Search results for: illumination techniques
5019 Sinhala Sign Language to Grammatically Correct Sentences using NLP
Authors: Anjalika Fernando, Banuka Athuraliya
Abstract:
This paper presents a comprehensive approach for converting Sinhala Sign Language (SSL) into grammatically correct sentences using Natural Language Processing (NLP) techniques in real-time. While previous studies have explored various aspects of SSL translation, the research gap lies in the absence of grammar checking for SSL. This work aims to bridge this gap by proposing a two-stage methodology that leverages deep learning models to detect signs and translate them into coherent sentences, ensuring grammatical accuracy. The first stage of the approach involves the utilization of a Long Short-Term Memory (LSTM) deep learning model to recognize and interpret SSL signs. By training the LSTM model on a dataset of SSL gestures, it learns to accurately classify and translate these signs into textual representations. The LSTM model achieves a commendable accuracy rate of 94%, demonstrating its effectiveness in accurately recognizing and translating SSL gestures. Building upon the successful recognition and translation of SSL signs, the second stage of the methodology focuses on improving the grammatical correctness of the translated sentences. The project employs a Neural Machine Translation (NMT) architecture, consisting of an encoder and decoder with LSTM components, to enhance the syntactical structure of the generated sentences. By training the NMT model on a parallel corpus of Sinhala wrong sentences and their corresponding grammatically correct translations, it learns to generate coherent and grammatically accurate sentences. The NMT model achieves an impressive accuracy rate of 98%, affirming its capability to produce linguistically sound translations. The proposed approach offers significant contributions to the field of SSL translation and grammar correction. Addressing the critical issue of grammar checking, it enhances the usability and reliability of SSL translation systems, facilitating effective communication between hearing-impaired and non-sign language users. Furthermore, the integration of deep learning techniques, such as LSTM and NMT, ensures the accuracy and robustness of the translation process. This research holds great potential for practical applications, including educational platforms, accessibility tools, and communication aids for the hearing-impaired. Furthermore, it lays the foundation for future advancements in SSL translation systems, fostering inclusive and equal opportunities for the deaf community. Future work includes expanding the existing datasets to further improve the accuracy and generalization of the SSL translation system. Additionally, the development of a dedicated mobile application would enhance the accessibility and convenience of SSL translation on handheld devices. Furthermore, efforts will be made to enhance the current application for educational purposes, enabling individuals to learn and practice SSL more effectively. Another area of future exploration involves enabling two-way communication, allowing seamless interaction between sign-language users and non-sign-language users.In conclusion, this paper presents a novel approach for converting Sinhala Sign Language gestures into grammatically correct sentences using NLP techniques in real time. The two-stage methodology, comprising an LSTM model for sign detection and translation and an NMT model for grammar correction, achieves high accuracy rates of 94% and 98%, respectively. By addressing the lack of grammar checking in existing SSL translation research, this work contributes significantly to the development of more accurate and reliable SSL translation systems, thereby fostering effective communication and inclusivity for the hearing-impaired communityKeywords: Sinhala sign language, sign Language, NLP, LSTM, NMT
Procedia PDF Downloads 1045018 Removal of Samarium in Environmental Water Samples by Modified Yeast Cells
Authors: Homayon Ahmad Panahi, Seyed Mehdi Seyed Nejad, Elham Moniri
Abstract:
A novel bio-adsorbent is fabricated by attaching a cibacron blue to yeast cells. The modified bio-sorbent has been characterized by some techniques like Fourier transform infrared spectroscopy (FT-IR) and elemental analysis (CHN) and applied for the preconcentration and determination of samarium from aqueous water samples. The best pH value for adsorption of the brilliant crecyle blue by yeast cells- cibacron blue was 7. The sorption capacity of modified biosorbent was 18.5 mg. g⁻¹. A recovery of 95.3% was obtained for Sm(III) when eluted with 0.5 M nitric acid. The method was applied for Sm(III) preconcentration and determination in river water sample.Keywords: samarium, solid phase extraction, yeast cells, water sample, removal
Procedia PDF Downloads 2555017 Interaction of Low-Impact Development Techniques and Urban River Flooding on the Zoning – Case Study Qomroud
Authors: Mohammad Reza Kavianpour, Arsalan Behzadifard Pour, Ali Aghazadeh Cloudy, Abolfazl Moqimi
Abstract:
In recent decades, and with increasing of urban population and development of the city, the amount of impermeable surfaces has been increased. This cause urban runoff enhancement. This enhancement, especially in cities with urban river, increases the possibility of urban flooding caused by the river flooding interaction and urban runoff. In this research, we tried SWMM utilizes software development methods and practices that seek to reduce the impact of runoff to the river flows to reduce Qomroud and Effects using Arc GIS and HEC-RAS software on how we see the flood zone.Keywords: flood management, SWMM, runoff, flood zone
Procedia PDF Downloads 6115016 Chemical Constituents of Silene Arenarioides Desf
Authors: Haba Hamada, Lavaud Cathrine, Benkhaled Mohammed
Abstract:
The Silene genus is the most representative of the caryophyllaceae family for their rich content in secondary metabolites; saponins, flavonoids and flavonoids glycosides, phytoecdysones, oligosaccharides have been isolated and identified. The Silene genus represented by about 700 species in the temrerate region of the word, the main concentration of spcies is Europe, Asia and North Africa. Three known compounds 1-3 were isolated from the aerial parts of Silene arenarioides Desf. by using different chromatographic methods. The structures of the isolated compounds were determined as stigmasterolglycoside, Soyacerebroside, maltol glycoside. The structures of the isolated compounds were determined by using the NMR (1H-NMR, 13C-NMR, COSY, HSQC, and HMBC) techniques and mass spectroscopy. The antimicrobial and antioxydant activities of the different extracts and compound have been reported.Keywords: caryophyllaceae, flavonoids, saponosids, flavonoids glycosides
Procedia PDF Downloads 4035015 Effective Counseling Techniques Working with At-Risk Youth in Residential and Outpatient Settings
Authors: David A. Scott, Michelle G. Scott
Abstract:
The problem of juvenile crime, school suspensions and oppositional behaviors indicates a need for a wide range of intervention programs for at-risk youth. Juvenile court systems and mental health agencies are examining alternative ways to deal with at-risk youth that will allow the adolescent to live within their home community. The previous trend that treatment away from home is more effective than treatment near one's community has shifted. Research now suggests that treatment be close to home for several reasons, such as increased treatment success, parental involvement, and reduced costs. Treatment options consist of a wide range of interventions, including outpatient, inpatient, and community-based services (therapeutic group homes, foster care and in-home preservation services). The juvenile justice system, families and other mental health agencies continue to seek the most effective treatment for at-risk youth in their communities. This research examines two possible treatment modalities, a multi-systemic outpatient program and a residential program. Research examining effective, evidence- based counseling will be discussed during this presentation. The presenter recently completed a three-year research grant examining effective treatment modalities for at-risk youth participating in a multi-systemic program. The presenter has also been involved in several research activities gathering data on effective techniques used in residential programs. The data and discussion will be broken down into two parts, each discussing one of the treatment modalities mentioned above. Data on the residential programs was collected on both a sample of 740 at- risk youth over a five-year period and also a sample of 63 participants during a one-year period residing in a residential programs. The effectiveness of these residential services was measured in three ways: services are evaluated by primary referral sources; follow-up data is obtained at various intervals after program participation to measure recidivism (what percentage got back into trouble with the Department of Juvenile Justice); and a more sensitive, "Offense Seriousness Score", has been computed and analyzed prior to, during and after treatment in the residential program. Data on the multi-systemic program was gathered over the past three years on 190 participants. Research will discuss pre and post test results, recidivism rates, academic performance, parental involvement, and effective counseling treatment modalities.Keywords: at-risk youth, group homes, therapeutic group homes, recidivism rates
Procedia PDF Downloads 825014 Predicting the Success of Bank Telemarketing Using Artificial Neural Network
Authors: Mokrane Selma
Abstract:
The shift towards decision making (DM) based on artificial intelligence (AI) techniques will change the way in which consumer markets and our societies function. Through AI, predictive analytics is being used by businesses to identify these patterns and major trends with the objective to improve the DM and influence future business outcomes. This paper proposes an Artificial Neural Network (ANN) approach to predict the success of telemarketing calls for selling bank long-term deposits. To validate the proposed model, we uses the bank marketing data of 41188 phone calls. The ANN attains 98.93% of accuracy which outperforms other conventional classifiers and confirms that it is credible and valuable approach for telemarketing campaign managers.Keywords: bank telemarketing, prediction, decision making, artificial intelligence, artificial neural network
Procedia PDF Downloads 1595013 The Effect of the Structural Arrangement of Binary Bisamide Organogelators on their Self-Assembly Behavior
Authors: Elmira Ghanbari, Jan Van Esch, Stephen J. Picken, Sahil Aggarwal
Abstract:
Low-molecular-weight organogelators form gels by self-assembly into the crystalline network which immobilizes the organic solvent. For single bisamide organogelator systems, the effect of the molecular structure on the molecular interaction and their self-assembly behavior has been explored. The spatial arrangement of bisamide molecules in the gel-state is driven by a combination of hydrogen bonding and Van der Waals interactions. The hydrogen-bonding pattern between the amide groups of bisamide molecules is regulated by the number of methylene spacers; the even number of methylene spacers between two amide groups, in even-spaced bisamides, leads to the antiparallel position of amide groups within a molecule. An even-spaced bisamide molecule with antiparallel amide groups can make two pairs of hydrogen bonding with the molecules on the same plane. The odd-spaced bisamide with a parallel directionality of amide groups can form four independent hydrogen bonds with four other bisamide molecules on different planes. The arrangement of bisamide molecules in the crystalline state and the interaction of these molecules depends on the molecular structure, particularly the parity of the spacer length between the amide groups in the bisamide molecule. In this study, the directionality of amide groups has been exploited as a structural characteristic to affect the arrangement of molecules in the crystalline state and produce different binary bisamide gelators with different degrees of crystallinities. Single odd- and even-spaced single bisamides were synthesized and blended to produce binary bisamide organogelators to be characterized in order to understand the effect of the different directionality of amide groups on the molecular interaction in the crystalline state. The pattern of molecular interactions between these blended molecules, mixing or phase separation, has been monitored via differential scanning calorimetry (DSC) and crystallography techniques; X-ray powder diffraction (XRD) and Small-angle X-ray scattering (SAXS). The formation of lamellar structures for odd- and even-spaced bisamide gelators was confirmed by using SAXS and XRD techniques. DSC results have shown that binary bisamide organogelators with different parity of methylene spacers (odd-even binary blends) have a higher tendency for phase separation compared to the binary bisamides with the same parity (odd-odd or even-even binary blends). Phase separation in binary odd-even bisamides was confirmed by the presence of individual (100) reflections of odd and even lamellar structures. The structural characteristic of bisamide organogelators, the parity of spacer length in binary systems, is a promising tool to control the arrangement of molecules and their crystalline structure.Keywords: binary bisamide organogelators, crystalline structure, phase separation, self-assembly behavior
Procedia PDF Downloads 1855012 Medical Image Compression Based on Region of Interest: A Review
Authors: Sudeepti Dayal, Neelesh Gupta
Abstract:
In terms of transmission, bigger the size of any image, longer the time the channel takes for transmission. It is understood that the bandwidth of the channel is fixed. Therefore, if the size of an image is reduced, a larger number of data or images can be transmitted over the channel. Compression is the technique used to reduce the size of an image. In terms of storage, compression reduces the file size which it occupies on the disk. Any image is based on two parameters, region of interest and non-region of interest. There are several algorithms of compression that compress the data more economically. In this paper we have reviewed region of interest and non-region of interest based compression techniques and the algorithms which compress the image most efficiently.Keywords: compression ratio, region of interest, DCT, DWT
Procedia PDF Downloads 3755011 Resistive Switching in TaN/AlNx/TiN Cell
Authors: Hsin-Ping Huang, Shyankay Jou
Abstract:
Resistive switching of aluminum nitride (AlNx) thin film was demonstrated in a TaN/AlNx/TiN memory cell that was prepared by sputter deposition techniques. The memory cell showed bipolar switching of resistance between +3.5 V and –3.5 V. The resistance ratio of high resistance state (HRS) to low resistance state (HRS), RHRS/RLRS, was about 2 over 100 cycles of endurance test. Both the LRS and HRS of the memory cell exhibited ohmic conduction at low voltages and Poole-Frenkel emission at high voltages. The electrical conduction in the TaN/AlNx/TiN memory cell was possibly attributed to the interactions between charges and defects in the AlNx film.Keywords: aluminum nitride, nonvolatile memory, resistive switching, thin films
Procedia PDF Downloads 3995010 Cognitive SATP for Airborne Radar Based on Slow-Time Coding
Authors: Fanqiang Kong, Jindong Zhang, Daiyin Zhu
Abstract:
Space-time adaptive processing (STAP) techniques have been motivated as a key enabling technology for advanced airborne radar applications. In this paper, the notion of cognitive radar is extended to STAP technique, and cognitive STAP is discussed. The principle for improving signal-to-clutter ratio (SCNR) based on slow-time coding is given, and the corresponding optimization algorithm based on cyclic and power-like algorithms is presented. Numerical examples show the effectiveness of the proposed method.Keywords: space-time adaptive processing (STAP), airborne radar, signal-to-clutter ratio, slow-time coding
Procedia PDF Downloads 2735009 Three-Dimensional Generalized Thermoelasticity with Variable Thermal Conductivity
Authors: Hamdy M. Youssef, Mowffaq Oreijah, Hunaydi S. Alsharif
Abstract:
In this paper, a three-dimensional model of the generalized thermoelasticity with one relaxation time and variable thermal conductivity has been constructed. The resulting non-dimensional governing equations together with the Laplace and double Fourier transforms techniques have been applied to a three-dimensional half-space subjected to thermal loading with rectangular pulse and traction free in the directions of the principle co-ordinates. The inverses of double Fourier transforms, and Laplace transforms have been obtained numerically. Numerical results for the temperature increment, the invariant stress, the invariant strain, and the displacement are represented graphically. The variability of the thermal conductivity has significant effects on the thermal and the mechanical waves.Keywords: thermoelasticity, thermal conductivity, Laplace transforms, Fourier transforms
Procedia PDF Downloads 2285008 An Architectural Model of Multi-Agent Systems for Student Evaluation in Collaborative Game Software
Authors: Monica Hoeldtke Pietruchinski, Andrey Ricardo Pimentel
Abstract:
The teaching of computer programming for beginners has been presented to the community as a not simple or trivial task. Several methodologies and research tools have been developed; however, the problem still remains. This paper aims to present multi-agent system architecture to be incorporated to the educational collaborative game software for teaching programming that monitors, evaluates and encourages collaboration by the participants. A literature review has been made on the concepts of Collaborative Learning, Multi-agents systems, collaborative games and techniques to teach programming using these concepts simultaneously.Keywords: architecture of multi-agent systems, collaborative evaluation, collaboration assessment, gamifying educational software
Procedia PDF Downloads 4645007 Thermal Technologies Applications for Soil Remediation
Authors: A. de Folly d’Auris, R. Bagatin, P. Filtri
Abstract:
This paper discusses the importance of having a good initial characterization of soil samples when thermal desorption has to be applied to polluted soils for the removal of contaminants. Particular attention has to be devoted on the desorption kinetics of the samples to identify the gases evolved during the heating, and contaminant degradation pathways. In this study, two samples coming from different points of the same contaminated site were considered. The samples are much different from each other. Moreover, the presence of high initial quantity of heavy hydrocarbons strongly affected the performance of thermal desorption, resulting in formation of dangerous intermediates. Analytical techniques such TGA (Thermogravimetric Analysis), DSC (Differential Scanning Calorimetry) and GC-MS (Gas Chromatography-Mass) provided a good support to give correct indication for field application.Keywords: desorption kinetics, hydrocarbons, thermal desorption, thermogravimetric measurements
Procedia PDF Downloads 2945006 Investigating the Effect of Plant Root Exudates and of Saponin on Polycyclic Aromatic Hydrocarbons Solubilization in Brownfield Contaminated Soils
Authors: Marie Davin, Marie-Laure Fauconnier, Gilles Colinet
Abstract:
In Wallonia, there are 6,000 estimated brownfields (rising to over 3.5 million in Europe) that require remediation. Polycyclic Aromatic Hydrocarbons (PAHs) are a class of recalcitrant carcinogenic/mutagenic organic compounds of major concern as they accumulate in the environment and represent 17% of all encountered pollutants. As an alternative to environmentally aggressive, expensive and often disruptive soil remediation strategies, a lot of research has been directed to developing techniques targeting organic pollutants. The following experiment, based on the observation that PAHs soil content decreases in the presence of plants, aimed at improving our understanding of the underlying mechanisms involved in phytoremediation. It focusses on plant root exudates and whether they improve PAHs solubilization, which would make them more available for bioremediation by soil microorganisms. The effect of saponin, a natural surfactant found in some plant roots such as members of the Fabaceae family, on PAHs solubilization was also investigated as part of the implementation of the experimental protocol. The experiments were conducted on soil collected from a brownfield in Saint-Ghislain (Belgium) and presenting weathered PAHs contamination. Samples of soil were extracted with different solutions containing either plant root exudates or commercial saponin. Extracted PAHs were determined in the different aqueous solutions using High-Performance Liquid Chromatography and Fluorimetric Detection (HPLC-FLD). Both root exudates of alfalfa (Medicago sativa L.) or red clover (Trifolium pratense L.) and commercial saponin were tested in different concentrations. Distilled water was used as a control. First of all, results show that PAHs are more extracted using saponin solutions than distilled water and that the amounts generally rise with the saponin concentration. However, the amount of each extracted compound diminishes as its molecular weight rises. Also, it appears that passed a certain surfactant concentration, PAHs are less extracted. This suggests that saponin might be investigated as a washing agent in polluted soil remediation techniques, either for ex-situ or in-situ treatments, as an alternative to synthetic surfactants. On the other hand, preliminary results on experiments using plant root exudates also show differences in PAHs solubilization compared to the control solution. Further results will allow discussion as to whether or not there are differences according to the exudates provenance and concentrations.Keywords: brownfield, Medicago sativa, phytoremediation, polycyclic aromatic hydrocarbons, root exudates, saponin, solubilization, Trifolium pratense
Procedia PDF Downloads 2535005 Training as a Service for Electronic Warfare
Authors: Toan Vo
Abstract:
Electronic attacks, illegal drones, interference, and jamming are no longer capabilities reserved for a state-sponsored, near-peer adversary. The proliferation of jammers on auction websites has lowered the price of entry for electronics hobbyists and nefarious actors. To enable local authorities and enforcement bodies to keep up with these challenges, this paper proposes a training as a service model to quickly and economically train and equip police departments and local law enforcement agencies. Using the U.S Department of Defense’s investment in Electronic Warfare as a guideline, a large number of personnel can be trained on effective spectrum monitoring techniques using commercial equipment readily available on the market. Finally, this paper will examine the economic benefits to the test and measurement industry if the TaaS model is applied.Keywords: training, electronic warfare, economics, law enforcement
Procedia PDF Downloads 1035004 Closest Possible Neighbor of a Different Class: Explaining a Model Using a Neighbor Migrating Generator
Authors: Hassan Eshkiki, Benjamin Mora
Abstract:
The Neighbor Migrating Generator is a simple and efficient approach to finding the closest potential neighbor(s) with a different label for a given instance and so without the need to calibrate any kernel settings at all. This allows determining and explaining the most important features that will influence an AI model. It can be used to either migrate a specific sample to the class decision boundary of the original model within a close neighborhood of that sample or identify global features that can help localising neighbor classes. The proposed technique works by minimizing a loss function that is divided into two components which are independently weighted according to three parameters α, β, and ω, α being self-adjusting. Results show that this approach is superior to past techniques when detecting the smallest changes in the feature space and may also point out issues in models like over-fitting.Keywords: explainable AI, EX AI, feature importance, counterfactual explanations
Procedia PDF Downloads 1925003 Data Science Inquiry to Manage Football Referees’ Careers
Authors: Iñaki Aliende, Tom Webb, Lorenzo Escot
Abstract:
There is a concern about the decrease in football referees globally. A study in Spain has analyzed the factors affecting a referee's career over the past 30 years through a survey of 758 referees. Results showed the impact of factors such as threats, education, initial vocation, and dependents on a referee's career. To improve the situation, the federation needs to provide better information, support young referees, monitor referees, and raise public awareness of violence toward referees. The study also formed a comprehensive model for federations to enhance their officiating policies by means of data-driven techniques that can serve other federations to improve referees' careers.Keywords: data science, football referees, sport management, sport careers, survival analysis
Procedia PDF Downloads 995002 Methods for Business Process Simulation Based on Petri Nets
Authors: K. Shoylekova, K. Grigorova
Abstract:
The Petri nets are the first standard for business process modeling. Most probably, it is one of the core reasons why all new standards created afterwards have to be so reformed as to reach the stage of mapping the new standard onto Petri nets. The paper presents a Business process repository based on a universal database. The repository provides the possibility the data about a given process to be stored in three different ways. Business process repository is developed with regard to the reformation of a given model to a Petri net in order to be easily simulated two different techniques for business process simulation based on Petri nets - Yasper and Woflan are discussed. Their advantages and drawbacks are outlined. The way of simulating business process models, stored in the Business process repository is shown.Keywords: business process repository, petri nets, simulation, Woflan, Yasper
Procedia PDF Downloads 3705001 Facial Emotion Recognition Using Deep Learning
Authors: Ashutosh Mishra, Nikhil Goyal
Abstract:
A 3D facial emotion recognition model based on deep learning is proposed in this paper. Two convolution layers and a pooling layer are employed in the deep learning architecture. After the convolution process, the pooling is finished. The probabilities for various classes of human faces are calculated using the sigmoid activation function. To verify the efficiency of deep learning-based systems, a set of faces. The Kaggle dataset is used to verify the accuracy of a deep learning-based face recognition model. The model's accuracy is about 65 percent, which is lower than that of other facial expression recognition techniques. Despite significant gains in representation precision due to the nonlinearity of profound image representations.Keywords: facial recognition, computational intelligence, convolutional neural network, depth map
Procedia PDF Downloads 2315000 The Combination of the Mel Frequency Cepstral Coefficients, Perceptual Linear Prediction, Jitter and Shimmer Coefficients for the Improvement of Automatic Recognition System for Dysarthric Speech
Authors: Brahim Fares Zaidi
Abstract:
Our work aims to improve our Automatic Recognition System for Dysarthria Speech based on the Hidden Models of Markov and the Hidden Markov Model Toolkit to help people who are sick. With pronunciation problems, we applied two techniques of speech parameterization based on Mel Frequency Cepstral Coefficients and Perceptual Linear Prediction and concatenated them with JITTER and SHIMMER coefficients in order to increase the recognition rate of a dysarthria speech. For our tests, we used the NEMOURS database that represents speakers with dysarthria and normal speakers.Keywords: ARSDS, HTK, HMM, MFCC, PLP
Procedia PDF Downloads 1084999 Anthropomorphism and Its Impact on the Implementation and Perception of AI
Authors: Marie Oldfield
Abstract:
Anthropomorphism is a technique used by humans to make sense of their surroundings. Anthropomorphism is a widely used technique used to influence consumers to purchase goods or services. These techniques can entice consumers into buying something to fulfill a gap or desire in their life, ranging from loneliness to the desire to be exclusive. By manipulating belief systems, consumer behaviour can be exploited. This paper examines a series of studies to show how anthropomorphism can be used as a basis for exploitation. The first set of studies in this paper examines how anthropomorphism is used in marketing and the effects on humans engaging with this technique. The second set of studies examines how humans can be potentially exploited by artificial agents. We then discuss the consequences of this type of activity within the context of dehumanisation. This research has found potential serious consequences for society and humanity, which indicate an urgent need for further research in this area.Keywords: anthropomorphism, ethics, human-computer interaction, AI
Procedia PDF Downloads 894998 Evaluation of SDS (Software Defined Storage) Controller (CorpHD) for Various Storage Demands
Authors: Shreya Bokare, Sanjay Pawar, Shika Nema
Abstract:
Growth in cloud applications is generating the tremendous amount of data, building load on traditional storage management systems. Software Defined Storage (SDS) is a new storage management concept becoming popular to handle this large amount of data. CoprHD is one of the open source SDS controller, available for experimentation and development in the storage industry. In this paper, the storage management techniques provided by CoprHD to manage heterogeneous storage platforms are experimented and analyzed. Various storage management parameters such as time to provision, storage capacity measurement, and heterogeneity are experimentally evaluated along with the theoretical expression to prove the completeness of CoprHD controller for storage management.Keywords: software defined storage, SDS, CoprHD, open source, SMI-S simulator, clarion, Symmetrix
Procedia PDF Downloads 3134997 Fine-Tuned Transformers for Translating Multi-Dialect Texts to Modern Standard Arabic
Authors: Tahar Alimi, Rahma Boujebane, Wiem Derouich, Lamia Hadrich Belguith
Abstract:
Machine translation task of low-resourced languages such as Arabic is a challenging task. Despite the appearance of sophisticated models based on the latest deep learning techniques, namely the transfer learning and transformers, all models prove incapable of carrying out an acceptable translation, which includes Arabic Dialects (AD), because they do not have official status. In this paper, we present a machine translation model designed to translate Arabic multidialectal content into Modern Standard Arabic (MSA), leveraging both new and existing parallel resources. The latter achieved the best results for both Levantine and Maghrebi dialects with a BLEU score of 64.99.Keywords: Arabic translation, dialect translation, fine-tune, MSA translation, transformer, translation
Procedia PDF Downloads 614996 Landslide Hazard Zonation Using Satellite Remote Sensing and GIS Technology
Authors: Ankit Tyagi, Reet Kamal Tiwari, Naveen James
Abstract:
Landslide is the major geo-environmental problem of Himalaya because of high ridges, steep slopes, deep valleys, and complex system of streams. They are mainly triggered by rainfall and earthquake and causing severe damage to life and property. In Uttarakhand, the Tehri reservoir rim area, which is situated in the lesser Himalaya of Garhwal hills, was selected for landslide hazard zonation (LHZ). The study utilized different types of data, including geological maps, topographic maps from the survey of India, Landsat 8, and Cartosat DEM data. This paper presents the use of a weighted overlay method in LHZ using fourteen causative factors. The various data layers generated and co-registered were slope, aspect, relative relief, soil cover, intensity of rainfall, seismic ground shaking, seismic amplification at surface level, lithology, land use/land cover (LULC), normalized difference vegetation index (NDVI), topographic wetness index (TWI), stream power index (SPI), drainage buffer and reservoir buffer. Seismic analysis is performed using peak horizontal acceleration (PHA) intensity and amplification factors in the evaluation of the landslide hazard index (LHI). Several digital image processing techniques such as topographic correction, NDVI, and supervised classification were widely used in the process of terrain factor extraction. Lithological features, LULC, drainage pattern, lineaments, and structural features are extracted using digital image processing techniques. Colour, tones, topography, and stream drainage pattern from the imageries are used to analyse geological features. Slope map, aspect map, relative relief are created by using Cartosat DEM data. DEM data is also used for the detailed drainage analysis, which includes TWI, SPI, drainage buffer, and reservoir buffer. In the weighted overlay method, the comparative importance of several causative factors obtained from experience. In this method, after multiplying the influence factor with the corresponding rating of a particular class, it is reclassified, and the LHZ map is prepared. Further, based on the land-use map developed from remote sensing images, a landslide vulnerability study for the study area is carried out and presented in this paper.Keywords: weighted overlay method, GIS, landslide hazard zonation, remote sensing
Procedia PDF Downloads 1334995 Application of Thermoplastic Microbioreactor to the Single Cell Study of Budding Yeast to Decipher the Effect of 5-Hydroxymethylfurfural on Growth
Authors: Elif Gencturk, Ekin Yurdakul, Ahmet Y. Celik, Senol Mutlu, Kutlu O. Ulgen
Abstract:
Yeast cells are generally used as a model system of eukaryotes due to their complex genetic structure, rapid growth ability in optimum conditions, easy replication and well-defined genetic system properties. Thus, yeast cells increased the knowledge of the principal pathways in humans. During fermentation, carbohydrates (hexoses and pentoses) degrade into some toxic by-products such as 5-hydroxymethylfurfural (5-HMF or HMF) and furfural. HMF influences the ethanol yield, and ethanol productivity; it interferes with microbial growth and is considered as a potent inhibitor of bioethanol production. In this study, yeast single cell behavior under HMF application was monitored by using a continuous flow single phase microfluidic platform. Microfluidic device in operation is fabricated by hot embossing and thermo-compression techniques from cyclo-olefin polymer (COP). COP is biocompatible, transparent and rigid material and it is suitable for observing fluorescence of cells considering its low auto-fluorescence characteristic. The response of yeast cells was recorded through Red Fluorescent Protein (RFP) tagged Nop56 gene product, which is an essential evolutionary-conserved nucleolar protein, and also a member of the box C/D snoRNP complexes. With the application of HMF, yeast cell proliferation continued but HMF slowed down the cell growth, and after HMF treatment the cell proliferation stopped. By the addition of fresh nutrient medium, the yeast cells recovered after 6 hours of HMF exposure. Thus, HMF application suppresses normal functioning of cell cycle but it does not cause cells to die. The monitoring of Nop56 expression phases of the individual cells shed light on the protein and ribosome synthesis cycles along with their link to growth. Further computational study revealed that the mechanisms underlying the inhibitory or inductive effects of HMF on growth are enriched in functional categories of protein degradation, protein processing, DNA repair and multidrug resistance. The present microfluidic device can successfully be used for studying the effects of inhibitory agents on growth by single cell tracking, thus capturing cell to cell variations. By metabolic engineering techniques, engineered strains can be developed, and the metabolic network of the microorganism can thus be manipulated such that chemical overproduction of target metabolite is achieved along with the maximum growth/biomass yield.Keywords: COP, HMF, ribosome biogenesis, thermoplastic microbioreactor, yeast
Procedia PDF Downloads 1714994 The Racism Found in Capitalism’s Poetry
Authors: Rich Murphy
Abstract:
‘The Racism Found in Capitalism’s Poetry’ claims that since the death of philosophy and the end of art modern poetry has been upstaged by capitalist poetry using similar strategies and techniques; while both sublime moments use spectacle one is more effective. The essay also claims that capitalist poetry is open to racism and analyzes KFC advertising campaign to produce evidence of wide spread acceptance in an era of ‘micro-aggressions’ and confederate flag removals. The essay spends considerable time outlining the history of advertising and the weak literary counters to it that inevitably lent its assistance in education. The essay also suggests that the concept of ‘Enormous Irony’ may be the only way to counter. However, as long as capitalism is the method of the economy and governance, the essay suggests, there was little hope in spite of Obama’s election.Keywords: modern poetry, advertising, Kentucky fried chicken, capitalism, poetry
Procedia PDF Downloads 2544993 A Contribution to Human Activities Recognition Using Expert System Techniques
Authors: Malika Yaici, Soraya Aloui, Sara Semchaoui
Abstract:
This paper deals with human activity recognition from sensor data. It is an active research area, and the main objective is to obtain a high recognition rate. In this work, a recognition system based on expert systems is proposed; the recognition is performed using the objects, object states, and gestures and taking into account the context (the location of the objects and of the person performing the activity, the duration of the elementary actions and the activity). The system recognizes complex activities after decomposing them into simple, easy-to-recognize activities. The proposed method can be applied to any type of activity. The simulation results show the robustness of our system and its speed of decision.Keywords: human activity recognition, ubiquitous computing, context-awareness, expert system
Procedia PDF Downloads 1184992 Condensed Benzo, Pyrido, Pyrimidino-Imidazole Derivatives as Antidiabetic Agents
Authors: Fatima Doganc, Hakan Goker
Abstract:
Benzimidazole moiety is an important pharmacophore and privileged structure for the medicinal chemists, since it exhibits various important biological activities. Some clinically used drugs have benzimidazole moiety, such as omeprazole, astemizole, albendazole and domperidone. 2-(4-tert-Butylphenyl)benzimidazole, is a PGC-1α transcriptional regulator shown to have beneficial effects in diabetic mice. We planned to modify the structure of this compound for developing new antidiabetic drug candidates. Hence, a series of guanidino or amidino, benzo/pyrido/pyrimidino-imidazole derivatives were freshly prepared. Mass, 1H-NMR, 13C-NMR, 2D-NMR spectroscopy techniques were used for the new derivatives to clarify their structures and their purity was controlled through the elemental analysis. Antidiabetic activity studies of the synthesized compounds are under the investigation.Keywords: antidiabetic agents, benzimidazole, imidazopyridine, imidazopyrimidine
Procedia PDF Downloads 3484991 Bug Localization on Single-Line Bugs of Apache Commons Math Library
Authors: Cherry Oo, Hnin Min Oo
Abstract:
Software bug localization is one of the most costly tasks in program repair technique. Therefore, there is a high claim for automated bug localization techniques that can monitor programmers to the locations of bugs, with slight human arbitration. Spectrum-based bug localization aims to help software developers to discover bugs rapidly by investigating abstractions of the program traces to make a ranking list of most possible buggy modules. Using the Apache Commons Math library project, we study the diagnostic accuracy using our spectrum-based bug localization metric. Our outcomes show that the greater performance of a specific similarity coefficient, used to inspect the program spectra, is mostly effective on localizing of single line bugs.Keywords: software testing, bug localization, program spectra, bug
Procedia PDF Downloads 1434990 Emotion Detection in a General Human-Robot Interaction System Optimized for Embedded Platforms
Authors: Julio Vega
Abstract:
Expression recognition is a field of Artificial Intelligence whose main objectives are to recognize basic forms of affective expression that appear on people’s faces and contributing to behavioral studies. In this work, a ROS node has been developed that, based on Deep Learning techniques, is capable of detecting the facial expressions of the people that appear in the image. These algorithms were optimized so that they can be executed in real time on an embedded platform. The experiments were carried out in a PC with a USB camera and in a Raspberry Pi 4 with a PiCamera. The final results shows a plausible system, which is capable to work in real time even in an embedded platform.Keywords: python, low-cost, raspberry pi, emotion detection, human-robot interaction, ROS node
Procedia PDF Downloads 129