol plan with the understanding of the discovery of the day of week cluster or supporting extra resources available.

Keywords: cluster detection, EM algorithm, interval censoring, intensity estimation

Procedia PDF Downloads 41

Authors: E. Fathallahi Aghdam, V. Hosseini

Abstract:

Environmental pollution is not limited to a specific region or country; that is why sustainable development, as a necessary process for improvement, pays attention to issues such as destruction of natural resources, degradation of biological system, global pollution, and climate change in the world, especially in the developing countries. According to the World Health Organization, as a developing city, Tehran (capital of Iran) is one of the most polluted cities in the world in terms of air pollution. In this study, three pollutants including particulate matter less than 10 microns, nitrogen oxides, and sulfur dioxide were evaluated in Tehran using data mining techniques and through Crisp approach. The data from 21 air pollution measuring stations in different areas of Tehran were collected from 1999 to 2013. Commercial softwares Clementine was selected for this study. Tehran was divided into distinct clusters in terms of the mentioned pollutants using the software. As a data mining technique, clustering is usually used as a prologue for other analyses, therefore, the similarity of clusters was evaluated in this study through analyzing local conditions, traffic behavior, and industrial activities. In fact, the results of this research can support decision-making system, help managers improve the performance and decision making, and assist in urban studies.

Keywords: data mining, clustering, air pollution, crisp approach

Procedia PDF Downloads 401

Authors: Živa Ravnikar, Alfonso Bahillo Martinez, Barbara Goličnik Marušić

Abstract:

Climate change mitigation has been formally adopted and announced by countries over the globe, where cities are targeting carbon neutrality through various more or less successful, systematic, and fragmentary actions. The article is based on the fact that environmental conditions affect human comfort and the usage of space. Urban planning can, with its sustainable solutions, not only support climate mitigation in terms of a planet reduction of global warming but as well enabling natural processes that in the immediate vicinity produce environmental conditions that encourage people to walk or cycle. However, the article draws attention to the importance of integrating climate consideration into urban planning, where detailed environmental data play a key role, enabling urban planners to improve or monitor environmental conditions on cycle paths. In a practical aspect, this paper tests a particular ICT tool, a prototype used for environmental data. Data gathering was performed along the cycling lanes in Ljubljana (Slovenia), where the main objective was to assess the tool's data applicable value within the planning of comfortable cycling lanes. The results suggest that such transportable devices for in-situ measurements can help a researcher interpret detailed environmental information, characterized by fine granularity and precise data spatial and temporal resolution. Data can be interpreted within human comfort zones, where graphical representation is in the form of a map, enabling the link of the environmental conditions with a spatial context. The paper also provides preliminary results in terms of the potential of such tools for identifying the correlations between environmental conditions and different spatial settings, which can help urban planners to prioritize interventions in places. The paper contributes to multidisciplinary approaches as it demonstrates the usefulness of such fine-grained data for better consideration of microclimatology in urban planning, which is a prerequisite for creating climate-comfortable cycling lanes promoting active mobility.

Keywords: information and communication technology tools, urban planning, human comfort, microclimate, cycling lanes

Procedia PDF Downloads 96

Authors: Kelemewerk Destalem, Joongjae Cho, Jaeseong Lee, Ju H. Park, Joonhyuk Yoo

Abstract:

Background subtraction and temporal difference are often used for moving object detection in video. Both approaches are computationally simple and easy to be deployed in real-time image processing. However, while the background subtraction is highly sensitive to dynamic background and illumination changes, the temporal difference approach is poor at extracting relevant pixels of the moving object and at detecting the stopped or slowly moving objects in the scene. In this paper, we propose a moving object detection scheme based on adaptive background subtraction and temporal difference exploiting dynamic background updates. The proposed technique consists of a histogram equalization, a linear combination of background and temporal difference, followed by the novel frame-based and pixel-based background updating techniques. Finally, morphological operations are applied to the output images. Experimental results show that the proposed algorithm can solve the drawbacks of both background subtraction and temporal difference methods and can provide better performance than that of each method.

Keywords: background subtraction, background updating, real time, light weight algorithm, temporal difference

Procedia PDF Downloads 313

Authors: Diego Rodrigues, Marcelo Lisboa, Elismar Batista, Marcos Dias

Abstract:

Based on data on child labor, this work arises questions about how to understand and locate the factors that make up the child labor rates, and which properties are important to analyze these cases. Using data mining techniques to discover valid patterns on Brazilian social databases were evaluated data of child labor in the State of Tocantins (located north of Brazil with a territory of 277000 km2 and comprises 139 counties). This work aims to detect factors that are deterministic for the practice of child labor and their relationships with financial indicators, educational, regional and social, generating information that is not explicit in the government database, thus enabling better monitoring and updating policies for this purpose.

Keywords: social data, government decision making, association of social data, data mining

Procedia PDF Downloads 336

Authors: Maria Christofi, George Plastiras, Rafaella Elia, Vaggelis Tsiourtis, Theocharis Theocharides, Miltiadis Katsaros

Abstract:

The rapidly expanding urban areas of the world constitute a challenge of how we need to make the transition to "the next urbanization", which will be defined by new analytical tools and new sources of data. This paper is about the production of a spatial application, the ‘FUMapp’, where space and its initiative will be available literally, in meters, but also abstractly, at a sensed level. While existing spatial applications typically focus on illustrations of the urban infrastructure, the suggested application goes beyond the existing: It investigates how our environment's perception adapts to the alterations of the built environment through a dataset construction of biophysical measurements (eye-tracking, heart beating), and physical metrics (spatial characteristics, size of stimuli, rhythm of mobility). It explores the intersections between architecture, cognition, and computing where future design can be improved and identifies the flexibility and livability of the ‘available space’ of specific examined urban paths.

Keywords: biophysical data, flexibility of urban, livability, next urbanization, spatial application

Procedia PDF Downloads 109

Authors: Akshay Agrawal, Anand K. Srivastava

Abstract:

The increasing amount of XML datasets available to casual users increases the necessity of investigating techniques to extract knowledge from these data. Data mining is widely applied in the database research area in order to extract frequent correlations of values from both structured and semi-structured datasets. The increasing availability of heterogeneous XML sources has raised a number of issues concerning how to represent and manage these semi structured data. In recent years due to the importance of managing these resources and extracting knowledge from them, lots of methods have been proposed in order to represent and cluster them in different ways.

Keywords: XML, similarity measure, clustering, cluster quality, semantic clustering

Procedia PDF Downloads 346

Authors: Anatoly D. Pluzhnikov, Elena N. Pribludova, Alexander G. Ryndyk

Abstract:

In conjunction with the problem of the target selection on a clutter background, the analysis of the scanning rate influence on the spatial-temporal signal structure, the generalized multivariate correlation function and the quality of the resolution with the increase pulse repetition frequency is made. The possibility of the object space-distance resolution, which is conditioned by the range-to-angle conversion with an increased scanning rate, is substantiated. The calculations for the real cylindrical array at high scanning rate are presented. The high scanning rate let to get the signal to noise improvement of the order of 10 dB for the space-time signal processing.

Keywords: antenna pattern, array, signal processing, spatial resolution

Procedia PDF Downloads 154

Authors: Taha SamadSoltani, Peyman Rezaei Hachesu, Marjan GhaziSaeedi, Maryam Zolnoori

Abstract:

Introduction: Data mining defined as a process to find patterns and relationships along data in the database to build predictive models. Application of data mining extended in vast sectors such as the healthcare services. Medical data mining aims to solve real-world problems in the diagnosis and treatment of diseases. This method applies various techniques and algorithms which have different accuracy and precision. The purpose of this study was to apply knowledge discovery and data mining techniques for the diagnosis of asthma based on patient symptoms and history. Method: Data mining includes several steps and decisions should be made by the user which starts by creation of an understanding of the scope and application of previous knowledge in this area and identifying KD process from the point of view of the stakeholders and finished by acting on discovered knowledge using knowledge conducting, integrating knowledge with other systems and knowledge documenting and reporting.in this study a stepwise methodology followed to achieve a logical outcome. Results: Sensitivity, Specifity and Accuracy of KNN, SVM, Naïve bayes, NN, Classification tree and CN2 algorithms and related similar studies was evaluated and ROC curves were plotted to show the performance of the system. Conclusion: The results show that we can accurately diagnose asthma, approximately ninety percent, based on the demographical and clinical data. The study also showed that the methods based on pattern discovery and data mining have a higher sensitivity compared to expert and knowledge-based systems. On the other hand, medical guidelines and evidence-based medicine should be base of diagnostics methods, therefore recommended to machine learning algorithms used in combination with knowledge-based algorithms.

Keywords: asthma, datamining, classification, machine learning

Procedia PDF Downloads 422

Authors: Reza Mohammadzadeh

Abstract:

The major challenges in geotechnical engineering in underground spaces arise from uncertainties and different probabilities. The collection, collation, and collaboration of existing data to incorporate them in analysis and design for given prospect evaluation would be a reliable, practical problem solving method under uncertainty. Machine learning (ML) is a subfield of artificial intelligence in statistical science which applies different techniques (e.g., Regression, neural networks, support vector machines, decision trees, random forests, genetic programming, etc.) on data to automatically learn and improve from them without being explicitly programmed and make decisions and predictions. In this paper, a conceptual database schema of geotechnical risks in underground coal mining based on a cloud system architecture has been designed. A new approach of risk assessment using a three-dimensional risk matrix supported by the level of knowledge (LoK) has been proposed in this model. Subsequently, the model workflow methodology stages have been described. In order to train data and LoK models deployment, an ML platform has been implemented. IBM Watson Studio, as a leading data science tool and data-driven cloud integration ML platform, is employed in this study. As a Use case, a data set of geotechnical hazards and risk assessment in underground coal mining were prepared to demonstrate the performance of the model, and accordingly, the results have been outlined.

Keywords: data model, geotechnical risks, machine learning, underground coal mining

Procedia PDF Downloads 242

Authors: Lubabatu Sada Sodangi

Abstract:

The rapid growth in exchange and accessibility of information via the internet makes many organisations acquire data on their own operation. The aim of data mining is to analyse the different behaviour of a dataset using observation. Although, the subset of the dataset being analysed may not display all the behaviours and relationships of the entire data and, therefore, may not represent other parts that exist in the dataset. There is a range of techniques used in data mining to determine the hidden or unknown information in datasets. In this paper, the performance of two algorithms Chi-Square Automatic Interaction Detection (CHAID) and multilayer perceptron (MLP) would be matched using an Adult dataset to find out the percentage of an/the adults that earn > 50k and those that earn <= 50k per year. The two algorithms were studied and compared using IBM SPSS statistics software. The result for CHAID shows that the most important predictors are relationship and education. The algorithm shows that those are married (husband) and have qualification: Bachelor, Masters, Doctorate or Prof-school whose their age is > 41<57 earn > 50k. Also, multilayer perceptron displays marital status and capital gain as the most important predictors of the income. It also shows that individuals that their capital gain is less than 6,849 and are single, separated or widow, earn <= 50K, whereas individuals with their capital gain is > 6,849, work > 35 hrs/wk, and > 27yrs their income will be > 50k. By comparing the two algorithms, it is observed that both algorithms are reliable but there is strong reliability in CHAID which clearly shows that relation and education contribute to the prediction as displayed in the data visualisation.

Keywords: data mining, CHAID, multi-layer perceptron, SPSS, Adult dataset

Procedia PDF Downloads 355

Authors: Kwan Hee Han

Abstract:

External environment of enterprise is rapidly changing majorly by global competition, cost reduction pressures, and new technology. In these situations, production scheduling function plays a critical role to meet customer requirements and to attain the goal of operational efficiency. It deals with short-term decision making in the production process of the whole supply chain. The major task of production scheduling is to seek a balance between customer orders and limited resources. In manufacturing companies, this task is so difficult because it should efficiently utilize resource capacity under the careful consideration of many interacting constraints. At present, many computerized software solutions have been utilized in many enterprises to generate a realistic production schedule to overcome the complexity of schedule generation. However, most production scheduling systems do not provide sufficient information about the validity of the generated schedule except limited statistics. Process mining only recently emerged as a sub-discipline of both data mining and business process management. Process mining techniques enable the useful analysis of a wide variety of processes such as process discovery, conformance checking, and bottleneck analysis. In this study, the performance of generated production schedule is evaluated by mining event log data of production scheduling software system by using the process mining techniques since every software system generates event logs for the further use such as security investigation, auditing and error bugging. An application of process mining approach is proposed for the validation of the goodness of production schedule generated by scheduling software systems in this study. By using process mining techniques, major evaluation criteria such as utilization of workstation, existence of bottleneck workstations, critical process route patterns, and work load balance of each machine over time are measured, and finally, the goodness of production schedule is evaluated. By using the proposed process mining approach for evaluating the performance of generated production schedule, the quality of production schedule of manufacturing enterprises can be improved.

Keywords: data mining, event log, process mining, production scheduling

Procedia PDF Downloads 238

Authors: Sanjay Kumar Srivastava, Anu Rani Sharma, Kamna Sachdeva

Abstract:

Every year, fog formation over the Indo-Gangetic Plains (IGPs) of Indian region during the winter months of December and January is believed to create numerous hazards, inconvenience, and economic loss to the inhabitants of this densely populated region of Indian subcontinent. The aim of the paper is to analyze the spatial and temporal variability of winter fog over IGPs. Long term ground observations of visibility and other meteorological parameters (1971-2010) have been analyzed to understand the formation of fog phenomena and its relevance during the peak winter months of January and December over IGP of India. In order to examine the temporal variability, time series and trend analysis were carried out by using the Mann-Kendall Statistical test. Trend analysis performed by using the Mann-Kendall test, accepts the alternate hypothesis with 95% confidence level indicating that there exists a trend. Kendall tau’s statistics showed that there exists a positive correlation between time series and fog frequency. Further, the Theil and Sen’s median slope estimate showed that the magnitude of trend is positive. Magnitude is higher during January compared to December for the entire IGP except in December when it is high over the western IGP. Decade wise time series analysis revealed that there has been continuous increase in fog days. The net overall increase of 99 % was observed over IGP in last four decades. Diurnal variability and average daily persistence were computed by using descriptive statistical techniques. Geo-statistical analysis of fog was carried out to understand the spatial variability of fog. Geo-statistical analysis of fog revealed that IGP is a high fog prone zone with fog occurrence frequency of more than 66% days during the study period. Diurnal variability indicates the peak occurrence of fog is between 06:00 and 10:00 local time and average daily fog persistence extends to 5 to 7 hours during the peak winter season. The results would offer a new perspective to take proactive measures in reducing the irreparable damage that could be caused due to changing trends of fog.

Keywords: fog, climatology, Mann-Kendall test, trend analysis, spatial variability, temporal variability, visibility

Procedia PDF Downloads 214

Authors: Andrzej Wałęga, Marta Cebulska, Agnieszka Ziernicka-Wojtaszek, Wojciech Młocek, Agnieszka Wałęga, Tommaso Caloiero

Abstract:

Drought is one of the natural phenomena influencing many aspects of human activities like food production, agriculture, industry, and the ecological conditions of the environment. In the area of the Polish Carpathians, there are periods with a deficit of rainwater and an increasing frequency in dry months, especially in the cold half of the year. The aim of this work is a spatial and temporal analysis of drought, expressed as SPI in a heterogenous area of the Polish Carpathian and of the highland Region in the Central part of Europe based on long-term precipitation data. Also, to our best knowledge, for the first time in this work, drought characteristics analyzed via the SPI were discussed based on the atmospheric circulation calendar. The study region is the Upper Vistula Basin, located in the southern and south-eastern part of Poland. In this work, monthly precipitation from 56 rainfall stations was analysed from 1961 to 2022. The 3-, 6-, 9-, and 12-month Standardized Precipitation Index (SPI) were used as indicators of meteorological drought. For the 3-month SPI, the main climatic mechanisms determining extreme droughts were defined based on the calendar of synoptic circulations. The Mann-Kendall test was used to detect the trend of extreme droughts. Statistically significant trends of SPI were observed on 52.7% of all analyzed stations, and in most cases, a positive trend was observed. Statistically significant trends were more frequently observed in stations located in the western part of the analyzed region. Long-term droughts, represented by the 12-month SPI, occurred in all stations but not in all years. Short-term droughts (3-month SPI) were most frequent in the winter season, 6 and 9-month SPI in winter and spring, and 12-month SPI in winter and autumn, respectively. The spatial distribution of drought was highly diverse. The most intensive drought occurred in 1984, with the 6-month SPI covering 98% of the analyzed region and the 9 and 12-month SPI covering 90% of the entire region. Droughts exhibit a seasonal pattern, with a dominant 10-year periodicity for all analyzed variants of SPI. Additionally, Fourier analysis revealed a 2-year periodicity for the 3-, 6-, and 9-month SPI and a 31-year periodicity for the 12-month SPI. The results provide insights into the typical climatic conditions in Poland, with strong seasonality in precipitation. The study highlighted that short-term extreme droughts, represented by the 3-month SPI, are often caused by anticyclonic situations with high-pressure wedges Ka and Wa, and anticyclonic West as observed in 52.3% of cases. These findings are crucial for understanding the spatial and temporal variability of short and long-term extreme droughts in Central Europe, particularly for the agriculture sector dominant in the northern part of the analyzed region, where drought frequency is highest.

Keywords: atmospheric circulation, drought, precipitation, SPI, the Upper Vistula Basin

Procedia PDF Downloads 42

Authors: Ashish Jaiswal, Ashwin Ramesh Babu, Mohammad Zaki Zadeh, Fillia Makedon, Glenn Wylie

Abstract:

Functional magnetic resonance imaging (fMRI) is a neuroimaging technique that records neural activations in the brain by capturing the blood oxygen level in different regions based on the task performed by a subject. Given fMRI data, the problem of predicting the state of cognitive fatigue in a person has not been investigated to its full extent. This paper proposes tackling this issue as a multi-class classification problem by dividing the state of cognitive fatigue into six different levels, ranging from no-fatigue to extreme fatigue conditions. We built a spatio-temporal model that uses convolutional neural networks (CNN) for spatial feature extraction and a long short-term memory (LSTM) network for temporal modeling of 4D fMRI scans. We also applied a self-supervised method called MoCo (Momentum Contrast) to pre-train our model on a public dataset BOLD5000 and fine-tuned it on our labeled dataset to predict cognitive fatigue. Our novel dataset contains fMRI scans from Traumatic Brain Injury (TBI) patients and healthy controls (HCs) while performing a series of N-back cognitive tasks. This method establishes a state-of-the-art technique to analyze cognitive fatigue from fMRI data and beats previous approaches to solve this problem.

Keywords: fMRI, brain imaging, deep learning, self-supervised learning, contrastive learning, cognitive fatigue

Procedia PDF Downloads 161

Authors: Trupti Chavan, Ramachandra Guda, Kameshwar Rao

Abstract:

The lack of data is a pain problem in medical image analysis using a convolutional neural network (CNN). This work uses various spatial transformation techniques to address the medical image augmentation issue for knee detection and localization using an enhanced single shot detector (SSD) network. The spatial transforms like a negative, histogram equalization, power law, sharpening, averaging, gaussian blurring, etc. help to generate more samples, serve as pre-processing methods, and highlight the features of interest. The experimentation is done on the OpenKnee dataset which is a collection of knee images from the openly available online sources. The CNN called enhanced single shot detector (SSD) is utilized for the detection and localization of the knee joint from a given X-ray image. It is an enhanced version of the famous SSD network and is modified in such a way that it will reduce the number of prediction boxes at the output side. It consists of a classification network (VGGNET) and an auxiliary detection network. The performance is measured in mean average precision (mAP), and 99.96% mAP is achieved using the proposed enhanced SSD with spatial transformations. It is also seen that the localization boundary is comparatively more refined and closer to the ground truth in spatial augmentation and gives better detection and localization of knee joints.

Keywords: data augmentation, enhanced SSD, knee detection and localization, medical image analysis, openKnee, Spatial transformations

Procedia PDF Downloads 129

Authors: Sean Paulsen, Michael Casey

Abstract:

In this work we present a self-supervised pretraining framework for transformers on functional Magnetic Resonance Imaging (fMRI) data. First, we pretrain our architecture on two self-supervised tasks simultaneously to teach the model a general understanding of the temporal and spatial dynamics of human auditory cortex during music listening. Our pretraining results are the first to suggest a synergistic effect of multitask training on fMRI data. Second, we finetune the pretrained models and train additional fresh models on a supervised fMRI classification task. We observe significantly improved accuracy on held-out runs with the finetuned models, which demonstrates the ability of our pretraining tasks to facilitate transfer learning. This work contributes to the growing body of literature on transformer architectures for pretraining and transfer learning with fMRI data, and serves as a proof of concept for our pretraining tasks and multitask pretraining on fMRI data.

Keywords: transfer learning, fMRI, self-supervised, brain decoding, transformer, multitask training

Procedia PDF Downloads 60

Authors: Moschos Vogiatzis, K. Perakis

Abstract:

Spatial-explicit and up-to-date land use/land cover information is fundamental for spatial planning, land management, sustainable development, and sound decision-making. In the last decade, many satellite-derived land cover products at different spatial, spectral, and temporal resolutions have been developed, such as the European Copernicus Land Cover product. However, more efficient and detailed information for land use/land cover is required at the regional or local scale. A typical Mediterranean basin with a complex landscape comprised of various forest types, crops, artificial surfaces, and wetlands was selected to test and develop our approach. In this study, we investigate the improvement of Copernicus Land Cover product (CLC2018) using Landsat 8 and Sentinel-2 pixel-based classification based on all available existing geospatial data (Forest Maps, LPIS, Natura2000 habitats, cadastral parcels, etc.). We examined and compared the performance of the Random Forest classifier for land use/land cover mapping. In total, 10 land use/land cover categories were recognized in Landsat 8 and 11 in Sentinel-2A. A comparison of the overall classification accuracies for 2018 shows that Landsat 8 classification accuracy was slightly higher than Sentinel-2A (82,99% vs. 80,30%). We concluded that the main land use/land cover types of CLC2018, even within a heterogeneous area, can be successfully mapped and updated according to CLC nomenclature. Future research should be oriented toward integrating spatiotemporal information from seasonal bands and spectral indexes in the classification process.

Keywords: classification, land use/land cover, mapping, random forest

Procedia PDF Downloads 98

Authors: Katalin Bodor, Zsolt Bodor, Robert Szep

Abstract:

The particulate matter (PM) smaller than 2.5 μm are less studied due to the limited availability of PM₂.₅, and less information is available on the health effects attributable to PM₁₀ in Central-Eastern Europe. The objective of the current study was to assess the human health risk and characterize the spatial and temporal variation of PM₂.₅ and PM₁₀ in eight Romanian regions between the 2009-2018 and. The PM concentrations showed high variability over time and spatial distribution. The highest concentration was detected in the Bucharest region in the winter period, and the lowest was detected in West. The relative risk caused by the PM₁₀ for all-cause mortality varied between 1.017 (B) and 1.025 (W), with an average 1.020. The results demonstrate a positive relative risk of cardiopulmonary and lung cancer disease due to exposure to PM₂.₅ on the national average 1.26 ( ± 0.023) and 1.42 ( ± 0.037), respectively.

Keywords: PM₂.₅, PM₁₀, relative risk, health effect

Procedia PDF Downloads 135

Authors: Lin Li, P. G. R. N. I. Pussella

Abstract:

When representing spatial data and their attributes on different types of maps, the scale plays a key role in the process of map generalization. The process is consisted with two main operators such as selection and omission. Once some data were selected, they would undergo of several geometrical changing processes such as elimination, simplification, smoothing, exaggeration, displacement, aggregation and size reduction. As a result of these operations at different levels of data, the geometry of the spatial features such as length, sinuosity, orientation, perimeter and area would be altered. This would be worst in the case of preparation of small scale maps, since the cartographer has not enough space to represent all the features on the map. What the GIS users do is when they wanted to analyze a set of spatial data; they retrieve a data set and does the analysis part without considering very important characteristics such as the scale, the purpose of the map and the degree of generalization. Further, the GIS users use and compare different maps with different degrees of generalization. Sometimes, GIS users are going beyond the scale of the source map using zoom in facility and violate the basic cartographic rule 'it is not suitable to create a larger scale map using a smaller scale map'. In the study, the effect of map generalization for GIS analysis would be discussed as the main objective. It was used three digital maps with different scales such as 1:10000, 1:50000 and 1:250000 which were prepared by the Survey Department of Sri Lanka, the National Mapping Agency of Sri Lanka. It was used common features which were on above three maps and an overlay analysis was done by repeating the data with different combinations. Road data, River data and Land use data sets were used for the study. A simple model, to find the best place for a wild life park, was used to identify the effects. The results show remarkable effects on different degrees of generalization processes. It can see that different locations with different geometries were received as the outputs from this analysis. The study suggests that there should be reasonable methods to overcome this effect. It can be recommended that, as a solution, it would be very reasonable to take all the data sets into a common scale and do the analysis part.

Keywords: generalization, GIS, scales, spatial analysis

Procedia PDF Downloads 305

Authors: A. T. Kuda, J. J. Dayya, A. Jimoh

Abstract:

This paper investigates the fault detection and Isolation technique of measurement data sets from a three tank system using analytical model-based temporal redundancy which is based on residual generation using parity equations/space approach. It further briefly outlines other approaches of model-based residual generation. The basic idea of parity space residual generation in temporal redundancy is dynamic relationship between sensor outputs and actuator inputs (input-output model). These residuals where then used to detect whether or not the system is faulty and indicate the location of the fault when it is faulty. The method obtains good results by detecting and isolating faults from the considered data sets measurements generated from the system.

Keywords: fault detection, fault isolation, disturbing influences, system failure, parity equation/relation, structured parity equations

Procedia PDF Downloads 270