Search results for: automatic summarization

Authors: Xin Jiao, Xin Zhang, Jian Fan, Zhenwei Cai, Yiming Xu

Abstract:

Tower cranes play a crucial role in the construction industry, facilitating the vertical and horizontal movement of materials and aiding in building construction, especially for high-rise structures. However, tower crane accidents can lead to severe consequences, highlighting the importance of effective safety management and inspection. This paper presents an innovative approach to tower crane inspection utilizing Unmanned Aerial Vehicles (UAVs) and an Intelligent Inspection APP System. The system leverages UAVs equipped with high-definition cameras to conduct efficient and comprehensive inspections, reducing manual labor, inspection time, and risk. By integrating advanced technologies such as Real-Time Kinematic (RTK) positioning and digital image processing, the system enables precise route planning and collection of safety hazards images. A case study conducted on a construction site demonstrates the practicality and effectiveness of the proposed method, showcasing its potential to enhance tower crane safety. On-site testing of UAV intelligent inspections reveals key findings: efficient tower crane hazard inspection within 30 minutes, with a full-identification capability coverage rates of 76.3%, 64.8%, and 76.2% for major, significant, and general hazards respectively and a preliminary-identification capability coverage rates of 18.5%, 27.2%, and 19%, respectively. Notably, UAVs effectively identify various tower crane hazards, except for those requiring auditory detection. The limitations of this study primarily involve two aspects: Firstly, during the initial inspection, manual drone piloting is required for marking tower crane points, followed by automated flight inspections and reuse based on the marked route. Secondly, images captured by the drone necessitate manual identification and review, which can be time-consuming for equipment management personnel, particularly when dealing with a large volume of images. Subsequent research efforts will focus on AI training and recognition of safety hazard images, as well as the automatic generation of inspection reports and corrective management based on recognition results. The ongoing development in this area is currently in progress, and outcomes will be released at an appropriate time.

Keywords: tower crane, inspection, unmanned aerial vehicle (UAV), intelligent inspection app system, safety management

Procedia PDF Downloads 42

Authors: Doris Lacej, Eni Bushi

Abstract:

Cleaning and disinfection procedures are essential for maintaining the cleanliness status of the pharmaceutical manufacturing environment particularly of the cleanrooms and sterile unit area. The Good Manufacturing Practice (GMP) Annex 1 recommendation highly requires the implementation of the standard and validated cleaning and disinfection protocols. However, environmental monitoring has shown that even a validated cleaning method with certified agents may result in the presence of atypical microorganisms’ colony that exceeds GMP limits for a specific cleanroom area. In response to this issue, this case study aims to arrive at the root cause of the microbial contamination observed in the sterile production environment in Profarma pharmaceutical industry in Albania through applying a problem-solving practical approach that ensures the appropriate sterility grade. The guidelines and literature emphasize the importance of several factors in the prevention of possible microbial contamination occurring in cleanrooms, grade A and C. These factors are integrated into a practical framework, to identify the root cause of the presence of Aspergillus Niger colony in the sterile production environment in Profarma pharmaceutical industry in Albania. In addition, the application of a semi-automatic disinfecting system such as H2O2 FOG into sterile grade A and grade C cleanrooms has been an effective solution in eliminating the atypical colony of Aspergillus Niger. Selecting the appropriate detergents and disinfectants at the right concentration, frequency, and combination; the presence of updated and standardized guidelines for cleaning and disinfection as well as continuous training of operators on these practices in accordance with the updated GMP guidelines are some of the identified factors that influence the success of achieving sterility grade. However, to ensure environmental sustainability it is important to be prepared for identifying the source of contamination and making the appropriate decision. The proposed case-based practical approach may help pharmaceutical companies to achieve sterile production and cleanliness environmental sustainability in challenging situations. Apart from the integration of valid agents and standardized cleaning and disinfection protocols according to GMP Annex 1, pharmaceutical companies must be careful and investigate the source and all the steps that can influence the results of an abnormal situation. Subsequently apart from identifying the root cause it is important to solve the problem with a successful alternative approach.

Keywords: cleanrooms, disinfectants, environmental monitoring, GMP Annex 1

Procedia PDF Downloads 216

Authors: Magali Mari, Misha Muller

Abstract:

The present study’s objectives were to determine how diverse implicit stereotypes affect the processing of written information and linguistic inferential processes, such as presupposition accommodation. When reading a text, one constructs a representation of the described situation, which is then updated, according to new outputs and based on stereotypes inscribed within society. If the new output contradicts stereotypical expectations, the representation must be corrected, resulting in longer reading times. A similar process occurs in cases of linguistic inferential processes like presupposition accommodation. Presupposition accommodation is traditionally regarded as fast, automatic processing of background information (e.g., ‘Mary stopped eating meat’ is quickly processed as Mary used to eat meat). However, very few accounts have investigated if this process is likely to be influenced by domains of social cognition, such as implicit stereotypes. To study the effects of implicit stereotypes on presupposition accommodation, adults were recorded while they read sentences in French, combining two methods, an eye-tracking task and a classic self-paced reading task (where participants read sentence segments at their own pace by pressing a computer key). In one condition, presuppositions were activated with the French definite articles ‘le/la/les,’ whereas in the other condition, the French indefinite articles ‘un/une/des’ was used, triggering no presupposition. Using a definite article presupposes that the object has already been uttered and is thus part of background information, whereas using an indefinite article is understood as the introduction of new information. Two types of stereotypes were under examination in order to enlarge the scope of stereotypes traditionally analyzed. Study 1 investigated gender stereotypes linked to professional occupations to replicate previous findings. Study 2 focused on nationality-related stereotypes (e.g. ‘the French are seducers’ versus ‘the Japanese are seducers’) to determine if the effects of implicit stereotypes on reading are generalizable to other types of implicit stereotypes. The results show that reading is influenced by the two types of implicit stereotypes; in the two studies, the reading pace slowed down when a counter-stereotype was presented. However, presupposition accommodation did not affect participants’ processing of information. Altogether these results show that (a) implicit stereotypes affect the processing of written information, regardless of the type of stereotypes presented, and (b) that implicit stereotypes prevail over the superficial linguistic treatment of presuppositions, which suggests faster processing for treating social information compared to linguistic information.

Keywords: eye-tracking, implicit stereotypes, reading, social cognition

Procedia PDF Downloads 199

Authors: Zhaoxu Lu, Yufeng Ma, Linying Gao, Li Wang, Mei Qiang

Abstract:

Mercury (Hg) is a well-recognized environmental pollutant known by its toxicity of development and neurotoxicity, which may result in adverse health outcomes. However, the mechanisms underlying the teratogenic effects of Hg are not well understood. Imprinting genes are emerging regulators for fetal development subject to environmental pollutants impacts. In this study, we examined the association between paternal preconception Hg exposures and the alteration of DNA methylation of imprinting genes in human sperm DNA. A total of 618 men aged from 22 to 59 was recruited from the Reproductive Medicine Clinic of Maternal and Child Care Service Center and the Urologic Surgery Clinic of Shanxi Academy of Medical Sciences during April 2015 and March 2016. Demographic information was collected using questionnaires. Urinary Hg concentrations were measured using a fully-automatic double-channel hydride generation atomic fluorescence spectrometer. And methylation status in the DMRs of imprinting genes H19, Meg3 and Peg3 of sperm DNA were examined by bisulfite pyrosequencing in 243 participants. Spearman’s rank and multivariate regression analysis were used for correlation analysis between sperm DNA methylation status of imprinting genes and urinary Hg levels. The median concentration of Hg for participants overall was 9.09μg/l (IQR: 5.54 - 12.52μg/l; range = 0 - 71.35μg/l); no significant difference was found in median concentrations of Hg among various demographic groups (p > 0.05). The proportion of samples that a beyond intoxication criterion (10μg/l) for urinary Hg was 42.6%. Spearman’s rank correlation analysis indicates a negative correlation between urinary Hg concentrations and average DNA methylation levels in the DMRs of imprinted genes H19 (rs=﹣0.330, p = 0.000). However, there was no such a correlation found in genes of Peg3 and Meg3. Further, we analyzed of correlation between methylation level at each CpG site of H19 and Hg level, the results showed that three out of 7 CpG sites on H19 DMR, namely CpG2 (rs =﹣0.138, p = 0.031), CpG4 (rs =﹣0.369, p = 0.000) and CpG6 (rs=﹣0.228, p = 0.000), demonstrated a significant negative correlation between methylation levels and the levels of urinary Hg. After adjusting age, smoking, drinking, intake of aquatic products and education by multivariate regression analysis, the results have shown a similar correlation. In summary, mercury nonoccupational environmental exposure in reproductive-aged men associated with altered DNA methylation outcomes at DMR of imprinting gene H19 in sperm, implicating the susceptibility of the developing sperm for environmental insults.

Keywords: epigenetics, genomic imprinting gene, DNA methylation, mercury, transgenerational effects, sperm

Procedia PDF Downloads 261

Authors: Victor Au, Khin Maung Than, Zaw Win Aung, Linawati Jumat

Abstract:

Background & Objectives: Cardiac arrests can occur anywhere or anytime, and most of the cases will be brought to the emergency department except the cases that happened in at in-patient setting. Raja IsteriPangiran Anak Saleha (RIPAS) Hospital is the only tertiary government hospital which located in Brunei Muara district and received all referral from other Brunei districts. Data of cardiac arrests in Brunei Darussalam scattered between Emergency Medical Ambulance Services (EMAS), Emergency Department (ED), general inpatient wards, and Intensive Care Unit (ICU). In this audit, we only focused on cardiac arrest cases which had happened or presented to the emergency department RIPAS Hospital. Theobjectives of this audit were to look at demographic of cardiac arrest cases and the survival to discharge rate of In-Hospital Cardiac Arrest (IHCA) and Out-Hospital Cardiac Arrest (OHCA). Methodology: This audit retrospective study was conducted on all cardiac arrest cases that underwent Cardiopulmonary Resuscitation (CPR) in ED RIPAS Hospital, Brunei Muara, in the year 2019-2020. All cardiac arrest cases that happened or were brought in to emergency department were included. All the relevant data were retrieved from ED visit registry book and electronic medical record “Bru-HIMS” with keyword diagnosis of “cardiac arrest”. Data were analyzed and tabulated using Excel software. Result: 313 cardiac arrests were recorded in the emergency department in year 2019-2020. 92% cases were categorized as OHCA, and the remaining 8% as IHCA. Majority of the cases were male with age between 50-60 years old. In OHCA subgroup, only 12.4% received bystander CPR, and 0.4% received Automatic External Defibrillator (AED) before emergency medical personnel arrived. Initial shockable rhythm in IHCA group accounted for 12% compare to 4.9% in OHCA group. Outcome of ED resuscitation, 32% of IHCA group achieved return of spontaneous circulation (ROSC) with a survival to discharge rate was 16%. For OHCA group, 12.35% achieved ROSC, but unfortunately, none of them survive till discharge. Conclusion: Standardized registry for cardiac arrest in the emergency department is required to provide valid baseline data to measure the quality and outcome of cardiac arrest. Zero survival rate for out hospital cardiac arrest is very concerning, and it might represent the significant breach in cardiac arrest chains of survival. Systematic prospective data collection is needed to identify contributing factors and to improve resuscitation outcome.

Keywords: cardiac arrest, OHCA, IHCA, resuscitation, emergency department

Procedia PDF Downloads 99

Authors: Priya Saha, Sourav Dey Roy Jr., Debotosh Bhattacharjee, Mita Nasipuri, Barin Kumar De, Mrinal Kanti Bhowmik

Abstract:

Biometric face recognition technology (FRT) has gained a lot of attention due to its extensive variety of applications in both security and non-security perspectives. It has come into view to provide a secure solution in identification and verification of person identity. Although other biometric based methods like fingerprint scans, iris scans are available, FRT is verified as an efficient technology for its user-friendliness and contact freeness. Accurate facial feature localization plays an important role for many facial analysis applications including biometrics and emotion recognition. But, there are certain factors, which make facial feature localization a challenging task. On human face, expressions can be seen from the subtle movements of facial muscles and influenced by internal emotional states. These non-rigid facial movements cause noticeable alterations in locations of facial landmarks, their usual shapes, which sometimes create occlusions in facial feature areas making face recognition as a difficult problem. The paper proposes a new hybrid based technique for automatic landmark detection in both neutral and expressive frontal and near frontal face images. The method uses the concept of thresholding, sequential searching and other image processing techniques for locating the landmark points on the face. Also, a Graphical User Interface (GUI) based software is designed that could automatically detect 16 landmark points around eyes, nose and mouth that are mostly affected by the changes in facial muscles. The proposed system has been tested on widely used JAFFE and Cohn Kanade database. Also, the system is tested on DeitY-TU face database which is created in the Biometrics Laboratory of Tripura University under the research project funded by Department of Electronics & Information Technology, Govt. of India. The performance of the proposed method has been done in terms of error measure and accuracy. The method has detection rate of 98.82% on JAFFE database, 91.27% on Cohn Kanade database and 93.05% on DeitY-TU database. Also, we have done comparative study of our proposed method with other techniques developed by other researchers. This paper will put into focus emotion-oriented systems through AU detection in future based on the located features.

Keywords: biometrics, face recognition, facial landmarks, image processing

Procedia PDF Downloads 412

Authors: V. A. Dubovsky, V. V. Savchenko, A. A. Baryskevich

Abstract:

The current trend in the automotive industry towards automatic vehicles is creating new challenges related to human factors. This occurs due to the fact that the driver is increasingly relieved of the need to be constantly involved in driving the vehicle, which can negatively impact his/her situation awareness when manual control is required, and decrease driving skills and abilities. These new problems need to be studied in order to provide road safety during the transition towards self-driving vehicles. For this purpose, it is important to develop an appropriate conceptual model of the interaction between the driver and the automated vehicle, which could serve as a theoretical basis for the development of mathematical and simulation models to explore different aspects of driver behaviour in different road situations. Well-known driver behaviour models describe the impact of different stages of the driver's cognitive process on driving performance but do not describe how the driver controls and adjusts his actions. A more complete description of the driver's cognitive process, including the evaluation of the results of his/her actions, will make it possible to more accurately model various aspects of the human factor in different road situations. This paper presents a conceptual model of the 'driver – highly automated vehicle' system based on the P.K. Anokhin's theory of functional systems, which is a theoretical framework for describing internal processes in purposeful living systems based on such notions as goal, desired and actual results of the purposeful activity. A central feature of the proposed model is a dynamic coupling mechanism between the decision-making of a driver to perform a particular action and changes of road conditions due to driver’s actions. This mechanism is based on the stage by stage evaluation of the deviations of the actual values of the driver’s action results parameters from the expected values. The overall functional structure of the highly automated vehicle in the proposed model includes a driver/vehicle/environment state analyzer to coordinate the interaction between driver and vehicle. The proposed conceptual model can be used as a framework to investigate different aspects of human factors in transitions between automated and manual driving for future improvements in driving safety, and for understanding how driver-vehicle interface must be designed for comfort and safety. A major finding of this study is the demonstration that the theory of functional systems is promising and has the potential to describe the interaction of the driver with the vehicle and the environment.

Keywords: automated vehicle, driver behavior, human factors, human-machine system

Procedia PDF Downloads 146

Authors: Mballa Abanda Luc Aurelien Serge, Henda Gnakate Biba, Kuate Guemo Romaric, Akono Rufine Nicole, Zabotom Yaya Fadel Biba, Petfiang Sidonie, Bella Suzane Jenifer

Abstract:

The main hypotheses proposed around the definition of the syllable and of music, of the common origin of music and language, should lead the reader to reflect on the cross-cutting questions raised by the debate on the notion of universals in linguistics and musicology. These are objects of controversy, and there lies its interest: the debate raises questions that are at the heart of theories on language. It is an inventive, original, and innovative research thesis. A contribution to the theoretical, musicological, ethno musicological, and linguistic conceptualization of languages, giving rise to the practice of interlocution between the social and cognitive sciences, the activities of artistic creation, and the question of modeling in the human sciences: mathematics, computer science, translation automation, and artificial intelligence. When you apply this theory to any text of a folksong of a world-tone language, you do not only piece together the exact melody, rhythm, and harmonies of that song as if you knew it in advance but also the exact speaking of this language. The author believes that the issue of the disappearance of tonal languages and their preservation has been structurally resolved, as well as one of the greatest cultural equations related to the composition and creation of tonal, polytonal, and random music. The experimentation confirming the theorization, I designed a semi-digital, semi-analog application that translates the tonal languages of Africa (about 2,100 languages) into blues, jazz, world music, polyphonic music, tonal and anatonal music, and deterministic and random music). To test this application, I use music reading and writing software that allows me to collect the data extracted from my mother tongue, which is already modeled in the musical staves saved in the ethnographic (semiotic) dictionary for automatic translation ( volume 2 of the book). The translation is done (from writing to writing, from writing to speech, and from writing to music). Mode of operation: you type a text on your computer, a structured song (chorus-verse), and you command the machine a melody of blues, jazz, and world music or variety, etc. The software runs, giving you the option to choose harmonies, and then you select your melody.

Keywords: language, music, sciences, quantum entenglement

Procedia PDF Downloads 77

Authors: Emmanuel Ophel Gilbert, Williams Speret

Abstract:

The control for fluid flow behaviours of viscous fluids and heat transfer occurrences within heated mini-channel is considered. Heat transfer and flow characteristics of different viscous liquids, such as engine oil, automatic transmission fluid, one-half ethylene glycol, and deionized water were numerically analyzed. Some mathematical applications such as Fourier series and Laplace Z-Transforms were employed to ascertain the behaviour-wave like structure of these each viscous fluids. The steady, laminar flow and heat transfer equations are reckoned by the aid of numerical simulation technique. Further, this numerical simulation technique is endorsed by using the accessible practical values in comparison with the anticipated local thermal resistances. However, the roughness of this mini-channel that is one of the physical limitations was also predicted in this study. This affects the frictional factor. When an additive such as tetracycline was introduced in the fluid, the heat input was lowered, and this caused pro rata effect on the minor and major frictional losses, mostly at a very minute Reynolds number circa 60-80. At this ascertained lower value of Reynolds numbers, there exists decrease in the viscosity and minute frictional losses as a result of the temperature of these viscous liquids been increased. It is inferred that the three equations and models are identified which supported the numerical simulation via interpolation and integration of the variables extended to the walls of the mini-channel, yields the utmost reliance for engineering and technology calculations for turbulence impacting jets in the near imminent age. Out of reasoning with a true equation that could support this control for the fluid flow, Navier-stokes equations were found to tangential to this finding. Though, other physical factors with respect to these Navier-stokes equations are required to be checkmated to avoid uncertain turbulence of the fluid flow. This paradox is resolved within the framework of continuum mechanics using the classical slip condition and an iteration scheme via numerical simulation method that takes into account certain terms in the full Navier-Stokes equations. However, this resulted in dropping out in the approximation of certain assumptions. Concrete questions raised in the main body of the work are sightseen further in the appendices.

Keywords: frictional losses, heat transfer, laminar flow, mini-channel, number simulation, Reynolds number, turbulence, viscous fluids

Procedia PDF Downloads 176

Authors: Tolulope Aremu

Abstract:

This paper is based on the idea of using deep learning methodology for optimizing production yield by tuning a few key process parameters in a manufacturing environment. The study was explicitly on how to maximize production yield and minimize operational costs by utilizing advanced neural network models, specifically Long Short-Term Memory and Convolutional Neural Networks. These models were implemented using Python-based frameworks—TensorFlow and Keras. The targets of the research are the precision molding processes in which temperature ranges between 150°C and 220°C, the pressure ranges between 5 and 15 bar, and the material flow rate ranges between 10 and 50 kg/h, which are critical parameters that have a great effect on yield. A dataset of 1 million production cycles has been considered for five continuous years, where detailed logs are present showing the exact setting of parameters and yield output. The LSTM model would model time-dependent trends in production data, while CNN analyzed the spatial correlations between parameters. Models are designed in a supervised learning manner. For the model's loss, an MSE loss function is used, optimized through the Adam optimizer. After running a total of 100 training epochs, 95% accuracy was achieved by the models recommending optimal parameter configurations. Results indicated that with the use of RSM and DOE traditional methods, there was an increase in production yield of 12%. Besides, the error margin was reduced by 8%, hence consistent quality products from the deep learning models. The monetary value was annually around $2.5 million, the cost saved from material waste, energy consumption, and equipment wear resulting from the implementation of optimized process parameters. This system was deployed in an industrial production environment with the help of a hybrid cloud system: Microsoft Azure, for data storage, and the training and deployment of their models were performed on Google Cloud AI. The functionality of real-time monitoring of the process and automatic tuning of parameters depends on cloud infrastructure. To put it into perspective, deep learning models, especially those employing LSTM and CNN, optimize the production yield by fine-tuning process parameters. Future research will consider reinforcement learning with a view to achieving further enhancement of system autonomy and scalability across various manufacturing sectors.

Keywords: production yield optimization, deep learning, tuning of process parameters, LSTM, CNN, precision manufacturing, TensorFlow, Keras, cloud infrastructure, cost saving

Procedia PDF Downloads 31

Authors: Ole-Christian Galbo Engstrøm, Erik Schou Dreier, Birthe Møller Jespersen, Kim Steenstrup Pedersen

Abstract:

Grain quality analysis is a multi-parameterized problem that includes a variety of qualitative and quantitative parameters such as grain type classification, damage type classification, and nutrient regression. Currently, these parameters require human inspection, a multitude of instruments employing a variety of sensor technologies, and predictive model types or destructive and slow chemical analysis. This paper investigates the feasibility of applying near-infrared hyperspectral imaging (NIR-HSI) to grain quality analysis. For this study two datasets of NIR hyperspectral images in the wavelength range of 900 nm - 1700 nm have been used. Both datasets contain images of sparsely and densely packed grain kernels. The first dataset contains ~87,000 image crops of bulk wheat samples from 63 harvests where protein value has been determined by the FOSS Infratec NOVA which is the golden industry standard for protein content estimation in bulk samples of cereal grain. The second dataset consists of ~28,000 image crops of bulk grain kernels from seven different wheat varieties and a single rye variety. In the first dataset, protein regression analysis is the problem to solve while variety classification analysis is the problem to solve in the second dataset. Deep convolutional neural networks (CNNs) have the potential to utilize spatio-spectral correlations within a hyperspectral image to simultaneously estimate the qualitative and quantitative parameters. CNNs can autonomously derive meaningful representations of the input data reducing the need for advanced preprocessing techniques required for classical chemometric model types such as artificial neural networks (ANNs) and partial least-squares regression (PLS-R). A comparison between different CNN architectures utilizing 2D and 3D convolution is conducted. These results are compared to the performance of ANNs and PLS-R. Additionally, a variety of preprocessing techniques from image analysis and chemometrics are tested. These include centering, scaling, standard normal variate (SNV), Savitzky-Golay (SG) filtering, and detrending. The results indicate that the combination of NIR-HSI and CNNs has the potential to be the foundation for an automatic system unifying qualitative and quantitative grain quality analysis within a single sensor technology and predictive model type.

Keywords: deep learning, grain analysis, hyperspectral imaging, preprocessing techniques

Procedia PDF Downloads 99

Authors: Srushti Patil, Preethi Baligar, Gopalkrishna Joshi, Gururaj N. Bhadri

Abstract:

In designing learning environments, the instructional strategies can be tailored to suit the learning style of an individual to ensure effective learning. In this study, the information shared on social media like Facebook is being used to predict learning style of a learner. Previous research studies have shown that Facebook data can be used to predict user personality. Users with a particular personality exhibit an inherent pattern in their digital footprint on Facebook. The proposed work aims to correlate the user's’ personality, predicted from Facebook data to the learning styles, predicted through questionnaires. For Millennial learners, Facebook has become a primary means for information sharing and interaction with peers. Thus, it can serve as a rich bed for research and direct the design of learning environments. The authors have conducted this study in an undergraduate freshman engineering course. Data from 320 freshmen Facebook users was collected. The same users also participated in the learning style and personality prediction survey. The Kolb’s Learning style questionnaires and Big 5 personality Inventory were adopted for the survey. The users have agreed to participate in this research and have signed individual consent forms. A specific page was created on Facebook to collect user data like personal details, status updates, comments, demographic characteristics and egocentric network parameters. This data was captured by an application created using Python program. The data captured from Facebook was subjected to text analysis process using the Linguistic Inquiry and Word Count dictionary. An analysis of the data collected from the questionnaires performed reveals individual student personality and learning style. The results obtained from analysis of Facebook, learning style and personality data were then fed into an automatic classifier that was trained by using the data mining techniques like Rule-based classifiers and Decision trees. This helps to predict the user personality and learning styles by analysing the common patterns. Rule-based classifiers applied for text analysis helps to categorize Facebook data into positive, negative and neutral. There were totally two models trained, one to predict the personality from Facebook data; another one to predict the learning styles from the personalities. The results show that the classifier model has high accuracy which makes the proposed method to be a reliable one for predicting the user personality and learning styles.

Keywords: educational data mining, Facebook, learning styles, personality traits

Procedia PDF Downloads 231

Authors: Kanika Gupta, Ashok Kumar

Abstract:

Biofilms are dense, highly hydrated cell clusters that are irreversibly attached to a substratum, to an interface or to each other, and are embedded in a self-produced gelatinous matrix composed of extracellular polymeric substances. Research in biofilm field has become very significant, as biofilm has shown high mechanical resilience and resistance to antibiotic treatment and constituted as a significant problem in both healthcare and other industry related to microorganisms. The massive information both stated and hidden in the biofilm literature are growing exponentially therefore it is not possible for researchers and practitioners to automatically extract and relate information from different written resources. So, the current work proposes and discusses the use of text mining techniques for the extraction of information from biofilm literature corpora containing 34306 documents. It is very difficult and expensive to obtain annotated material for biomedical literature as the literature is unstructured i.e. free-text. Therefore, we considered unsupervised approach, where no annotated training is necessary and using this approach we developed a system that will classify the text on the basis of growth and development, drug effects, radiation effects, classification and physiology of biofilms. For this, a two-step structure was used where the first step is to extract keywords from the biofilm literature using a metathesaurus and standard natural language processing tools like Rapid Miner_v5.3 and the second step is to discover relations between the genes extracted from the whole set of biofilm literature using pubmed.mineR_v1.0.11. We used unsupervised approach, which is the machine learning task of inferring a function to describe hidden structure from 'unlabeled' data, in the above-extracted datasets to develop classifiers using WinPython-64 bit_v3.5.4.0Qt5 and R studio_v0.99.467 packages which will automatically classify the text by using the mentioned sets. The developed classifiers were tested on a large data set of biofilm literature which showed that the unsupervised approach proposed is promising as well as suited for a semi-automatic labeling of the extracted relations. The entire information was stored in the relational database which was hosted locally on the server. The generated biofilm vocabulary and genes relations will be significant for researchers dealing with biofilm research, making their search easy and efficient as the keywords and genes could be directly mapped with the documents used for database development.

Keywords: biofilms literature, classifiers development, text mining, unsupervised learning approach, unstructured data, relational database

Procedia PDF Downloads 170

Authors: M. Kharrat, G. Moreau, Z. Aboura

Abstract:

The latest advances in the weaving industry, combined with increasingly sophisticated means of materials processing, have made it possible to produce complex 3D composite structures. Mainly used in aeronautics, composite materials with 3D architecture offer better mechanical properties than 2D reinforced composites. Nevertheless, these materials require a good understanding of their behavior. Because of the complexity of such materials, the damage mechanisms are multiple, and the scenario of their appearance and evolution depends on the nature of the exerted solicitations. The AE technique is a well-established tool for discriminating between the damage mechanisms. Suitable sensors are used during the mechanical test to monitor the structural health of the material. Relevant AE-features are then extracted from the recorded signals, followed by a data analysis using pattern recognition techniques. In order to better understand the damage scenarios of interlock composite materials, a multi-instrumentation was set-up in this work for tracking damage initiation and development, especially in the vicinity of the first significant damage, called macro-damage. The deployed instrumentation includes video-microscopy, Digital Image Correlation, Acoustic Emission (AE) and micro-tomography. In this study, a multi-variable AE data analysis approach was developed for the discrimination between the different signal classes representing the different emission sources during testing. An unsupervised classification technique was adopted to perform AE data clustering without a priori knowledge. The multi-instrumentation and the clustered data served to label the different signal families and to build a learning database. This latter is useful to construct a supervised classifier that can be used for automatic recognition of the AE signals. Several materials with different ingredients were tested under various solicitations in order to feed and enrich the learning database. The methodology presented in this work was useful to refine the damage threshold for the new generation materials. The damage mechanisms around this threshold were highlighted. The obtained signal classes were assigned to the different mechanisms. The isolation of a 'noise' class makes it possible to discriminate between the signals emitted by damages without resorting to spatial filtering or increasing the AE detection threshold. The approach was validated on different material configurations. For the same material and the same type of solicitation, the identified classes are reproducible and little disturbed. The supervised classifier constructed based on the learning database was able to predict the labels of the classified signals.

Keywords: acoustic emission, classifier, damage mechanisms, first damage threshold, interlock composite materials, pattern recognition

Procedia PDF Downloads 155

Authors: Joanna Grzybowska, Magdalena Igras, Mariusz Ziółko

Abstract:

Association rule learning is an approach for discovering interesting relationships in large databases. The analysis of relations, invisible at first glance, is a source of new knowledge which can be subsequently used for prediction. We used this data mining technique (which is an automatic and objective method) to learn about interesting affects associations in a corpus of emergency phone calls. We also made an attempt to match revealed rules with their possible situational context. The corpus was collected and subjectively annotated by two researchers. Each of 3306 recordings contains information on emotion: (1) type (sadness, weariness, anxiety, surprise, stress, anger, frustration, calm, relief, compassion, contentment, amusement, joy) (2) valence (negative, neutral, or positive) (3) intensity (low, typical, alternating, high). Also, additional information, that is a clue to speaker’s emotional state, was annotated: speech rate (slow, normal, fast), characteristic vocabulary (filled pauses, repeated words) and conversation style (normal, chaotic). Exponentially many rules can be extracted from a set of items (an item is a previously annotated single information). To generate the rules in the form of an implication X → Y (where X and Y are frequent k-itemsets) the Apriori algorithm was used - it avoids performing needless computations. Then, two basic measures (Support and Confidence) and several additional symmetric and asymmetric objective measures (e.g. Laplace, Conviction, Interest Factor, Cosine, correlation coefficient) were calculated for each rule. Each applied interestingness measure revealed different rules - we selected some top rules for each measure. Owing to the specificity of the corpus (emergency situations), most of the strong rules contain only negative emotions. There are though strong rules including neutral or even positive emotions. Three examples of the strongest rules are: {sadness} → {anxiety}; {sadness, weariness, stress, frustration} → {anger}; {compassion} → {sadness}. Association rule learning revealed the strongest configurations of affects (as well as configurations of affects with affect-related information) in our emergency phone calls corpus. The acquired knowledge can be used for prediction to fulfill the emotional profile of a new caller. Furthermore, a rule-related possible context analysis may be a clue to the situation a caller is in.

Keywords: data mining, emergency phone calls, emotional profiles, rules

Procedia PDF Downloads 408

Authors: Iryna Biskub

Abstract:

The interdisciplinary approach to modern linguistic studies is exemplified by the merge of various research methods, which sometimes causes complications related to the verification of the research results. This methodological confusion can be resolved by means of creating new techniques of linguistic analysis combining several scientific paradigms. Modern linguistics has developed really productive and efficient methods for the investigation of cognitive and communicative phenomena of which language is the central issue. In the field of discourse studies, one of the best examples of research methods is the method of Critical Discourse Analysis (CDA). CDA can be viewed both as a method of investigation, as well as a critical multidisciplinary perspective. In CDA the position of the scholar is crucial from the point of view exemplifying his or her social and political convictions. The generally accepted approach to obtaining scientifically reliable results is to use a special well-defined scientific method for researching special types of language phenomena: cognitive methods applied to the exploration of cognitive aspects of language, whereas communicative methods are thought to be relevant only for the investigation of communicative nature of language. In the recent decades discourse as a sociocultural phenomenon has been the focus of careful linguistic research. The very concept of discourse represents an integral unity of cognitive and communicative aspects of human verbal activity. Since a human being is never able to discriminate between cognitive and communicative planes of discourse communication, it doesn’t make much sense to apply cognitive and communicative methods of research taken in isolation. It is possible to modify the classical CDA procedure by means of mapping human cognitive procedures onto the strategic communicative planning of discourse communication. The analysis of the electronic petition 'Block Donald J Trump from UK entry. The signatories believe Donald J Trump should be banned from UK entry' (584, 459 signatures) and the parliamentary debates on it has demonstrated the ability to map cognitive and communicative levels in the following way: the strategy of discourse modeling (communicative level) overlaps with the extraction of semantic macrostructures (cognitive level); the strategy of discourse management overlaps with the analysis of local meanings in discourse communication; the strategy of cognitive monitoring of the discourse overlaps with the formation of attitudes and ideologies at the cognitive level. Thus, the experimental data have shown that it is possible to develop a new complex methodology of discourse analysis, where cognition would meet communication, both metaphorically and literally. The same approach may appear to be productive for the creation of computational models of human-computer interaction, where the automatic generation of a particular type of a discourse could be based on the rules of strategic planning involving cognitive models of CDA.

Keywords: cognition, communication, discourse, strategy

Procedia PDF Downloads 254

Authors: Sarkawt M. Hama, Paul S. Monks, Rebecca L. Cordell

Abstract:

Within the Joaquin project, ultrafine particles (UFP) are continuously measured at one urban background site in Leicester. The main aims are to examine the temporal and seasonal variations in UFP number concentration and size distribution in an urban environment, and to try to assess the added value of continuous UFP measurements. In addition, relations of UFP with more commonly monitored pollutants such as black carbon (BC), nitrogen oxides (NOX), particulate matter (PM2.5), and the lung deposited surface area(LDSA) were evaluated. The effects of meteorological conditions, particularly wind speed and direction, and also temperature on the observed distribution of ultrafine particles will be detailed. The study presents the results from an experimental investigation into the particle number concentration size distribution of UFP, BC, and NOX with measurements taken at the Automatic Urban and Rural Network (AURN) monitoring site in Leicester. The monitoring was performed as part of the EU project JOAQUIN (Joint Air Quality Initiative) supported by the INTERREG IVB NWE program. The total number concentrations (TNC) were measured by a water-based condensation particle counter (W-CPC) (TSI model 3783), the particle number concentrations (PNC) and size distributions were measured by an ultrafine particle monitor (UFP TSI model 3031), the BC by MAAP (Thermo-5012), the NOX by NO-NO2-NOx monitor (Thermos Scientific 42i), and a Nanoparticle Surface Area Monitor (NSAM, TSI 3550) was used to measure the LDSA (reported as μm2 cm−3) corresponding to the alveolar region of the lung between November 2013 and November 2015. The average concentrations of particle number concentrations were observed in summer with lower absolute values of PNC than in winter might be related mainly to particles directly emitted by traffic and to the more favorable conditions of atmospheric dispersion. Results showed a traffic-related diurnal variation of UFP, BC, NOX and LDSA with clear morning and evening rush hour peaks on weekdays, only an evening peak at the weekends. Correlation coefficients were calculated between UFP and other pollutants (BC and NOX). The highest correlation between them was found in winter months. Overall, the results support the notion that local traffic emissions were a major contributor of the atmospheric particles pollution and a clear seasonal pattern was found, with higher values during the cold season.

Keywords: size distribution, traffic emissions, UFP, urban area

Procedia PDF Downloads 330

Authors: Hannele Kuusisto, Paivi Makila, Ursula Hyrkkanen

Abstract:

Introduction: There have been arguments about the skills university students should have when graduated. Current trends argue that as well as the specific job-related skills the graduated students need problem-solving, interaction and networking skills as well as self-management skills. Skills required in working life are also considered in the Finnish national project called VALTE (short for 'prepared for working life'). The project involves 11 Finnish school organizations. As one result of this project, a five-credit independent online course in study and job engagement as well as in study and job crafting was developed at Turku University of Applied Sciences. The aim of the oral or e-poster presentation is to present the online course developed in the project. The purpose of this abstract is to present the development work of the online course and the feedback received from the pilots. Method: As the University of Turku is the leading partner of the VALTE project, the collaborative education platform ViLLE (https://ville.utu.fi, developed by the University of Turku) was chosen as the online platform for the course. Various exercise types with automatic assessment were used; for example, quizzes, multiple-choice questions, classification exercises, gap filling exercises, model answer questions, self-assessment tasks, case tasks, and collaboration in Padlet. In addition, the free material and free platforms on the Internet were used (Youtube, Padlet, Todaysmeet, and Prezi) as well as the net-based questionnaires about the study engagement and study crafting (made with Webropol). Three teachers with long teaching experience (also with job crafting and online pedagogy) and three students working as trainees in the project developed the content of the course. The online course was piloted twice in 2017 as an elective course for the students at Turku University of Applied Sciences, a higher education institution of about 10 000 students. After both pilots, feedback from the students was gathered and the online course was developed. Results: As the result, the functional five-credit independent online course suitable for students of different educational institutions was developed. The student feedback shows that students themselves think that the developed online course really enhanced their job and study crafting skills. After the course, 91% of the students considered their knowledge in job and study engagement as well as in job and study crafting to be at a good or excellent level. About two-thirds of the students were going to exploit their knowledge significantly in the future. Students appreciated the variability and the game-like feeling of the exercises as well as the opportunity to study online at the time and place they chose themselves. On a five-point scale (1 being poor and 5 being excellent), the students graded the clarity of the ViLLE platform as 4.2, the functionality of the platform as 4.0 and the easiness of operating as 3.9.

Keywords: job crafting, job engagement, online course, study crafting, study engagement

Procedia PDF Downloads 153

Authors: Sara A. Ben Lashihar

Abstract:

The heritage building information modelling (HBIM) of the historical masonry buildings has expanded lately to meet the urgent needs for conservation and structural analysis. The masonry structures are unique features for ancient building architectures worldwide that have special cultural, spiritual, and historical significance. However, there is a research gap regarding the reliability of the HBIM modeling process of these structures. The HBIM modeling process of the masonry structures faces significant challenges due to the inherent complexity and uniqueness of their structural systems. Most of these processes are based on tracing the point clouds and rarely follow documents, archival records, or direct observation. The results of these techniques are highly abstracted models where the accuracy does not exceed LOD 200. The masonry assemblages, especially curved elements such as arches, vaults, and domes, are generally modeled with standard BIM components or in-place models, and the brick textures are graphically input. Hence, future investigation is necessary to establish a methodology to generate automatically parametric masonry components. These components are developed algorithmically according to mathematical and geometric accuracy and the validity of the survey data. The main aim of this paper is to provide a comprehensive review of the state of the art of the existing researches and papers that have been conducted on the HBIM modeling of the masonry structural elements and the latest approaches to achieve parametric models that have both the visual fidelity and high geometric accuracy. The paper reviewed more than 800 articles, proceedings papers, and book chapters focused on "HBIM and Masonry" keywords from 2017 to 2021. The studies were downloaded from well-known, trusted bibliographic databases such as Web of Science, Scopus, Dimensions, and Lens. As a starting point, a scientometric analysis was carried out using VOSViewer software. This software extracts the main keywords in these studies to retrieve the relevant works. It also calculates the strength of the relationships between these keywords. Subsequently, an in-depth qualitative review followed the studies with the highest frequency of occurrence and the strongest links with the topic, according to the VOSViewer's results. The qualitative review focused on the latest approaches and the future suggestions proposed in these researches. The findings of this paper can serve as a valuable reference for researchers, and BIM specialists, to make more accurate and reliable HBIM models for historic masonry buildings.

Keywords: HBIM, masonry, structure, modeling, automatic, approach, parametric

Procedia PDF Downloads 165

Authors: Martina Marinelli, Samanta Vellante, Francesco Pilotti, Daniele Di Valerio, Gaetanino Paolone

Abstract:

Any development in web marketing technology requires changes in information engineering to identify instruments and techniques suitable for the production of software applications for informative marketing. Moreover, for large web solutions, designing an interface that enables human interactions is a complex process that must bridge between informative marketing requirements and the developed solution. A user-friendly interface in web marketing applications is crucial for a successful business. The paper introduces mkInfo - a software platform that implements informative marketing. Informative marketing is a new interpretation of marketing which places the information at the center of every marketing action. The creative team includes software engineering researchers who have recently authored an article on automatic code generation. The authors have created the mkInfo software platform to generate informative marketing web applications. For each web application, it is possible to automatically implement an opt in page, a landing page, a sales page, and a thank you page: one only needs to insert the content. mkInfo implements an autoresponder to send mail according to a predetermined schedule. The mkInfo platform also includes e-commerce for a product or service. The stakeholder can access any opt-in page and get basic information about a product or service. If he wants to know more, he will need to provide an e-mail address to access a landing page that will generate an e-mail sequence. It will provide him with complete information about the product or the service. From this point on, the stakeholder becomes a user and is now able to purchase the product or related services through the mkInfo platform. This paper suggests a possible definition for Informative Marketing, illustrates its basic principles, and finally details the mkInfo platform that implements it. This paper also offers some Informative Marketing models, which are implemented in the mkInfo platform. Informative marketing can be applied to products or services. It is necessary to realize a web application for each product or service. The mkInfo platform enables the product or the service producer to send information concerning a specific product or service to all stakeholders. In conclusion, the technical contributions of this paper are: a different interpretation of marketing based on information; a modular architecture for web applications, particularly for one with standard features such as information storage, exchange, and delivery; multiple models to implement informative marketing; a software platform enabling the implementation of such models in a web application. Future research aims to enable stakeholders to provide information about a product or a service so that the information gathered about a product or a service includes both the producer’s and the stakeholders' point of view. The purpose is to create an all-inclusive management system of the knowledge regarding a specific product or service: a system that includes everything about the product or service and is able to address even unexpected questions.

Keywords: informative marketing, opt in page, software platform, web application

Procedia PDF Downloads 127

Authors: Yuan-Hao Lee, Chia-Wei Lee, Ming-Fang Lin, Tzu-Huei Wu, Chih-Hsiang Ko, Wing P. Chan

Abstract:

Computed tomography (CT) scan of the head is a good method for investigating cranial lesions. However, radiation-induced oxidative stress can be accumulated in the eyes and promote carcinogenesis and cataract. In this regard, we aimed to protect the eyes with barium sulfate shield(s) during CT scans and investigate the resultant image quality and radiation dose to the eye. Patients who underwent health examinations were selectively enrolled in this study in compliance with the protocol approved by the Ethics Committee of the Joint Institutional Review Board at Taipei Medical University. Participants’ brains were scanned with a water-based marker simultaneously by a multislice CT scanner (SOMATON Definition Flash) under a fixed tube current-time setting or automatic tube current modulation (TCM). The lens dose was measured by Gafchromic films, whose dose response curve was previously fitted using thermoluminescent dosimeters, with or without barium sulfate or bismuth-antimony shield laid above. For the assessment of image quality CT images at slice planes that exhibit the interested regions on the zygomatic, orbital and nasal bones of the head phantom as well as the water-based marker were used for calculating the signal-to-noise and contrast-to-noise ratios. The application of barium sulfate and bismuth-antimony shields decreased 24% and 47% of the lens dose on average, respectively. Under topogram-based TCM, the dose saving power of bismuth-antimony shield was mitigated whereas that of barium sulfate shield was enhanced. On the other hand, the signal-to-noise and contrast-to-noise ratios of DSCT images were decreased separately by barium sulfate and bismuth-antimony shield, resulting in an overall reduction of the CNR. In contrast, the integration of topogram-based TCM elevated signal difference between the ROIs on the zygomatic bones and eyeballs while preferentially decreasing the signal-to-noise ratios upon the use of barium sulfate shield. The results of this study indicate that the balance between eye exposure and image quality can be optimized by combining eye shields with topogram-based TCM on the multislice scanner. Eye shielding could change the photon attenuation characteristics of tissues that are close to the shield. The application of both shields on eye protection hence is not recommended for seeking intraorbital lesions.

Keywords: computed tomography, barium sulfate shield, dose saving, image quality

Procedia PDF Downloads 268

Authors: Karin M. Granstrom

Abstract:

Paper mills produce wastewater with a high content of organic substances. Treatment usually consists of sedimentation, biological treatment of activated sludge basins, and chemical precipitation. The resulting sludges are currently a waste problem, deposited in landfills or used as low-grade fuels for incineration. There is a growing awareness of the need for energy efficiency and environmentally sound management of sludge. A resource-efficient method would be to digest the wastewater sludges anaerobically to produce biogas, refine the biogas to biomethane for use in the transportation sector, and utilize the resulting digestate for soil improvement. The biomethane yield of pulp and paper wastewater sludge is comparable to that of straw or manure. As a bonus, the digestate has an improved dewaterability compared to the feedstock biosludge. Limitations of this process are predominantly a weak economic viability - necessitating both sufficiently large-scale paper production for the necessary large amounts of produced wastewater sludge, and the resolving of remaining questions on the certifiability of the digestate and thus its sales price. A way to improve the practical and economical feasibility of using paper mill wastewater for biomethane production and soil improvement is to co-digest it with other feedstocks. In this study, pulp and paper sludge were co-digested with (1) silage and manure, (2) municipal sewage sludge, (3) food waste, or (4) microalgae. Biomethane yield analysis was performed in 500 ml batch reactors, using an Automatic Methane Potential Test System at thermophilic temperature, with a 20 days test duration. The results show that (1) the harvesting season of grass silage and manure collection was an important factor for methane production, with spring feedstocks producing much more than autumn feedstock, and pulp mill sludge benefitting the most from co-digestion; (2) pulp and paper mill sludge is a suitable co-substrate to add when a high nitrogen content cause impaired biogas production due to ammonia inhibition; (3) the combination of food waste and paper sludge gave higher methane yield than either of the substrates digested separately; (4) pure microalgae gave the highest methane yield. In conclusion, although pulp and paper mills are an almost untapped resource for biomethane production, their wastewater is a suitable feedstock for such a process. Furthermore, through co-digestion, the pulp and paper mill wastewater and mill sludges can aid biogas production from more nutrient-rich waste streams from other industries. Such co-digestion also enhances the soil improvement properties of the residue digestate.

Keywords: anaerobic, biogas, biomethane, paper, sludge, soil

Procedia PDF Downloads 259

Authors: Pablo Chico De Guzman, Cesar Sanchez

Abstract:

Microservices are a software development methodology in which applications are built by composing a set of independently deploy-able, small, modular services. Each service runs a unique process and it gets instantiated and deployed in one or more machines (we assume that different microservices are deployed into different machines). Microservices are becoming the de facto standard for developing distributed cloud applications due to their reduced release cycles. In principle, the responsibility of a microservice can be as simple as implementing a single function, which can lead to the following issues: - Resource fragmentation due to the virtual machine boundary. - Poor communication performance between microservices. Two composition techniques can be used to optimize resource fragmentation and communication performance: aggregation and embedding of microservices. Aggregation allows the deployment of a set of microservices on the same machine using a proxy server. Aggregation helps to reduce resource fragmentation, and is particularly useful when the aggregated services have a similar scalability behavior. Embedding deals with communication performance by deploying on the same virtual machine those microservices that require a communication channel (localhost bandwidth is reported to be about 40 times faster than cloud vendor local networks and it offers better reliability). Embedding can also reduce dependencies on load balancer services since the communication takes place on a single virtual machine. For example, assume that microservice A has two instances, a1 and a2, and it communicates with microservice B, which also has two instances, b1 and b2. One embedding can deploy a1 and b1 on machine m1, and a2 and b2 are deployed on a different machine m2. This deployment configuration allows each pair (a1-b1), (a2-b2) to communicate using the localhost interface without the need of a load balancer between microservices A and B. Aggregation and embedding techniques are complex since different microservices might have incompatible runtime dependencies which forbid them from being installed on the same machine. There is also a security concern since the attack surface between microservices can be larger. Luckily, container technology allows to run several processes on the same machine in an isolated manner, solving the incompatibility of running dependencies and the previous security concern, thus greatly simplifying aggregation/embedding implementations by just deploying a microservice container on the same machine as the aggregated/embedded microservice container. Therefore, a wide variety of deployment configurations can be described by combining aggregation and embedding to create an efficient and robust microservice architecture. This paper presents a formal method that receives a declarative definition of a microservice architecture and proposes different optimized deployment configurations by aggregating/embedding microservices. The first prototype is based on i2kit, a deployment tool also submitted to ICWS 2018. The proposed prototype optimizes the following parameters: network/system performance, resource usage, resource costs and failure tolerance.

Keywords: aggregation, deployment, embedding, resource allocation

Procedia PDF Downloads 203

Authors: Mohamed Alimoussa, Alice Porebski, Nicolas Vandenbroucke, Rachid Oulad Haj Thami, Sana El Fkihi

Abstract:

Color and texture are highly discriminant visual cues that provide an essential information in many types of images. Color texture representation and classification is therefore one of the most challenging problems in computer vision and image processing applications. Color textures can be represented in different color spaces by using multiple image descriptors which generate a high dimensional set of texture features. In order to reduce the dimensionality of the feature set, feature selection techniques can be used. The goal of feature selection is to find a relevant subset from an original feature space that can improve the accuracy and efficiency of a classification algorithm. Traditionally, feature selection is focused on removing irrelevant features, neglecting the possible redundancy between relevant ones. This is why some feature selection approaches prefer to use feature clustering analysis to aid and guide the search. These techniques can be divided into two categories. i) Feature clustering-based ranking algorithm uses feature clustering as an analysis that comes before feature ranking. Indeed, after dividing the feature set into groups, these approaches perform a feature ranking in order to select the most discriminant feature of each group. ii) Feature clustering-based subset search algorithms can use feature clustering following one of three strategies; as an initial step that comes before the search, binded and combined with the search or as the search alternative and replacement. In this paper, we propose a new feature clustering-based sequential selection approach for the purpose of color texture representation and classification. Our approach is a three step algorithm. First, irrelevant features are removed from the feature set thanks to a class-correlation measure. Then, introducing a new automatic feature clustering algorithm, the feature set is divided into several feature clusters. Finally, a sequential search algorithm, based on a filter model and a separability measure, builds a relevant and non redundant feature subset: at each step, a feature is selected and features of the same cluster are removed and thus not considered thereafter. This allows to significantly speed up the selection process since large number of redundant features are eliminated at each step. The proposed algorithm uses the clustering algorithm binded and combined with the search. Experiments using a combination of two well known texture descriptors, namely Haralick features extracted from Reduced Size Chromatic Co-occurence Matrices (RSCCMs) and features extracted from Local Binary patterns (LBP) image histograms, on five color texture data sets, Outex, NewBarktex, Parquet, Stex and USPtex demonstrate the efficiency of our method compared to seven of the state of the art methods in terms of accuracy and computation time.

Keywords: feature selection, color texture classification, feature clustering, color LBP, chromatic cooccurrence matrix

Procedia PDF Downloads 137

Authors: Hortènsia Curell, Ana Fernández-Montraveta

Abstract:

This paper presents the creation, development, and analysis of a corpus designed to study the presence of attitude markers and author’s stance in research articles in two different areas of linguistics (theoretical linguistics and sociolinguistics). These two disciplines are expected to behave differently in this respect, given the disparity in their discursive conventions. Attitude markers in this work are understood as the linguistic elements (adjectives, nouns and verbs) used to convey the writer's stance towards the content presented in the article, and are crucial in understanding writer-reader interaction and the writer's position. These attitude markers are divided into three broad classes: assessment, significance, and emotion. In addition to them, we also consider first-person singular and plural pronouns and possessives, modal verbs, and passive constructions, which are other linguistic elements expressing the author’s stance. The corpus, Corpus of Attitude in Academic Writing (CAAW), comprises a collection of 21 articles, collected from six journals indexed in JCR. These articles were originally written in English by a single native-speaker author from the UK or USA and were published between 2022 and 2023. The total number of words in the corpus is approximately 222,400, with 106,422 from theoretical linguistics (Lingua, Linguistic Inquiry and Journal of Linguistics) and 116,022 from sociolinguistics journals (International Journal of the Sociology of Language, Language in Society and Journal of Sociolinguistics). Together with the corpus, we present the tool created for the creation and storage of the corpus, along with a tool for automatic annotation. The steps followed in the compilation of the corpus are as follows. First, the articles were selected according to the parameters explained above. Second, they were downloaded and converted to txt format. Finally, examples, direct quotes, section titles and references were eliminated, since they do not involve the author’s stance. The resulting texts were the input for the annotation of the linguistic features related to stance. As for the annotation, two articles (one from each subdiscipline) were annotated manually by the two researchers. An existing list was used as a baseline, and other attitude markers were identified, together with the other elements mentioned above. Once a consensus was reached, the rest of articles were annotated automatically using the tool created for this purpose. The annotated corpus will serve as a resource for scholars working in discourse analysis (both in linguistics and communication) and related fields, since it offers new insights into the expression of attitude. The tools created for the compilation and annotation of the corpus will be useful to study author’s attitude and stance in articles from any academic discipline: new data can be uploaded and the list of markers can be enlarged. Finally, the tool can be expanded to other languages, which will allow cross-linguistic studies of author’s stance.

Keywords: academic writing, attitude, corpus, english

Procedia PDF Downloads 74

Authors: Despoina Mouratidis, Katia Lida Kermanidis

Abstract:

Machine translation (MT) is a very important task in Natural Language Processing (NLP). MT evaluation is crucial in MT development, as it constitutes the means to assess the success of an MT system, and also helps improve its performance. Several methods have been proposed for the evaluation of (MT) systems. Some of the most popular ones in automatic MT evaluation are score-based, such as the BLEU score, and others are based on lexical similarity or syntactic similarity between the MT outputs and the reference involving higher-level information like part of speech tagging (POS). This paper presents a language-independent machine learning framework for classifying pairwise translations. This framework uses vector representations of two machine-produced translations, one from a statistical machine translation model (SMT) and one from a neural machine translation model (NMT). The vector representations consist of automatically extracted word embeddings and string-like language-independent features. These vector representations used as an input to a multi-layer neural network (NN) that models the similarity between each MT output and the reference, as well as between the two MT outputs. To evaluate the proposed approach, a professional translation and a "ground-truth" annotation are used. The parallel corpora used are English-Greek (EN-GR) and English-Italian (EN-IT), in the educational domain and of informal genres (video lecture subtitles, course forum text, etc.) that are difficult to be reliably translated. They have tested three basic deep learning (DL) architectures to this schema: (i) fully-connected dense, (ii) Convolutional Neural Network (CNN), and (iii) Long Short-Term Memory (LSTM). Experiments show that all tested architectures achieved better results when compared against those of some of the well-known basic approaches, such as Random Forest (RF) and Support Vector Machine (SVM). Better accuracy results are obtained when LSTM layers are used in our schema. In terms of a balance between the results, better accuracy results are obtained when dense layers are used. The reason for this is that the model correctly classifies more sentences of the minority class (SMT). For a more integrated analysis of the accuracy results, a qualitative linguistic analysis is carried out. In this context, problems have been identified about some figures of speech, as the metaphors, or about certain linguistic phenomena, such as per etymology: paronyms. It is quite interesting to find out why all the classifiers led to worse accuracy results in Italian as compared to Greek, taking into account that the linguistic features employed are language independent.

Keywords: machine learning, machine translation evaluation, neural network architecture, pairwise classification

Procedia PDF Downloads 132

Authors: Tadele Tesfaw, Ajit Pal Singh, Abebaw Mekonnen Gezahegn

Abstract:

Welding is a basic manufacturing process for making components or assemblies. Recent welding economics research has focused on developing the reliable machinery database to ensure optimum production. Research on welding of materials like steel is still critical and ongoing. Welding input parameters play a very significant role in determining the quality of a weld joint. The metal active gas (MAG) welding parameters are the most important factors affecting the quality, productivity and cost of welding in many industrial operations. The aim of this study is to investigate the optimization process parameters for metal active gas welding for 60x60x5mm dead mild steel plate work-piece using Taguchi method to formulate the statistical experimental design using semi-automatic welding machine. An experimental study was conducted at Bishoftu Automotive Industry, Bishoftu, Ethiopia. This study presents the influence of four welding parameters (control factors) like welding voltage (volt), welding current (ampere), wire speed (m/min.), and gas (CO2) flow rate (lit./min.) with three different levels for variability in the welding hardness. The objective functions have been chosen in relation to parameters of MAG welding i.e., welding hardness in final products. Nine experimental runs based on an L9 orthogonal array Taguchi method were performed. An orthogonal array, signal-to-noise (S/N) ratio and analysis of variance (ANOVA) are employed to investigate the welding characteristics of dead mild steel plate and used in order to obtain optimum levels for every input parameter at 95% confidence level. The optimal parameters setting was found is welding voltage at 22 volts, welding current at 125 ampere, wire speed at 2.15 m/min and gas flow rate at 19 l/min by using the Taguchi experimental design method within the constraints of the production process. Finally, six conformations welding have been carried out to compare the existing values; the predicated values with the experimental values confirm its effectiveness in the analysis of welding hardness (quality) in final products. It is found that welding current has a major influence on the quality of welded joints. Experimental result for optimum setting gave a better hardness of welding condition than initial setting. This study is valuable for different material and thickness variation of welding plate for Ethiopian industries.

Keywords: Weld quality, metal active gas welding, dead mild steel plate, orthogonal array, analysis of variance, Taguchi method

Procedia PDF Downloads 481

Authors: Chiyoung Kim, Jaegeol Yim

Abstract:

Bus service is often either main or the only public transportation available in cities. In metropolitan areas, both subways and buses are available whereas in the medium sized cities buses are usually the only type of public transportation available. Bus Information Systems (BIS) provide current locations of running buses, efficient routes to travel from one place to another, points of interests around a given bus stop, a series of bus stops consisting of a given bus route, and so on to users. Thanks to BIS, people do not have to waste time at a bus stop waiting for a bus because BIS provides exact information on bus arrival times at a given bus stop. Therefore, BIS does a lot to promote the use of buses contributing to pollution reduction and saving natural resources. BIS implementation costs a huge amount of budget as it requires a lot of special equipment such as road side equipment, automatic vehicle identification and location systems, trunked radio systems, and so on. Consequently, medium and small sized cities with a low budget cannot afford to install BIS even though people in these cities need BIS service more desperately than people in metropolitan areas. It is possible to provide BIS service at virtually no cost under the assumption that everybody carries a smartphone and there is at least one person with a smartphone in a running bus who is willing to reveal his/her location details while he/she is sitting in a bus. This assumption is usually true in the real world. The smartphone penetration rate is greater than 100% in the developed countries and there is no reason for a bus driver to refuse to reveal his/her location details while driving. We have developed a mobile app that periodically reads values of sensors including GPS and sends GPS data to the server when the bus stops or when the elapsed time from the last send attempt is greater than a threshold. This app detects the bus stop state by investigating the sensor values. The server that receives GPS data from this app has also been developed. Under the assumption that the current locations of all running buses collected by the mobile app are recorded in a database, we have also developed a web site that provides all kinds of information that most BISs provide to users through the Internet. The development environment is: OS: Windows 7 64bit, IDE: Eclipse Luna 4.4.1, Spring IDE 3.7.0, Database: MySQL 5.1.7, Web Server: Apache Tomcat 7.0, Programming Language: Java 1.7.0_79. Given a start and a destination bus stop, it finds a shortest path from the start to the destination using the Dijkstra algorithm. Then, it finds a convenient route considering number of transits. For the user interface, we use the Google map. Template classes that are used by the Controller, DAO, Service and Utils classes include BUS, BusStop, BusListInfo, BusStopOrder, RouteResult, WalkingDist, Location, and so on. We are now integrating the mobile app system and the web app system.

Keywords: bus information system, GPS, mobile app, web site

Procedia PDF Downloads 216

Authors: Ruchi B. Semwal, Deepak K. Semwal, Thobile A. N. Nkosi, Alvaro M. Viljoen

Abstract:

The use of Lawsonia inermis L. (Lythraeae), commonly known as henna, has many medicinal benefits and is used as a remedy for the treatment of diarrhoea, cancer, inflammation, headache, jaundice and skin diseases in folk medicine. Although widely used for hair dyeing and temporary tattooing, henna body art has popularized over the last 15 years and changed from being a traditional bridal and festival adornment to an exotic fashion accessory. The naphthoquinone, lawsone, is one of the main constituents of the plant and responsible for its dyeing property. Henna leaves typically contain 1.8–1.9% lawsone, which is used as a marker compound for the quality control of henna products. Adulteration of henna with various toxic chemicals such as p-phenylenediamine, p-methylaminophenol, p-aminobenzene and p-toluenodiamine to produce a variety of colours, is very common and has resulted in serious health problems, including allergic reactions. This study aims to assess the quality of henna products collected from different parts of the world by determining the lawsone content, as well as the concentrations of any adulterants present. Ultra high performance liquid chromatography-mass spectrometry (UPLC-MS) was used to determine the lawsone concentrations in 172 henna products. Separation of the chemical constituents was achieved on an Acquity UPLC BEH C18 column using gradient elution (0.1% formic acid and acetonitrile). The results from UPLC-MS revealed that of 172 henna products, 11 contained 1.0-1.8% lawsone, 110 contained 0.1-0.9% lawsone, whereas 51 samples did not contain detectable levels of lawsone. High performance thin layer chromatography was investigated as a cheaper, more rapid technique for the quality control of henna in relation to the lawsone content. The samples were applied using an automatic TLC Sampler 4 (CAMAG) to pre-coated silica plates, which were subsequently developed with acetic acid, acetone and toluene (0.5: 1.0: 8.5 v/v). A Reprostar 3 digital system allowed the images to be captured. The results obtained corresponded to those from UPLC-MS analysis. Vibrational spectroscopy analysis (MIR or NIR) of the powdered henna, followed by chemometric modelling of the data, indicates that this technique shows promise as an alternative quality control method. Principal component analysis (PCA) was used to investigate the data by observing clustering and identifying outliers. Partial least squares (PLS) multivariate calibration models were constructed for the quantification of lawsone. In conclusion, only a few of the samples analysed contain lawsone in high concentrations, indicating that they are of poor quality. Currently, the presence of adulterants that may have been added to enhance the dyeing properties of the products, is being investigated.

Keywords: Lawsonia inermis, paraphenylenediamine, temporary tattooing, lawsone

Procedia PDF Downloads 459

Authors: Anderson Braga Mendes

Abstract:

Itaipu Hydroelectric Power Plant is settled on the Paraná River, which is a natural boundary between Brazil and Paraguay; thus, the facility is shared by both countries. Itaipu Power Plant is the biggest hydroelectric generator in the world, and provides clean and renewable electrical energy supply for 17% and 76% of Brazil and Paraguay, respectively. The plant started its generation in 1984. It counts on 20 Francis turbines and has installed capacity of 14,000 MWh. Its historic generation record occurred in 2016 (103,098,366 MWh), and since the beginning of its operation until the last day of 2016 the plant has achieved the sum of 2,415,789,823 MWh. The distinct sedimentologic aspects of the drainage area of Itaipu Power Plant, from its stretch upstream (Porto Primavera and Rosana dams) to downstream (Itaipu dam itself), were taken into account in order to best estimate the increase/decrease in the sediment yield by using data from 2001 to 2016. Such data are collected through a network of 14 automatic sedimentometric stations managed by the company itself and operating in an hourly basis, covering an area of around 136,000 km² (92% of the incremental drainage area of the undertaking). Since 1972, a series of lifespan studies for the Itaipu Power Plant have been made, being first assessed by Sir Hans Albert Einstein, at the time of the feasibility studies for the enterprise. From that date onwards, eight further studies were made through the last 44 years aiming to confer more precision upon the estimates based on more updated data sets. From the analysis of each monitoring station, it was clearly noticed strong increase tendencies in the sediment yield through the last 14 years, mainly in the Iguatemi, Ivaí, São Francisco Falso and Carapá Rivers, the latter situated in Paraguay, whereas the others are utterly in Brazilian territory. Five lifespan scenarios considering different sediment yield tendencies were simulated with the aid of the softwares SEDIMENT and DPOSIT, both developed by the author of the present work. Such softwares thoroughly follow the Borland & Miller methodology (empirical method of area-reduction). The soundest scenario out of the five ones under analysis indicated a lifespan foresight of 168 years, being the reservoir only 1.8% silted by the end of 2016, after 32 years of operation. Besides, the mass balance in the reservoir (water inflows minus outflows) between 1986 and 2016 shows that 2% of the whole Itaipu lake is silted nowadays. Owing to the convergence of both results, which were acquired by using different methodologies and independent input data, it is worth concluding that the mathematical modeling is satisfactory and calibrated, thus assigning credibility to this most recent lifespan estimate.

Keywords: Borland and Miller method, hydroelectricity, Itaipu Power Plant, lifespan, mass balance

Procedia PDF Downloads 274