Search results for: text mining analysis

Authors: Esther Chiramal, Kelvin Soh Boon Kai

Abstract:

Explainable AI is a strong strategy implemented to understand complex black-box model predictions in a human-interpretable language. It provides the evidence required to execute the use of trustworthy and reliable AI systems. On the other hand, however, it also opens the door to locating possible vulnerabilities in an AI model. Traditional adversarial text attack uses word substitution, data augmentation techniques, and gradient-based attacks on powerful pre-trained Bidirectional Encoder Representations from Transformers (BERT) variants to generate adversarial sentences. These attacks are generally white-box in nature and not practical as they can be easily detected by humans e.g., Changing the word from “Poor” to “Rich”. We proposed a simple yet effective Grey-box cum Black-box approach that does not require the knowledge of the model while using a set of surrogate Transformer/BERT models to perform the attack using Explainable AI techniques. As Transformers are the current state-of-the-art models for almost all Natural Language Processing (NLP) tasks, an attack generated from BERT1 is transferable to BERT2. This transferability is made possible due to the attention mechanism in the transformer that allows the model to capture long-range dependencies in a sequence. Using the power of BERT generalisation via attention, we attempt to exploit how transformers learn by attacking a few surrogate transformer variants which are all based on a different architecture. We demonstrate that this approach is highly effective to generate semantically good sentences by changing as little as one word that is not detectable by humans while still fooling other BERT models.

Keywords: BERT, explainable AI, Grey-box text attack, transformer

Procedia PDF Downloads 133

Authors: Zineb Touati Hamad, Mohamed Ridda Laouar, Issam Bendib

Abstract:

With the massive development of technology today, the Arabic language has gained a prominent position among the languages most used for writing articles, expressing opinions, and also for citing in many websites, defying its growing sensitivity in terms of structure, language skills, diacritics, writing methods, etc. In the context of the spread of the Arabic language, the Holy Quran represents the most prevalent Arabic text today in many applications and websites for citation purposes or for the reading and learning rituals. The Quranic verses / surahs are published quickly and without cost, which may cause great concern to ensure the safety of the content from tampering and alteration. To protect the content of texts from distortion, it is necessary to refer to the original database and conduct a comparison process to extract the percentage of distortion. The disadvantage of this method is that it takes time, in addition to the lack of any guarantee on the integrity of the database itself as it belongs to one central party. Blockchain technology today represents the best way to maintain immutable content. Blockchain is a distributed database that stores information in blocks linked to each other through encryption, where the modification of each block can be easily known. To exploit these advantages, we seek in this paper to justify the use of this technique in preserving the integrity of Arabic texts sensitive to change by building a decentralized framework to authenticate and verify the integrity of the digital Quranic verses/surahs spread on websites.

Keywords: arabic text, authentication, blockchain, integrity, quran, verification

Procedia PDF Downloads 158

Authors: Eugenia P. Ramirez, Kevin Matthe Caramancion, Mia Eleazar

Abstract:

Getting the attention of students is a constant challenge to the instructors/lecturers. Although in the computer laboratories some networking and entertainment websites are blocked, yet, these websites have unlimited ways of attracting students to get into it. Thus, when an instructor gives a specific set of instructions, some students may not be able to follow sequentially the steps that are given. The instructor has to physically go to the specific remote terminal and show the student the details. Sometimes, during an examination in laboratory set-up, a proctor may prefer to give detailed and text-written instructions rather than verbal instructions. Even the mere calling of a specific student at any time will distract the whole class especially when activities are being performed. What is needed is : An application software that is able to lock the student's monitor and at the same time display the instructor’s screen; a software that is powerful enough to process in its side alone and manipulate a specific user’s terminal in terms of free configuration that is, without restrictions at the server level is a required functionality for a modern and optimal server structure; a software that is able to send text messages to students, per terminal or in group will be a solution. These features are found in LabSupport. This paper outlines the LabSupport application software framework to efficiently manage computer laboratory sessions and will include different modules: screen viewer, demonstration mode, monitor locking system, text messaging, and class management. This paper's ultimate aim is to provide a system that increases instructor productivity.

Keywords: application software, broadcast messaging, class management, locking system

Procedia PDF Downloads 437

Authors: Maphuti Georgina Kwata

Abstract:

Coal mining in Mpumalanga Province is known of contributing to the atmospheric pollution from various activities. Gold mining in North-West Province is known of also contributing to the atmospheric pollution especially with the production of radon gas. In this research directional dust deposition gauge was used to measure source of direction and meteorological data was used to determine the wind rose blowing and the influence of the seasonal changes. Fourteen months of dust collection was undertaken in Witbank Area and Carletonville Area. The results shows that the sources of direction for Ericson Dam its East in February 2010 and Tip Area shows that the source of direction its West in October 2010. In the East direction there were mining operations, power stations which contributed to the East to be the sources of direction. In the West direction there were smelters, power stations and agricultural activities which contributed for the source of direction to be the West direction for Driefontein Mine: East Recreational Village Club. The East of Leslie Williams hospital is the source of direction which also indicated that there dust generating activities such as mining operation, agricultural activities. The meteorological results for Emalahleni Area in summer and winter the wind rose blow with wind speed of 5-10 ms-1 from the East sector. Annual average for the wind rose blow its East South eastern sector with 20 ms-1 and day time the wind rose from northwestern sector with excess of 20 ms-1. The night time wind direction East-eastern direction with a maximum wind speed of 20 ms-1. The meteorogical results for Driefontein Mine show that North-western sector and north-eastern sector wind rose is blowing with 5-10 ms-1 win speed. Day time wind blows from the West sector and night time wind blows from the north sector. In summer the wind blows North-east sector with 5-10 ms-1 and winter wind blows from North-west and it’s also predominant. In spring wind blows from north-east. The conclusion is that not only mining operation where the directional dust deposit gauge were installed contributed to the source of direction also the power stations, smelters, and other activities nearby the mining operation contributed. The recommendations are the dust suppressant for unpaved roads should be used on a regular basis and there should be monitoring of the weather conditions (the wind speed and direction prior to blasting to ensure minimal emissions).

Keywords: directional dust deposition gauge, BS part 5 1747 dust deposit gauge, wind rose, wind blowing

Procedia PDF Downloads 502

Authors: Sarah Amodeo

Abstract:

Drawing on the author’s research about the experiences of female immigrant students in academic Adult Education, in Montreal, Quebec, this paper deconstructs the benefits of autoethnography as a methodology for educators in Adult Education. Autoethnography is an advantageous methodology for teachers in Adult Education as it allows for deep engagement, allowing for educators to reflect on student experiences and their day-to-day realities, and in turn, allowing for professional development, improved andragogy, and changes to classroom practices. Autoethnography is a qualitative research methodology that cultivates strategies for improving adult learning. The paper begins by outlining the context that inspired autoethnography for the author’s work, highlighting the emergence of autoethnography as a method, while examining how it is evolving and drawing on foundational work that continues to inspire research. The basic autoethnographic methodologies that are explored in this paper include the use of memory work in episode formation, the use of personal photographs, and textual readings of artworks. Memory work allows for the researcher to use their professional experience and the lived/shared experiences of their students in their research, drawing on episodes from their past. Personal photographs and descriptions of artwork allow researchers to explore images of learning environments/realities in ways that compliment student experiences. Major findings of the text are examined through the analysis of categories of autoethnography. Specific categories include realism, impressionism, and conceptualism which aid in orientating the analysis and emergent themes that develop through self-study. Finally, the text presents a discussion surrounding the limitations of autoethnography, with attention to the trustworthiness and ethical issues. The paper concludes with a consideration of the implications of autoethnography for adult educators in juxtaposition with youth sector work.

Keywords: artwork, autoethnography, conceptualism, episode formation, impressionism, memory work, personal photographs, and realism, realism

Procedia PDF Downloads 188

Authors: Arif Ahmed Mohammed Al-Ahdal

Abstract:

Poetry, tales, and fables have always been a part of the L1 repertoire and one that takes the learners to another amazing and fascinating world of imagination. The storytelling class and the genre of poems are activities greatly enjoyed by all age groups. The very significant idea behind their inclusion in the language curriculum is to sensitize young minds to a wide range of human emotions that are believed to greatly contribute to building their social resilience, emotional stability, empathy towards fellow creatures, and literacy. Quite certainly, the learning objective at this stage is not language acquisition (though it happens as an automatic process) but getting the young learners to be acquainted with an entire spectrum of what may be called the ‘noble’ abilities of the human race. They enrich their very existence, inspiring them to unearth ‘selves’ that help them as adults and enable them to co-exist fruitfully and symbiotically with their fellow human beings. By extension, ‘higher’ training in these literature genres shows the universality of human emotions, sufferings, aspirations, and hopes. The current study is anchored on the Reader-Response-Theory in literature learning, which suggests that the reader reconstructs work and re-enacts the author's creative role. Reiteratingly, literary works provide clues or verbal symbols in a linguistic system, widely accepted by everyone who shares the language, but everyone reads their own life experiences and situations into them. The significance of words depends on the reader, even if they have a typical relationship. In every reading, there is an interaction between the reader and the text. The process of reading is an experience in which the reader tries to comprehend the literary work, which surpasses its full potential since it provides emotional and intellectual reactions that are not anticipated from the document but cannot be affirmed just by the reader as a part of the text. The idea is that the text forms the basis of a unifying experience. A reinterpretation of the literary text may transform it into a guiding principle to respond to actual experiences and personal memories. The impulses delivered to the reader vary according to poetry or texts; nevertheless, the readers differ considerably even with the same material. Previous studies confirm that poetry is a useful tool for learning a language. This present paper works on these hypotheses and proposes to study the impetus given to L2 learning as a factor of exposure to poetry and meaningful stories in L1. The driving force behind the choice of this topic is the first-hand experience that the researcher had while teaching a literary text to a group of BA students who, as a reaction to the text, initially burst into tears and ultimately turned the class into an interactive session. The study also intends to compare the performance of male and female students post intervention using pre and post-tests, apart from undertaking a detailed inquiry via interviews with college learners of English to understand how L1 literature plays a great role in the acquisition of L2.

Keywords: SLA, literary text, poetry, tales, affective factors

Procedia PDF Downloads 75

Authors: Duncan Wallace, M-Tahar Kechadi

Abstract:

In recent years, Machine Learning (ML) approaches have been successfully applied to an analysis of patient symptom data in the context of disease diagnosis, at least where such data is well codified. However, much of the data present in Electronic Health Records (EHR) are unlikely to prove suitable for classic ML approaches. Furthermore, as scores of data are widely spread across both hospitals and individuals, a decentralized, computationally scalable methodology is a priority. The focus of this paper is to develop a method to predict outliers in an out-of-hours healthcare provision center (OOHC). In particular, our research is based upon the early identification of patients who have underlying conditions which will cause them to repeatedly require medical attention. OOHC act as an ad-hoc delivery of triage and treatment, where interactions occur without recourse to a full medical history of the patient in question. Medical histories, relating to patients contacting an OOHC, may reside in several distinct EHR systems in multiple hospitals or surgeries, which are unavailable to the OOHC in question. As such, although a local solution is optimal for this problem, it follows that the data under investigation is incomplete, heterogeneous, and comprised mostly of noisy textual notes compiled during routine OOHC activities. Through the use of Deep Learning methodologies, the aim of this paper is to provide the means to identify patient cases, upon initial contact, which are likely to relate to such outliers. To this end, we compare the performance of Long Short-Term Memory, Gated Recurrent Units, and combinations of both with Convolutional Neural Networks. A further aim of this paper is to elucidate the discovery of such outliers by examining the exact terms which provide a strong indication of positive and negative case entries. While free-text is the principal data extracted from EHRs for classification, EHRs also contain normalized features. Although the specific demographical features treated within our corpus are relatively limited in scope, we examine whether it is beneficial to include such features among the inputs to our neural network, or whether these features are more successfully exploited in conjunction with a different form of a classifier. In this section, we compare the performance of randomly generated regression trees and support vector machines and determine the extent to which our classification program can be improved upon by using either of these machine learning approaches in conjunction with the output of our Recurrent Neural Network application. The output of our neural network is also used to help determine the most significant lexemes present within the corpus for determining high-risk patients. By combining the confidence of our classification program in relation to lexemes within true positive and true negative cases, with an inverse document frequency of the lexemes related to these cases, we can determine what features act as the primary indicators of frequent-attender and non-frequent-attender cases, providing a human interpretable appreciation of how our program classifies cases.

Keywords: artificial neural networks, data-mining, machine learning, medical informatics

Procedia PDF Downloads 126

Authors: Kurt S. Candilas

Abstract:

This expressive critical study is an effort to bring in light new interpretation of Robert Frost poem 'The Road Not Taken' as a reflection of his indecisiveness in life. Specifically, it aims at examining Frost’s inner being, emphasizing his own self and experiences in the poem or text. The study employs the qualitative research design which made use of discourse analysis using the critical theory of expressivism as the main guide. In acquiring the data of the study, the art of historiography is used such as autobiographical and/or biographical notes, sources documents, and web information. In executing the methods involved in this study, it is observed that the poem shows a naturalist implicatures, expressing Frost’s strong feelings and emotions being devoid of free will and a narrow bit of confusions and ambiguities with his indecisions in life.

Keywords: The Road Not Taken, expressivism, indecisiveness, naturalist implicatures

Procedia PDF Downloads 339

Authors: Lu Song Ma Li Zhi

Abstract:

With the rapid advancement of artificial intelligence technology, large language models (LLMs) have become a milestone in the field of natural language processing, demonstrating remarkable capabilities in semantic understanding, intelligent question answering, and text generation. These models are gradually penetrating various industries, particularly showcasing significant application potential in the data analysis domain. However, retraining or fine-tuning these models requires substantial computational resources and ample downstream task datasets, which poses a significant challenge for many enterprises and research institutions. Without modifying the internal parameters of the large models, prompt engineering techniques can rapidly adapt these models to new domains. This paper proposes a prompt design strategy aimed at leveraging the capabilities of large language models to automate the generation of data analysis code. By carefully designing prompts, data analysis requirements can be described in natural language, which the large language model can then understand and convert into executable data analysis code, thereby greatly enhancing the efficiency and convenience of data analysis. This strategy not only lowers the threshold for using large models but also significantly improves the accuracy and efficiency of data analysis. Our approach includes requirements for the precision of natural language descriptions, coverage of diverse data analysis needs, and mechanisms for immediate feedback and adjustment. Experimental results show that with this prompt design strategy, large language models perform exceptionally well in multiple data analysis tasks, generating high-quality code and significantly shortening the data analysis cycle. This method provides an efficient and convenient tool for the data analysis field and demonstrates the enormous potential of large language models in practical applications.

Keywords: large language models, prompt design, data analysis, code generation

Procedia PDF Downloads 24

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

Abstract:

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

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

Procedia PDF Downloads 366

Authors: Vishwanath Pethri Kamath, Jayantha Gowda Sarapanahalli, Vishal Mishra, Siddhesh Balwant Bandgar

Abstract:

Recognition of emotional information is essential in any form of communication. Growing HCI (Human-Computer Interaction) in recent times indicates the importance of understanding of emotions expressed and becomes crucial for improving the system or the interaction itself. In this research work, textual data for emotion recognition is used. The text being the least expressive amongst the multimodal resources poses various challenges such as contextual information and also sequential nature of the language construction. In this research work, the proposal is made for a neural architecture to resolve not less than 8 emotions from textual data sources derived from multiple datasets using google pre-trained word2vec word embeddings and a Multi-head attention-based bidirectional LSTM model with a one-vs-all Multi-Level Classification. The emotions targeted in this research are Anger, Disgust, Fear, Guilt, Joy, Sadness, Shame, and Surprise. Textual data from multiple datasets were used for this research work such as ISEAR, Go Emotions, Affect datasets for creating the emotions’ dataset. Data samples overlap or conflicts were considered with careful preprocessing. Our results show a significant improvement with the modeling architecture and as good as 10 points improvement in recognizing some emotions.

Keywords: text emotion recognition, bidirectional LSTM, multi-head attention, multi-level classification, google word2vec word embeddings

Procedia PDF Downloads 172

Authors: Chen Yang, Jun Hu, Ping Li, Lili Xue

Abstract:

Most companies pay careful attention to consumer feedback collection, so it is popular to find the ‘feedback’ button of all kinds of mobile apps. Yet it is much more changeling to analyze these feedback texts and to catch the true feelings of a consumer regarding either a problem or a complimentary of consumers who hands out the feedback. Especially to the Chinese content, it is possible that; in one context the Chinese feedback expresses positive feedback, but in the other context, the same Chinese feedback may be a negative one. For example, in Chinese, the feedback 'operating with loudness' works well with both refrigerator and stereo system. Apparently, this feedback towards a refrigerator shows negative feedback; however, the same feedback is positive towards a stereo system. By introducing Bradley, M. and Lang, P.'s Affective Norms for English Text (ANET) theory and Bucci W.’s Referential Activity (RA) theory, we, usability researchers at Pingan, are able to decipher the feedback and to find the hidden feelings behind the content. We subtract 2 disciplines ‘valence’ and ‘dominance’ out of 3 of ANET and 2 disciplines ‘concreteness’ and ‘specificity’ out of 4 of RA to organize our own rating system with a scale of 1 to 5 points. This rating system enables us to judge the feelings/emotion behind each feedback, and it works well with both single word/phrase and a whole paragraph. The result of the rating reflects the strength of the feeling/emotion of the consumer when he/she is typing the feedback. In our daily work, we first require a consumer to answer the net promoter score (NPS) before writing the feedback, so we can determine the feedback is positive or negative. Secondly, we code the feedback content according to company problematic list, which contains 200 problematic items. In this way, we are able to collect the data that how many feedbacks left by the consumer belong to one typical problem. Thirdly, we rate each feedback based on the rating system mentioned above to illustrate the strength of the feeling/emotion when our consumer writes the feedback. In this way, we actually obtain two kinds of data 1) the portion, which means how many feedbacks are ascribed into one problematic item and 2) the severity, how strong the negative feeling/emotion is when the consumer is writing this feedback. By crossing these two, and introducing the portion into X-axis and severity into Y-axis, we are able to find which typical problem gets the high score in both portion and severity. The higher the score of a problem has, the more urgent a problem is supposed to be solved as it means more people write stronger negative feelings in feedbacks regarding this problem. Moreover, by introducing hidden Markov model to program our rating system, we are able to computerize the scoring system and are able to process thousands of feedback in a short period of time, which is efficient and accurate enough for the industrial purpose.

Keywords: computerized scoring system, feeling/emotion of consumer feedback, referential activity, text mining

Procedia PDF Downloads 171

Authors: Imran Dayan, Ashiqul Khan

Abstract:

Internal corporate fraud, which is fraud carried out by internal stakeholders of a company, affects the well-being of the organisation just like its external counterpart. Even if such an act is carried out for the short-term benefit of a corporation, the act is ultimately harmful to the entity in the long run. Internal fraud is often carried out by relying upon aberrations from usual business processes. Business processes are the lifeblood of a company in modern managerial context. Such processes are developed and fine-tuned over time as a corporation grows through its life stages. Modern corporations have embraced technological innovations into their business processes, and Enterprise Resource Planning (ERP) systems being at the heart of such business processes is a testimony to that. Since ERP systems record a huge amount of data in their event logs, the logs are a treasure trove for anyone trying to detect any sort of fraudulent activities hidden within the day-to-day business operations and processes. This research utilises the ERP systems in place within corporations to assess the likelihood of prospective internal fraud through developing a framework for measuring the risks of fraud through Process Mining techniques and hence finds risky designs and loose ends within these business processes. This framework helps not only in identifying existing cases of fraud in the records of the event log, but also signals the overall riskiness of certain business processes, and hence draws attention for carrying out a redesign of such processes to reduce the chance of future internal fraud while improving internal control within the organisation. The research adds value by applying the concepts of Process Mining into the analysis of data from modern day applications of business process records, which is the ERP event logs, and develops a framework that should be useful to internal stakeholders for strengthening internal control as well as provide external auditors with a tool of use in case of suspicion. The research proves its usefulness through a few case studies conducted with respect to big corporations with complex business processes and an ERP in place.

Keywords: enterprise resource planning, fraud risk framework, internal corporate fraud, process mining

Procedia PDF Downloads 327

Authors: Gui Yang Wu, Bo Wang, Xin Wang

Abstract:

Nowadays, 5G service-based interface architecture uses text-based payload like JSON to transfer business data between network functions, which has obvious advantages as internet services but causes unnecessarily larger traffic. In this paper, a new 5G application payload size reduction method is presented to provides the mechanism to negotiate about new capability between network functions when network communication starts up and how 5G application data are reduced according to negotiated information with peer network function. Without losing the advantages of 5G text-based payload, this method demonstrates an excellent result on application payload size reduction and does not increase the usage quota of computing resource. Implementation of this method does not impact any standards or specifications and not change any encoding or decoding functionality too. In a real 5G network, this method will contribute to network efficiency and eventually save considerable computing resources.

Keywords: 5G, JSON, payload size, service-based interface

Procedia PDF Downloads 176

Authors: Oktanika Wahyu Nurjanah, Anggun Fitriana Dewi

Abstract:

An undergraduate thesis is one of the academic writings which should fulfill some characteristics, one of them is coherency. Moreover, a coherence of a text depends on the usage of discourse markers. In other word, discourse markers take an essential role in writing. Therefore, the researchers aim to know the awareness of the discourse markers usage in writing the under-graduate thesis of an English Education student at Sebelas Maret University. This research uses a qualitative case study in order to obtain a deep analysis. The sample of this research is an under-graduate thesis of English Education student in Sebelas Maret University which chosen based on some criteria. Additionally, the researchers were guided by some literature attempted to group the discourse markers based on their functions. Afterward, the analysis was held based on it. From the analysis, it found that the awareness of discourse markers usage is moderate. The last point, the researcher suggest undergraduate students to familiarize themselves with discourse markers, especially for those who want to write thesis.

Keywords: discourse markers, English education, thesis writing, undergraduate student

Procedia PDF Downloads 350

Authors: Nhleko Monique Chiloane

Abstract:

The gold mining industry has predominantly used ammonium nitrate fuel oil (ANFO) explosives for decades, although these are known to be “gassier” and their detonation results in toxic fumes, for example, carbon monoxide (CO), nitrogen oxides (NOx) and ammonia. Re-entry into underground workings too soon after blasting can lead to fatal exposure to toxic fumes. It is, therefore, required that the polluted air be removed from the affected areas within a reasonable period before employees' re-entry into the working area. Post-blast re-entry times have therefore been described as a productivity bottleneck. The known causes of post-blast fumes are water ingress, incorrect fuel to oxygen ratio, confinement, explosive additives etc. To prevent or minimize post-blast fumes, some researchers have used neutralization, re-burning technique and non-explosive products or different oxidizing agents. The use of commercial explosives without nitrate oxidizing agents can also minimize the production of blasting fumes and thereby reduce the time needed for the clearance of these fumes to allow workers to re-enter the underground workings safely. The reduction in non-production time directly contributes to an increase in the available time per shift for productive work, thus leading to continuous mining. However, owing to its low cost and ease of use, ANFO is still widely used in South African underground blasting operations.

Keywords: post-blast fumes, continuous mining, ammonium nitrate explosive, non-explosive blasting, re-entry period

Procedia PDF Downloads 177

Authors: Mohsen Maraoui

Abstract:

In the aim of natural language processing applications improvement, such as information retrieval, machine translation, lexical disambiguation, we focus on statistical approach to semantic indexing for multilingual text documents based on conceptual network formalism. We propose to use this formalism as an indexing language to represent the descriptive concepts and their weighting. These concepts represent the content of the document. Our contribution is based on two steps. In the first step, we propose the extraction of index terms using the multilingual lexical resource Euro WordNet (EWN). In the second step, we pass from the representation of index terms to the representation of index concepts through conceptual network formalism. This network is generated using the EWN resource and pass by a classification step based on association rules model (in attempt to discover the non-taxonomic relations or contextual relations between the concepts of a document). These relations are latent relations buried in the text and carried by the semantic context of the co-occurrence of concepts in the document. Our proposed indexing approach can be applied to text documents in various languages because it is based on a linguistic method adapted to the language through a multilingual thesaurus. Next, we apply the same statistical process regardless of the language in order to extract the significant concepts and their associated weights. We prove that the proposed indexing approach provides encouraging results.

Keywords: concept extraction, conceptual network formalism, fuzzy association rules, multilingual thesaurus, semantic indexing

Procedia PDF Downloads 137

Authors: Carla Palencia-Aguilar

Abstract:

Calculations of Net Carbon Balance can be obtained by means of Net Biome Productivity (NBP), Net Ecosystem Productivity (NEP), and Net Primary Production (NPP). The latter is an important component of the biosphere carbon cycle and is easily obtained data from MODIS MOD17A3HGF; however, the results are only available yearly. To overcome data availability, bands 33 to 36 from MODIS MYD021KM (obtained on a daily basis) were analyzed and compared with NPP data from the years 2000 to 2021 in 7 sites where surface mining takes place in the Colombian territory. Coal, Gold, Iron, and Limestone were the minerals of interest. Scales and Units as well as thermal anomalies, were considered for net carbon balance per location. The NPP time series from the satellite images were filtered by using two Matlab filters: First order and Discrete Transfer. After filtering the NPP time series, comparing the graph results from the satellite’s image value, and running a linear regression, the results showed R2 from 0,72 to 0,85. To establish comparable units among NPP and bands 33 to 36, the Greenhouse Gas Equivalencies Calculator by EPA was used. The comparison was established in two ways: one by the sum of all the data per point per year and the other by the average of 46 weeks and finding the percentage that the value represented with respect to NPP. The former underestimated the total CO2 emissions. The results also showed that coal and gold mining in the last 22 years had less CO2 emissions than limestone, with an average per year of 143 kton CO2 eq for gold, 152 kton CO2 eq for coal, and 287 kton CO2 eq for iron. Limestone emissions varied from 206 to 441 kton CO2 eq. The maximum emission values from unfiltered data correspond to 165 kton CO2 eq. for gold, 188 kton CO2 eq. for coal, and 310 kton CO2 eq. for iron and limestone, varying from 231 to 490 kton CO2 eq. If the most pollutant limestone site improves its production technology, limestone could count with a maximum of 318 kton CO2 eq emissions per year, a value very similar respect to iron. The importance of gathering data is to establish benchmarks in order to attain 2050’s zero emissions goal.

Keywords: carbon dioxide, NPP, MODIS, MINING

Procedia PDF Downloads 100

Authors: Ahmed Hammed, Wady Naanaa

Abstract:

In this paper, we propose a general approach to deal with the problem of a convolutive mixture of images. We use a direct blind source separation method by adding only one non-statistical justified constraint describing the relationships between different mixing matrix at the aim to make its resolution easy. This method can be applied, provided that this constraint is known, to degraded document affected by the overlapping of text-patterns and images. This is due to chemical and physical reactions of the materials (paper, inks,...) occurring during the documents aging, and other unpredictable causes such as humidity, microorganism infestation, human handling, etc. We will demonstrate that this problem corresponds to a convolutive mixture of images. Subsequently, we will show how the validation of our method through numerical examples. We can so obtain clear images from unreadable ones which can be caused by pages superposition, a phenomenon similar to that we find every often in archival documents.

Keywords: blind source separation, convoluted mixture, degraded documents, text-patterns overlapping

Procedia PDF Downloads 321

Authors: Gintaras Mitrulevičius

Abstract:

This text, which is based on the conference report, seeks to briefly examine the relationship between the concepts of social democracy and democratic socialism, drawing attention to the essential aspects of its development and, in particular, discussing the contradictions in the relationship between these concepts in the modern period. In the preparation of this text, such research methods as historical, historical-comparative methods were used, as well as methods of analyzing, synthesizing, and generalizing texts. The history of the use of terms in social democracy and democratic socialism shows that these terms were used alternately and almost synonymously. At the end of the 20th century, traditional social democracy was transformed into the so-called "new social democracy." Many of the new social democrats do not consider themselves democratic socialists and avoid the historically characteristic identification of social democracy with democratic socialism. It has become quite popular to believe that social democracy is a separate ideology from democratic socialism. Or that it has become a variant of the ideology of liberalism. This is a testimony to the crisis of ideological self-awareness of social democracy. Since the beginning of the 21st century, social democracy has also experienced a growing crisis of electoral support. This, among other things, led to her slight shift to the left. In this context, some social democrats are once again talking about democratic socialism. The rise of the ideas of democratic socialism in the United States was catalyzed by Bernie Sanders. But the proponents of democratic socialism in the United States have different concepts of democratic socialism. In modern Europe, democratic socialism is also spoken of by leftists of non-social democratic origin, whose understanding is different from that of democratic socialism inherent in classical social democracy. Some political scientists also single out the concepts in question. Analysis of the problem shows that there are currently several concepts of democratic socialism on the spectrum of the political left, both social-democratic and non-social-democratic.

Keywords: democratic socializm, socializm, social democracy, new social democracy, political ideologies

Procedia PDF Downloads 110

Authors: Mustafa Col, Funda Gul Koc, Merve Yangaz, Eylem Subasi, Can Akbasoglu

Abstract:

G38NiCrMo8-4-4 steel is widely used in mining industries, machine parts, gears due to its high strength and toughness properties. In this study, microstructure, wear and mechanical properties of G38NiCrMo8-4-4 steel modified with boron used in the mining industry were investigated. For this purpose, cast materials were alloyed by melting in an induction furnace to include boron with the rates of 0 ppm, 15 ppm, and 50 ppm (wt.) and were formed in the dimensions of 150x200x150 mm by casting into the sand mould. Homogenization heat treatment was applied to the specimens at 1150˚C for 7 hours. Then all specimens were austenitized at 930˚C for 1 hour, quenched in the polymer solution and tempered at 650˚C for 1 hour. Microstructures of the specimens were investigated by using light microscope and SEM to determine the effect of boron and heat treatment conditions. Changes in microstructure properties and material hardness were obtained due to increasing boron content and heat treatment conditions after microstructure investigations and hardness tests. Wear tests were carried out using a pin-on-disc tribometer under dry sliding conditions. Charpy V notch impact test was performed to determine the toughness properties of the specimens. Fracture and worn surfaces were investigated with scanning electron microscope (SEM). The results show that boron element has a positive effect on the hardness and wear properties of G38NiCrMo8-4-4 steel.

Keywords: G38NiCrMo8-4-4 steel, boron, heat treatment, microstructure, wear, mechanical properties

Procedia PDF Downloads 193

Authors: Olaniyi Awe, Adelana R. Adetunji, Abraham Adeleke

Abstract:

Field observation revealed a lot of artisanal gold mining activities in Ilesa gold belt of southwestern Nigeria. The possibility of alluvial and lode gold deposits in commercial quantities around this location is very high, as there are many resident artisanal gold miners who have been mining and trading alluvial gold ore for decades and to date in the area. Their major process of solid gold recovery from its ore is by gravity concentration using the convectional panning method. This method is simple to learn and fast to recover gold from its alluvial ore, but its effectiveness is based on rules of thumb and the artisanal miners' experience in handling gold ore panning tool while processing the ore. Research samples from five alluvial gold ore tailings dumps were collected and studied. Samples were subjected to particle size analysis and mineralogical and elemental characterization using X-Ray Diffraction (XRD) and Particle-Induced X-ray Emission (PIXE) methods, respectively. The results showed that the tailings were of major quartz in association with albite, plagioclase, mica, gold, calcite and sulphide minerals. The elemental composition analysis revealed a 15ppm of gold concentration in particle size fraction of -90 microns in one of the tailings dumps investigated. These results are significant. It is recommended that heaps of panning tailings should be further reprocessed using other gold recovery methods such as shaking tables, flotation and controlled cyanidation that can efficiently recover fine gold particles that were previously lost into the gold panning tailings. The tailings site should also be well controlled and monitored so that these heavy minerals do not find their way into surrounding water streams and rivers, thereby causing health hazards.

Keywords: gold ore, panning, PIXE, tailings, XRD

Procedia PDF Downloads 84

Authors: A. Ali, V. Strezov, P. Davies, I. Wright, T. Kan

Abstract:

The environmental impacts arising from mining activities affect the air, water, and soil quality. Impacts may result in unexpected and adverse environmental outcomes. This study reports on the impact of coal production on sediment in Sydney region of Australia. The sediment samples upstream and downstream from the discharge points from three mines were taken, and 80 parameters were tested. The results were assessed against sediment quality based on presence of metals. The study revealed the increment of metal content in the sediment downstream of the reference locations. In many cases, the sediment was above the Australia and New Zealand Environment Conservation Council and international sediment quality guidelines value (SQGV). The major outliers to the guidelines were nickel (Ni) and zinc (Zn).

Keywords: coal mine, environmental impact, produced water, sediment quality guidelines value (SQGV)

Procedia PDF Downloads 300

Authors: M. F. Mamabolo

Abstract:

Mining activities are identified as the most significant source of heavy metal contamination in river basins, due to inadequate disposal of mining waste thus resulting in acid mine drainage. Waste materials generated from gold mining and processing have severe and widespread impacts on water resources. Therefore, a total of 30 water samples were collected from Fig Tree Creek, Kaapriver, Sheba mine stream & Sauid kaap river to investigate the impact of gold mines on the Kaap River system. Physicochemical parameters (pH, EC and TDS) were taken using a BANTE 900P portable water quality meter. The concentration of Fe, Cu, Co, and SO₄²⁻ in water samples were analysed using Inductively Coupled Plasma-Mass spectrophotometry (ICP-MS) at 0.01 mg/L. The results were compared to the regulatory guideline of the World Health Organization (WHO) and the South Africa National Standards (SANS). It was found that Fe, Cu and Co were below the guideline values while SO₄²⁻ detected in Sheba mine stream exceeded the 250 mg/L limit for both seasons, attributed by mine wastewater. SO₄²⁻ was higher in wet season due to high evaporation rates and greater interaction between rocks and water. The pH of all the streams was within the limit (≥5 to ≤9.7), however EC of the Sheba mine stream, Suid Kaap River & where the tributary connects with the Fig Tree Creek exceeded 1700 uS/m, due to dissolved material. The TDS of Sheba mine stream exceeded 1000 mg/L, attributed by high SO₄²⁻ concentration. While the tributary connecting to the Fig Tree Creek exceed the value due to pollution from household waste, runoff from agriculture etc. In conclusion, the water from all sampled streams were safe for consumption due to low concentrations of physicochemical parameters. However, elevated concentration of SO₄²⁻ should be monitored and managed to avoid water quality deterioration in the Kaap River system.

Keywords: Kaap river system, mines, heavy metals, sulphate

Procedia PDF Downloads 76

Authors: Thomas F. Ducey, Kristin M. Trippe, James A. Ippolito, Jeffrey M. Novak, Mark G. Johnson, Gilbert C. Sigua

Abstract:

The Oronogo-Duenweg mining belt –approximately 20 square miles around the Joplin, Missouri area– is a designated United States Environmental Protection Agency Superfund site due to lead-contaminated soil and groundwater by former mining and smelting operations. Over almost a century of mining (from 1848 to the late 1960’s), an estimated ten million tons of cadmium, lead, and zinc containing material have been deposited on approximately 9,000 acres. Sites that have undergone remediation, in which the O, A, and B horizons have been removed along with the lead contamination, the exposed C horizon remains incalcitrant to revegetation efforts. These sites also suffer from poor soil microbial activity, as measured by soil extracellular enzymatic assays, though 16S ribosomal ribonucleic acid (rRNA) indicates that microbial diversity is equal to sites that have avoided mine-related contamination. Soil analysis reveals low soil organic carbon, along with high levels of bio-available zinc, that reflect the poor soil fertility conditions and low microbial activity. Our study looked at the use of several materials to restore and remediate these sites, with the goal of improving soil health. The following materials, and their purposes for incorporation into the study, were as follows: manure-based biochar for the binding of zinc and other heavy metals responsible for phytotoxicity, locally sourced biosolids and compost to incorporate organic carbon into the depleted soils, effective microorganisms harvested from nearby pristine sites to provide a stable community for nutrient cycling in the newly composited 'soil material'. Our results indicate that all four materials used in conjunction result in the greatest benefit to these mine-impacted soils, based on above ground biomass, microbial biomass, and soil enzymatic activities.

Keywords: locally effective microorganisms, biochar, remediation, reclamation

Procedia PDF Downloads 214

Authors: S. Sharan Sundar, Nithish B. Moudhgalya, Nidhi Bhandari, Vineeth Vijayaraghavan

Abstract:

Automatic Short Answer Grading is one of the prime applications of artificial intelligence in education. Several approaches involving the utilization of selective handcrafted features, graphical matching techniques, concept identification and mapping, complex deep frameworks, sentence embeddings, etc. have been explored over the years. However, keeping in mind the real-world application of the task, these solutions present a slight overhead in terms of computations and resources in achieving high performances. In this work, a simple and effective solution making use of elemental features based on statistical, linguistic properties, and word-based similarity measures in conjunction with tree-based classifiers and regressors is proposed. The results for classification tasks show improvements ranging from 1%-30%, while the regression task shows a stark improvement of 35%. The authors attribute these improvements to the addition of multiple similarity scores to provide ensemble of scoring criteria to the models. The authors also believe the work could reinstate that classical natural language processing techniques and simple machine learning models can be used to achieve high results for short answer grading.

Keywords: artificial intelligence, intelligent systems, natural language processing, text mining

Procedia PDF Downloads 129

Authors: Smah Almotiri

Abstract:

One of the most common fields of natural language processing (NLP) is sentimental analysis. The inferred feeling in the text can be successfully mined for various events using sentiment analysis. Twitter is viewed as a reliable data point for sentimental analytics studies since people are using social media to receive and exchange different types of data on a broad scale during the COVID-19 epidemic. The processing of such data may aid in making critical decisions on how to keep the situation under control. The aim of this research is to look at how sentimental states differed in a single geographic region during the lockdown at two different times.1162 tweets were analyzed related to the COVID-19 pandemic lockdown using keywords hashtags (lockdown, COVID-19) for the first sample tweets were from March 23, 2020, until April 23, 2020, and the second sample for the following year was from March 1, 2020, until April 4, 2020. Natural language processing (NLP), which is a form of Artificial intelligence, was used for this research to calculate the sentiment value of all of the tweets by using AFINN Lexicon sentiment analysis method. The findings revealed that the sentimental condition in both different times during the region's lockdown was positive in the samples of this study, which are unique to the specific geographical area of New Zealand. This research suggests applying machine learning sentimental methods such as Crystal Feel and extending the size of the sample tweet by using multiple tweets over a longer period of time.

Keywords: sentiment analysis, Twitter analysis, lockdown, Covid-19, AFINN, NodeJS

Procedia PDF Downloads 187

Authors: Yufen Qin

Abstract:

Topic-to-Essay generation is a challenging task in Natural language processing, which aims to generate novel, diverse, and topic-related text based on user input. Previous research has overlooked the generation of articles under the constraints of event elements, resulting in issues such as incomplete event elements and logical inconsistencies in the generated results. To fill this gap, this paper proposes an event-constrained approach for a topic-to-essay generation that enforces the completeness of event elements during the generation process. Additionally, a language model is employed to verify the logical consistency of the generated results. Experimental results demonstrate that the proposed model achieves a better BLEU-2 score and performs better than the baseline in terms of subjective evaluation on a real dataset, indicating its capability to generate higher-quality topic-related text.

Keywords: event element, language model, natural language processing, topic-to-essay generation.

Procedia PDF Downloads 232

Authors: Shengnan Chen, Shuhua Wang

Abstract:

Successful production of hydrocarbon from unconventional tight oil reserves has changed the energy landscape in North America. The oil contained within these reservoirs typically will not flow to the wellbore at economic rates without assistance from advanced horizontal well and multi-stage hydraulic fracturing. Efficient and economic development of these reserves is a priority of society, government, and industry, especially under the current low oil prices. Meanwhile, society needs technological and process innovations to enhance oil recovery while concurrently reducing environmental impacts. Recently, big data analysis and artificial intelligence become very popular, developing data-driven insights for better designs and decisions in various engineering disciplines. However, the application of data mining in petroleum engineering is still in its infancy. The objective of this research aims to apply intelligent data analysis and data-driven models to exploit unconventional oil reserves both efficiently and economically. More specifically, a comprehensive database including the reservoir geological data, reservoir geophysical data, well completion data and production data for thousands of wells is firstly established to discover the valuable insights and knowledge related to tight oil reserves development. Several data analysis methods are introduced to analysis such a huge dataset. For example, K-means clustering is used to partition all observations into clusters; principle component analysis is applied to emphasize the variation and bring out strong patterns in the dataset, making the big data easy to explore and visualize; exploratory factor analysis (EFA) is used to identify the complex interrelationships between well completion data and well production data. Different data mining techniques, such as artificial neural network, fuzzy logic, and machine learning technique are then summarized, and appropriate ones are selected to analyze the database based on the prediction accuracy, model robustness, and reproducibility. Advanced knowledge and patterned are finally recognized and integrated into a modified self-adaptive differential evolution optimization workflow to enhance the oil recovery and maximize the net present value (NPV) of the unconventional oil resources. This research will advance the knowledge in the development of unconventional oil reserves and bridge the gap between the big data and performance optimizations in these formations. The newly developed data-driven optimization workflow is a powerful approach to guide field operation, which leads to better designs, higher oil recovery and economic return of future wells in the unconventional oil reserves.

Keywords: big data, artificial intelligence, enhance oil recovery, unconventional oil reserves

Procedia PDF Downloads 281

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 312