Search results for: information entropy.

Authors: Neelima Gupta, Seema Aggarwal

Abstract:

Most of the biclustering/projected clustering algorithms are based either on the Euclidean distance or correlation coefficient which capture only linear relationships. However, in many applications, like gene expression data and word-document data, non linear relationships may exist between the objects. Mutual Information between two variables provides a more general criterion to investigate dependencies amongst variables. In this paper, we improve upon our previous algorithm that uses mutual information for biclustering in terms of computation time and also the type of clusters identified. The algorithm is able to find biclusters with mixed relationships and is faster than the previous one. To the best of our knowledge, none of the other existing algorithms for biclustering have used mutual information as a similarity measure. We present the experimental results on synthetic data as well as on the yeast expression data. Biclusters on the yeast data were found to be biologically and statistically significant using GO Tool Box and FuncAssociate.

Keywords: Biclustering, mutual information.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1589

Authors: Saleh Alumaran, Giampaolo Bella, Feng Chen

Abstract:

The study of organisations’ information security cultures has attracted scholars as well as healthcare services industry to research the topic and find appropriate tools and approaches to develop a positive culture. The vast majority of studies in Saudi national health services are on the use of technology to protect and secure health services information. On the other hand, there is a lack of research on the role and impact of an organisation’s cultural dimensions on information security. This research investigated and analysed the role and impact of cultural dimensions on information security in Saudi Arabia health service. Hypotheses were tested and two surveys were carried out in order to collect data and information from three major hospitals in Saudi Arabia (SA). The first survey identified the main cultural-dimension problems in SA health services and developed an initial information security culture framework model. The second survey evaluated and tested the developed framework model to test its usefulness, reliability and applicability. The model is based on human behaviour theory, where the individual’s attitude is the key element of the individual’s intention to behave as well as of his or her actual behaviour. The research identified a set of cultural and sub-cultural dimensions in SA health information security and services.

Keywords: Behaviour theory, Culture dimensions, Electronic health records, Information security.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2309

Authors: F. Lhafiane, A. Elbyed, M. Bouchoum

Abstract:

Reverse Logistics (RL) Network is considered as complex and dynamic network that involves many stakeholders such as: suppliers, manufactures, warehouse, retails and costumers, this complexity is inherent in such process due to lack of perfect knowledge or conflicting information. Ontologies on the other hand can be considered as an approach to overcome the problem of sharing knowledge and communication among the various reverse logistics partners. In this paper we propose a semantic representation based on hybrid architecture for building the Ontologies in ascendant way, this method facilitates the semantic reconciliation between the heterogeneous information systems that support reverse logistics processes and product data.

Keywords: Reverse Logistics, information management, heterogeneity, Ontologies, semantic web.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2923

Authors: H. L. Chan, T. M. Choi, C. L. Hui, S. F. Ng

Abstract:

In this study, we explore the use of information for inventory decision in the healthcare organization (HO). We consider the scenario when the HO can make use of the information collected from some correlated products to enhance its inventory planning. Motivated by our real world observations that HOs adopt RFID and bar-coding system for information collection purpose, we examine the effectiveness of these systems for inventory planning with Bayesian information updating. We derive the optimal ordering decision and study the issue of Pareto improvement in the supply chain. Our analysis demonstrates that RFID system will outperform the bar-coding system when the RFID system installation cost and the tag cost reduce to a level that is comparable with that of the barcoding system. We also show how an appropriately set wholesale pricing contract can achieve Pareto improvement in the HO supply chain.

Keywords: Efficient consumer response program, healthcare, inventory management, RFID system, bar-coding system.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1873

Authors: Akhilesh Khapre, Basudeb Munshi

Abstract:

A computational fluid dynamics simulation is done for non-Newtonian fluid in a baffled stirred tank. The CMC solution is taken as non-Newtonian shear thinning fluid for simulation. The Reynolds Average Navier Stocks equation with steady state multi reference frame approach is used to simulate flow in the stirred tank. The turbulent flow field is modelled using realizable k-ε turbulence model. The simulated velocity profiles of Rushton turbine is validated with literature data. Then, the simulated flow field of CD-6 impeller is compared with the Rushton turbine. The flow field generated by CD-6 impeller is less in magnitude than the Rushton turbine. The impeller global parameter, power number and flow number, and entropy generation due to viscous dissipation rate is also reported.

Keywords: Computational fluid dynamics, non-Newtonian, Rushton turbine, CD-6 impeller, power number, flow number, viscous dissipation rate.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4102

Authors: Ahmed Arara

Abstract:

Information sharing and exchange, rather than information processing, is what characterizes information technology in the 21st century. Ontologies, as shared common understanding, gain increasing attention, as they appear as the most promising solution to enable information sharing both at a semantic level and in a machine-processable way. Domain Ontology-based modeling has been exploited to provide shareability and information exchange among diversified, heterogeneous applications of enterprises. Contextual ontologies are “an explicit specification of contextual conceptualization". That is: ontology is characterized by concepts that have multiple representations and they may exist in several contexts. Hence, contextual ontologies are a set of concepts and relationships, which are seen from different perspectives. Contextualization is to allow for ontologies to be partitioned according to their contexts. The need for contextual ontologies in enterprise modeling has become crucial due to the nature of today's competitive market. Information resources in enterprise is distributed and diversified and is in need to be shared and communicated locally through the intranet and globally though the internet. This paper discusses the roles that ontologies play in an enterprise modeling, and how ontologies assist in building a conceptual model in order to provide communicative and interoperable information systems. The issue of enterprise modeling based on contextual domain ontology is also investigated, and a framework is proposed for an enterprise model that consists of various applications.

Keywords: Contextual ontologies, Enterprise model, domainontology.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1807

Authors: Hassan Noureddine, Maria Sokhn, Iman Jarkass, Elena Mugellini, Omar Abou Khaled

Abstract:

From the importance of the conference and its constructive role in the studies discussion, there must be a strong organization that allows the exploitation of the discussions in opening new horizons. The vast amount of information scattered across the web, make it difficult to find experts, who can play a prominent role in organizing conferences. In this paper we proposed a new approach of extracting researchers- information from various Web resources and correlating them in order to confirm their correctness. As a validator of this approach, we propose a service that will be useful to set up a conference. Its main objective is to find appropriate experts, as well as the social events for a conference. For this application we us Semantic Web technologies like RDF and ontology to represent the confirmed information, which are linked to another ontology (skills ontology) that are used to present and compute the expertise.

Keywords: Expert finding, Information extraction, Ontologies, Semantic web, Social events.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1584

Authors: N. Soussi, M. Bahaj

Abstract:

The enormous amount of information stored on the web increases from one day to the next, exposing the web currently faced with the inevitable difficulties of research pertinent information that users really want. The problem today is not limited to expanding the size of the information highways, but to design a system for intelligent search. The vast majority of this information is stored in relational databases, which in turn represent a backend for managing RDF data of the semantic web. This problem has motivated us to write this paper in order to establish an effective approach to support semantic transformation algorithm for SPARQL queries to SQL queries, more precisely SPARQL SELECT queries; by adopting this method, the relational database can be questioned easily with SPARQL queries maintaining the same performance.

Keywords: RDF, Semantic Web, SPARQL, SPARQL Query Transformation, SQL.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1717

Authors: Hendry Muljadi, Hideaki Takeda, Koichi Ando

Abstract:

A manufacturing feature can be defined simply as a geometric shape and its manufacturing information to create the shape. In a feature-based process planning system, feature library that consists of pre-defined manufacturing features and the manufacturing information to create the shape of the features, plays an important role in the extraction of manufacturing features with their proper manufacturing information. However, to manage the manufacturing information flexibly, it is important to build a feature library that can be easily modified. In this paper, the implementation of Semantic Wiki for the development of the feature library is proposed.

Keywords: Manufacturing feature, feature library, feature ontology, process planning, Wiki, MediaWiki, Semantic Wiki.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1402

Authors: Ai Cheo Yeo, Md. Mahbubur Rahim, Yin Ying Ren

Abstract:

Persuasive technology has been applied in marketing, health, environmental conservation, safety and other domains and is found to be quite effective in changing people-s attitude and behaviours. This research extends the application domains of persuasive technology to information security awareness and uses a theory-driven approach to evaluate the effectiveness of a web-based program developed based on the principles of persuasive technology to improve the information security awareness of end users. The findings confirm the existence of a very strong effect of the webbased program in raising users- attitude towards information security aware behavior. This finding is useful to the IT researchers and practitioners in developing appropriate and effective education strategies for improving the information security attitudes for endusers.

Keywords: Information security, persuasive technology, ITsecurity-aware behaviour, theory of planned behaviour survey.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2369

Authors: T. T. Naas, Y. Lasbet, C. Kezrane

Abstract:

The thermal control in many systems is widely accomplished applying mixed convection process due to its low cost, reliability and easy maintenance. Typical applications include the aircraft electronic equipment, rotating-disc heat exchangers, turbo machinery, and nuclear reactors, etc. Natural convection in an inclined square enclosure heated via wall heater has been studied numerically. Finite volume method is used for solving momentum and energy equations in the form of stream function–vorticity. The right and left walls are kept at a constant temperature, while the other parts are adiabatic. The range of the inclination angle covers a whole revolution. The method is validated for a vertical cavity. A general power law dependence of the Nusselt number with respect to the Rayleigh number with the coefficient and exponent as functions of the inclination angle is presented. For a fixed Rayleigh number, the inclination angle increases or decreases is found.

Keywords: Inclined enclosure, natural convection in enclosure, Nusselt number.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2195

Authors: Zaza Tabagari, Zaza Sanikidze, George Giorgobiani

Abstract:

Abovepresented work deals with the new scope of application of information and communication technologies for the improvement of the election process in the biased environment. We are introducing a new concept of construction of the information-communication system for the election participant. It consists of four main components: Software, Physical Infrastructure, Structured Information and the Trained Stuff. The Structured Information is the bases of the whole system and is the collection of all possible events (irregularities among them) at the polling stations, which are structured in special templates, forms and integrated in mobile devices.The software represents a package of analytic modules, which operates with the dynamic database. The application of modern communication technologies facilities the immediate exchange of information and of relevant documents between the polling stations and the Server of the participant. No less important is the training of the staff for the proper functioning of the system. The e-training system with various modules should be applied in this respect. The presented methodology is primarily focused on the election processes in the countries of emerging democracies.It can be regarded as the tool for the monitoring of elections process by the political organization(s) and as one of the instruments to foster the spread of democracy in these countries.

Keywords: ICT, elections, structured information, dynamic databases, e-training.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1704

Authors: Ahmed I. Shehab, Sabah M. Abdel Basir, M. A. Abdel Khalek, M. H. Soliman, G. Elgemeie

Abstract:

Spent bleaching earth (SBE) recycling and utilization as an adsorbent to eliminate dyes from aqueous solution was studied. Organic solvents and subsequent thermal treatment were carried out to recover and reactivate the SBE. The effect of pH, temperature, dye’s initial concentration, and contact time on the dye removal using recycled spent bleaching earth (RSBE) was investigated. Recycled SBE showed better removal affinity of cationic than anionic dyes. The maximum removal was achieved at pH 2 and 8 for anionic and cationic dyes, respectively. Kinetic data matched with the pseudo second-order model. The adsorption phenomenon governing this process was identified by the Langmuir and Freundlich isotherms for anionic dye while Freundlich model represented the sorption process for cationic dye. The changes of Gibbs free energy (ΔG°), enthalpy (ΔH°), and entropy (ΔS°) were computed and compared through thermodynamic study for both dyes.

Keywords: Spent bleaching earth, Regeneration, Dye removal, Thermodynamics.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 896

Authors: M. Tsirintani

Abstract:

The article is proposing a base plan for the future Patient Care Information Systems in a changing health care environment where it is necessary to assure quality patient care services and reducing cost and where new technology trends give the opportunities to develop clinical applications and services patient focused according to new business objectives.

Keywords: Health care management, planning patient care information system.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1758

Authors: Alhamdi Alfi Fajri

Abstract:

The purpose of this study is to analyze and to give empirical proof about the effect of fair value implementation on financial asset against information asymmetry in Indonesia’s banking sector. This research tested the effect of fair value implementation on financial asset based on Statement of Financial Accounting Standard (PSAK) No. 55 and the fair value reliability measurement based on PSAK No. 60 against level of information asymmetry. The scope of research is Indonesia’s banking sector. The test’s result shows that the use of fair value based on PSAK No. 55 is significantly associated with information asymmetry. This positive relation is higher than the amortized cost implementation on financial asset. In addition, the fair value hierarchy based on PSAK No. 60 is significantly associated with information asymmetry. This research proves that the more reliable measurement of fair value on financial asset, the more observable fair value measurement and reduces level of information asymmetry.

Keywords: Fair value, PSAK No. 55, PSAK No. 60, information asymmetry, banks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1913

Authors: Benhamouda Sara, Guezouli Larbi

Abstract:

Nowadays, the dissemination of information touches the distributed world, where selecting the relevant servers to a user request is an important problem in distributed information retrieval. During the last decade, several research studies on this issue have been launched to find optimal solutions and many approaches of collection selection have been proposed. In this paper, we propose a new collection selection approach that takes into consideration the number of documents in a collection that contains terms of the query and the weights of those terms in these documents. We tested our method and our studies show that this technique can compete with other state-of-the-art algorithms that we choose to test the performance of our approach.

Keywords: Distributed information retrieval, relevance, server selection, collection selection.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1339

Authors: Hoda Waguih

Abstract:

A serious problem on the WWW is finding reliable information. Not everything found on the Web is true and the Semantic Web does not change that in any way. The problem will be even more crucial for the Semantic Web, where agents will be integrating and using information from multiple sources. Thus, if an incorrect premise is used due to a single faulty source, then any conclusions drawn may be in error. Thus, statements published on the Semantic Web have to be seen as claims rather than as facts, and there should be a way to decide which among many possibly inconsistent sources is most reliable. In this work, we propose a trust model for the Semantic Web. The proposed model is inspired by the use trust in human society. Trust is a type of social knowledge and encodes evaluations about which agents can be taken as reliable sources of information or services. Our proposed model allows agents to decide which among different sources of information to trust and thus act rationally on the semantic web.

Keywords: Semantic Web, Trust, Web of Trust, WWW.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1502

Authors: Tamara Djurickovic

Abstract:

The waves of eGovernment are rising very fast through almost all public administration, or at least most of the public administrations around the world, and not only the public administration, but also the entire government and all of their organization as a whole. The government uses information technology, and above all the internet or web network, to facilitate the exchange of services between government agencies and citizens, businesses, employees and other non-governmental agencies. With efficient and transparent information exchange, the information becomes accessible to the society (citizens, business, employees etc.), and as a result of these processes the society itself becomes the information society or knowledge society. This paper discusses the knowledge management for eGovernment development in significance and role. Also, the paper reviews the role of virtual communities as a knowledge management mechanism to support eGovernment in Montenegro. It explores the need for knowledge management in eGovernment, identifies knowledge management technologies, and highlights the challenges for developing countries, such as Montenegro in the implementation of eGovernment. The paper suggests that knowledge management is needed to facilitate information exchange and transaction processing with citizens, as well as to enable creation of knowledge society.

Keywords: information, eGovernment, knowledge management, knowledge society

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1516

Authors: Nurshuhada Zainon, Hafez Salleh, Faizul A. Rahim

Abstract:

Information technology managers nowadays are facing with tremendous pressure to plan, implement, and adopt new technology solution due to the rapidity of technology changes. Resulted from a lack of study that have been done in this topic, the aim of this paper is to provide a comparison review on current tools that are currently being used in order to respond to technological changes. The study is based on extensive literature review of published works with majority of them are ranging from 2000 to the first part of 2011. The works were gathered from journals, books, and other information sources available on the Web. Findings show that, each tools has different focus and none of the tools are providing a framework in holistic view, which should include technical, people, process, and business environment aspect. Hence, this result provides potential information about current available tools that IT managers could use to manage changes in technology. Further, the result reveals a research gap in the area where the industries a short of such framework.

Keywords: Information technology, IT adaption, IT revolution, IT trends

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1690

Authors: R. Mahjoub, K. Maghsoudi Mehraban

Abstract:

In recent years, solid oxide fuel cells have been used as one of the main technologies for the production of electrical energy with high-efficiency ratio, which is used hydrogen and other hydrocarbons as fuels. The fuel cell technology can be used either alone or in hybrid gas turbines systems. In this study, thermodynamics analysis for GT-SOFC hybrid system is developed, and then mass balance and exergy equations have been applied not only on the process but also on the individual components of the hybrid system, which enable us to estimate the thermal efficiency of the hybrid systems. Furthermore, various sources of irreversibility in the solid oxide fuel cell system are discussed, and modeling and parametric analyses like heat and pressure are carried out. This study enables us to consider the irreversible effects of solid oxide fuel cells, and also it leads to the specification of efficiency of the system accurately. Next in the study, both methane and hydrogen as a fuel for SOFC are used and implemented, and finally, our results are compared with other references.

Keywords: hybrid system, gas turbine, entropy and exergy analysis, irreversibility analysis

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 439

Authors: Lae-Jeong Park, Kyusoo Chung, Jungho Moon

Abstract:

This paper introduces an effective method of segmenting Korean text (place names in Korean) from a Korean road sign image. A Korean advanced directional road sign is composed of several types of visual information such as arrows, place names in Korean and English, and route numbers. Automatic classification of the visual information and extraction of Korean place names from the road sign images make it possible to avoid a lot of manual inputs to a database system for management of road signs nationwide. We propose a series of problem-specific heuristics that correctly segments Korean place names, which is the most crucial information, from the other information by leaving out non-text information effectively. The experimental results with a dataset of 368 road sign images show 96% of the detection rate per Korean place name and 84% per road sign image.

Keywords: Segmentation, road signs, characters, classification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2699

Authors: Hanmin Jung, Mikyoung Lee, Won-kyung Sung

Abstract:

Academic research information service is a must for surveying previous studies in research and development process. OntoFrame is an academic research information service under Semantic Web framework different from simple keyword-based services such as CiteSeer and Google Scholar. The first purpose of this study is for revealing user behavior in their surveys, the objects of using academic research information services, and their needs. The second is for applying lessons learned from the results to OntoFrame.

Keywords: User Behavior, Usability Evaluation, OntoFrame, CiteSeer, Google Scholar, Academic Research Information Service.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1484

Authors: Hae-Won Seo, Yong-Gu Lee

Abstract:

Recent progress in the next generation of automobile technology is geared towards incorporating information technology into cars. Collectively called smart cars are bringing intelligence to cars that provides comfort, convenience and safety. A branch of smart cars is connected-car system. The key concept in connected-cars is the sharing of driving information among cars through decentralized manner enabling collective intelligence. This paper proposes a foundation of the information model that is necessary to define the driving information for smart-cars. Road conditions are modeled through a unique data structure that unambiguously represent the time variant traffics in the streets. Additionally, the modeled data structure is exemplified in a navigational scenario and usage using UML. Optimal driving route searching is also discussed using the proposed data structure in a dynamically changing road conditions.

Keywords: Connected-car, data modeling, route planning, navigation system.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1925

Authors: T. Suresh Kumar, M. Arthanari, N. Shanthi

Abstract:

Nowadays, the Web has become one of the most pervasive platforms for information change and retrieval. It collects the suitable and perfectly fitting information from websites that one requires. Data mining is the form of extracting data’s available in the internet. Web mining is one of the elements of data mining Technique, which relates to various research communities such as information recovery, folder managing system and simulated intellects. In this Paper we have discussed the concepts of Web mining. We contain generally focused on one of the categories of Web mining, specifically the Web Content Mining and its various farm duties. The mining tools are imperative to scanning the many images, text, and HTML documents and then, the result is used by the various search engines. We conclude by presenting a comparative table of these tools based on some pertinent criteria.

Keywords: Data Mining, Web Mining, Web Content Mining, Mining Tools, Information retrieval.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3515

Authors: Hui-Ling Huang, Yue-Yang Chen, Ming-Chi Tsai, Cheng-Jiun Lee

Abstract:

Recently, a great number of theoretical frameworks have been proposed to develop the linkages between knowledge management (KM) and organizational strategies. However, while there has been much theorizing and case study in the area, validated research models integrating KM and information technology strategies for empirical testing of these theories have been scarce. In this research, we try to develop a research model for explaining the relationship between KM strategy and IT strategy and their effects on performance. Finally, meaningful propositions and conclusions are derived, and suggestions for future research are proposed and discussed.

Keywords: Knowledge management strategy, information technology strategy, knowledge management performance, information technology performance

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2969

Authors: M. Sadeghi, A.H. Jafari, S.M.P. Firoozabadi

Abstract:

Deep Brain Stimulation or DBS is a surgical treatment for Parkinson-s Disease with three stimulation parameters: frequency, pulse width, and voltage. The parameters should be selected appropriately to achieve effective treatment. This selection now, performs clinically. The aim of this research is to study chaotic behavior of recorded tremor of patients under DBS in order to present a computational method to recognize stimulation optimum voltage. We obtained some chaotic features of tremor signal, and discovered embedding space of it has an attractor, and its largest Lyapunov exponent is positive, which show tremor signal has chaotic behavior, also we found out, in optimal voltage, entropy and embedding space variance of tremor signal have minimum values in comparison with other voltages. These differences can help neurologists recognize optimal voltage numerically, which leads to reduce patients' role and discomfort in optimizing stimulation parameters and to do treatment with high accuracy.

Keywords: Chaos, Deep Brain Stimulation, Parkinson's Disease, Stimulation Parameters, tremor.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1787

Authors: Chad Goldsworthy, B. Rajeswari Matam

Abstract:

The use of deep learning for species identification in camera trap images has revolutionised our ability to study, conserve and monitor species in a highly efficient and unobtrusive manner, with state-of-the-art models achieving accuracies surpassing the accuracy of manual human classification. The high imbalance of camera trap datasets, however, results in poor accuracies for minority (rare or endangered) species due to their relative insignificance to the overall model accuracy. This paper investigates the use of Focal Loss, in comparison to the traditional Cross Entropy Loss function, to improve the identification of minority species in the “255 Bird Species” dataset from Kaggle. The results show that, although Focal Loss slightly decreased the accuracy of the majority species, it was able to increase the F1-score by 0.06 and improve the identification of the bottom two, five and ten (minority) species by 37.5%, 15.7% and 10.8%, respectively, as well as resulting in an improved overall accuracy of 2.96%.

Keywords: Convolutional neural networks, data imbalance, deep learning, focal loss, species classification, wildlife conservation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1349

Authors: Mazziotti Gomez de Teran C., Fiore D., Cola B., Fardelli A.

Abstract:

The present paper summarizes the analysis of the request for consultation of information and data on industrial emissions made publicly available on the web site of the Ministry of Environment, Land and Sea on integrated pollution prevention and control from large industrial installations, the so called “AIA Portal”. As a matter of fact, a huge amount of information on national industrial plants is already available on internet, although it is usually proposed as textual documentation or images. Thus, it is not possible to access all the relevant information through interoperability systems and also to retrieval relevant information for decision making purposes as well as rising of awareness on environmental issue. Moreover, since in Italy the number of institutional and private subjects involved in the management of the public information on industrial emissions is substantial, the access to the information is provided on internet web sites according to different criteria; thus, at present it is not structurally homogeneous and comparable. To overcome the mentioned difficulties in the case of the Coordinating Committee for the implementation of the Agreement for the industrial area in Taranto and Statte, operating before the IPPC permit granting procedures of the relevant installation located in the area, a big effort was devoted to elaborate and to validate data and information on characterization of soil, ground water aquifer and coastal sea at disposal of different subjects to derive a global perspective for decision making purposes. Thus, the present paper also focuses on main outcomes matured during such experience.

Keywords: Public information, emissions into atmosphere, IPPC permits, territorial information systems.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2024

Authors: Kanda Runapongsa Saikaew, Chaluemwut Noyunsan

Abstract:

Nowadays social media information, such as news, links, images, or VDOs, is shared extensively. However, the effectiveness of disseminating information through social media lacks in quality: less fact checking, more biases, and several rumors. Many researchers have investigated about credibility on Twitter, but there is no the research report about credibility information on Facebook. This paper proposes features for measuring credibility on Facebook information. We developed the system for credibility on Facebook. First, we have developed FB credibility evaluator for measuring credibility of each post by manual human’s labelling. We then collected the training data for creating a model using Support Vector Machine (SVM). Secondly, we developed a chrome extension of FB credibility for Facebook users to evaluate the credibility of each post. Based on the usage analysis of our FB credibility chrome extension, about 81% of users’ responses agree with suggested credibility automatically computed by the proposed system.

Keywords: Facebook, social media, credibility measurement.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3625

Authors: Elin Cahyaningsih, Dana Indra Sensuse, Wahyu Catur Wibowo, Sofiyanti Indriasari

Abstract:

Bureaucracy reform program drives Indonesian government to change their management to enhance their organizational performance. Information technology became one of strategic plan that organization tried to improve. Knowledge management system is one of information system that supporting knowledge management implementation in government which categorized as people perspective, because this system has high dependency in human interaction and participation. Strategic plan for developing knowledge management system can be determine using some of information system strategic methods. This research conducted to define type of strategic method of information system, stage of activity each method, strength and weakness. Literature review methods used to identify and classify strategic methods of information system, differentiate method type, categorize common activities, strength and weakness. Result of this research are determine and compare six strategic information system methods, Balanced Scorecard and Risk Analysis believe as common strategic method that usually used and have the highest excellence strength.

Keywords: Knowledge management system, balanced scorecard, five force, risk analysis, gap analysis, value chain analysis, SWOT analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2610