Search results for: web usage mining

Authors: L. Chevez, A. Apaza, J. Rodriguez, R. Puga, H. Loro, Juan Z. Davalos

Abstract:

Virtual Dimension (VD) procedure is used to analyze Hyperspectral Image (HIS) treatment-data in order to estimate the abundance of mineral components of a mining sample. Hyperspectral images coming from reflectance spectra (NIR region) are pre-treated using Standard Normal Variance (SNV) and Minimum Noise Fraction (MNF) methodologies. The endmember components are identified by the Simplex Growing Algorithm (SVG) and after adjusted to the reflectance spectra of reference-databases using Simulated Annealing (SA) methodology. The obtained abundance of minerals of the sample studied is very near to the ones obtained using XRD with a total relative error of 2%.

Keywords: hyperspectral imaging, minimum noise fraction, MNF, simplex growing algorithm, SGA, standard normal variance, SNV, virtual dimension, XRD

Procedia PDF Downloads 150

Authors: Joshua N. Edokpayi, John O. Odiyo, Patience P. Shikwambana

Abstract:

Water is a very rare natural resource in South Africa. Ga-Selati River is used for both domestic and industrial purposes. This study was carried out in order to assess the quality of Ga-Selati River in a mining area of Limpopo Province-Phalaborwa. The pH, Electrical Conductivity (EC) and Total Dissolved Solids (TDS) were determined using a Crinson multimeter while turbidity was measured using a Labcon Turbidimeter. The concentrations of Al, Ca, Cd, Cr, Fe, K, Mg, Mn, Na and Pb were analysed in triplicate using a Varian 520 flame atomic absorption spectrometer (AAS) supplied by PerkinElmer, after acid digestion with nitric acid in a fume cupboard. The average pH of the river from eight different sampling sites was 8.00 and 9.38 in wet and dry season respectively. Higher EC values were determined in the dry season (138.7 mS/m) than in the wet season (96.93 mS/m). Similarly, TDS values were higher in dry (929.29 mg/L) than in the wet season (640.72 mg/L) season. These values exceeded the recommended guideline of South Africa Department of Water Affairs and Forestry (DWAF) for domestic water use (70 mS/m) and that of the World Health Organization (WHO) (600 mS/m), respectively. Turbidity varied between 1.78-5.20 and 0.95-2.37 NTU in both wet and dry seasons. Total hardness of 312.50 mg/L and 297.75 mg/L as the concentration of CaCO3 was computed for the river in both the wet and the dry seasons and the river water was categorised as very hard. Mean concentration of the metals studied in both the wet and the dry seasons are: Na (94.06 mg/L and 196.3 mg/L), K (11.79 mg/L and 13.62 mg/L), Ca (45.60 mg/L and 41.30 mg/L), Mg (48.41 mg/L and 44.71 mg/L), Al (0.31 mg/L and 0.38 mg/L), Cd (0.01 mg/L and 0.01 mg/L), Cr (0.02 mg/L and 0.09 mg/L), Pb (0.05 mg/L and 0.06 mg/L), Mn (0.31 mg/L and 0.11 mg/L) and Fe (0.76 mg/L and 0.69 mg/L). Results from this study reveal that most of the metals were present in concentrations higher than the recommended guidelines of DWAF and WHO for domestic use and the protection of aquatic life.

Keywords: contamination, mining activities, surface water, trace metals

Procedia PDF Downloads 305

Authors: O. S. Omorogiuwa, E. J. Omozusi

Abstract:

The monitoring of spectrum usage and signal identification, using cognitive radio, is done to identify frequencies that are vacant for reuse. It has been established that ‘internet of things’ device uses secondary frequency which is free, thereby facing the challenge of interference from other users, where some primary frequencies are not being utilised. The design was done by analysing a specific frequency spectrum, checking if all the frequency stations that range from 87.5-108 MHz are presently being used in Benin City, Edo State, Nigeria. From the results, it was noticed that by using Software Defined Radio/Simulink, we were able to identify vacant frequencies in the range of frequency under consideration. Also, we were able to use the significance of energy detection threshold to reuse this vacant frequency spectrum, when the cognitive radio displays a zero output (that is decision H0), meaning that the channel is unoccupied. Hence, the analysis was able to find the spectrum hole and identify how it can be reused.

Keywords: spectrum, interference, telecommunication, cognitive radio, frequency

Procedia PDF Downloads 216

Authors: Pichamon Chansuchai

Abstract:

The study of Thai consumer behavior toward buying goods on the Internet is a survey research. The five-level rating scale and open-ended questionnaire are applied for this research procedure, which has more than 400 random sampling of Thai people aged between 15-40 years old. The summary findings are: The analysis of respondents profile were female 55.3% and male 44.8% , 35.3% aged between 20-30 years old, had been employed 29.5% with average income up to 11,000 baht/month 50.2% and expenditure more than 11,000 baht per month 29.3%. The internet usage behavior of respondents mostly found that objectives of the internet usage are: 1) Communication 93.3% 2) the categories of websites usage was trading 42.8% 3) The marketing mix effected to trading behavior via internet which can be analyzed in term of marketing factor as following: Product focused on product quality was the most influenced factor with average value 4.75. The cheaper price than overview market was the most effect factor to internet shopping with mean value 4.53. The average value 4.67 of the available place that could reduce spending time for shopping. The effective promotion of the buy 1 get 1 was the stimulus factor for internet shopping with mean value 4.60. For hypothesis testing, the different sex has relationship with buying decision. It presented that male and female have vary purchasing decision via internet with value of significant difference 0.05. Furthermore, the variety occupations of respondents related to the use of selected type of website. It also found that the vary of personal occupation effected to the type of website selection dissimilar with value of significant difference 0.05.

Keywords: behavior, internet, consumer, goods

Procedia PDF Downloads 234

Authors: Chayaporn Kaensar

Abstract:

Recently, Job Recommender Systems have gained much attention in industries since they solve the problem of information overload on the recruiting website. Therefore, we proposed Extended Personalized Job System that has the capability of providing the appropriate jobs for job seeker and recommending some suitable information for them using Data Mining Techniques and Dynamic User Profile. On the other hands, company can also interact to the system for publishing and updating job information. This system have emerged and supported various platforms such as web application and android mobile application. In this paper, User profiles, Implicit User Action, User Feedback, and Clustering Techniques in WEKA libraries have gained attention and implemented for this application. In additions, open source tools like Yii Web Application Framework, Bootstrap Front End Framework and Android Mobile Technology were also applied.

Keywords: recommendation, user profile, data mining, web and mobile technology

Procedia PDF Downloads 308

Authors: Yujia Sun

Abstract:

Research on nominalizations in English can be traced back to at least the 1960s and even centered in the field nowadays. At the very beginning, the discussion was about the relationship between verbs and nouns, but then it moved to the distinct senses embodied in different forms of nominals, namely, various types of nominalizations. This paper tries to address the issue that how speakers perceive different forms of verbal nouns, and what might influence their perceptions. The data are collected through a self-designed questionnaire targeted at native speakers of American English, and the employment of the Corpus of Contemporary American English (COCA). The results show that semantic differences between different forms of nominals do play a role in people’s preference to certain form than another. But it still awaits more explorations to see how the frequency of usage is interrelates to this issue.

Keywords: corpus of contemporary American English, derived nominalization, frequency of usage, ing-formed nominalization

Procedia PDF Downloads 169

Authors: Kyung Bae Park, Sung Ho Ha

Abstract:

Online user-generated contents (UGC) significantly change the way customers behave (e.g., shop, travel), and a pressing need to handle the overwhelmingly plethora amount of various UGC is one of the paramount issues for management. However, a current approach (e.g., sentiment analysis) is often ineffective for leveraging textual information to detect the problems or issues that a certain management suffers from. In this paper, we employ text mining of Latent Dirichlet Allocation (LDA) on a popular online review site dedicated to complaint from users. We find that the employed LDA efficiently detects customer complaints, and a further inspection with the visualization technique is effective to categorize the problems or issues. As such, management can identify the issues at stake and prioritize them accordingly in a timely manner given the limited amount of resources. The findings provide managerial insights into how analytics on social media can help maintain and improve their reputation management. Our interdisciplinary approach also highlights several insights by applying machine learning techniques in marketing research domain. On a broader technical note, this paper illustrates the details of how to implement LDA in R program from a beginning (data collection in R) to an end (LDA analysis in R) since the instruction is still largely undocumented. In this regard, it will help lower the boundary for interdisciplinary researcher to conduct related research.

Keywords: latent dirichlet allocation, R program, text mining, topic model, user generated contents, visualization

Procedia PDF Downloads 179

Authors: Sokkhey Phauk, Takeo Okazaki

Abstract:

The challenging task in educational institutions is to maximize the high performance of students and minimize the failure rate of poor-performing students. An effective method to leverage this task is to know student learning patterns with highly influencing factors and get an early prediction of student learning outcomes at the timely stage for setting up policies for improvement. Educational data mining (EDM) is an emerging disciplinary field of data mining, statistics, and machine learning concerned with extracting useful knowledge and information for the sake of improvement and development in the education environment. The study is of this work is to propose techniques in EDM and integrate it into a web-based system for predicting poor-performing students. A comparative study of prediction models is conducted. Subsequently, high performing models are developed to get higher performance. The hybrid random forest (Hybrid RF) produces the most successful classification. For the context of intervention and improving the learning outcomes, a feature selection method MICHI, which is the combination of mutual information (MI) and chi-square (CHI) algorithms based on the ranked feature scores, is introduced to select a dominant feature set that improves the performance of prediction and uses the obtained dominant set as information for intervention. By using the proposed techniques of EDM, an academic performance prediction system (APPS) is subsequently developed for educational stockholders to get an early prediction of student learning outcomes for timely intervention. Experimental outcomes and evaluation surveys report the effectiveness and usefulness of the developed system. The system is used to help educational stakeholders and related individuals for intervening and improving student performance.

Keywords: academic performance prediction system, educational data mining, dominant factors, feature selection method, prediction model, student performance

Procedia PDF Downloads 97

Authors: Kisik Song, Kyuwoong Kim, Sungjoo Lee

Abstract:

Many global firms and corporations derive new technology and opportunity by identifying vacant technology from patent analysis. However, previous studies failed to focus on technologies that promised continuous growth in industrial fields. Most studies that derive new technology opportunities do not test practical effectiveness. Since previous studies depended on expert judgment, it became costly and time-consuming to evaluate new technologies based on patent analysis. Therefore, research suggests a quantitative and systematic approach to technology evaluation indicators by using patent data to and from customer communities. The first step involves collecting two types of data. The data is used to construct evaluation indicators and apply these indicators to the evaluation of new technologies. This type of data mining allows a new method of technology evaluation and better predictor of how new technologies are adopted.

Keywords: data mining, evaluating new technology, technology opportunity, patent analysis

Procedia PDF Downloads 363

Authors: Arif Armagan Gozutok, Alper Kule, Burak Tos, Selman Demirel

Abstract:

Wireless communication chain requires effective ways to keep throughput efficiency high while it suffers location-dependent, time-varying burst errors. Several techniques are developed in order to assure that the receiver recovers the transmitted information without errors. The most fundamental approaches are error checking and correction besides re-transmission of the non-acknowledged packets. In this paper, stop & wait (SAW) and chase combined (CC) hybrid automated repeat request (HARQ) protocols are compared and analyzed in terms of throughput and average delay for the usage of low earth orbit (LEO) mega-constellations case. Several assumptions and technological implementations are considered as well as usage of low-density parity check (LDPC) codes together with several constellation orbit configurations.

Keywords: HARQ, LEO, satellite constellation, throughput

Procedia PDF Downloads 133

Authors: P. Bharathiraja

Abstract:

Computer Aided decision making system is used to enhance diagnosis and prognosis of diseases and also to assist clinicians and junior doctors in clinical decision making. Medical Data used for decision making should be definite and consistent. Data Mining and soft computing techniques are used for cleaning the data and for incorporating human reasoning in decision making systems. Fuzzy rule based inference technique can be used for classification in order to incorporate human reasoning in the decision making process. In this work, missing values are imputed using the mean or mode of the attribute. The data are normalized using min-ma normalization to improve the design and efficiency of the fuzzy inference system. The fuzzy inference system is used to handle the uncertainties that exist in the medical data. Equal-width-partitioning is used to partition the attribute values into appropriate fuzzy intervals. Fuzzy rules are generated using Class Based Associative rule mining algorithm. The system is trained and tested using heart disease data set from the University of California at Irvine (UCI) Machine Learning Repository. The data was split using a hold out approach into training and testing data. From the experimental results it can be inferred that classification using fuzzy inference system performs better than trivial IF-THEN rule based classification approaches. Furthermore it is observed that the use of fuzzy logic and fuzzy inference mechanism handles uncertainty and also resembles human decision making. The system can be used in the absence of a clinical expert to assist junior doctors and clinicians in clinical decision making.

Keywords: decision making, data mining, normalization, fuzzy rule, classification

Procedia PDF Downloads 503

Authors: Jeong-Moh John Yahng, Angelika Na

Abstract:

Introduction: Increasing numbers of general surgical patients are being prescribed antiplatelet and anticoagulant medications (APAC) for various cardiovascular and cerebrovascular conditions. Surgical patients who are on APAC present a management challenge as bleeding risk needs to be balanced with thromboembolic risk. Although guidelines exist in regards to APAC management in elective surgery, there is a lack of guidelines in the emergency surgery setting. In this study we aim to characterise APAC usage in emergency general surgical patients admitted to a rural hospital. We also assess the impact of APAC usage on clinical management of these patients. Methods: Prospective study of emergency general surgical admissions at Northeast Health Wangaratta (Victoria) from 2 July to 25 Oct 2014. Questionnaire collected demographics data, admission diagnosis, APAC usage, anaesthesia techniques, operation types, transfusion requirement and morbidity / mortality data. Results: During the 4 month study, 118 patients were classified into two groups: non-APAC (n=96, 81%) and APAC (n=22, 19%). Patients in the APAC group were older compared to the non-APAC patients (mean age 72 vs 42 years old). Amongst patients younger than 60 years old, only 1% of them were on APAC. In contrast, 49% of patients older than 60 years old were on APAC (p<0.001). Patients who were admitted with a bleeding problem were more likely to be on APAC (p<0.05). 19% of emergency general surgery patients were on APAC. The majority (91%) of them were on antiplatelet medication, with two patients being on dual antiplatelet agents (aspirin + clopidogrel or ticagrelor). 15% of emergency general surgical patients requiring operations were on APAC. 11% of all laparotomies and 33% of gastroscopy for haematemesis/melaena patients were on APAC. Both of the patients operated for bleeding following surgery at another hospital were in the APAC group. In regards to impact on clinical management, 59% of APAC patients had their medications interrupted or ceased, on average by 3.5 days (range 1-13 days). 2 out of 75 operations were delayed due to APAC usage. There was no difference in the use of central venous or arterial line for increased monitoring (p=0.14) or in the use of warming blanket (Bair Hugger™) (p=0.94). Overall, transfusion rate was higher amongst APAC patients (14% vs 3%) (p 0.04). The recorded morbidity (n=2) and mortality (n=1) in this study were all in the APAC group. Discussion: Nineteen percent of emergency general surgical admissions and fifteen percent of operated patients were on APAC. The prevalence of APAC usage was higher in those aged sixty and above. General surgical patients who were admitted with a bleeding problem were more likely to be on APAC. Two patients who were operated for bleeding following surgery at another hospital were in the APAC group. Note that there was no patient in the non-APAC group who was admitted for post-operative bleeding. We observed two cases in which operation was delayed due to APAC usage. Transfusion, morbidity and mortality rate were higher in the APAC group. Conclusion: In this study, nineteen percent of emergency general surgical admissions were on APAC. The use of APAC is more prevalent in the older age group, particularly those aged sixty and above. Higher proportion of APAC compared to non-APAC patients were admitted and operated for bleeding problems. There is an urgent need for clinical guidelines regarding APAC management in emergency general surgical patients.

Keywords: antiplatelet, anticoagulants, emergency general surgery, rural general surgery, morbidity, mortality

Procedia PDF Downloads 127

Authors: Deeman Yousif Mahmood, Mohammed Abdullah Hussein

Abstract:

The goal of a network-based intrusion detection system is to classify activities of network traffics into two major categories: normal and attack (intrusive) activities. Nowadays, data mining and machine learning plays an important role in many sciences; including intrusion detection system (IDS) using both supervised and unsupervised techniques. However, one of the essential steps of data mining is feature selection that helps in improving the efficiency, performance and prediction rate of proposed approach. This paper applies unsupervised K-means clustering algorithm with information gain (IG) for feature selection and reduction to build a network intrusion detection system. For our experimental analysis, we have used the new NSL-KDD dataset, which is a modified dataset for KDDCup 1999 intrusion detection benchmark dataset. With a split of 60.0% for the training set and the remainder for the testing set, a 2 class classifications have been implemented (Normal, Attack). Weka framework which is a java based open source software consists of a collection of machine learning algorithms for data mining tasks has been used in the testing process. The experimental results show that the proposed approach is very accurate with low false positive rate and high true positive rate and it takes less learning time in comparison with using the full features of the dataset with the same algorithm.

Keywords: information gain (IG), intrusion detection system (IDS), k-means clustering, Weka

Procedia PDF Downloads 284

Authors: Atje Setiawan Abdullah, Budi Nurani Ruchjana, I. Gede Nyoman Mindra Jaya, Eddy Hermawan

Abstract:

Ethnoscience is used to see the culture with a scientific perspective, which may help to understand how people develop various forms of knowledge and belief, initially focusing on the ecology and history of the contributions that have been there. One of the areas studied in ethnoscience is etno-informatics, is the application of informatics in the culture. In this study the science of informatics used is data mining, a process to automatically extract knowledge from large databases, to obtain interesting patterns in order to obtain a knowledge. While the application of culture described by naming database village on the island of Java were obtained from Geographic Indonesia Information Agency (BIG), 2014. The purpose of this study is; first, to classify the naming of the village on the island of Java based on the structure of the word naming the village, including the prefix of the word, syllable contained, and complete word. Second to classify the meaning of naming the village based on specific categories, as well as its role in the community behavioral characteristics. Third, how to visualize the naming of the village to a map location, to see the similarity of naming villages in each province. In this research we have developed two theorems, i.e theorems area as a result of research studies have collected intersection naming villages in each province on the island of Java, and the composition of the wedge theorem sets the provinces in Java is used to view the peculiarities of a location study. The methodology in this study base on the method of Knowledge Discovery in Database (KDD) on data mining, the process includes preprocessing, data mining and post processing. The results showed that the Java community prioritizes merit in running his life, always working hard to achieve a more prosperous life, and love as well as water and environmental sustainment. Naming villages in each location adjacent province has a high degree of similarity, and influence each other. Cultural similarities in the province of Central Java, East Java and West Java-Banten have a high similarity, whereas in Jakarta-Yogyakarta has a low similarity. This research resulted in the cultural character of communities within the meaning of the naming of the village on the island of Java, this character is expected to serve as a guide in the behavior of people's daily life on the island of Java.

Keywords: ethnoscience, ethno-informatics, data mining, clustering, Java island culture

Procedia PDF Downloads 268

Authors: Minami Ito, Akihiro Iijima

Abstract:

On March 11, 2011, the Great East Japan Earthquake occurred off the coast of Sanriku, Japan. It is important to build a sustainable society through the reconstruction process rather than simply restoring the infrastructure. To compare the goals of reconstruction plans of quake-stricken municipalities, Japanese language morphological analysis was performed by using text mining techniques. Frequently-used nouns were sorted into four main categories of “life”, “disaster prevention”, “economy”, and “harmony with environment”. Because Soma City is affected by nuclear accident, sentences tagged to “harmony with environment” tended to be frequent compared to the other municipalities. Results from cluster analysis and principle component analysis clearly indicated that the local government reinforces the efforts to reduce risks from radiation exposure as a top priority.

Keywords: eco-friendly reconstruction, harmony with environment, decontamination, nuclear disaster

Procedia PDF Downloads 212

Authors: Mais Nijim, Rama Devi Chennuboyina, Waseem Al Aqqad

Abstract:

Advances in spatial and spectral resolution of satellite images have led to tremendous growth in large image databases. The data we acquire through satellites, radars and sensors consists of important geographical information that can be used for remote sensing applications such as region planning, disaster management. Spatial data classification and object recognition are important tasks for many applications. However, classifying objects and identifying them manually from images is a difficult task. Object recognition is often considered as a classification problem, this task can be performed using machine-learning techniques. Despite of many machine-learning algorithms, the classification is done using supervised classifiers such as Support Vector Machines (SVM) as the area of interest is known. We proposed a classification method, which considers neighboring pixels in a region for feature extraction and it evaluates classifications precisely according to neighboring classes for semantic interpretation of region of interest (ROI). A dataset has been created for training and testing purpose; we generated the attributes by considering pixel intensity values and mean values of reflectance. We demonstrated the benefits of using knowledge discovery and data-mining techniques, which can be on image data for accurate information extraction and classification from high spatial resolution remote sensing imagery.

Keywords: remote sensing, object recognition, classification, data mining, waterbody identification, feature extraction

Procedia PDF Downloads 326

Authors: Anshar Ajatasatru

Abstract:

The decline of coal prices over past years have been significantly increasing the awareness of effective mining operation. A viable step must be undertaken in becoming more cost competitive while striving for best mining practice especially at Melak Coal Mine in East Kalimantan, Indonesia. This paper aims to show how effective dozer push measurement method can be implemented as it is controlled by contract rate on the unit basis of USD ($) per bcm. The method emerges from an idea of daily dozer push activity that continually shifts the overburden until final target design by mine planning. Volume calculation is then performed by calculating volume of each time overburden is removed within determined distance using cut and fill method from a high precision GNSS system which is applied into dozer as a guidance to ensure the optimum result of overburden removal. Accumulation of daily to weekly dozer push volume is found 95 bcm which is multiplied by average sell rate of $ 0,95, thus the amount monthly revenue is $ 90,25. Furthermore, the payment mechanism is then based on push distance and push grade. The push distance interval will determine the rates that vary from $ 0,9 - $ 2,69 per bcm and are influenced by certain push slope grade from -25% until +25%. The amount payable rates for dozer push operation shall be specifically following currency adjustment and is to be added to the monthly overburden volume claim, therefore, the sell rate of overburden volume per bcm may fluctuate depends on the real time exchange rate of Jakarta Interbank Spot Dollar Rate (JISDOR). The result indicates that dozer push measurement can be one of the surface mining alternative since it has enabled to refine method of work, operating cost and productivity improvement apart from exposing risk of low rented equipment performance. In addition, payment mechanism of contract rate by dozer push operation scheduling will ultimately deliver clients by almost 45% cost reduction in the form of low and consistent cost.

Keywords: contract rate, cut-fill method, dozer push, overburden volume

Procedia PDF Downloads 301

Authors: Ahmet Akdemir, Güzide Karakuş, Leyla Polat

Abstract:

Aviation that has been arisen in accordance with flying request that is existing inside of people, has not only made life easier by making a great contribution to humanity; it has also accelerated globalization by reducing distances between countries. It is seen that the growth rate of aviation industry has reached the undreamed level when it is looked back on. Today, the last point in aviation is unmanned aerial vehicles that are self-ventilating and move in desired coordinates without any onboard pilot. For those vehicles, there are two different control systems are developed. In the first type of control, an unmanned aerial vehicle (UAV) moves according to instructions of a remote control. UAV that moves with a remote control is named as drone; it can be used personally. In the second one, there is a flight plan that is programmed and placed inside of UAV before flight. Recently, drones have started to be used in unimagined areas and utilize specific, important benefits for any industry. Within this framework, this study answers the question that is drone usage would be beneficial for businesses or not. To answer this question, applied basic methodologies are determining businesses using drone in the world, their purposes to use drone, and then, comparing their economy as before drone and after drone. In the end of this study, it is seen that many companies in different business areas use drone in logistics support, and it makes their work easier than before. This paper has contributed to academic literature about this subject, and it has introduced the benefits of drone usage for businesses. In addition, it has encouraged businesses that they keep pace with this technological age by following the developments about drones.

Keywords: aviation, drone, drone in business, unmanned aerial vehicle

Procedia PDF Downloads 241

Authors: Tae-Uk Yun, Pullip Chung, Kee-Young Kwahk, Hyunchul Ahn

Abstract:

Fake news is defined as the news articles that are intentionally and verifiably false, and could mislead readers. Spread of fake news may provoke anxiety, chaos, fear, or irrational decisions of the public. Thus, detecting fake news and preventing its spread has become very important issue in our society. However, due to the huge amount of fake news produced every day, it is almost impossible to identify it by a human. Under this context, researchers have tried to develop automated fake news detection using machine learning techniques over the past years. But, there have been no prior studies proposed an automated fake news detection method for Korean news to our best knowledge. In this study, we aim to detect Korean fake news using text mining and machine learning techniques. Our proposed method consists of two steps. In the first step, the news contents to be analyzed is convert to quantified values using various text mining techniques (topic modeling, TF-IDF, and so on). After that, in step 2, classifiers are trained using the values produced in step 1. As the classifiers, machine learning techniques such as logistic regression, backpropagation network, support vector machine, and deep neural network can be applied. To validate the effectiveness of the proposed method, we collected about 200 short Korean news from Seoul National University’s FactCheck. which provides with detailed analysis reports from 20 media outlets and links to source documents for each case. Using this dataset, we will identify which text features are important as well as which classifiers are effective in detecting Korean fake news.

Keywords: fake news detection, Korean news, machine learning, text mining

Procedia PDF Downloads 263

Authors: Aisyiyah Fauziah Rahmah

Abstract:

Generally, an urban city has a rapid growth, it has frequent a variety of problems, especially of convenience in public space usage. The density of population in urban areas and the high activity is also indicated as a cause of urban resident lifestyle for the worse in social relationships and allow for the stress. Streets and green space (parks) are the only public space in a residential area which is used as a place to build social activity, to meet and interact with the other housing dweller. The high level of activity and social interaction that occurs will affect the spatial arrangement. It can be effected the space structures in housing more complex. Ease in access to public space is the reason many dweller prefer doing social activities there. Hillier in Carmona et al (2003) explains that the pattern and intensity of movement of individuals is influenced by the configuration of space, even the space structure can be regarded as the single most influential determinant of movements in the space. Whyte in Zhang and Lawson (2009) also suggest some factors such as seats, trees, water and legibility of space encourage people to stay in public outdoor space. Furthermore this activities can attract more activities. Villa Bukit Tidar is a housing in Lowokwaru District which highest number of people in Malang City, so social activity is also high there. It has natural and recreational concept and provided with view of Malang City from heights. This potential is able to attract the people who live there to stay in public outdoor space and doing activities there. From this study we can find whether the ease of access to public space and visual satisfaction of Villa Bukit Tidar housing affect the usage of public space. This study was carried out by observing the streets pattern and plot pattern to know the configuration space of Villa Bukit Tidar housing through values of connectivity and integrity by resulting from space sintax analysis. Distributing questionnaires also carried out to determine the level of satisfaction and importance perception of visual condition in the public space in Villa Bukit Tidar housing through Important Performance Analysis (IPA). Results of this research indicated that the public spaces in Villa Bukit Tidar housing who has high connectivity and integrity is considered to be visually satisfied and it has a higher public space usage than has low connectivity and integrity are considered to be visually dissatisfied.

Keywords: configuration space, visual perception, social activities, public space usage

Procedia PDF Downloads 476

Authors: Ahmed I. Alutabi, Naghmeh Dezhabad, Sudhakar Ganti

Abstract:

Data centers have been growing in size and dema nd continuously in the last two decades. Planning for the deployment of resources has been shallow and always resorted to over-provisioning. Data center operators try to maximize the availability of their services by allocating multiple of the needed resources. One resource that has been wasted, with little thought, has been energy. In recent years, programmable resource allocation has paved the way to allow for more efficient and robust data centers. In this work, we examine the predictability of resource usage in a data center environment. We use a number of models that cover a wide spectrum of machine learning categories. Then we establish a framework to guarantee the client service level agreement (SLA). Our results show that using prediction can cut energy loss by up to 55%.

Keywords: machine learning, artificial intelligence, prediction, data center, resource allocation, green computing

Procedia PDF Downloads 99

Authors: Chong Zhang, Guoming Tang, Bin Ge, Jiuyang Tang

Abstract:

With the fast growing road traffic and increasingly severe traffic congestion, more and more citizens choose to use the public transportation for daily travelling. Meanwhile, the shared bike provides a convenient option for the first and last mile to the public transit. As of 2016, over one thousand cities around the world have deployed the bike-sharing system. The combination of these two transportations have stimulated the development of each other and made significant contribution to the reduction of carbon footprint. A lot of work has been done on mining the riding behaviors in various bike-sharing systems. Most of them, however, treated the bike-sharing system as an isolated system and thus their results provide little reference for the public transit construction and optimization. In this work, we treat the bike-sharing and public transit as a whole and investigate the customers’ bike-and-ride behaviors. Specifically, we develop a spatio-temporal traffic delivery model to study the riding patterns between the two transportation systems and explore the traffic characteristics (e.g., distributions of customer arrival/departure and traffic peak hours) from the time and space dimensions. During the model construction and evaluation, we make use of large open datasets from real-world bike-sharing systems (the CitiBike in New York, GoBike in San Francisco and BIXI in Montreal) along with corresponding public transit information. The developed two-dimension traffic model, as well as the mined bike-and-ride behaviors, can provide great help to the deployment of next-generation intelligent transportation systems.

Keywords: riding pattern mining, bike-sharing system, public transportation, bike-and-ride behavior

Procedia PDF Downloads 765

Authors: Reiner-Ace P. Mateo, Vince Paolo F. Obille

Abstract:

The traditional method of classifying the potential mineral resources requires a significant amount of time and money. In this paper, an alternative way to classify potential mineral resources with GIS application in Surigao del Sur. The three (3) analog map data inputs integrated to GIS are geologic map, topographic map, and land cover/vegetation map. The indicators used in the classification of potential nickel laterite integrated from the analog map data inputs are a geologic indicator, which is the presence of ultramafic rock from the geologic map; slope indicator and the presence of plateau edges from the topographic map; areas of forest land, grassland, and shrublands from the land cover/vegetation map. The potential mineral of the area was classified from low up to very high potential. The produced mineral potential classification map of Surigao del Sur has an estimated 4.63% low nickel laterite potential, 42.15% medium nickel laterite potential, 43.34% high nickel laterite potential, and 9.88% very high nickel laterite from its ultramafic terrains. For the validation of the produced map, it was compared with known occurrences of nickel laterite in the area using a nickel mining tenement map from the area with the application of remote sensing. Three (3) prominent nickel mining companies were delineated in the study area. The generated potential classification map of nickel-laterite in Surigao Del Sur may be of aid to the mining companies which are currently in the exploration phase in the study area. Also, the currently operating nickel mines in the study area can help to validate the reliability of the mineral classification map produced.

Keywords: mineral potential classification, nickel laterites, GIS, remote sensing, Surigao del Sur

Procedia PDF Downloads 111

Authors: Elaheh Talebi, Fariba Yavari, Lucy Philip, Lesley Town

Abstract:

The mining industry generates vast amounts of data, necessitating robust data management systems and advanced analytics tools to achieve better decision-making processes in the development of mining production and maintaining safety. This paper highlights the advantages of Power BI, a powerful intelligence tool, over traditional Excel-based approaches for effectively managing and harnessing mining data. Power BI enables professionals to connect and integrate multiple data sources, ensuring real-time access to up-to-date information. Its interactive visualizations and dashboards offer an intuitive interface for exploring and analyzing geotechnical data. Advanced analytics is a collection of data analysis techniques to improve decision-making. Leveraging some of the most complex techniques in data science, advanced analytics is used to do everything from detecting data errors and ensuring data accuracy to directing the development of future project phases. However, while Power BI is a robust tool, specific visualizations required by geotechnical engineers may have limitations. This paper studies the capability to use Python or R programming within the Power BI dashboard to enable advanced analytics, additional functionalities, and customized visualizations. This dashboard provides comprehensive tools for analyzing and visualizing key geotechnical data metrics, including spatial representation on maps, field and lab test results, and subsurface rock and soil characteristics. Advanced visualizations like borehole logs and Stereonet were implemented using Python programming within the Power BI dashboard, enhancing the understanding and communication of geotechnical information. Moreover, the dashboard's flexibility allows for the incorporation of additional data and visualizations based on the project scope and available data, such as pit design, rock fall analyses, rock mass characterization, and drone data. This further enhances the dashboard's usefulness in future projects, including operation, development, closure, and rehabilitation phases. Additionally, this helps in minimizing the necessity of utilizing multiple software programs in projects. This geotechnical dashboard in Power BI serves as a user-friendly solution for analyzing, visualizing, and communicating both new and historical geotechnical data, aiding in informed decision-making and efficient project management throughout various project stages. Its ability to generate dynamic reports and share them with clients in a collaborative manner further enhances decision-making processes and facilitates effective communication within geotechnical projects in the mining industry.

Keywords: geotechnical data analysis, power BI, visualization, decision-making, mining industry

Procedia PDF Downloads 76

Authors: Caroline Correia, Stefani Perna, John Gaughan, Elizabeth Cerceo

Abstract:

Introduction: The COVID-19 pandemic has brought unprecedented changes to how hospitals function on a daily basis. Increased personal protective equipment (PPE) usage and measures to pre-package, separate, and decontaminate have the potential to increase the waste load. However, limiting non-essential surgeries drastically reduces operating room (OR) waste, and restricting visitation policies to contain outbreaks may help conserve resources. The impact of these policy changes with increased disposable PPE usage on hospital production of waste is unknown. Methods: Waste produced in pounds (lbs) was measured for January through June during both 2019 and 2020 through Stericycle in Cooper University Hospital in Camden, NJ. This timeframe was selected since the pandemic began in January 2020 in the US. The total waste produced during this time was 328,623 lbs in 2019 and 306,454 lbs in 2020. Using Poisson counts (α=.05), less waste was produced in 2020 (p < 0.001). The amount of sharps and regulated medical waste (grossly bloody items) were both significantly decreased as well (p < 0.0001, p=0.0002), and these account for 10-15% of the total waste produced. Discussion: Despite the increased usage of disposable PPE, overall hospital waste was decreased during the pandemic as compared to prior. As surgeries are estimated to be responsible for up to one-half of waste produced by hospitals, it is possible that constraint on elective procedures contributed to the decreased waste in all three categories; estimates of a 35% decrease in surgical volume would be expected to impact waste production. The effects of the pandemic on waste production should continue to be monitored to understand the environmental impact as health systems resume backlogged surgeries at a higher volume.

Keywords: COVID-19, hospital, surgery, waste

Procedia PDF Downloads 94

Authors: Dasom Kim, William Xiu Shun Wong, Yoonjin Hyun, Donghoon Lee, Minji Paek, Sungho Byun, Namgyu Kim

Abstract:

There have been many researches on document classification for classifying voluminous documents automatically. Through document classification, we can assign a specific category to each unlabeled document on the basis of various machine learning algorithms. However, providing labeled documents manually requires considerable time and effort. To overcome the limitations, the semi-supervised learning which uses unlabeled document as well as labeled documents has been invented. However, traditional document classifiers, regardless of supervised or semi-supervised ones, cannot sufficiently explain the reason or the process of the classification. Thus, in this paper, we proposed a methodology to visualize major topics and class components of each document. We believe that our methodology for visualizing topics and classes of each document can enhance the reliability and explanatory power of document classifiers.

Keywords: data mining, document classifier, text mining, topic modeling

Procedia PDF Downloads 387

Authors: Faiza Hussain, Usman Qamar

Abstract:

Synonym-based searching is recognized to be a complicated problem as text mining from unstructured data of web is challenging. Finding useful information which matches user need from bulk of web pages is a cumbersome task. In this paper, a novel and practical synonym retrieval technique is proposed for addressing this problem. For replacement of semantics, user intent is taken into consideration to realize the technique. Parts-of-Speech tagging is applied for pattern generation of the query and a thesaurus for this experiment was formed and used. Comparison with Non-Context Based Searching, Context Based searching proved to be a more efficient approach while dealing with linguistic semantics. This approach is very beneficial in doing intent based searching. Finally, results and future dimensions are presented.

Keywords: natural language processing, text mining, information retrieval, parts-of-speech tagging, grammar, semantics

Procedia PDF Downloads 297

Authors: Dong-Bo Hsu

Abstract:

Universal Grammar (UG) claims that the constraints that are derived from this should operate in language users’ L2 grammars. This study investigated this hypothesis on knowledge of Subjacency and resumptive pronoun usage among Chinese learners of English. Chinese fulfills two requirements to examine the existence of UG, i.e., Subjacency does not operate in Chinese and resumptive pronouns in English are very different from those in Chinese and second L2 input undermines the knowledge of Subjacency. The results indicated that Chinese learners of English demonstrated a nearly identical pattern as English native speakers do but the resumptive pronoun in the embedding clauses. This may be explained in terms of the case that Chinese speakers’ usage of pronouns is not influenced by the number of embedding clauses. Chinese learners of English have full access to knowledge endowed by UG but their processing of English sentences may be different from native speakers as a general slow rate for processing in their L2 English.

Keywords: universal grammar, Chinese, English, wh-questions, resumption

Procedia PDF Downloads 457

Authors: Sanaz Moayer, Fang Huang, Scott Gardner

Abstract:

In the highly leveraged business world of today, an organisation’s success depends on how it can manage and organize its traditional and intangible assets. In the knowledge-based economy, knowledge as a valuable asset gives enduring capability to firms competing in rapidly shifting global markets. It can be argued that ability to create unique knowledge assets by configuring ICT and human capabilities, will be a defining factor for international competitive advantage in the mid-21st century. The concept of KM is recognized in the strategy literature, and increasingly by senior decision-makers (particularly in large firms which can achieve scalable benefits), as an important vehicle for stimulating innovation and organisational performance in the knowledge economy. This thinking has been evident in professional services and other knowledge intensive industries for over a decade. It highlights the importance of social capital and the value of the intellectual capital embedded in social and professional networks, complementing the traditional focus on creation of intellectual property assets. Despite the growing interest in KM within professional services there has been limited discussion in relation to multinational resource based industries such as mining and petroleum where the focus has been principally on global portfolio optimization with economies of scale, process efficiencies and cost reduction. The Australian minerals and metals mining industry, although traditionally viewed as capital intensive, employs a significant number of knowledge workers notably- engineers, geologists, highly skilled technicians, legal, finance, accounting, ICT and contracts specialists working in projects or functions, representing potential knowledge silos within the organisation. This silo effect arguably inhibits knowledge sharing and retention by disaggregating corporate memory, with increased operational and project continuity risk. It also may limit the potential for process, product, and service innovation. In this paper the strategic application of knowledge management incorporating contemporary ICT platforms and data mining practices is explored as an important enabler for knowledge discovery, reduction of risk, and retention of corporate knowledge in resource based industries. With reference to the relevant strategy, management, and information systems literature, this paper highlights possible connections (currently undergoing empirical testing), between an Strategic Knowledge Management (SKM) framework incorporating supportive Data Mining (DM) practices and competitive advantage for multinational firms operating within the Australian resource sector. We also propose based on a review of the relevant literature that more effective management of soft and hard systems knowledge is crucial for major Australian firms in all sectors seeking to improve organisational performance through the human and technological capability captured in organisational networks.

Keywords: competitive advantage, data mining, mining organisation, strategic knowledge management

Procedia PDF Downloads 402

Authors: Samson F. Agberotimi, Rachel B. Asagba, Choja Oduaran

Abstract:

Disturbing rate of use of different substances such as cannabis, alcohol, as well as pharmaceutical drugs among Nigerian youth in recent times has been affirmed in the literature. There is, however, a paucity of literature addressing the pattern of usage of such drugs, especially for clinical relevance and intervention planning. The present study investigated the prevalence and pattern of drug usage among youth in Ogbomoso, Nigeria. A cross-sectional survey involving 92 purposively selected participants comprising of 82 males and 10 females aged between 15 and 24 years was conducted. A measure of drug involvement and demographic characteristics was administered to the participants. Descriptive analysis was done using the SPSS v.21. Cannabis (79.4%), alcohol (77.2%), codeine (70.7%), tobacco (65.2%) and tramadol (47.8%) are the five most frequently used substances. However, the majority of the users of tobacco (68.3%) and alcohol (62.0%) are casual users indicating a mild level of use of the substances among the participants. On the other hand, 49.2% of the codeine users, 27.3% of the tramadol users, and 21.9% of the cannabis users reported harmful/intensive levels of use. Furthermore, the results revealed individuals at the pathological level of use as 28.8% for cannabis, 25.0% for tramadol, and 21.6% for codeine, and thus require clinical/therapeutic intervention. In conclusion, cannabis remains the most frequently used substance among youths. However, there appears to be a shift from the use of conventional psychoactive substances to pharmaceutical/prescription drugs such as codeine and tramadol. The findings of this study raised the need for both preventive and therapeutic interventions addressing the problem of substance use disorder among youth in contemporary society.

Keywords: Ogbomoso, pattern of drug use, prevalence of drug use, youth

Procedia PDF Downloads 154