Search results for: text mining.

Authors: Wang Yang

Abstract:

Shenzhen is a modern city of China's reform and opening-up policy, the development of urban morphology has been established on the administration of the Chinese government. This city`s planning paradigm is primarily affected by the spatial structure and human behavior. The subjective urban agglomeration center is divided into several groups and centers. In comparisons of this effect, the city development law has better to be neglected. With the continuous development of the internet, extensive data technology has been introduced in China. Data mining and data analysis has become important tools in municipal research. Data mining has been utilized to improve data cleaning such as receiving business data, traffic data and population data. Prior to data mining, government data were collected by traditional means, then were analyzed using city-relationship research, delaying the timeliness of urban development, especially for the contemporary city. Data update speed is very fast and based on the Internet. The city's point of interest (POI) in the excavation serves as data source affecting the city design, while satellite remote sensing is used as a reference object, city analysis is conducted in both directions, the administrative paradigm of government is broken and urban research is restored. Therefore, the use of data mining in urban analysis is very important. The satellite remote sensing data of the Shenzhen city in July 2018 were measured by the satellite Modis sensor and can be utilized to perform land surface temperature inversion, and analyze city heat island distribution of Shenzhen. This article acquired and classified the data from Shenzhen by using Data crawler technology. Data of Shenzhen heat island and interest points were simulated and analyzed in the GIS platform to discover the main features of functional equivalent distribution influence. Shenzhen is located in the east-west area of China. The city’s main streets are also determined according to the direction of city development. Therefore, it is determined that the functional area of the city is also distributed in the east-west direction. The urban heat island can express the heat map according to the functional urban area. Regional POI has correspondence. The research result clearly explains that the distribution of the urban heat island and the distribution of urban POIs are one-to-one correspondence. Urban heat island is primarily influenced by the properties of the underlying surface, avoiding the impact of urban climate. Using urban POIs as analysis object, the distribution of municipal POIs and population aggregation are closely connected, so that the distribution of the population corresponded with the distribution of the urban heat island.

Keywords: POI, satellite remote sensing, the population distribution, urban heat island thermal map.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 931

Authors: Pablo Zoghbi-Manrique-de-Lara, Miguel A. Suárez-Acosta

Abstract:

The goal of the present paper is to model two classic lines of research in which employees starred, organizational justice and citizenship behavior (OCB), but that have never been studied together when targeting customers. The suggestion is made that a hotel’s fair treatment (in terms of distributive, procedural, and interactional justice) toward customers will be appreciated by the employees, who will reciprocate in kind by favoring the hotel with increased customer-oriented behaviors (COBs). Data were collected from 204 employees at eight upscale hotels in the Canary Islands (Spain). Unlike in the case of perceptions of distributive justice, results of structural equation modeling demonstrate that employees substantively react to interactional and procedural justice toward guests by engaging in customer-oriented behaviors (COBs). The findings offer new reasons why employees decide to engage in COBs, and they highlight potentially beneficial effects of fair treatment toward guests bring to hospitality through promoting COBs.

Keywords: Hotel guests’ (mis) treatment, customer-oriented behaviors, employee citizenship, organizational justice, third-party observers, third-party intervention.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2404

Authors: Ileladewa Adeoye Abiodun, Cheng Wai Khuen

Abstract:

Multi-Agent Systems (MAS) emerged in the pursuit to improve our standard of living, and hence can manifest complex human behaviors such as communication, decision making, negotiation and self-organization. The Social Network Services (SNSs) have attracted millions of users, many of whom have integrated these sites into their daily practices. The domains of MAS and SNS have lots of similarities such as architecture, features and functions. Exploring social network users- behavior through multiagent model is therefore our research focus, in order to generate more accurate and meaningful information to SNS users. An application of MAS is the e-Auction and e-Rental services of the Universiti Cyber AgenT(UniCAT), a Social Network for students in Universiti Tunku Abdul Rahman (UTAR), Kampar, Malaysia, built around the Belief- Desire-Intention (BDI) model. However, in spite of the various advantages of the BDI model, it has also been discovered to have some shortcomings. This paper therefore proposes a multi-agent framework utilizing a modified BDI model- Belief-Desire-Intention in Dynamic and Uncertain Situations (BDIDUS), using UniCAT system as a case study.

Keywords: Distributed Data Mining, Multi-Agent Systems, Preference-Based, SNS.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1503

Authors: Kyi Pyar Zaw, Zin Mar Kyu

Abstract:

Character recognition is the process of converting a text image file into editable and searchable text file. Feature Extraction is the heart of any character recognition system. The character recognition rate may be low or high depending on the extracted features. In the proposed paper, 25 features for one character are used in character recognition. Basically, there are three steps of character recognition such as character segmentation, feature extraction and classification. In segmentation step, horizontal cropping method is used for line segmentation and vertical cropping method is used for character segmentation. In the Feature extraction step, features are extracted in two ways. The first way is that the 8 features are extracted from the entire input character using eight direction chain code frequency extraction. The second way is that the input character is divided into 16 blocks. For each block, although 8 feature values are obtained through eight-direction chain code frequency extraction method, we define the sum of these 8 feature values as a feature for one block. Therefore, 16 features are extracted from that 16 blocks in the second way. We use the number of holes feature to cluster the similar characters. We can recognize the almost Myanmar common characters with various font sizes by using these features. All these 25 features are used in both training part and testing part. In the classification step, the characters are classified by matching the all features of input character with already trained features of characters.

Keywords: Chain code frequency, character recognition, feature extraction, features matching, segmentation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 755

Authors: S. Sarumathi, N. Shanthi, M. Sharmila

Abstract:

Over the past epoch a rampant amount of work has been done in the data clustering research under the unsupervised learning technique in Data mining. Furthermore several algorithms and methods have been proposed focusing on clustering different data types, representation of cluster models, and accuracy rates of the clusters. However no single clustering algorithm proves to be the most efficient in providing best results. Accordingly in order to find the solution to this issue a new technique, called Cluster ensemble method was bloomed. This cluster ensemble is a good alternative approach for facing the cluster analysis problem. The main hope of the cluster ensemble is to merge different clustering solutions in such a way to achieve accuracy and to improve the quality of individual data clustering. Due to the substantial and unremitting development of new methods in the sphere of data mining and also the incessant interest in inventing new algorithms, makes obligatory to scrutinize a critical analysis of the existing techniques and the future novelty. This paper exposes the comparative study of different cluster ensemble methods along with their features, systematic working process and the average accuracy and error rates of each ensemble methods. Consequently this speculative and comprehensive analysis will be very useful for the community of clustering practitioners and also helps in deciding the most suitable one to rectify the problem in hand.

Keywords: Clustering, Cluster Ensemble methods, Co-association matrix, Consensus function, Median partition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2606

Authors: Hamid R. S. Mojaveri, Seyed S. Mousavi, Mojtaba Heydar, Ahmad Aminian

Abstract:

The aim of this paper is to present a methodology in three steps to forecast supply chain demand. In first step, various data mining techniques are applied in order to prepare data for entering into forecasting models. In second step, the modeling step, an artificial neural network and support vector machine is presented after defining Mean Absolute Percentage Error index for measuring error. The structure of artificial neural network is selected based on previous researchers' results and in this article the accuracy of network is increased by using sensitivity analysis. The best forecast for classical forecasting methods (Moving Average, Exponential Smoothing, and Exponential Smoothing with Trend) is resulted based on prepared data and this forecast is compared with result of support vector machine and proposed artificial neural network. The results show that artificial neural network can forecast more precisely in comparison with other methods. Finally, forecasting methods' stability is analyzed by using raw data and even the effectiveness of clustering analysis is measured.

Keywords: Artificial Neural Networks (ANN), bullwhip effect, demand forecasting, Support Vector Machine (SVM).

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2011

Authors: M. Bassoui, M. Ferfra, M. Chraygane, M. Ould Ahmedou, N. Elghazal, A. Belhaiba

Abstract:

Currently, the High voltage power supply for microwave generators with one magnetron uses a single-phase transformer with magnetic shunt. To contribute in the development of technological innovation in industry of manufacturing of power supplies of magnetrons for microwaves, ovens for domestic or industrial use, this original work treats the optimization of a new three-phase high voltage power supply for industrial microwaves generators with N magnetrons by phase (Treated case N=1), from its modeling with Matlab-Simulink. The design of this power supply uses three π quadruple models equivalents of new three-phase transformer with magnetic shunt of each phase. Every one supplies at its output a voltage doubler cell composed of a capacitor and a diode that in its output supplies only one magnetron.  In this work we will define a strategy that aims to reduce the volume of the transformer and the weight and cost of the entire system of the high voltage power supply, while respecting the conditions recommended by the manufacturer, concerning the current flowing in each magnetron: (Imax <1.2 A, IAv ≈ 300 mA).

 

Keywords: Optimization, Three-phase transformer, Modeling, power supply, magnetrons, Matlab Simulink, High Voltage

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2806

Authors: Seyyed Yasser Hashemi, Khalil Monfaredi

Abstract:

Automatic transformation of paper documents into electronic documents requires document segmentation at the first stage. However, some parameters restrictions such as variations in character font sizes, different text line spacing, and also not uniform document layout structures altogether have made it difficult to design a general-purpose document layout analysis algorithm for many years. Thus in most previously reported methods it is inevitable to include these parameters. This problem becomes excessively acute and severe, especially in Persian/Arabic documents. Since the Persian/Arabic scripts differ considerably from the English scripts, most of the proposed methods for the English scripts do not render good results for the Persian scripts. In this paper, we present a novel parameter-free method for segmenting the Persian/Arabic document images which also works well for English scripts. This method segments the document image into maximal homogeneous regions and identifies them as texts and non-texts based on a pyramidal image structure. In other words the proposed method is capable of document segmentation without considering the character font sizes, text line spacing, and document layout structures. This algorithm is examined for 150 Arabic/Persian and English documents and document segmentation process are done successfully for 96 percent of documents.

Keywords: Persian/Arabic document, document segmentation, Pyramidal Image Structure, skew detection and correction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1765

Authors: Matthias Dehmer, Frank Emmert Streib, Alexander Mehler, Jürgen Kilian, Max Mühlhauser

Abstract:

Due to the tremendous amount of information provided by the World Wide Web (WWW) developing methods for mining the structure of web-based documents is of considerable interest. In this paper we present a similarity measure for graphs representing web-based hypertext structures. Our similarity measure is mainly based on a novel representation of a graph as linear integer strings, whose components represent structural properties of the graph. The similarity of two graphs is then defined as the optimal alignment of the underlying property strings. In this paper we apply the well known technique of sequence alignments for solving a novel and challenging problem: Measuring the structural similarity of generalized trees. In other words: We first transform our graphs considered as high dimensional objects in linear structures. Then we derive similarity values from the alignments of the property strings in order to measure the structural similarity of generalized trees. Hence, we transform a graph similarity problem to a string similarity problem for developing a efficient graph similarity measure. We demonstrate that our similarity measure captures important structural information by applying it to two different test sets consisting of graphs representing web-based document structures.

Keywords: Graph similarity, hierarchical and directed graphs, hypertext, generalized trees, web structure mining.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1893

Authors: Siddeeq Y. Ameen, Mohammed K. Yousif

Abstract:

Cooperative communication systems are considered to be a promising technology to improve the system capacity, reliability and performances over fading wireless channels. Cooperative relaying system with a single antenna will be able to reach the advantages of multiple antenna communication systems. It is ideally suitable for the distributed communication systems; the relays can cooperate and form virtual MIMO systems. Thus the paper will aim to investigate the possible enhancement of cooperated system using decode and forward protocol. On the decode and forward an attempt to cancel or at least reduce the interference instead of increasing the SNR values is achieved. The latter can be achieved via the use group of relays depending on the channel status from source to relay and relay to destination respectively.

In the proposed system, the transmission time has been divided into two phases to be used by the decode and forward protocol. The first phase has been allocated for the source to transmit its data whereas the relays and destination nodes are in receiving mode. On the other hand, the second phase is allocated for the first and second groups of relay nodes to relay the data to the destination node. Simulations results have shown an improvement in performance is achieved compared to the conventional decode and forward in terms of BER and transmission rate.

Keywords: Cooperative systems, decode and forward, interference cancellation, virtual MIMO.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3725

Authors: Rhoann Kerh, Chen-Fu Chien, Kuo-Yi Lin

Abstract:

In the era of rapidly increasing notebook market, consumer electronics manufacturers are facing a highly dynamic and competitive environment. In particular, the product appearance is the first part for user to distinguish the product from the product of other brands. Notebook product should differ in its appearance to engage users and contribute to the user experience (UX). The UX evaluates various product concepts to find the design for user needs; in addition, help the designer to further understand the product appearance preference of different market segment. However, few studies have been done for exploring the relationship between consumer background and the reaction of product appearance. This study aims to propose a data mining framework to capture the user’s information and the important relation between product appearance factors. The proposed framework consists of problem definition and structuring, data preparation, rules generation, and results evaluation and interpretation. An empirical study has been done in Taiwan that recruited 168 subjects from different background to experience the appearance performance of 11 different portable computers. The results assist the designers to develop product strategies based on the characteristics of consumers and the product concept that related to the UX, which help to launch the products to the right customers and increase the market shares. The results have shown the practical feasibility of the proposed framework.

Keywords: Consumers Decision Making, Product Design, Rough Set Theory, User Experience.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3512

Authors: Apichaya Kaewuthai

Abstract:

To study the meaning of Muslim name in order to analyze the underlining value and identity from first year to forth year Muslim students at Prince of Songkla University, Hatyai Campus. The questionnaires are employed as a main analytical tool to acquire the names from 80 Muslim students in four study years. The meanings of obtained names are subsequently analyzed and summarized base upon related documents to uncover the beneath value. The study reveals that name of male is derived from the name of prophet; Nabi Muhammad, merit, dignity, origins, leadership and the faith in Islam. For female, on the other hand, their names are related to virtue and beauty, cleanliness and peace, hope and flowers which comply with their characteristics. One of the reasons contribute to the principle of naming is the regulation of Ministry of Culture which states that the name should represent one’s nature and characters. The given name reflects value and identity of Muslim which can be classified into three categories including 1) Value related to belief in Islam 2) value related to relationship among families and relatives 3) value about relationship with nature and environment. All the above mentioned reflect Muslim value and identity vividly.    The name of Muslim students allows the researcher to perceive the perspective, belief and value in giving the name of Thai Muslim. Besides, it reveals social condition and their culture. It can also be the fundamental of studying the meaning of name in other races.

Keywords: The naming, Thai Muslim.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1298

Authors: Jiqing Han, Rongchun Gao

Abstract:

One major source of performance decline in speaker recognition system is channel mismatch between training and testing. This paper focuses on improving channel robustness of speaker recognition system in two aspects of channel compensation technique and channel robust features. The system is text-independent speaker identification system based on two-stage recognition. In the aspect of channel compensation technique, this paper applies MAP (Maximum A Posterior Probability) channel compensation technique, which was used in speech recognition, to speaker recognition system. In the aspect of channel robust features, this paper introduces pitch-dependent features and pitch-dependent speaker model for the second stage recognition. Based on the first stage recognition to testing speech using GMM (Gaussian Mixture Model), the system uses GMM scores to decide if it needs to be recognized again. If it needs to, the system selects a few speakers from all of the speakers who participate in the first stage recognition for the second stage recognition. For each selected speaker, the system obtains 3 pitch-dependent results from his pitch-dependent speaker model, and then uses ANN (Artificial Neural Network) to unite the 3 pitch-dependent results and 1 GMM score for getting a fused result. The system makes the second stage recognition based on these fused results. The experiments show that the correct rate of two-stage recognition system based on MAP channel compensation technique and pitch-dependent features is 41.7% better than the baseline system for closed-set test.

Keywords: Channel Compensation, Channel Robustness, MAP, Speaker Identification

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1546

Authors: Josiel Delgadillo, Johnson Kinyua, Charles Mutigwe

Abstract:

The purpose of sentiment analysis is to determine the sentiment strength (e.g., positive, negative, neutral) from a textual source for good decision-making. Natural Language Processing (NLP) in domains such as financial markets requires knowledge of domain ontology, and pre-trained language models, such as BERT, have made significant breakthroughs in various NLP tasks by training on large-scale un-labeled generic corpora such as Wikipedia. However, sentiment analysis is a strong domain-dependent task. The rapid growth of social media has given users a platform to share their experiences and views about products, services, and processes, including financial markets. StockTwits and Twitter are social networks that allow the public to express their sentiments in real time. Hence, leveraging the success of unsupervised pre-training and a large amount of financial text available on social media platforms could potentially benefit a wide range of financial applications. This work is focused on sentiment analysis using social media text on platforms such as StockTwits and Twitter. To meet this need, SkyBERT, a domain-specific language model pre-trained and fine-tuned on financial corpora, has been developed. The results show that SkyBERT outperforms current state-of-the-art models in financial sentiment analysis. Extensive experimental results demonstrate the effectiveness and robustness of SkyBERT.

Keywords: BERT, financial markets, Twitter, sentiment analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 725

Authors: T. H. Derdzyan, K. A. Ghazaryan, G. A. Gevorgyan

Abstract:

Beta-glucosidase, chitinase, leucine-aminopeptidase, acid phosphomonoesterase and acetate-esterase enzyme activities in the soils under the impact of metallurgical industrial activity in Lori marz (district) were investigated. The results of the study showed that the activities of the investigated enzymes in the soils decreased with increasing distance from the Shamlugh copper mine, the Chochkan tailings storage facility and the ore transportation road. Statistical analysis revealed that the activities of the enzymes were positively correlated (significant) to each other according to the observation sites which indicated that enzyme activities were affected by the same anthropogenic factor. The investigations showed that the soils were polluted with heavy metals (Cu, Pb, As, Co, Ni, Zn) due to copper mining activity in this territory. The results of Pearson correlation analysis revealed a significant negative correlation between heavy metal pollution degree (Nemerow integrated pollution index) and soil enzyme activity. All of this indicated that copper mining activity in this territory causing the heavy metal pollution of the soils resulted in the inhabitation of the activities of the enzymes which are considered as biological catalysts to decompose organic materials and facilitate the cycling of nutrients.

Keywords: Armenia, metallurgical industrial activity, heavy metal pollutionl, soil enzyme activity.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2570

Authors: Dawei Wang, Rujing Wang, Ying Li, Baozi Wei

Abstract:

FAQ system can make user find answer to the problem that puzzles them. But now the research on Chinese FAQ system is still on the theoretical stage. This paper presents an approach to semantic inference for FAQ mining. To enhance the efficiency, a small pool of the candidate question-answering pairs retrieved from the system for the follow-up work according to the concept of the agriculture domain extracted from user input .Input queries or questions are converted into four parts, the question word segment (QWS), the verb segment (VS), the concept of agricultural areas segment (CS), the auxiliary segment (AS). A semantic matching method is presented to estimate the similarity between the semantic segments of the query and the questions in the pool of the candidate. A thesaurus constructed from the HowNet, a Chinese knowledge base, is adopted for word similarity measure in the matcher. The questions are classified into eleven intension categories using predefined question stemming keywords. For FAQ mining, given a query, the question part and answer part in an FAQ question-answer pair is matched with the input query, respectively. Finally, the probabilities estimated from these two parts are integrated and used to choose the most likely answer for the input query. These approaches are experimented on an agriculture FAQ system. Experimental results indicate that the proposed approach outperformed the FAQ-Finder system in agriculture FAQ retrieval.

Keywords: FAQ, Semantic Inference, Ontology.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1380

Authors: A. M. John-Otumu, M. M. Rahman, O. C. Nwokonkwo, M. C. Onuoha

Abstract:

Online social media networks have long served as a primary arena for group conversations, gossip, text-based information sharing and distribution. The use of natural language processing techniques for text classification and unbiased decision making has not been far-fetched. Proper classification of these textual information in a given context has also been very difficult. As a result, a systematic review was conducted from previous literature on sentiment classification and AI-based techniques. The study was done in order to gain a better understanding of the process of designing and developing a robust and more accurate sentiment classifier that could correctly classify social media textual information of a given context between hate speech and inverted compliments with a high level of accuracy using the knowledge gain from the evaluation of different artificial intelligence techniques reviewed. The study evaluated over 250 articles from digital sources like ACM digital library, Google Scholar, and IEEE Xplore; and whittled down the number of research to 52 articles. Findings revealed that deep learning approaches such as Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Bidirectional Encoder Representations from Transformer (BERT), and Long Short-Term Memory (LSTM) outperformed various machine learning techniques in terms of performance accuracy. A large dataset is also required to develop a robust sentiment classifier. Results also revealed that data can be obtained from places like Twitter, movie reviews, Kaggle, Stanford Sentiment Treebank (SST), and SemEval Task4 based on the required domain. The hybrid deep learning techniques like CNN+LSTM, CNN+ Gated Recurrent Unit (GRU), CNN+BERT outperformed single deep learning techniques and machine learning techniques. Python programming language outperformed Java programming language in terms of development simplicity and AI-based library functionalities. Finally, the study recommended the findings obtained for building robust sentiment classifier in the future.

Keywords: Artificial Intelligence, Natural Language Processing, Sentiment Analysis, Social Network, Text.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 595

Authors: Yunseok Noh, Chang-Uk Kwak, Sun-Joong Kim, Seong-Bae Park

Abstract:

Scripts are one of the basic text resources to understand broadcasting contents. Topic modeling is the method to get the summary of the broadcasting contents from its scripts. Generally, scripts represent contents descriptively with directions and speeches, and provide scene segments that can be seen as semantic units. Therefore, a script can be topic modeled by treating a scene segment as a document. Because scene segments consist of speeches mainly, however, relatively small co-occurrences among words in the scene segments are observed. This causes inevitably the bad quality of topics by statistical learning method. To tackle this problem, we propose a method to improve topic quality with additional word co-occurrence information obtained using scene similarities. The main idea of improving topic quality is that the information that two or more texts are topically related can be useful to learn high quality of topics. In addition, more accurate topical representations lead to get information more accurate whether two texts are related or not. In this paper, we regard two scene segments are related if their topical similarity is high enough. We also consider that words are co-occurred if they are in topically related scene segments together. By iteratively inferring topics and determining semantically neighborhood scene segments, we draw a topic space represents broadcasting contents well. In the experiments, we showed the proposed method generates a higher quality of topics from Korean drama scripts than the baselines.

Keywords: Broadcasting contents, generalized P´olya urn model, scripts, text similarity, topic model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1818

Authors: Addin Osman, Anwar Ali Yahya, Mohammed Basit Kamal

Abstract:

Datasets or collections are becoming important assets by themselves and now they can be accepted as a primary intellectual output of a research. The quality and usage of the datasets depend mainly on the context under which they have been collected, processed, analyzed, validated, and interpreted. This paper aims to present a collection of program educational objectives mapped to student’s outcomes collected from self-study reports prepared by 32 engineering programs accredited by ABET. The manual mapping (classification) of this data is a notoriously tedious, time consuming process. In addition, it requires experts in the area, which are mostly not available. It has been shown the operational settings under which the collection has been produced. The collection has been cleansed, preprocessed, some features have been selected and preliminary exploratory data analysis has been performed so as to illustrate the properties and usefulness of the collection. At the end, the collection has been benchmarked using nine of the most widely used supervised multiclass classification techniques (Binary Relevance, Label Powerset, Classifier Chains, Pruned Sets, Random k-label sets, Ensemble of Classifier Chains, Ensemble of Pruned Sets, Multi-Label k-Nearest Neighbors and Back-Propagation Multi-Label Learning). The techniques have been compared to each other using five well-known measurements (Accuracy, Hamming Loss, Micro-F, Macro-F, and Macro-F). The Ensemble of Classifier Chains and Ensemble of Pruned Sets have achieved encouraging performance compared to other experimented multi-label classification methods. The Classifier Chains method has shown the worst performance. To recap, the benchmark has achieved promising results by utilizing preliminary exploratory data analysis performed on the collection, proposing new trends for research and providing a baseline for future studies.

Keywords: Benchmark collection, program educational objectives, student outcomes, ABET, Accreditation, machine learning, supervised multiclass classification, text mining.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 837

Authors: P. S. Hiremath, Siddu P. Algur

Abstract:

With the explosive growth of information sources available on the World Wide Web, it has become increasingly difficult to identify the relevant pieces of information, since web pages are often cluttered with irrelevant content like advertisements, navigation-panels, copyright notices etc., surrounding the main content of the web page. Hence, tools for the mining of data regions, data records and data items need to be developed in order to provide value-added services. Currently available automatic techniques to mine data regions from web pages are still unsatisfactory because of their poor performance and tag-dependence. In this paper a novel method to extract data items from the web pages automatically is proposed. It comprises of two steps: (1) Identification and Extraction of the data regions based on visual clues information. (2) Identification of data records and extraction of data items from a data region. For step1, a novel and more effective method is proposed based on visual clues, which finds the data regions formed by all types of tags using visual clues. For step2 a more effective method namely, Extraction of Data Items from web Pages (EDIP), is adopted to mine data items. The EDIP technique is a list-based approach in which the list is a linear data structure. The proposed technique is able to mine the non-contiguous data records and can correctly identify data regions, irrespective of the type of tag in which it is bound. Our experimental results show that the proposed technique performs better than the existing techniques.

Keywords: Web data records, web data regions, web mining.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1902

Authors: Bremananth R., Veerabadran C. S., Andy W. H. Khong

Abstract:

Automatic reading of handwritten cheque is a computationally complex process and it plays an important role in financial risk management. Machine vision and learning provide a viable solution to this problem. Research effort has mostly been focused on recognizing diverse pitches of cheques and demand drafts with an identical outline. However most of these methods employ templatematching to localize the pitches and such schemes could potentially fail when applied to different types of outline maintained by the bank. In this paper, the so-called outline problem is resolved by a cheque information tree (CIT), which generalizes the localizing method to extract active-region-of-entities. In addition, the weight based density plot (WBDP) is performed to isolate text entities and read complete pitches. Recognition is based on texture features using neural classifiers. Legal amount is subsequently recognized by both texture and perceptual features. A post-processing phase is invoked to detect the incorrect readings by Type-2 grammar using the Turing machine. The performance of the proposed system was evaluated using cheque and demand drafts of 22 different banks. The test data consists of a collection of 1540 leafs obtained from 10 different account holders from each bank. Results show that this approach can easily be deployed without significant design amendments.

Keywords: Cheque reading, Connectivity checking, Text localization, Texture analysis, Turing machine, Signature verification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1658

Authors: Zahid O. Alibrahim, Craig D. Williams, Clive L. Roberts

Abstract:

The study area (Ecton mining area) is located in the southern part of the Peak District in Derbyshire, England. It is bounded by the River Manifold from the west. This area has been mined for a long period. As a result, huge amounts of potentially toxic metals were released into the surrounding area and are most likely to be a significant source of heavy metal contamination to the local soil, water and vegetation. In order to appraise the potential heavy metal pollution in this area, 37 topsoil samples (5-20 cm depth) were collected and analysed for their total content of Cu, Pb, Zn, Mn, Cr, Ni and V using ICP (Inductively Coupled Plasma) optical emission spectroscopy. Multivariate Geospatial analyses using the GIS technique were utilised to draw geochemical maps of the metals of interest over the study area. A few hotspot points, areas of elevated concentrations of metals, were specified, which are presumed to be the results of anthropogenic activities. In addition, the soil’s environmental quality was evaluated by calculating the Mullers’ Geoaccumulation index (I geo), which suggests that the degree of contamination of the investigated heavy metals has the following trend: Pb > Zn > Cu > Mn > Ni = Cr = V. Furthermore, the potential ecological risk, using the enrichment factor (EF), was also specified. On the basis of the calculated amount or the EF, the levels of pollution for the studied metals in the study area have the following order: Pb>Zn>Cu>Cr>V>Ni>Mn.

Keywords: Heavy metals, GIS, multivariate analysis, geoaccumulation index, enrichment factor.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1245

Authors: Gaetano Zazzaro, Angelo Martone, Roberto V. Montaquila, Luigi Pavone

Abstract:

Seizure is the main factor that affects the quality of life of epileptic patients. The diagnosis of epilepsy, and hence the identification of epileptogenic zone, is commonly made by using continuous Electroencephalogram (EEG) signal monitoring. Seizure identification on EEG signals is made manually by epileptologists and this process is usually very long and error prone. The aim of this paper is to describe an automated method able to detect seizures in EEG signals, using knowledge discovery in database process and data mining methods and algorithms, which can support physicians during the seizure detection process. Our detection method is based on Artificial Neural Network classifier, trained by applying the multilayer perceptron algorithm, and by using a software application, called Training Builder that has been developed for the massive extraction of features from EEG signals. This tool is able to cover all the data preparation steps ranging from signal processing to data analysis techniques, including the sliding window paradigm, the dimensionality reduction algorithms, information theory, and feature selection measures. The final model shows excellent performances, reaching an accuracy of over 99% during tests on data of a single patient retrieved from a publicly available EEG dataset.

Keywords: Artificial Neural Network, Data Mining, Electroencephalogram, Epilepsy, Feature Extraction, Seizure Detection, Signal Processing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1318

Authors: Zs. J. Becze, Á. Krivián, M. Sárvári

Abstract:

Hybrid selection and the application of hybrid specific production technologies are important in terms of the increase of the yield and crop safety of maize. The main explanation for this is climate change, since weather extremes are going on and seem to accelerate in Hungary too.

The biological bases, the selection of appropriate hybrids will be of greater importance in the future. The issue of the adaptability of hybrids will be considerably appreciated. Its good agronomical traits and stress bearing against climatic factors and agrotechnical elements (e.g. different types of herbicides) will be important. There have been examples of 3-4 consecutive droughty years in the past decades, e.g. 1992-1993-1994 or 2009-2011-2012, which made the results of crop production critical. Irrigation cannot be the solution for the problem since currently only the 2% of the arable land is irrigated. Temperatures exceeding the multi-year average are characteristic mainly to the July and August in Hungary, which significantly increase the soil surface evaporation, thus further enhance water shortage. In terms of the yield and crop safety of maize, the weather of these two months is crucial, since the extreme high temperature in July decreases the viability of the pollen and the pistil of maize, decreases the extent of fertilization and makes grain-filling tardy. Consequently, yield and crop safety decrease.

Keywords: Abiotic factors, drought, nutrition content, yield.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1902

Authors: Kohtaroh Miyamoto

Abstract:

As enterprise computing becomes more and more complex, the costs and technical challenges of IT system maintenance and support are increasing rapidly. One popular approach to managing IT system maintenance is to prepare and use a FAQ (Frequently Asked Questions) system to manage and reuse systems knowledge. Such a FAQ system can help reduce the resolution time for each service incident ticket. However, there is a major problem where over time the knowledge in such FAQs tends to become outdated. Much of the knowledge captured in the FAQ requires periodic updates in response to new insights or new trends in the problems addressed in order to maintain its usefulness for problem resolution. These updates require a systematic approach to define the exact portion of the FAQ and its content. Therefore, we are working on a novel method to hierarchically structure the FAQ and automate the updates of its structure and content. We use structured information and the unstructured text information with the timelines of the information in the service incident tickets. We cluster the tickets by structured category information, by keywords, and by keyword modifiers for the unstructured text information. We also calculate an urgency score based on trends, resolution times, and priorities. We carefully studied the tickets of one of our projects over a 2.5-year time period. After the first 6 months we started to create FAQs and confirmed they improved the resolution times. We continued observing over the next 2 years to assess the ongoing effectiveness of our method for the automatic FAQ updates. We improved the ratio of tickets covered by the FAQ from 32.3% to 68.9% during this time. Also, the average time reduction of ticket resolution was between 31.6% and 43.9%. Subjective analysis showed more than 75% reported that the FAQ system was useful in reducing ticket resolution times.

Keywords: FAQ System, Resolution Time, Service Incident Tickets, IT System Maintenance.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2496

Authors: Mamta Garg

Abstract:

While compressing text files is useful, compressing still image files is almost a necessity. A typical image takes up much more storage than a typical text message and without compression images would be extremely clumsy to store and distribute. The amount of information required to store pictures on modern computers is quite large in relation to the amount of bandwidth commonly available to transmit them over the Internet and applications. Image compression addresses the problem of reducing the amount of data required to represent a digital image. Performance of any image compression method can be evaluated by measuring the root-mean-square-error & peak signal to noise ratio. The method of image compression that will be analyzed in this paper is based on the lossy JPEG image compression technique, the most popular compression technique for color images. JPEG compression is able to greatly reduce file size with minimal image degradation by throwing away the least “important" information. In JPEG, both color components are downsampled simultaneously, but in this paper we will compare the results when the compression is done by downsampling the single chroma part. In this paper we will demonstrate more compression ratio is achieved when the chrominance blue is downsampled as compared to downsampling the chrominance red in JPEG compression. But the peak signal to noise ratio is more when the chrominance red is downsampled as compared to downsampling the chrominance blue in JPEG compression. In particular we will use the hats.jpg as a demonstration of JPEG compression using low pass filter and demonstrate that the image is compressed with barely any visual differences with both methods.

Keywords: JPEG, Discrete Cosine Transform, Quantization, Color Space Conversion, Image Compression, Peak Signal to Noise Ratio & Compression Ratio.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1679

Authors: Mai Miyabe, Taku Fukushima, Takashi Yoshino, Aguri Shigeno

Abstract:

The need for multilingual communication in Japan has increased due to an increase in the number of foreigners in the country. When people communicate in their nonnative language, the differences in language prevent mutual understanding among the communicating individuals. In the medical field, communication between the hospital staff and patients is a serious problem. Currently, medical translators accompany patients to medical care facilities, and the demand for medical translators is increasing. However, medical translators cannot necessarily provide support, especially in cases in which round-the-clock support is required or in case of emergencies. The medical field has high expectations from information technology. Hence, a system that supports accurate multilingual communication is required. Despite recent advances in machine translation technology, it is very difficult to obtain highly accurate translations. We have developed a support system called M3 for multilingual medical reception. M3 provides support functions that aid foreign patients in the following respects: conversation, questionnaires, reception procedures, and hospital navigation; it also has a Q&A function. Users can operate M3 using a touch screen and receive text-based support. In addition, M3 uses accurate translation tools called parallel texts to facilitate reliable communication through conversations between the hospital staff and the patients. However, if there is no parallel text that expresses what users want to communicate, the users cannot communicate. In this study, we have developed a circulating support environment for multilingual medical communication using parallel texts. The proposed environment can circulate necessary parallel texts through the following procedure: (1) a user provides feedback about the necessary parallel texts, following which (2) these parallel texts are created and evaluated.

Keywords: multilingual medical communication, parallel texts.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1483

Authors: Sidharth Talan, Devendra Kumar Yadav, Yuvraj Singh Rajput, Subhajit Bhattacharjee

Abstract:

Mining industry is known for its appetite to spend sizeable capital on mine equipment. However, in the current scenario, the mining industry is challenged by daunting factors of non-uniform geological conditions, uneven ore grade, uncontrollable and volatile mineral commodity prices and the ever increasing quest to optimize the capital and operational costs. Thus, the role of equipment reliability and maintenance planning inherits a significant role in augmenting the equipment availability for the operation and in turn boosting the mine productivity. This paper presents the Risk Based Maintenance (RBM) planning conducted on mine loading equipment namely Load Haul Dumpers (LHDs) at Vedanta Resources Ltd subsidiary Hindustan Zinc Limited operated Sindesar Khurd Mines, an underground zinc and lead mine situated in Dariba, Rajasthan, India. The mining equipment at the location is maintained by the Original Equipment Manufacturers (OEMs) namely Sandvik and Atlas Copco, who carry out the maintenance and inspection operations for the equipment. Based on the downtime data extracted for the equipment fleet over the period of 6 months spanning from 1^st January 2017 until 30^th June 2017, it was revealed that significant contribution of three downtime issues related to namely Engine, Hydraulics, and Transmission to be common among all the loading equipment fleet and substantiated by Pareto Analysis. Further scrutiny through Bubble Matrix Analysis of the given factors revealed the major influence of selective factors namely Overheating, No Load Taken (NTL) issues, Gear Changing issues and Hose Puncture and leakage issues. Utilizing the equipment wise analysis of all the downtime factors obtained, spares consumed, and the alarm logs extracted from the machines, technical design changes in the equipment and pre shift critical alarms checklist were proposed for the equipment maintenance. The given analysis is beneficial to allow OEMs or mine management to focus on the critical issues hampering the reliability of mine equipment and design necessary maintenance strategies to mitigate them.

Keywords: Bubble matrix analysis, LHDs, OEMs, pareto chart analysis, spares consumption matrix, critical alarms checklist.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1092

Authors: Yuan-Jye Tseng, Ching-Yen Chen

Abstract:

In the design cycle, a main design task is to determine the external shape of the product. The external shape of a product is one of the key factors that can affect the customers’ preferences linking to the motivation to buy the product, especially in the case of a consumer electronic product such as a mobile phone. The relationship between the external shape and the customer preferences needs to be studied to enhance the customer’s purchase desire and action. In this research, a design for customer preferences model is developed for investigating the relationships between the external shape and the customer preferences of a product. In the first stage, the names of the geometric features are collected and evaluated from the data of the specified internet web pages using the developed text miner. The key geometric features can be determined if the number of occurrence on the web pages is relatively high. For each key geometric feature, the numerical values are explored using the text miner to collect the internet data from the web pages. In the second stage, a cluster analysis model is developed to evaluate the numerical values of the key geometric features to divide the external shapes into several groups. Several design suggestion cases can be proposed, for example, large model, mid-size model, and mini model, for designing a mobile phone. A customer preference index is developed by evaluating the numerical data of each of the key geometric features of the design suggestion cases. The design suggestion case with the top ranking of the customer preference index can be selected as the final design of the product. In this paper, an example product of a notebook computer is illustrated. It shows that the external shape of a product can be used to drive customer preferences. The presented design for customer preferences model is useful for determining a suitable external shape of the product to increase customer preferences.

Keywords: Cluster analysis, customer preferences, design evaluation, design for customer preferences, product design.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 779

Authors: Kamal K.Bharadwaj, Rekha Kandwal

Abstract:

An important structuring mechanism for knowledge bases is building clusters based on the content of their knowledge objects. The objects are clustered based on the principle of maximizing the intraclass similarity and minimizing the interclass similarity. Clustering can also facilitate taxonomy formation, that is, the organization of observations into a hierarchy of classes that group similar events together. Hierarchical representation allows us to easily manage the complexity of knowledge, to view the knowledge at different levels of details, and to focus our attention on the interesting aspects only. One of such efficient and easy to understand systems is Hierarchical Production rule (HPRs) system. A HPR, a standard production rule augmented with generality and specificity information, is of the following form Decision If < condition> Generality Specificity . HPRs systems are capable of handling taxonomical structures inherent in the knowledge about the real world. In this paper, a set of related HPRs is called a cluster and is represented by a HPR-tree. This paper discusses an algorithm based on cumulative learning scenario for dynamic structuring of clusters. The proposed scheme incrementally incorporates new knowledge into the set of clusters from the previous episodes and also maintains summary of clusters as Synopsis to be used in the future episodes. Examples are given to demonstrate the behaviour of the proposed scheme. The suggested incremental structuring of clusters would be useful in mining data streams.

Keywords: Cumulative learning, clustering, data mining, hierarchical production rules.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1439