Search results for: Natural Language Inference

Authors: Akiyoshi Wakatani

Abstract:

This paper describes the Message Passing Interface (MPI) implementation of ADETRAN language, and its evaluation on SX-ACE supercomputers. ADETRAN language includes pdo statement that specifies the data distribution and parallel computations and pass statement that specifies the redistribution of arrays. Two methods for implementation of pass statement are discussed and the performance evaluation using Splitting-Up CG method is presented. The effectiveness of the parallelization is evaluated and the advantage of one dimensional distribution is empirically confirmed by using the results of experiments.

Keywords: Iterative methods, array redistribution, translator, distributed memory.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1193

Authors: Ticiane Rossi, Maurício C. Araújo, José O. Brito, Harold S. Freeman

Abstract:

Natural dyes are gaining interest due their expected low risk to human health and to the environment. In this study, the wash fastness of a natural coloring matter from the liquid waste produced in the steam treatment of eucalyptus wood in textile fabrics was investigated. Specifically, eucalyptus wood extract was used to dye cotton, nylon and wool in an exhaust dyeing process without the addition of the traditional mordanting agents and then submitted to wash fastness analysis. The resulting dyed fabrics were evaluated for color fastness. It was found that wash fastness of dyed fabrics was very good to cotton and excellent to nylon and wool.

Keywords: Eucalyptus, natural dye, textile fibers, wash fastness.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3325

Authors: Rosziati Ibrahim, Noraini Ibrahim

Abstract:

Unified Modeling Language (UML) is a standard language for modeling of a system. UML is used to visually specify the structure and behavior of a system. The system requirements are captured and then converted into UML specification. UML specification uses a set of rules and notations, and diagrams to specify the system requirements. In this paper, we present a tool for developing the UML specification. The tool will ease the use of the notations and diagrams for UML specification as well as increase the understanding and familiarity of the UML specification. The tool will also be able to check the conformance of the diagrams against each other for basic compliance of UML specification.

Keywords: Software Engineering, Unified Modeling Language (UML), UML Specification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2193

Authors: C. Pacheco, A. Cipriano

Abstract:

A new concept of response system is proposed for filling the gap that exists in reducing vulnerability during immediate response to natural disasters. Real Time Early Response Systems (RTERSs) incorporate real time information as feedback data for closing control loop and for generating real time situation assessment. A review of the state of the art on works that fit the concept of RTERS is presented, and it is found that they are mainly focused on manmade disasters. At the same time, in response phase of natural disaster management many works are involved in creating early warning systems, but just few efforts have been put on deciding what to do once an alarm is activated. In this context a RTERS arises as a useful tool for supporting people in their decision making process during natural disasters after an event is detected, and also as an innovative context for applying well-known automation technologies and automatic control concepts and tools.

Keywords: Disaster management, emergency response system, natural disasters, real time.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3575

Authors: Jie Zhang, Qianyu Guo, Tieyi Zhang, Zhiyong Feng, Xiaohong Li

Abstract:

The widespread popularity of mobile devices and the development of artificial intelligence (AI) have led to the widespread adoption of deep learning (DL) in Android apps. Compared with traditional Android apps (traditional apps), deep learning based Android apps (DL-based apps) need to use more third-party application programming interfaces (APIs) to complete complex DL inference tasks. However, existing methods (e.g., FlowDroid) for detecting sensitive information leakage in Android apps cannot be directly used to detect DL-based apps as they are difficult to detect third-party APIs. To solve this problem, we design DLtrace, a new static information flow analysis tool that can effectively recognize third-party APIs. With our proposed trace and detection algorithms, DLtrace can also efficiently detect privacy leaks caused by sensitive APIs in DL-based apps. Additionally, we propose two formal definitions to deal with the common polymorphism and anonymous inner-class problems in the Android static analyzer. Using DLtrace, we summarize the non-sequential characteristics of DL inference tasks in DL-based apps and the specific functionalities provided by DL models for such apps. We conduct an empirical assessment with DLtrace on 208 popular DL-based apps in the wild and found that 26.0% of the apps suffered from sensitive information leakage. Furthermore, DLtrace outperformed FlowDroid in detecting and identifying third-party APIs. The experimental results demonstrate that DLtrace expands FlowDroid in understanding DL-based apps and detecting security issues therein.

Keywords: Mobile computing, deep learning apps, sensitive information, static analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 566

Authors: Junaid Kameran Ahmed

Abstract:

A laminated plate composite of graphite/epoxy has been analyzed dynamically in the present work by using a quadratic element (8-node diso-parametric), and by depending on 1^st order shear deformation theory, every node in this element has 6-degrees of freedom (displacement in x, y, and z axis and twist about x, y, and z axis). The dynamic analysis in the present work covered parametric studies on a composite laminated plate (square plate) to determine its effect on the natural frequency of the plate. The parametric study is represented by set of changes (plate thickness, number of layers, support conditions, layer orientation), and the plates have been simulated by using ANSYS package 12. The boundary conditions considered in this study, at all four edges of the plate, are simply supported and fixed boundary condition. The results obtained from ANSYS program show that the natural frequency for both fixed and simply supported increases with increasing the number of layers, but this increase in the natural frequency for the first five modes will be neglected after 10 layers. And it is observed that the natural frequency of a composite laminated plate will change with the change of ply orientation, the natural frequency increases and it will be at maximum with angle 45 of ply for simply supported laminated plate, and maximum natural frequency will be with cross-ply (0/90) for fixed laminated composite plate. It is also observed that the natural frequency increase is approximately doubled when the thickness is doubled.

Keywords: Laminated plate, orthotropic plate, square plate, natural frequency, graphite/epoxy.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 972

Authors: Chamindi Dilkushi Senaratne

Abstract:

Communicating via a text or an SMS (Short Message Service) has become an integral part of our daily lives. With the increase in the use of mobile phones, text messaging has become a genre by itself worth researching and studying. It is undoubtedly a major phenomenon revealing language change. This paper attempts to describe the morphological processes of text language of urban bilinguals in Sri Lanka. It will be a typological study based on 500 English text messages collected from urban bilinguals residing in Colombo. The messages are selected by categorizing the deviant forms of language use apparent in text messages. These stylistic deviations are a deliberate skilled performance by the users of the language possessing an in-depth knowledge of linguistic systems to create new words and thereby convey their linguistic identity and individual and group solidarity via the message. The findings of the study solidifies arguments that the manipulation of language in text messages is both creative and appropriate. In addition, code mixing theories will be used to identify how existing morphological processes are adapted by bilingual users in Sri Lanka when texting. The study will reveal processes such as omission, initialism, insertion and alternation in addition to other identified linguistic features in text language. The corpus reveals the most common morphological processes used by Sri Lankan urban bilinguals when sending texts.

Keywords: Bilingual, deviations, morphology, texts.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1967

Authors: Pattaranut Eakwaropas, Khemjira Jarmkom, Warachate Khobjai, Surachai Techaoei

Abstract:

The aim of this study is to improve Pang-Rum (PR) hardness by adding natural binders. PR is one of Thai tradition aroma products. In the past, it was used for aesthetic propose on face and body with good odor. Nowadays, PR is not popular and going to be disappeared. Five natural materials, i.e. agar, rice flour, glutinous flour, corn starch, and tapioca starch were selected to use as binders. Binders were dissolved with boiled water into concentration 5% and 10% w/w except agar that was prepared 0.5% and 1% w/w. PR with and without binder were formulated. Physical properties, i.e. weight, shape, color, and hardness were evaluated. PR with 10% of corn starch solution had suitable hardness (14.2±0.9 kg) and the best appearance. In the future, it would be planned to study about odor and physical stability for decorated product development.

Keywords: Aromatic water, hardness, natural binder, pang-rum.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1054

Authors: J. Hroudova, J. Zach

Abstract:

The majority of contemporary insulation materials commonly used in the building industry is made from non-renewable raw materials; furthermore, their production often brings high energy costs. A long-term trend as far as sustainable development is concerned has been the reduction of energy and material demands of building material production. One of the solutions is the possibility of using easily renewable natural raw material sources which are considerably more ecological and their production is mostly less energy-consuming compared to the production of normal insulations (mineral wool, polystyrene). The paper describes the results of research focused on the development of thermal and acoustic insulation materials based on natural fibres intended for floor constructions. Given the characteristic open porosity of natural fibre materials, the hygrothermal behaviour of the developed materials was studied. Especially the influence of relative humidity and temperature on thermal insulation properties was observed.

Keywords: Green thermal and acoustic insulating materials, natural fibres, technical hemp, flax, floor construction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3192

Authors: Rinaldo Christian Tanumara, Ming Xie

Abstract:

Color categorization is shared among members in a society. This allows communication of color, especially when using natural language such as English. Hence sociable robot, to live coexist with human in human society, must also have the shared color categorization. To achieve this, many works have been done relying on modeling of human color perception and mathematical complexities. In contrast, in this work, the computer as brain of the robot learns color categorization through interaction with humans without much mathematical complexities.

Keywords: Color categorization, color learning, machinelearning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1431

Authors: Samera Salimpour Abkenar

Abstract:

In traditional dyeing of natural fibers with natural dyes, metal salts are commonly used to increase color stability. This method always carries the risk of environmental pollution (contamination of arable soils and fresh groundwater) due to the release of dyeing effluents containing large amounts of metal. Therefore, researchers are always looking for new methods to obtain a green dyeing system. In this research, the use of the enzymatic dyeing method to prevent environmental pollution with metals and reduce production costs has been proposed. After degumming and bleaching, raw silk fabrics were dyed with natural dyes (Madder and Sumac) by three methods (pre-mordanting with a metal salt, one-step enzymatic dyeing, and two-step enzymatic dyeing). Results show that silk dyed with natural dyes by the enzymatic method has higher color strength and colorfastness than the pretreated with a metal salt. Also, the amount of remained dyes in the dyeing wastewater is significantly reduced by the enzymatic method. It is found that the enzymatic dyeing method leads to improvement of dye absorption, color strength, soft hand, no change in color shade, low production costs (due to low dyeing temperature), and a significant reduction in environmental pollution.

Keywords: Eco-friendly, natural dyes, silk, traditional dyeing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 564

Authors: Erika Pigliapoco, Valerio Freschi, Alessandro Bogliolo

Abstract:

This work presents a new phonetic transcription system based on a tree of hierarchical pronunciation rules expressed as context-specific grapheme-phoneme correspondences. The tree is automatically inferred from a phonetic dictionary by incrementally analyzing deeper context levels, eventually representing a minimum set of exhaustive rules that pronounce without errors all the words in the training dictionary and that can be applied to out-of-vocabulary words. The proposed approach improves upon existing rule-tree-based techniques in that it makes use of graphemes, rather than letters, as elementary orthographic units. A new linear algorithm for the segmentation of a word in graphemes is introduced to enable outof- vocabulary grapheme-based phonetic transcription. Exhaustive rule trees provide a canonical representation of the pronunciation rules of a language that can be used not only to pronounce out-of-vocabulary words, but also to analyze and compare the pronunciation rules inferred from different dictionaries. The proposed approach has been implemented in C and tested on Oxford British English and Basic English. Experimental results show that grapheme-based rule trees represent phonetically sound rules and provide better performance than letter-based rule trees.

Keywords: Automatic phonetic transcription, pronunciation rules, hierarchical tree inference.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1915

Authors: Ahmet Yetik, Seyit Ali Kara, Cevat Özarpa

Abstract:

Load changes occur on natural gas and oil pipelines due to natural disasters. The displacement of the soil around the natural gas and oil pipes due to situations that may cause erosion, such as earthquakes, landslides, and floods, is the source of this load change. The exposure of natural gas and oil pipes to variable loads causes deformation, cracks, and breaks in these pipes. Such cracks and breaks can cause significant damage to people and the environment, including the risk of explosions. Especially with the examinations made after natural disasters, it can be easily understood which of the pipes has sustained more damage in those quake-affected regions. It has been determined that earthquakes in Türkiye have caused permanent damage to pipelines. This project was initiated in response to the identification of cracks and gas leaks in the insulation gaskets placed in the pipelines, especially at the junction points. In this study, a SCADA (Supervisory Control and Data Acquisition) application has been developed to monitor load changes caused by natural disasters. The developed SCADA application monitors the changes in the x, y, and z axes of the stresses occurring in the pipes with the help of strain gauge sensors placed on the pipes. For the developed SCADA system, test setups in accordance with the standards were created during the fieldwork. The test setups created were integrated into the SCADA system, and the system was followed up. Thanks to the SCADA system developed with the field application, the load changes that will occur on the natural gas and oil pipes are instantly monitored, and the accumulations that may create a load on the pipes and their surroundings are immediately intervened, and new risks that may arise are prevented. It has contributed to energy supply security, asset management, pipeline holistic management, and overall sustainability in the industry.

Keywords: Earthquake, natural gas pipes, oil pipes, voltage measurement, landslide.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 87

Authors: E. Podhovnik

Abstract:

Cultures play a role in business communication and in research. At the example of language in international business, this paper addresses the issue of how the research cultures of management research and linguistics as well as cultures as such can be linked. After looking at existing research on language in international business, this paper approaches communication in international business from a linguistic angle and attempts to explain communication issues in businesses based on linguistic research. Thus the paper makes a step into cross-disciplinary research combining management research with linguistics.

Keywords: Language in international business, sociolinguistics, ethnopragmatics, cultural scripts.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2357

Authors: Mehmet Ozcan

Abstract:

This study is designed to investigate errors emerged in written texts produced by 30 Turkish EFL learners with an explanatory, and thus, qualitative perspective. Erroneous language elements were identified by the researcher first and then their grammaticality and intelligibility were checked by five native speakers of English. The analysis of the data showed that it is difficult to claim that an error stems from only one single factor since different features of an error are triggered by different factors. Our findings revealed two different types of errors: those which stem from the interference of L1 with L2 and those which are developmental ones. The former type contains more global errors whereas the errors in latter type are more intelligible.

Keywords: Contrastive analysis, Error analysis, Language acquisition, Language transfer, Turkish

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2097

Authors: Ameneh Zare, Shahin Nematzadeh, Shahla Raghibdoust, Iran Kalbassi

Abstract:

Autism spectrum disorder is characterized by abnormalities in social communication, language abilities and repetitive behaviors. The present study focused on some grammatical deficits in autistic children. We evaluated the impairment of correct use of different Persian verb tenses in autistic children-s speech. Two standardized Language Test were administered then gathered data were analyzed. The main result of this study was significant difference between the mean scores of correct responses to present tense in comparison with past tense in Persian language. This study demonstrated that tense is severely impaired in autistic children-s speech. Our findings indicated those autistic children-s production of simple present/ past tense opposition to be better than production of future and past periphrastic forms (past perfect, present perfect, past progressive).

Keywords: Autism, Past, Persian Language, Present, Tense

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2745

Authors: P.P. Diale, S.S.L. Mkhize, E. Muzenda, J. Zimba

Abstract:

For more than 120 years, gold mining formed the backbone the South Africa-s economy. The consequence of mine closure was observed in large-scale land degradation and widespread pollution of surface water and groundwater. This paper investigates the feasibility of using natural zeolite in removing heavy metals contaminating the Wonderfonteinspruit Catchment Area (WCA), a water stream with high levels of heavy metals and radionuclide pollution. Batch experiments were conducted to study the adsorption behavior of natural zeolite with respect to Fe2+, Mn2+, Ni2+, and Zn2+. The data was analysed using the Langmuir and Freudlich isotherms. Langmuir was found to correlate the adsorption of Fe2+, Mn2+, Ni2+, and Zn2+ better, with the adsorption capacity of 11.9 mg/g, 1.2 mg/g, 1.3 mg/g, and 14.7 mg/g, respectively. Two kinetic models namely, pseudo-first order and pseudo second order were also tested to fit the data. Pseudo-second order equation was found to be the best fit for the adsorption of heavy metals by natural zeolite. Zeolite functionalization with humic acid increased its uptake ability.

Keywords: gold-mining, natural zeolites, water pollution, WestRand.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2514

Authors: Mehmet Ozcan

Abstract:

This study was designed to investigate the relationship between language and children’s construction of the concept of objects, actions, and states. Participants of this study are 120 children whose ages range from 3 to 14 years. Ten children participated from each age group and 10 adults participated as normative group. Data were collected using 28 words which were identified and grouped according to the purpose of this study. Participants were asked the question “What is x?’ for each word in a reserved room. The audio recorded data were transcribed and coded. The data were analyzed primarily qualitatively but quantitatively as well to support qualitative findings. The findings reveal that younger children rely more on their perceptual experience and linguistic input while 7-year-olds and older ones rely more on instructional language in the construction of the concepts related to objects, actions and states. Adults differ from all age groups with their usage of metaphors to refer to objects. It has been noted that linguistic, perceptual and instructional experiences work in an interwoven way but each one seems to be dominant at certain ages.

Keywords: Cognition, concept construction, first language acquisition, language, thought.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1084

Authors: S. Pesina, T. Solonchak

Abstract:

In the process of information transmission (concept verbalization) we deal mostly with the substance (contents), and then pay attention to the form. Recalling events from the remote past, often we cannot exactly reproduce specific heard or pronounced words, as well as the syntactic structures. We remember events, feelings, images; we recall the general contents of the discourse. The thought gets a specific language form only during the concept verbalization phase. With minimum time for pondering, depending on the language competence level, the grammar and syntactic shaping often occurs automatically with the use of famous models and stereotypes. This means that the language form adapts itself to the consciousness, and not vice versa.

Keywords: Lexical eidos, phenomenology, noema, polysemantic word, semantic core.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1933

Authors: Ahmet Kivanc Kutluca, Semahat Ozdemir

Abstract:

Urban disaster risks and vulnerabilities are great problems for Turkey. The annual loss of life and property through disaster in the world-s major metropolitan areas is increasing. Urban concentrations of the poor and less-informed in environmentally fragile locations suffer the impact of disaster disproportionately. Gecekondu (squatter) developments will compound the inherent risks associated with high-density environments, in appropriate technologies, and inadequate infrastructure. On the other hand, there are many geological disadvantages such as sitting on top of active tectonic plate boundaries, and why having avalanche, flood, and landslide and drought prone areas in Turkey. However, this natural formation is inevitable; the only way to survive in such a harsh geography is to be aware of importance of these natural events and to take political and physical measures. The main aim of this research is to bring up the magnitude of natural hazard risks in Izmir built-up zone, not being taken into consideration adequately. Because the dimensions of the peril are not taken seriously enough, the natural hazard risks, which are commonly well known, are not considered important or they are being forgotten after some time passes. Within this research, the magnitude of natural hazard risks for Izmir is being presented in the scope of concrete and local researches over Izmir risky areas.

Keywords: Earthquake, Flood, Landslide, Natural Hazard Planning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3095

Authors: Kanso Hassan, Elhore Ali, Soule-dupuy Chantal, Tazi Said

Abstract:

Information Retrieval has the objective of studying models and the realization of systems allowing a user to find the relevant documents adapted to his need of information. The information search is a problem which remains difficult because the difficulty in the representing and to treat the natural languages such as polysemia. Intentional Structures promise to be a new paradigm to extend the existing documents structures and to enhance the different phases of documents process such as creation, editing, search and retrieval. The intention recognition of the author-s of texts can reduce the largeness of this problem. In this article, we present intentions recognition system is based on a semi-automatic method of extraction the intentional information starting from a corpus of text. This system is also able to update the ontology of intentions for the enrichment of the knowledge base containing all possible intentions of a domain. This approach uses the construction of a semi-formal ontology which considered as the conceptualization of the intentional information contained in a text. An experiments on scientific publications in the field of computer science was considered to validate this approach.

Keywords: Information research, text analyzes, intentionalstructure, segmentation, ontology, natural language processing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1631

Authors: L. Ludovic, R. Daniel, S-E Tbahriti

Abstract:

Database management systems that integrate user preferences promise better solution for personalization, greater flexibility and higher quality of query responses. This paper presents a tentative work that studies and investigates approaches to express user preferences in queries. We sketch an extend capabilities of SQLf language that uses the fuzzy set theory in order to define the user preferences. For that, two essential points are considered: the first concerns the expression of user preferences in SQLf by so-called fuzzy commensurable predicates set. The second concerns the bipolar way in which these user preferences are expressed on mandatory and/or optional preferences.

Keywords: Flexible query language, relational database, userpreference.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1004

Authors: M. Behbahani-Nejad, Y. Shekari

Abstract:

A reduced order modeling approach for natural gas transient flow in pipelines is presented. The Euler equations are considered as the governing equations and solved numerically using the implicit Steger-Warming flux vector splitting method. Next, the linearized form of the equations is derived and the corresponding eigensystem is obtained. Then, a few dominant flow eigenmodes are used to construct an efficient reduced-order model. A well-known test case is presented to demonstrate the accuracy and the computational efficiency of the proposed method. The results obtained are in good agreement with those of the direct numerical method and field data. Moreover, it is shown that the present reduced-order model is more efficient than the conventional numerical techniques for transient flow analysis of natural gas in pipelines.

Keywords: Eigenmode, Natural Gas, Reduced Order Modeling, Transient Flow.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1926

Authors: Agnès Garletti

Abstract:

Our research aims at helping the tutor on line to evaluate the student-s cognitive processes. The student is a learner in French as a Second Language who studies an on-line socio-cognitive scenario in written communication. In our method, these cognitive processes are defined. For that, the language abilities and learning tasks are associated to cognitive operation. Moreover, the found cognitive processes are named with specific terms. The result was to create an instrumental pattern to question the learner about the cognitive processes used to build an item of written comprehension. Our research follows the principles of the third historical generation of studies on the cognitive activity of the text comprehension. The strength of our instrumental pattern stands in the precision and the logical articulation of the questions to the learner. However, the learner-s answers can still be subjective but the precision of the instrument restricts it.

Keywords: Cognitive processes, Evaluation pattern, French as asecond language, Socio-cognitive scenario, Written comprehension.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1486

Authors: Shahad Nagoor, Lucy Hederman, Kevin Koidl, Annalina Caputo

Abstract:

Doctors’ notes reflect their impressions, attitudes, clinical sense, and opinions about patients’ conditions and progress, and other information that is essential for doctors’ daily clinical decisions. Despite their value, clinical notes are insufficiently researched within the language processing community. Automatically extracting information from unstructured text data is known to be a difficult task as opposed to dealing with structured information such as physiological vital signs, images and laboratory results. The aim of this research is to investigate how Natural Language Processing (NLP) techniques and machine learning techniques applied to clinician notes can assist in doctors’ decision making in Intensive Care Unit (ICU) for coronavirus disease 2019 (COVID-19) patients. The hypothesis is that clinical outcomes like survival or mortality can be useful to influence the judgement of clinical sentiment in ICU clinical notes. This paper presents two contributions: first, we introduce COVID_ICU_BERT, a fine-tuned version of a clinical transformer model that can reliably predict clinical sentiment for notes of COVID patients in ICU. We train the model on clinical notes for COVID-19 patients, ones not previously seen by Bio_ClinicalBERT or Bio_Discharge_Summary_BERT. The model which was based on Bio_ClinicalBERT achieves higher predictive accuracy than the one based on Bio_Discharge_Summary_BERT (Acc 93.33%, AUC 0.98, and Precision 0.96). Second, we perform data augmentation using clinical contextual word embedding that is based on a pre-trained clinical model to balance the samples in each class in the data (survived vs. deceased patients). Data augmentation improves the accuracy of prediction slightly (Acc 96.67%, AUC 0.98, and Precision 0.92).

Keywords: BERT fine-tuning, clinical sentiment, COVID-19, data augmentation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 252

Authors: R. Walha, F. Drira, H. El-Abed, A. M. Alimi

Abstract:

The Automatic Speech Recognition (ASR) applied to Arabic language is a challenging task. This is mainly related to the language specificities which make the researchers facing multiple difficulties such as the insufficient linguistic resources and the very limited number of available transcribed Arabic speech corpora. In this paper, we are interested in the development of a HMM-based ASR system for Standard Arabic (SA) language. Our fundamental research goal is to select the most appropriate acoustic parameters describing each audio frame, acoustic models and speech recognition unit. To achieve this purpose, we analyze the effect of varying frame windowing (size and period), acoustic parameter number resulting from features extraction methods traditionally used in ASR, speech recognition unit, Gaussian number per HMM state and number of embedded re-estimations of the Baum-Welch Algorithm. To evaluate the proposed ASR system, a multi-speaker SA connected-digits corpus is collected, transcribed and used throughout all experiments. A further evaluation is conducted on a speaker-independent continue SA speech corpus. The phonemes recognition rate is 94.02% which is relatively high when comparing it with another ASR system evaluated on the same corpus.

Keywords: ASR, HMM, acoustical analysis, acoustic modeling, Standard Arabic language

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1772

Authors: Marie Alaghband, Niloofar Yousefi, Ivan Garibay

Abstract:

Facial expressions are important parts of both gesture and sign language recognition systems. Despite the recent advances in both fields, annotated facial expression datasets in the context of sign language are still scarce resources. In this manuscript, we introduce an annotated sequenced facial expression dataset in the context of sign language, comprising over 3000 facial images extracted from the daily news and weather forecast of the public tv-station PHOENIX. Unlike the majority of currently existing facial expression datasets, FePh provides sequenced semi-blurry facial images with different head poses, orientations, and movements. In addition, in the majority of images, identities are mouthing the words, which makes the data more challenging. To annotate this dataset we consider primary, secondary, and tertiary dyads of seven basic emotions of "sad", "surprise", "fear", "angry", "neutral", "disgust", and "happy". We also considered the "None" class if the image’s facial expression could not be described by any of the aforementioned emotions. Although we provide FePh as a facial expression dataset of signers in sign language, it has a wider application in gesture recognition and Human Computer Interaction (HCI) systems.

Keywords: Annotated Facial Expression Dataset, Sign Language Recognition, Gesture Recognition, Sequenced Facial Expression Dataset.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 707

Authors: A. Azadeh, Z. Raoofi

Abstract:

Natural gas, as one of the most important sources of energy for many of the industrial and domestic users all over the world, has a complex, huge supply chain which is in need of heavy investments in all the phases of exploration, extraction, production, transportation, storage and distribution. The main purpose of supply chain is to meet customers’ need efficiently and with minimum cost. In this study, with the aim of minimizing economic costs, different levels of natural gas supply chain in the form of a multi-echelon, multi-period fuzzy linear programming have been modeled. In this model, different constraints including constraints on demand satisfaction, capacity, input/output balance and presence/absence of a path have been defined. The obtained results suggest efficiency of the recommended model in optimal allocation and reduction of supply chain costs.

Keywords: Cost Approach, Fuzzy Theory, Linear Programming, Natural Gas Supply Chain.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2511

Authors: Mohd Pouzi Hamzah, Tengku Mohd Tengku Sembok

Abstract:

Phrases has a long history in information retrieval, particularly in commercial systems. Implicit semantic relationship between words in a form of BaseNP have shown significant improvement in term of precision in many IR studies. Our research focuses on linguistic phrases which is language dependent. Our results show that using BaseNP can improve performance although above 62% of words formation in Malay Language based on derivational affixes and suffixes.

Keywords: Information Retrieval, Malay Language, Semantic Relationship, Retrieval Effectiveness, Conceptual Indexing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1420

Authors: Yukiko Sasaki Alam, Shahid Alam

Abstract:

Syntactic parsing is vital for semantic treatment by many applications related to natural language processing (NLP), because form and content coincide in many cases. However, it has not yet reached the levels of reliable performance. By manually examining and analyzing individual machine translation output errors that involve syntax as well as semantics, this study attempts to discover what is required for improving syntactic and semantic parsing.

Keywords: Machine translation, error analysis, syntactic errors, knowledge required for parsing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1237