Search results for: images processing

Authors: Rabi Mouhcine, Amrouch Mustapha, Mahani Zouhir, Mammass Driss

Abstract:

In this paper, we present a system for offline recognition cursive Arabic handwritten text based on Hidden Markov Models (HMMs). The system is analytical without explicit segmentation used embedded training to perform and enhance the character models. Extraction features preceded by baseline estimation are statistical and geometric to integrate both the peculiarities of the text and the pixel distribution characteristics in the word image. These features are modelled using hidden Markov models and trained by embedded training. The experiments on images of the benchmark IFN/ENIT database show that the proposed system improves recognition.

Keywords: recognition, handwriting, Arabic text, HMMs, embedded training

Procedia PDF Downloads 354

Authors: Teodora Vukovic, Christoph Hottiger, Noah Bubenhofer

Abstract:

The development of VIAN-DH aims at bridging two linguistic approaches: conversation analysis/interactional linguistics (IL), so far a dominantly qualitative field, and computational/corpus linguistics and its quantitative and automated methods. Contemporary IL investigates the systematic organization of conversations and interactions composed of speech, gaze, gestures, and body positioning, among others. These highly integrated multimodal behaviour is analysed based on video data aimed at uncovering so called “multimodal gestalts”, patterns of linguistic and embodied conduct that reoccur in specific sequential positions employed for specific purposes. Multimodal analyses (and other disciplines using videos) are so far dependent on time and resource intensive processes of manual transcription of each component from video materials. Automating these tasks requires advanced programming skills, which is often not in the scope of IL. Moreover, the use of different tools makes the integration and analysis of different formats challenging. Consequently, IL research often deals with relatively small samples of annotated data which are suitable for qualitative analysis but not enough for making generalized empirical claims derived quantitatively. VIAN-DH aims to create a workspace where many annotation layers required for the multimodal analysis of videos can be created, processed, and correlated in one platform. VIAN-DH will provide a graphical interface that operates state-of-the-art tools for automating parts of the data processing. The integration of tools that already exist in computational linguistics and computer vision, facilitates data processing for researchers lacking programming skills, speeds up the overall research process, and enables the processing of large amounts of data. The main features to be introduced are automatic speech recognition for the transcription of language, automatic image recognition for extraction of gestures and other visual cues, as well as grammatical annotation for adding morphological and syntactic information to the verbal content. In the ongoing instance of VIAN-DH, we focus on gesture extraction (pointing gestures, in particular), making use of existing models created for sign language and adapting them for this specific purpose. In order to view and search the data, VIAN-DH will provide a unified format and enable the import of the main existing formats of annotated video data and the export to other formats used in the field, while integrating different data source formats in a way that they can be combined in research. VIAN-DH will adapt querying methods from corpus linguistics to enable parallel search of many annotation levels, combining token-level and chronological search for various types of data. VIAN-DH strives to bring crucial and potentially revolutionary innovation to the field of IL, (that can also extend to other fields using video materials). It will allow the processing of large amounts of data automatically and, the implementation of quantitative analyses, combining it with the qualitative approach. It will facilitate the investigation of correlations between linguistic patterns (lexical or grammatical) with conversational aspects (turn-taking or gestures). Users will be able to automatically transcribe and annotate visual, spoken and grammatical information from videos, and to correlate those different levels and perform queries and analyses.

Keywords: multimodal analysis, corpus linguistics, computational linguistics, image recognition, speech recognition

Procedia PDF Downloads 108

Authors: C. Sánchez de Rojas Candela, A. Riquelme, P. Rodrigo, M. D. Escalera-Rodríguez, B. Torres, J. Rams

Abstract:

Selective laser melting is one of the most commonly used AM techniques. In it, a thin layer of metallic powder is deposited, and a laser is used to melt selected zones. The accumulation of layers, each one molten in the preselected zones, gives rise to the formation of a 3D sample with a nearly arbitrary design. To ensure that the properties of the final parts match those of the powder, all the process is carried out in an inert atmosphere, preferentially Ar, although this gas could be substituted. Ti6Al4V alloy is widely used in multiple industrial applications such as aerospace, maritime transport and biomedical, due to its properties. However, due to the demanding requirements of these applications, greater hardness and wear resistance are necessary, together with a better machining capacity, which currently limits its commercialization. To improve these properties, in this study, Selective Laser Melting (SLM) is used to manufacture Ti/TiN metal matrix composites with in-situ and ex-situ titanium nitride reinforcement where the scanning speed is modified (from 28.5 up to 65 mm/s) to study the influence of the processing parameters in SLM. A one-step method of nitriding the Ti6Al4V alloy is carried out to create in-situ TiN reinforcement in a reactive atmosphere and it is compared with ex-situ composites manufactured by previous mixture of both the titanium alloy powder and the ceramic reinforcement particles. The microstructure and mechanical properties of the different Ti/TiN composite materials have been analyzed. As a result, the existence of a similar matrix has been confirmed in in-situ and ex-situ fabrications and the growth mechanisms of the nitrides have been studied. An increase in the mechanical properties with respect to the initial alloy has been observed in both cases and related to changes in their microstructure. Specifically, a greater improvement (around 30.65%) has been identified in those manufactured by the in-situ method at low speeds although other properties such as porosity must be improved for their future industrial applicability.

Keywords: in-situ reinforcement, nitriding reaction, selective laser melting, titanium nitride

Procedia PDF Downloads 79

Authors: Pulkeria Pascoe, Hawa P. Tundui, Marcia Dutra de Barcellos, Hans de Steur, Xavier Gellynck

Abstract:

A majority of Micro and Small Enterprises (MSEs) experience low or no growth. Understanding their performance remains unfinished and disjointed as there is no consensus on the factors influencing it, especially in developing countries. Using a Resource-Based View (RBV) as the theoretical background, this cross-sectional study employed four regression models to examine the influence of firm-level factors (firm-specific characteristics, firm resources, manager socio-demographic characteristics, and selected management practices) on the overall performance variations among 442 Tanzanian micro and small agri-food processing firms. Study results confirmed the RBV argument that intangible resources make a larger contribution to overall performance variations among firms than that tangible resources. Firms' tangible and intangible resources explained 34.5% of overall performance variations (intangible resources explained the overall performance variability by 19.4% compared to tangible resources, which accounted for 15.1%), ranking first in explaining the overall performance variance. Firm-specific characteristics ranked second by influencing variations in overall performance by 29.0%. Selected management practices ranked third (6.3%), while the manager's socio-demographic factors were last on the list, as they influenced the overall performance variability among firms by only 5.1%. The study also found that firms that focus on proper utilization of tangible resources (financial and physical), set targets, and undertake better working capital management practices performed higher than their counterparts (low and average performers). Furthermore, accumulation and proper utilization of intangible resources (relational, organizational, and reputational), undertaking performance monitoring practices, age of the manager, and the choice of the firm location and activity were the dominant significant factors influencing the variations among average and high performers, relative to low performers. The entrepreneurial background was a significant factor influencing variations in average and low-performing firms, indicating that entrepreneurial skills are crucial to achieving average levels of performance. Firm age, size, legal status, source of start-up capital, gender, education level, and total business experience of the manager were not statistically significant variables influencing the overall performance variations among the agri-food processors under the study. The study has identified both significant and non-significant factors influencing performance variations among low, average, and high-performing micro and small agri-food processing firms in Tanzania. Therefore, results from this study will help managers, policymakers and researchers to identify areas where more attention should be placed in order to improve overall performance of MSEs in agri-food industry.

Keywords: firm-level factors, micro and small enterprises, performance, regression analysis, resource-based-view

Procedia PDF Downloads 86

Authors: Nikat Parveen, M. Ananthi

Abstract:

Big data is one of the emerging technology, which collects the data from various sensors and those data will be used in many fields. Data retrieval is one of the major issue where there is a need to extract the exact data as per the need. In this paper, large amount of data set is processed by using the feature selection. Feature selection helps to choose the data which are actually needed to process and execute the task. The key value is the one which helps to point out exact data available in the storage space. Here the available data is streamed and R-Center is proposed to achieve this task.

Keywords: big data, key value, feature selection, retrieval, performance

Procedia PDF Downloads 341

Authors: Qiaosi Li, Frankie Kwan Kit Wong, Tung Fung

Abstract:

Lightweight unmanned aerial vehicle (UAV) loading with novel sensors offers a low cost approach for data acquisition in complex environment. This study established a framework for applying UAV system in complex environment quick mapping and assessed the performance of UAV-based hyperspectral image and digital surface model (DSM) derived from photogrammetric point clouds for 13 species classification in wetland area Mai Po Inner Deep Bay Ramsar Site, Hong Kong. The study area was part of shallow bay with flat terrain and the major species including reedbed and four mangroves: Kandelia obovata, Aegiceras corniculatum, Acrostichum auerum and Acanthus ilicifolius. Other species involved in various graminaceous plants, tarbor, shrub and invasive species Mikania micrantha. In particular, invasive species climbed up to the mangrove canopy caused damage and morphology change which might increase species distinguishing difficulty. Hyperspectral images were acquired by Headwall Nano sensor with spectral range from 400nm to 1000nm and 0.06m spatial resolution image. A sequence of multi-view RGB images was captured with 0.02m spatial resolution and 75% overlap. Hyperspectral image was corrected for radiative and geometric distortion while high resolution RGB images were matched to generate maximum dense point clouds. Furtherly, a 5 cm grid digital surface model (DSM) was derived from dense point clouds. Multiple feature reduction methods were compared to identify the efficient method and to explore the significant spectral bands in distinguishing different species. Examined methods including stepwise discriminant analysis (DA), support vector machine (SVM) and minimum noise fraction (MNF) transformation. Subsequently, spectral subsets composed of the first 20 most importance bands extracted by SVM, DA and MNF, and multi-source subsets adding extra DSM to 20 spectrum bands were served as input in maximum likelihood classifier (MLC) and SVM classifier to compare the classification result. Classification results showed that feature reduction methods from best to worst are MNF transformation, DA and SVM. MNF transformation accuracy was even higher than all bands input result. Selected bands frequently laid along the green peak, red edge and near infrared. Additionally, DA found that chlorophyll absorption red band and yellow band were also important for species classification. In terms of 3D data, DSM enhanced the discriminant capacity among low plants, arbor and mangrove. Meanwhile, DSM largely reduced misclassification due to the shadow effect and morphological variation of inter-species. In respect to classifier, nonparametric SVM outperformed than MLC for high dimension and multi-source data in this study. SVM classifier tended to produce higher overall accuracy and reduce scattered patches although it costs more time than MLC. The best result was obtained by combining MNF components and DSM in SVM classifier. This study offered a precision species distribution survey solution for inaccessible wetland area with low cost of time and labour. In addition, findings relevant to the positive effect of DSM as well as spectral feature identification indicated that the utility of UAV-borne hyperspectral and photogrammetry deriving 3D data is promising in further research on wetland species such as bio-parameters modelling and biological invasion monitoring.

Keywords: digital surface model (DSM), feature reduction, hyperspectral, photogrammetric point cloud, species mapping, unmanned aerial vehicle (UAV)

Procedia PDF Downloads 257

Authors: Akash Amalan, Rui Wang, Yanqi Qiao, Emmanouil Panaousis, Kaitai Liang

Abstract:

Federated learning is an emerging concept in the domain of distributed machine learning. This concept has enabled General Adversarial Networks (GANs) to benefit from the rich distributed training data while preserving privacy. However, in a non-IID setting, current federated GAN architectures are unstable, struggling to learn the distinct features, and vulnerable to mode collapse. In this paper, we propose an architecture MULTI-FLGAN to solve the problem of low-quality images, mode collapse, and instability for non-IID datasets. Our results show that MULTI-FLGAN is four times as stable and performant (i.e., high inception score) on average over 20 clients compared to baseline FLGAN.

Keywords: federated learning, generative adversarial network, inference attack, non-IID data distribution

Procedia PDF Downloads 158

Authors: Archana Rao R., Deepak P., Chayashree P. D., Darshan H. S.

Abstract:

Cognitive abilities in bilinguals have been widely studied over the last few decades. Bilingualism has been found to extensively facilitate the ability to store and manipulate information in Working Memory (WM). The mechanism of WM includes primary memory, attentional control, and secondary memory, each of which makes a contribution to WM. Many researches have been done in an attempt to measure WM capabilities through both verbal (phonological) and nonverbal tasks (visuospatial). Since there is a lot of speculations regarding the relationship between WM and bilingualism, further investigation is required to understand the nature of WM in bilinguals, i.e., with respect to sequential and simultaneous bilinguals. Hence the present study aimed to highlight the verbal working memory abilities in sequential and simultaneous bilinguals with respect to the processing and recall abilities of nouns and verbs. Two groups of bilinguals aged between 18-30 years were considered for the study. Group 1 consisted of 20 (10 males and 10 females) sequential bilinguals who had acquired L1 (Kannada) before the age of 3 and had exposure to L2 (English) for a period of 8-10 years. Group 2 consisted of 20 (10 males and 10 females) simultaneous bilinguals who have acquired both L1 and L2 before the age of 3. Working memory abilities were assessed using two tasks, and a set of stimuli which was presented in gradation of complexity and the stimuli was inclusive of frequent and infrequent nouns and verbs. The tasks involved the participants to judge the correctness of the sentence and simultaneously remember the last word of each sentence and the participants are instructed to recall the words at the end of each set. The results indicated no significant difference between sequential and simultaneous bilinguals in processing the nouns and verbs, and this could be attributed to the proficiency level of the participants in L1 and the alike cognitive abilities between the groups. And recall of nouns was better compared to verbs, maybe because of the complex argument structure involved in verbs. Similarly, authors found a frequency of occurrence of nouns and verbs also had an effect on WM abilities. The difference was also found across gradation due to the load imposed on the central executive function and phonological loop.

Keywords: bilinguals, nouns, verbs, working memory

Procedia PDF Downloads 130

Authors: Carolina Brandão Piva

Abstract:

In our visual culture, images play a newly significant role in the basis of a complex dialogue between imagination, creativity, and social practice. Insofar as imagination has broken out of the 'special expressive space of art' to become a part of the quotidian mental work of ordinary people, it is pertinent to recognize that visual representation can no longer be assumed as if in a domain detached from everyday life or exclusively 'centered' within the limited frame of 'art history.' The approach of Visual Culture as a field of study is, in this sense, indispensable to comprehend that not only 'the image,' but also 'the imagined' and 'the imaginary' are produced in the plurality of social interactions; crucial enough, this assertion directs us to something new in contemporary cultural processes, namely both imagination and image production constitute a social practice. This paper starts off with this approach and seeks to examine the artistic practice of two women from the State of Goiás, Brazil, who are ordinary citizens with their daily activities and narratives but also dedicated to visuality production. With no formal training from art schools, branded or otherwise, Maria Aparecida de Souza Pires deploys 'waste disposal' of daily life—from car tires to old work clothes—as a trampoline for art; also adept at sourcing raw materials collected from her surroundings, she manipulates raw hewn wood, tree trunks, plant life, and various other pieces she collects from nature giving them new meaning and possibility. Hilda Freire works with sculptures in clay using different scales and styles; her art focuses on representations of women and pays homage to unprivileged groups such as the practitioners of African-Brazilian religions, blue-collar workers, poor live-in housekeepers, and so forth. Although they have never been acknowledged by any mainstream art institution in Brazil, whose 'criterion of value' still favors formally trained artists, Maria Aparecida de Souza Pires, and Hilda Freire have produced visualities that instigate 'new ways of seeing,' meriting cultural significance in many ways. Their artworks neither descend from a 'traditional' medium nor depend on 'canonical viewing settings' of visual representation; rather, they consist in producing relationships with the world which do not result in 'seeing more,' but 'at least differently.' From this perspective, the paper finally demonstrates that grouping this kind of artistic production under the label of 'mere craft' has much more to do with who is privileged within the fields of power in art system, who we see and who we do not see, and whose imagination of what is fed by which visual images in Brazilian contemporary society.

Keywords: visual culture, artistic practice, women's art in the Brazilian State of Goiás, Maria Aparecida de Souza Pires, Hilda Freire

Procedia PDF Downloads 152

Authors: Bing Gu

Abstract:

Abstract—Most of Conventional facial recognition systems are based on image features, such as LBP, SIFT. Recently some DBN-based 2D facial recognition systems have been proposed. However, we find there are few DBN-based 3D facial recognition system and relative researches. 3D facial images include all the individual biometric information. We can use these information to build more accurate features, So we present our DBN-based face recognition system using Light Field. We can see Light Field as another presentation of 3D image, and Light Field Camera show us a way to receive a Light Field. We use the commercially available Light Field Camera to act as the collector of our face recognition system, and the system receive a state-of-art performance as convenient as conventional 2D face recognition system.

Keywords: DBN, face recognition, light field, Lytro

Procedia PDF Downloads 464

Authors: Jae-Il Jeong, Hoon-Jae Park, Jung-Woo Cho, Yang-Gon Kim, Jin-Young Park, Joo-Young Oh, Si-Geun Choi, Seock-Sam Kim, Young Tae Cho, Chan Gyu Kim, Jong-Hyoung Kim

Abstract:

Bearing component has strongly required to decrease vibration and wear to achieve high durability and life time. In the industry field, bearing durability is improved by surface treatment on the bearing surface by centrifugal casting or gravity casting production method. However, this manufacturing method has caused problems such as long processing time, defect rate, and health harmful effect. To solve this problem, there is a laser cladding deposition treatment, which provides fast processing and food adhesion. Therefore, optimum conditions of white metal laser deposition should be studied to minimize bearing contact axis wear using laser cladding techniques. In this study, we deposit a soft white metal layer on SCM440, which is mainly used for shaft and bolt. On laser deposition process, the laser power and powder feed rate and laser head speed factors are controlled to find out the optimal conditions. We also measure hardness using micro Vickers, analyze FE-SEM (Field Emission Scanning Electron Microscope) and EDS (Energy Dispersive Spectroscopy) to study the mechanical properties and surface characteristics with various parameters change. Furthermore, this paper suggests the optimum condition of laser cladding deposition to apply in industrial fields. This work was supported by the Industrial Innovation Project of the Korea Evaluation Institute of Industrial Technology (KEIT) granted financial resource from the Ministry of Trade, Industry & Energy, Republic of Korea (Research no. 10051653).

Keywords: laser deposition, bearing, white metal, mechanical properties

Procedia PDF Downloads 264

Authors: Robert Caulk

Abstract:

A generalized framework for adaptive machine learning deployments in algorithmic trading is introduced, tested, and released as open-source code. The presented software aims to test the hypothesis that recent data contains enough information to form a probabilistically favorable short-term price prediction. Further, the framework contains various adaptive machine learning techniques that are geared toward generating profit during strong trends and minimizing losses during trend changes. Results demonstrate that this adaptive machine learning approach is capable of capturing trends and generating profit. The presentation also discusses the importance of defining the parameter space associated with the dynamic training data-set and using the parameter space to identify and remove outliers from prediction data points. Meanwhile, the generalized architecture enables common users to exploit the powerful machinery while focusing on high-level feature engineering and model testing. The presentation also highlights common strengths and weaknesses associated with the presented technique and presents a broad range of well-tested starting points for feature set construction, target setting, and statistical methods for enforcing risk management and maintaining probabilistically favorable entry and exit points. The presentation also describes the end-to-end data processing tools associated with FreqAI, including automatic data fetching, data aggregation, feature engineering, safe and robust data pre-processing, outlier detection, custom machine learning and statistical tools, data post-processing, and adaptive training backtest emulation, and deployment of adaptive training in live environments. Finally, the generalized user interface is also discussed in the presentation. Feature engineering is simplified so that users can seed their feature sets with common indicator libraries (e.g. TA-lib, pandas-ta). The user also feeds data expansion parameters to fill out a large feature set for the model, which can contain as many as 10,000+ features. The presentation describes the various object-oriented programming techniques employed to make FreqAI agnostic to third-party libraries and external data sources. In other words, the back-end is constructed in such a way that users can leverage a broad range of common regression libraries (Catboost, LightGBM, Sklearn, etc) as well as common Neural Network libraries (TensorFlow, PyTorch) without worrying about the logistical complexities associated with data handling and API interactions. The presentation finishes by drawing conclusions about the most important parameters associated with a live deployment of the adaptive learning framework and provides the road map for future development in FreqAI.

Keywords: machine learning, market trend detection, open-source, adaptive learning, parameter space exploration

Procedia PDF Downloads 89

Authors: Nilüfer Yıldız Varan

Abstract:

The antimicrobial activities of chitosan against various bacteria and fungi are well known, and the antimicrobial activity of chitosan depends on pH. This study investigates the antimicrobial activity at different pH levels. Nylon 6,6 fabrics were treated with different chitosan solutions. Additionally, samples were treated also in basic conditions to see the antimicrobial activities. AATCC Test Method 100 was followed to evaluate the antimicrobial activity using Staphylococcus aureus ATCC 6538 test inoculum. The pH of the chitosan solutions was controlled below 6.5 since chitosan shows its antimicrobial activity only in acidic conditions because of its poor solubility above 6.5. In basic conditions, the samples did not show any antimicrobial activity. It appears from SEM images that the bonded chitosan in the structures exists. In acidic media (ph < 6.5), all samples showed antimicrobial activity. No correlation was found between pH levels and antimicrobial activity in acidic media.

Keywords: chitosan, nylon 6, 6, crosslinking, pH stability, antimicrobial

Procedia PDF Downloads 219

Authors: Khalid Omari, Rene Chenier, Enrique Blondel, Ryan Ahola

Abstract:

Northern Canadian coasts have vulnerable and very dynamic intertidal zones with very high tides occurring in several areas. The impact of climate change presents challenges not only for maintaining this biodiversity but also for navigation safety adaptation due to the high sediment mobility in these coastal areas. Thus, frequent mapping of shorelines and intertidal changes is of high importance. To help in quantifying the changes in these fragile ecosystems, remote sensing provides practical monitoring tools at local and regional scales. Traditional methods based on high-resolution optical sensors are often used to map intertidal areas by benefiting of the spectral response contrast of intertidal classes in visible, near and mid-infrared bands. Tidal areas are highly reflective in visible bands mainly because of the presence of fine sand deposits. However, getting a cloud-free optical data that coincide with low tides in intertidal zones in northern regions is very difficult. Alternatively, the all-weather capability and daylight-independence of the microwave remote sensing using synthetic aperture radar (SAR) can offer valuable geophysical parameters with a high frequency revisit over intertidal zones. Multi-polarization SAR parameters have been used successfully in mapping intertidal zones using incoherence target decomposition. Moreover, the crustal displacements caused by ocean tide loading may reach several centimeters that can be detected and quantified across differential interferometric synthetic aperture radar (DInSAR). Soil moisture change has a significant impact on both the coherence and the backscatter. For instance, increases in the backscatter intensity associated with low coherence is an indicator for abrupt surface changes. In this research, we present primary results obtained following our investigation of the potential of the fully polarimetric Radarsat-2 data for mapping an inter-tidal zone located on Tasiujaq on the south-west shore of Ungava Bay, Quebec. Using the repeat pass cycle of Radarsat-2, multiple seasonal fine quad (FQ14W) images are acquired over the site between 2016 and 2018. Only 8 images corresponding to low tide conditions are selected and used to build an interferometric stack of data. The observed displacements along the line of sight generated using HH and VV polarization are compared with the changes noticed using the Freeman Durden polarimetric decomposition and Touzi degree of polarization extrema. Results show the consistency of both approaches in their ability to monitor the changes in intertidal zones.

Keywords: SAR, degree of polarization, DInSAR, Freeman-Durden, polarimetry, Radarsat-2

Procedia PDF Downloads 137

Authors: Mohammed Abu Shquier

Abstract:

This paper introduces a word segmentation method using the novel BP-LSTM-CRF architecture for processing semantic output training. The objective of web morphological analysis tools is to link a formal morpho-syntactic description to a lemma, along with morpho-syntactic information, a vocalized form, a vocalized analysis with morpho-syntactic information, and a list of paradigms. A key objective is to continuously enhance the proposed system through an inductive learning approach that considers semantic influences. The system is currently under construction and development based on data-driven learning. To evaluate the tool, an experiment on homograph analysis was conducted. The tool also encompasses the assumption of deep binary segmentation hypotheses, the arbitrary choice of trigram or n-gram continuation probabilities, language limitations, and morphology for both Modern Standard Arabic (MSA) and Dialectal Arabic (DA), which provide justification for updating this system. Most Arabic word analysis systems are based on the phonotactic morpho-syntactic analysis of a word transmitted using lexical rules, which are mainly used in MENA language technology tools, without taking into account contextual or semantic morphological implications. Therefore, it is necessary to have an automatic analysis tool taking into account the word sense and not only the morpho-syntactic category. Moreover, they are also based on statistical/stochastic models. These stochastic models, such as HMMs, have shown their effectiveness in different NLP applications: part-of-speech tagging, machine translation, speech recognition, etc. As an extension, we focus on language modeling using Recurrent Neural Network (RNN); given that morphological analysis coverage was very low in dialectal Arabic, it is significantly important to investigate deeply how the dialect data influence the accuracy of these approaches by developing dialectal morphological processing tools to show that dialectal variability can support to improve analysis.

Keywords: NLP, DL, ML, analyser, MSA, RNN, CNN

Procedia PDF Downloads 43

Authors: Mafawez Alharbi, Mahdi Jemmali

Abstract:

E-learning is a developing area especially in education. E-learning can provide several benefits to learners. An intelligent system to collect all components satisfying user preferences is so important. This research presents an approach that it capable to personalize e-information and give the user their needs following their preferences. This proposal can make some knowledge after more evaluations made by the user. In addition, it can learn from the habit from the user. Finally, we show a walk-through to prove how intelligent process work.

Keywords: artificial intelligence, architecture, e-learning, software engineering, processing

Procedia PDF Downloads 191

Authors: Marianna Maiaru, Gregory M. Odegard

Abstract:

During the processing of high-performance thermoset polymer matrix composites, chemical reactions occur during elevated pressure and temperature cycles, causing the constituent monomers to crosslink and form a molecular network that gradually can sustain stress. As the crosslinking process progresses, the material naturally experiences a gradual shrinkage due to the increase in covalent bonds in the network. Once the cured composite completes the cure cycle and is brought to room temperature, the thermal expansion mismatch of the fibers and matrix cause additional residual stresses to form. These compounded residual stresses can compromise the reliability of the composite material and affect the composite strength. Composite process modeling is greatly complicated by the multiscale nature of the composite architecture. At the molecular level, the degree of cure controls the local shrinkage and thermal-mechanical properties of the thermoset. At the microscopic level, the local fiber architecture and packing affect the magnitudes and locations of residual stress concentrations. At the macroscopic level, the layup sequence controls the nature of crack initiation and propagation due to residual stresses. The goal of this research is use molecular dynamics (MD) and finite element analysis (FEA) to predict the residual stresses in composite laminates and the corresponding effect on composite failure. MD is used to predict the polymer shrinkage and thermomechanical properties as a function of degree of cure. This information is used as input into FEA to predict the residual stresses on the microscopic level resulting from the complete cure process. Virtual testing is subsequently conducted to predict strength allowables. Experimental characterization is used to validate the modeling.

Keywords: molecular dynamics, finite element analysis, processing modeling, multiscale modeling

Procedia PDF Downloads 92

Authors: Srikanta Tagore Sarkar, Prasanta Kumar Mandal, Dibakar Roy

Abstract:

The association of a capitate fracture with a scaphoid fracture has been termed as the naviculocapitate syndrome. The existence of some nondisplaced fractures of scaphoid and capitate with or without the fracture of lunate or radius suggests that there is a spectrum of these injuries, and this confuses the terminology. With our case; we report an unusual variety of this naviculocapitate syndrome with distal radial Colles fracture in addition to the nondisplaced fractures of the scaphoid, capitate and the dorsal lip of radial fracture. When we looked at the literature there is no another Colles fracture reported together with undisplaced scapho-capitate syndrome. The coronal and sagittal images that obtained from the MDCT (Multidetector computed tomography) is useful and effective imaging modality to diagnose complex wrist fractures with more details that are not detected in X-rays.

Keywords: scaphoid, capitate, Colles’ fracture, syndrome, MDCT, unusual

Procedia PDF Downloads 393

Authors: Mohammadhosein Rahimi, Mohammad Raouf Hosseini, Mehran Bakhshi, Alireza Baghbanan

Abstract:

Silver ions (Ag⁺) and their compounds are consequentially toxic to microorganisms, showing biocidal effects on many species of bacteria. Silver-phosphate (or silver orthophosphate) is one of these compounds, which is famous for its antimicrobial effect and catalysis application. In the present study, a green method was presented to synthesis silver-phosphate nanoparticles using Sporosarcina pasteurii. The composition of the biosynthesized nanoparticles was identified as Ag₃PO₄ using X-ray Diffraction (XRD) and Energy Dispersive Spectroscopy (EDS). Also, Fourier Transform Infrared (FTIR) spectroscopy showed that Ag₃PO₄ nanoparticles was synthesized in the presence of biosurfactants, enzymes, and proteins. In addition, UV-Vis adsorption of the produced colloidal suspension approved the results of XRD and FTIR analyses. Finally, Transmission Electron Microscope (TEM) images indicated that the size of the nanoparticles was about 20 nm.

Keywords: bacteria, biosynthesis, silver-phosphate, Sporosarcina pasteurii, nanoparticle

Procedia PDF Downloads 452

Authors: Amarendar Reddy Addula

Abstract:

Definition of Artificial Intelligence: Artificial intelligence is the simulation of mortal intelligence processes by machines, especially computer systems. Explicit operations of AI comprise expert systems, natural language processing, and speech recognition, and machine vision. Artificial Intelligence (AI) is an original medium for digital business, according to a new report by Gartner. The last 10 times represent an advance period in AI’s development, prodded by the confluence of factors, including the rise of big data, advancements in cipher structure, new machine literacy ways, the materialization of pall computing, and the vibrant open- source ecosystem. Influence of AI to a broader set of use cases and druggies and its gaining fashionability because it improves AI’s versatility, effectiveness, and rigidity. Edge AI will enable digital moments by employing AI for real- time analytics closer to data sources. Gartner predicts that by 2025, further than 50 of all data analysis by deep neural networks will do at the edge, over from lower than 10 in 2021. Responsible AI is a marquee term for making suitable business and ethical choices when espousing AI. It requires considering business and societal value, threat, trust, translucency, fairness, bias mitigation, explainability, responsibility, safety, sequestration, and nonsupervisory compliance. Responsible AI is ever more significant amidst growing nonsupervisory oversight, consumer prospects, and rising sustainability pretensions. Generative AI is the use of AI to induce new vestiges and produce innovative products. To date, generative AI sweats have concentrated on creating media content similar as photorealistic images of people and effects, but it can also be used for law generation, creating synthetic irregular data, and designing medicinals and accoutrements with specific parcels. AI is the subject of a wide- ranging debate in which there's a growing concern about its ethical and legal aspects. Constantly, the two are varied and nonplussed despite being different issues and areas of knowledge. The ethical debate raises two main problems the first, abstract, relates to the idea and content of ethics; the alternate, functional, and concerns its relationship with the law. Both set up models of social geste, but they're different in compass and nature. The juridical analysis is grounded on anon-formalistic scientific methodology. This means that it's essential to consider the nature and characteristics of the AI as a primary step to the description of its legal paradigm. In this regard, there are two main issues the relationship between artificial and mortal intelligence and the question of the unitary or different nature of the AI. From that theoretical and practical base, the study of the legal system is carried out by examining its foundations, the governance model, and the nonsupervisory bases. According to this analysis, throughout the work and in the conclusions, International Law is linked as the top legal frame for the regulation of AI.

Keywords: artificial intelligence, ethics & human rights issues, laws, international laws

Procedia PDF Downloads 95

Authors: Z. Ghorannevis, E. Akbarnejad, B. Aghazadeh, M. Ghoranneviss

Abstract:

Carbon nanotubes (CNTs) modified with semiconductor nanocrystalline particles may find wide applications due to their unique properties. Here Cadmium Sulfide (CdS) nanoparticles were successfully grown on Multi-Walled Carbon Nanotubes (MWNTs) via a magnetron sputtering method for the first time. The CdS/MWNTs sample was characterized with X-ray diffraction (XRD), Field Emission Scanning and High Resolution Transmission Electron Microscopies (SEM/TEM) and four point probe. The obtained images show clearly the decoration of the MWNTs by the CdS nanoparticles, and the XRD measurements indicate the CdS structure as hexagonal type. Moreover, the physical properties of the CdS/MWNTs were compared with the physical properties of the CdS nanoparticles grown on the silicon. Electrical measurements of CdS and CdS/MWNTs reveal that CdS/MWNTs has lower resistivity than the CdS sample which may be due to the higher carrier concentrations.

Keywords: CdS, MWNTs, HRTEM, magnetron sputtering

Procedia PDF Downloads 405

Authors: M. Shahin Alam, Satoru Takahashi, Mariko Itoh, Miyuki Komura, Mayuko Suzuki, Natthanan Sangsriratanakul, Kazuaki Takehara

Abstract:

Cleaning and disinfection are key components of routine biosecurity in livestock farming and food processing industry. The usage of suitable disinfectants and their proper concentration are important factors for a successful biosecurity program. Disinfectants have optimum bactericidal and virucidal efficacies at temperatures above 20°C, but very few studies on application and effectiveness of disinfectants at low temperatures have been done. In the present study, the bactericidal efficacies of food additive grade calcium hydroxide (FdCa(OH)), quaternary ammonium compound (QAC) and their mixture, were investigated under different conditions, including time, organic materials (fetal bovine serum: FBS) and temperature, either in suspension or in carrier test. Salmonella Infantis and Escherichia coli, which are the most prevalent gram negative bacteria in commercial poultry housing and food processing industry, were used in this study. Initially, we evaluated these disinfectants at two different temperatures (4°C and room temperature (RT) (25°C ± 2°C)) and 7 contact times (0, 5 and 30 sec, 1, 3, 20 and 30 min), with suspension tests either in the presence or absence of 5% FBS. Secondly, we investigated the bactericidal efficacies of these disinfectants by carrier tests (rubber, stainless steel and plastic) at same temperatures and 4 contact times (30 sec, 1, 3, and 5 min). Then, we compared the bactericidal efficacies of each disinfectant within their mixtures, as follows. When QAC was diluted with redistilled water (dW2) at 1: 500 (QACx500) to obtain the final concentration of didecyl-dimethylammonium chloride (DDAC) of 200 ppm, it could inactivate Salmonella Infantis within 5 sec at RT either with or without 5% FBS in suspension test; however, at 4°C it required 30 min in presence of 5% FBS. FdCa(OH)2 solution alone could inactivate bacteria within 1 min both at RT and 4°C even with 5% FBS. While FdCa(OH)2 powder was added at final concentration 0.2% to QACx500 (Mix500), the mixture could inactivate bacteria within 30 sec and 5 sec, respectively, with or without 5% FBS at 4°C. The findings from the suspension test indicated that low temperature inhibited the bactericidal efficacy of QAC, whereas Mix500 was effective, regardless of short contact time and low temperature, even with 5% FBS. In the carrier test, single disinfectant required bit more time to inactivate bacteria on rubber and plastic surfaces than on stainless steel. However, Mix500 could inactivate S. Infantis on rubber, stainless steel and plastic surfaces within 30 sec and 1 min, respectively, at RT and 4°C; but, for E. coli, it required only 30 sec at both temperatures. So, synergistic effects were observed on different carriers at both temperatures. For a successful enhancement of biosecurity during winter, the disinfectants should be selected that could have short contact times with optimum efficacy against the target pathogen. The present study findings help farmers to make proper strategies for application of disinfectants in their livestock farming and food processing industry.

Keywords: carrier, food additive grade calcium hydroxide (FdCa(OH)₂), quaternary ammonium compound, synergistic effects

Procedia PDF Downloads 294

Authors: Seyedeh Sepideh Amini, Navideh Aghaei Amirkhizi, Seyedeh Paniz Amini, Seyed Soheil Sayyahi, Mohammad Reza Davar Panah

Abstract:

CT-Scan is one of the lateral and sectional imaging methods that produce 3D-images with use of rotational x-ray tube around central axis. This study is about evaluation and calculation of effective doses around heart organs such as breast, lung and liver with CT-Scan 128 dual sources with TLD_100 and RANDO Phantom by spiral, flash and conventional protocols. In results, it is showed that in spiral protocol organs have maximum effective dose and minimum in flash protocol. Thus flash protocol advised for children and risk persons.

Keywords: X-ray computed tomography, dosimetry, TLD-100, RANDO, phantom

Procedia PDF Downloads 475

Authors: Xiaochen Mu

Abstract:

Data rights confirmation, as a key legal issue in the development of the digital economy, is undergoing a transition from a traditional rights paradigm to a more complex private-economic paradigm. In this process, data rights confirmation has evolved from a simple claim of rights to a complex structure encompassing multiple dimensions of personality rights and property rights. Current data rights confirmation practices are primarily reflected in two models: holistic rights confirmation and process rights confirmation. The holistic rights confirmation model continues the traditional "one object, one right" theory, while the process rights confirmation model, through contractual relationships in the data processing process, recognizes rights that are more adaptable to the needs of data circulation and value release. In the design of the data property rights system, there is a hierarchical characteristic aimed at decoupling from raw data to data applications through horizontal stratification and vertical staging. This design not only respects the ownership rights of data originators but also, based on the usufructuary rights of enterprises, constructs a corresponding rights system for different stages of data processing activities. The subjects of data property rights include both data originators, such as users, and data producers, such as enterprises, who enjoy different rights at different stages of data processing. The intellectual property rights system, with the mission of incentivizing innovation and promoting the advancement of science, culture, and the arts, provides a complete set of mechanisms for protecting innovative results. However, unlike traditional private property rights, the granting of intellectual property rights is not an end in itself; the purpose of the intellectual property system is to balance the exclusive rights of the rights holders with the prosperity and long-term development of society's public learning and the entire field of science, culture, and the arts. Therefore, the intellectual property granting mechanism provides both protection and limitations for the rights holder. This perfectly aligns with the dual attributes of data. In terms of achieving the protection of data property rights, the granting of intellectual property rights is an important institutional choice that can enhance the effectiveness of the data property exchange mechanism. Although this is not the only path, the granting of data property rights within the framework of the intellectual property rights system helps to establish fundamental legal relationships and rights confirmation mechanisms and is more compatible with the classification and grading system of data. The modernity of the intellectual property rights system allows it to adapt to the needs of big data technology development through special clauses or industry guidelines, thus promoting the comprehensive advancement of data intellectual property rights legislation. This paper analyzes data protection under the virtual property layer theory and two-fold virtual property rights system. Based on the “bundle of right” theory, this paper establishes specific three-level data rights. This paper analyzes the cases: Google v. Vidal-Hall, Halliday v Creation Consumer Finance, Douglas v Hello Limited, Campbell v MGN and Imerman v Tchenquiz. This paper concluded that recognizing property rights over personal data and protecting data under the framework of intellectual property will be beneficial to establish the tort of misuse of personal information.

Keywords: data protection, property rights, intellectual property, Big data

Procedia PDF Downloads 40

Authors: Diane Ghanem, Arjun Gupta, Rohan Vijayan, Ali Uneri, Babar Shafiq

Abstract:

Introduction: Ankle sprains and fractures often result in syndesmosis injuries. Unstable syndesmotic injuries result from relative motion between the distal ends of the tibia and fibula, anatomic juncture which should otherwise be rigid, and warrant operative management. Clinical and radiological evaluations of intraoperative syndesmosis stability remain a challenging task as traditional 2D fluoroscopy is limited to a uniplanar translational displacement. The purpose of this pilot cadaveric study is to compare the 2D fluoroscopy and 3D cone beam computed tomography (CBCT) stress-induced syndesmosis displacements. Methods: Three fresh-frozen lower legs underwent 2D fluoroscopy and 3D CIOS CBCT to measure syndesmosis position before dissection. Syndesmotic injury was simulated by resecting the (1) anterior inferior tibiofibular ligament (AITFL), the (2) posterior inferior tibiofibular ligament (PITFL) and the inferior transverse ligament (ITL) simultaneously, followed by the (3) interosseous membrane (IOM). Manual external rotation and Cotton stress test were performed after each of the three resections and 2D and 3D images were acquired. Relevant 2D and 3D parameters included the tibiofibular overlap (TFO), tibiofibular clear space (TCS), relative rotation of the fibula, and anterior-posterior (AP) and medial-lateral (ML) translations of the fibula relative to the tibia. Parameters were measured by two independent observers. Inter-rater reliability was assessed by intraclass correlation coefficient (ICC) to determine measurement precision. Results: Significant mismatches were found in the trends between the 2D and 3D measurements when assessing for TFO, TCS and AP translation across the different resection states. Using 3D CBCT, TFO was inversely proportional to the number of resected ligaments while TCS was directly proportional to the latter across all cadavers and ‘resection + stress’ states. Using 2D fluoroscopy, this trend was not respected under the Cotton stress test. 3D AP translation did not show a reliable trend whereas 2D AP translation of the fibula was positive under the Cotton stress test and negative under the external rotation. 3D relative rotation of the fibula, assessed using the Tang et al. ratio method and Beisemann et al. angular method, suggested slight overall internal rotation with complete resection of the ligaments, with a change < 2mm - threshold which corresponds to the commonly used buffer to account for physiologic laxity as per clinical judgment of the surgeon. Excellent agreement (>0.90) was found between the two independent observers for each of the parameters in both 2D and 3D (overall ICC 0.9968, 95% CI 0.995 - 0.999). Conclusions: The 3D CIOS CBCT appears to reliably depict the trend in TFO and TCS. This might be due to the additional detection of relevant rotational malpositions of the fibula in comparison to the standard 2D fluoroscopy which is limited to a single plane translation. A better understanding of 3D imaging may help surgeons identify the precise measurements planes needed to achieve better syndesmosis repair.

Keywords: 2D fluoroscopy, 3D computed tomography, image processing, syndesmosis injury

Procedia PDF Downloads 70

Authors: A. M. John-Otumu, M. M. Rahman, O. C. Nwokonkwo, M. C. Onuoha

Abstract:

Online social media networks have long served as a primary arena for group conversations, gossip, text-based information sharing and distribution. The use of natural language processing techniques for text classification and unbiased decision-making has not been far-fetched. Proper classification of this textual information in a given context has also been very difficult. As a result, we decided to conduct a systematic review of previous literature on sentiment classification and AI-based techniques that have been used in order to gain a better understanding of the process of designing and developing a robust and more accurate sentiment classifier that can correctly classify social media textual information of a given context between hate speech and inverted compliments with a high level of accuracy by assessing different artificial intelligence techniques. We evaluated over 250 articles from digital sources like ScienceDirect, ACM, Google Scholar, and IEEE Xplore and whittled down the number of research to 31. Findings revealed that Deep learning approaches such as CNN, RNN, BERT, and LSTM outperformed various machine learning techniques in terms of performance accuracy. A large dataset is also necessary for developing a robust sentiment classifier and can be obtained from places like Twitter, movie reviews, Kaggle, SST, and SemEval Task4. Hybrid Deep Learning techniques like CNN+LSTM, CNN+GRU, CNN+BERT outperformed single Deep Learning techniques and machine learning techniques. Python programming language outperformed Java programming language in terms of sentiment analyzer development due to its simplicity and AI-based library functionalities. Based on some of the important findings from this study, we made a recommendation for future research.

Keywords: artificial intelligence, natural language processing, sentiment analysis, social network, text

Procedia PDF Downloads 115

Authors: Burak Oksuzoglu, Savas Yildirim, Ferhat Kutlu

Abstract:

Opinion mining (OM) is one of the natural language processing (NLP) problems to determine the polarity of opinions, mostly represented on a positive-neutral-negative axis. The data for OM is usually collected from various social media platforms. In an era where social media has considerable control over companies’ futures, it’s worth understanding social media and taking actions accordingly. OM comes to the fore here as the scale of the discussion about companies increases, and it becomes unfeasible to gauge opinion on individual levels. Thus, the companies opt to automize this process by applying machine learning (ML) approaches to their data. For the last two decades, OM or sentiment analysis (SA) has been mainly performed by applying ML classification algorithms such as support vector machines (SVM) and Naïve Bayes to a bag of n-gram representations of textual data. With the advent of deep learning and its apparent success in NLP, traditional methods have become obsolete. Transfer learning paradigm that has been commonly used in computer vision (CV) problems started to shape NLP approaches and language models (LM) lately. This gave a sudden rise to the usage of the pretrained language model (PTM), which contains language representations that are obtained by training it on the large datasets using self-supervised learning objectives. The PTMs are further fine-tuned by a specialized downstream task dataset to produce efficient models for various NLP tasks such as OM, NER (Named-Entity Recognition), Question Answering (QA), and so forth. In this study, the traditional and modern NLP approaches have been evaluated for OM by using a sizable corpus belonging to a large private company containing about 76,000 comments in Turkish: SVM with a bag of n-grams, and two chosen pre-trained models, multilingual universal sentence encoder (MUSE) and bidirectional encoder representations from transformers (BERT). The MUSE model is a multilingual model that supports 16 languages, including Turkish, and it is based on convolutional neural networks. The BERT is a monolingual model in our case and transformers-based neural networks. It uses a masked language model and next sentence prediction tasks that allow the bidirectional training of the transformers. During the training phase of the architecture, pre-processing operations such as morphological parsing, stemming, and spelling correction was not used since the experiments showed that their contribution to the model performance was found insignificant even though Turkish is a highly agglutinative and inflective language. The results show that usage of deep learning methods with pre-trained models and fine-tuning achieve about 11% improvement over SVM for OM. The BERT model achieved around 94% prediction accuracy while the MUSE model achieved around 88% and SVM did around 83%. The MUSE multilingual model shows better results than SVM, but it still performs worse than the monolingual BERT model.

Keywords: BERT, MUSE, opinion mining, pretrained language model, SVM, Turkish

Procedia PDF Downloads 146

Authors: Ozan Kahraman, Hao Feng

Abstract:

Several models such as Weibull, Modified Gompertz, Biphasic linear, and Log-logistic models have been proposed in order to describe non-linear inactivation kinetics and used to fit non-linear inactivation data of several microorganisms for inactivation by heat, high pressure processing or pulsed electric field. First-order kinetic parameters (D-values and z-values) have often been used in order to identify microbial inactivation by non-thermal processing methods such as ultrasound. Most ultrasonic inactivation studies employed first-order kinetic parameters (D-values and z-values) in order to describe the reduction on microbial survival count. This study was conducted to analyze the E. coli O157:H7 inactivation data by using five microbial survival models (First-order, Weibull, Modified Gompertz, Biphasic linear and Log-logistic). First-order, Weibull, Modified Gompertz, Biphasic linear and Log-logistic kinetic models were used for fitting inactivation curves of Escherichia coli O157:H7. The residual sum of squares and the total sum of squares criteria were used to evaluate the models. The statistical indices of the kinetic models were used to fit inactivation data for E. coli O157:H7 by MTS at three temperatures (40, 50, and 60 0C) and three pressures (100, 200, and 300 kPa). Based on the statistical indices and visual observations, the Weibull and Biphasic models were best fitting of the data for MTS treatment as shown by high R2 values. The non-linear kinetic models, including the Modified Gompertz, First-order, and Log-logistic models did not provide any better fit to data from MTS compared the Weibull and Biphasic models. It was observed that the data found in this study did not follow the first-order kinetics. It is possibly because of the cells which are sensitive to ultrasound treatment were inactivated first, resulting in a fast inactivation period, while those resistant to ultrasound were killed slowly. The Weibull and biphasic models were found as more flexible in order to determine the survival curves of E. coli O157:H7 treated by MTS on apple-carrot juice.

Keywords: Weibull, Biphasic, MTS, kinetic models, E.coli O157:H7

Procedia PDF Downloads 366

Authors: Bohuslava Juhasova, Igor Halenar, Martin Juhas

Abstract:

The contribution deals with the current situation in modern manufacturing enterprises, which is affected by digital virtualization of different parts of the production process. The overview part of this article points to the fact, that wide informatization of all areas causes substitution of real elements and relationships between them with their digital, often virtual images, in real practice. Key characteristics of the systems implemented using digital twin technology along with essential conditions for intelligent products deployment were identified across many published studies. The goal was to propose a template for the production system realization using digital twin technology as a supplement to standardized concepts for Industry 4.0. The main resulting idea leads to the statement that the current trend of implementation of the new technologies and ways of communication between industrial facilities erases the boundaries between the real environment and the virtual world.

Keywords: communication, digital twin, Industry 4.0, simulation, virtualization

Procedia PDF Downloads 249

Authors: L. Chevez, A. Apaza, J. Rodriguez, R. Puga, H. Loro, Juan Z. Davalos

Abstract:

Virtual Dimension (VD) procedure is used to analyze Hyperspectral Image (HIS) treatment-data in order to estimate the abundance of mineral components of a mining sample. Hyperspectral images coming from reflectance spectra (NIR region) are pre-treated using Standard Normal Variance (SNV) and Minimum Noise Fraction (MNF) methodologies. The endmember components are identified by the Simplex Growing Algorithm (SVG) and after adjusted to the reflectance spectra of reference-databases using Simulated Annealing (SA) methodology. The obtained abundance of minerals of the sample studied is very near to the ones obtained using XRD with a total relative error of 2%.

Keywords: hyperspectral imaging, minimum noise fraction, MNF, simplex growing algorithm, SGA, standard normal variance, SNV, virtual dimension, XRD

Procedia PDF Downloads 158