Search results for: deep mixing method

Authors: Doo Ki Lee, Kumaresh Selvakumar, Man Young Kim, In Jae Song

Abstract:

The widespread utilization of mixer in selective catalytic reduction (SCR) system marks a remarkable advantage in diesel engines. In the automotive selective catalytic reduction (SCR) system, the de-NOX efficiency can be improved by highly uniform flow with effective turbulent mixing. In this paper, the exhaust pipe is complemented with the swirling mixers of three different vane angles installed at the upstream of the SCR reactor. The attributes of the mixer are established by the variation in flow behavior followed by the drawback owing to the absence of mixer. In particular, the information pertaining to the selection of proper static mixer is provided based on the correlation between the uniformity index (UI) and the pressure drop. The uniform distribution of the flow at the entrance of the SCR reactor aids to determine the configuration which gives high mixing performance and comprehend the function of the mixer.

Keywords: pressure drop, selective catalytic reduction, static mixer, turbulent mixing, uniformity index

Procedia PDF Downloads 909

Authors: Omid Adibi, Nategheh Najafpour, Bijan Farhanieh, Hossein Afshin

Abstract:

Gas release from the pipelines is one of the main factors in the gas industry accidents. Released gas ejects from the pipeline as a free jet and in the growth process, the fuel gets mixed with the ambient air. Accordingly, an accidental spark will release the chemical energy of the mixture with an explosion. Gas explosion damages the equipment and endangers the life of staffs. So due to importance of safety in gas industries, prevision of accident can reduce the number of the casualties. In this paper, natural gas leakages from the low pressure pipelines are studied in two steps: 1) the simulation of mixing process and identification of flammable zones and 2) the simulation of wind effects on the mixing process. The numerical simulations were performed by using the finite volume method and the pressure-based algorithm. Also, for the grid generation the structured method was used. The results show that, in just 6.4 s after accident, released natural gas could penetrate to 40 m in vertical and 20 m in horizontal direction. Moreover, the results show that the wind speed is a key factor in dispersion process. In fact, the wind transports the flammable zones into the downstream. Hence, to improve the safety of the people and human property, it is preferable to construct gas facilities and buildings in the opposite side of prevailing wind direction.

Keywords: flammable zones, gas pipelines, numerical simulation, wind effects

Procedia PDF Downloads 142

Authors: Lokes Parvatha Kumaran S., Sakthi Jay Mahenthar C., Sathyaprakash P., Jayakumar V., Shobanadevi A.

Abstract:

With the evolution of technology, the need to solve complex computational problems like machine learning and deep learning has shot up. But even the most powerful classical supercomputers find it difficult to execute these tasks. With the recent development of quantum computing, researchers and tech-giants strive for new quantum circuits for machine learning tasks, as present works on Quantum Machine Learning (QML) ensure less memory consumption and reduced model parameters. But it is strenuous to simulate classical deep learning models on existing quantum computing platforms due to the inflexibility of deep quantum circuits. As a consequence, it is essential to design viable quantum algorithms for QML for noisy intermediate-scale quantum (NISQ) devices. The proposed work aims to explore Variational Quantum Circuits (VQC) for Deep Reinforcement Learning by remodeling the experience replay and target network into a representation of VQC. In addition, to reduce the number of model parameters, quantum information encoding schemes are used to achieve better results than the classical neural networks. VQCs are employed to approximate the deep Q-value function for decision-making and policy-selection reinforcement learning with experience replay and the target network.

Keywords: quantum computing, quantum machine learning, variational quantum circuit, deep reinforcement learning, quantum information encoding scheme

Procedia PDF Downloads 92

Authors: Amir Sattari, Mac Panah, Naeim Rashidfarokhi

Abstract:

To enhance the mixing of fluid in a rectangular enclosure with a circular inlet and outlet, an energy-efficient approach is further investigated through computational fluid dynamics (CFD). Particle image velocimetry (PIV) measurements help confirm that the pulsation of the inflow velocity improves the mixing performance inside the enclosure considerably without increasing energy consumption. In this study, multiple CFD simulations with different turbulent models were performed. The results obtained were compared with experimental PIV results. This study investigates small-scale representations of flow patterns in a ventilated rectangular room. The objective is to validate the concept of an energy-efficient ventilation strategy with improved thermal comfort and reduction of stagnant air inside the room. Experimental and simulated results confirm that through pulsation of the inflow velocity, strong secondary vortices are generated downstream of the entrance wall-jet. The pulsatile inflow profile promotes a periodic generation of vortices with stronger eddies despite a relatively low inlet velocity, which leads to a larger boundary layer with increased kinetic energy in the occupied zone. A real-scale study was not conducted; however, it can be concluded that a constant velocity inflow profile can be replaced with a lower pulsated flow rate profile while preserving the mixing efficiency. Among the turbulent CFD models demonstrated in this study, SST-kω is most advantageous, exhibiting a similar global airflow pattern as in the experiments. The detailed near-wall velocity profile is utilized to identify the wall-jet instabilities that consist of mixing and boundary layers. The SAS method was later applied to predict the turbulent parameters in the center of the domain. In both cases, the predictions are in good agreement with the measured results.

Keywords: CFD, PIV, pulsatile inflow, ventilation, wall-jet

Procedia PDF Downloads 145

Authors: Yifan Fan, Xudong Luo, Pingping Lin

Abstract:

Nowadays, dialogue systems increasingly become the way for humans to access many computer systems. So, humans can interact with computers in natural language. A dialogue system consists of three parts: understanding what humans say in natural language, managing dialogue, and generating responses in natural language. In this paper, we survey deep learning based methods for dialogue management, response generation and dialogue evaluation. Specifically, these methods are based on neural network, long short-term memory network, deep reinforcement learning, pre-training and generative adversarial network. We compare these methods and point out the further research directions.

Keywords: dialogue management, response generation, deep learning, evaluation

Procedia PDF Downloads 133

Authors: F. Zouai, F. Z. Benabid, S. Bouhelal, D. Benachour

Abstract:

A method for the exfoliation of polyethylene terephtalate (PET) - clay nanocomposites has been reported in this study. Montmorillonite clay based polyethylene terephtalate nanocomposites were prepared by reactive melt-mixing. To achieve this, untreated clay was first functionalized with the crosslinking agent compound based mainly on peroxide/sulphur and TMTD as accelerator or activator for sulphur. Furthermore, the different blends composition of PET/clay were directly mixed in melt state in closed chamber of plastograph at given working conditions for short time and in one step process. To investigate the microstructure modification and thermal, mechanical and rheological properties the DSC, WAXS, microhardness, FTIR and tensile properties were performed. The resulting structure of the modified samples shows that total exfoliation appears at 4% w/w of clay to PET matrices. The crystallinity and tensile modulus were correlated by the H microhardness and the DSC shows no significant effect on the cristallinity degree. The mechanical properties were improved significantly. The viscosity decreases for 4% clay and the activation energy is the minimum. The WAXS measurement shows a partial exfoliation without any intercalation which is the most relevant point. The grafting of organic to inorganic nanolayers was observed by Si—O—C and Si—C bonds by FTIR.

Keywords: PET, montmorillonite, nanocomposites, exfoliation, reactive melt-mixing

Procedia PDF Downloads 231

Authors: Atef Ahmad Bleibel

Abstract:

Most codes of practice, like ACI 318-14, require the use of strut-and-tie modeling to analyze and design reinforced concrete deep beams. Though, investigations that conducted on deep beams do not include ring deep beams of influential parameters. This work presents an analytical parametric study using strut-and-tie modeling stated by ACI 318-14 to predict load capacity of 20 reinforced concrete ring deep beam specimens with different parameters. The parameters that were under consideration in the current work are ring diameter (Dc), number of supports (NS), width of ring beam (bw), concrete compressive strength (f'c) and width of bearing plate (Bp). It is found that the load capacity decreases by about 14-36% when ring diameter increases by about 25-75%. It is also found that load capacity increases by about 62-189% when number of supports increases by about 33-100%, while the load capacity increases by about 25-75% when the beam ring width increases by about 25-75%. Finally, it is found that load capacity increases by about 24-76% when compressive strength increases by about 24-76%, while the load capacity increases by about 5-16% when Bp increases by about 25-75%.

Keywords: load parameters, reinforced concrete, ring deep beam, strut and tie

Procedia PDF Downloads 77

Authors: Neda Azimi, Masoud Rahimi, Faezeh Mohammadi

Abstract:

Computational fluid dynamics (CFD) simulation was performed to investigate the effect of ferrofluid stimulation on hydrodynamic and mass transfer characteristics of two immiscible liquid phases in a Y-micromixer. The main purpose of this work was to develop a numerical model that is able to simulate hydrodynamic of the ferrofluid flow under magnetic field and determine its effect on mass transfer characteristics. A uniform external magnetic field was applied perpendicular to the flow direction. The volume of fluid (VOF) approach was used for simulating the multiphase flow of ferrofluid and two-immiscible liquid flows. The geometric reconstruction scheme (Geo-Reconstruct) based on piecewise linear interpolation (PLIC) was used for reconstruction of the interface in the VOF approach. The mass transfer rate was defined via an equation as a function of mass concentration gradient of the transported species and added into the phase interaction panel using the user-defined function (UDF). The magnetic field was solved numerically by Fluent MHD module based on solving the magnetic induction equation method. CFD results were validated by experimental data and good agreements have been achieved, which maximum relative error for extraction efficiency was about 7.52 %. It was showed that ferrofluid actuation by a magnetic field can be considered as an efficient mixing agent for liquid-liquid two-phase mass transfer in microdevices.

Keywords: CFD modeling, hydrodynamic, micromixer, ferrofluid, mixing

Procedia PDF Downloads 169

Authors: Shariful Islam, Sharun Akter Khushbu, S. M. Shaqib, Shahriar Sultan Ramit

Abstract:

In the construction sector, ensuring worker safety is of the utmost significance. In this study, a deep learning-based technique is presented for identifying safety gear worn by construction workers, such as helmets, goggles, jackets, gloves, and footwear. The suggested method precisely locates these safety items by using the YOLO v7 (You Only Look Once) object detection algorithm. The dataset utilized in this work consists of labeled images split into training, testing and validation sets. Each image has bounding box labels that indicate where the safety equipment is located within the image. The model is trained to identify and categorize the safety equipment based on the labeled dataset through an iterative training approach. We used custom dataset to train this model. Our trained model performed admirably well, with good precision, recall, and F1-score for safety equipment recognition. Also, the model's evaluation produced encouraging results, with a [email protected] score of 87.7%. The model performs effectively, making it possible to quickly identify safety equipment violations on building sites. A thorough evaluation of the outcomes reveals the model's advantages and points up potential areas for development. By offering an automatic and trustworthy method for safety equipment detection, this research contributes to the fields of computer vision and workplace safety. The proposed deep learning-based approach will increase safety compliance and reduce the risk of accidents in the construction industry.

Keywords: deep learning, safety equipment detection, YOLOv7, computer vision, workplace safety

Procedia PDF Downloads 38

Authors: Ali Berkan Ural

Abstract:

This paper presents the analysis, evaluation, and pre-diagnosis of early stage breast based diagnostic problems (breast cancer, nodulesorlumps) by Computer Aided Diagnosing (CAD) system from mammogram radiological images. According to the statistics, the time factor is crucial to discover the disease in the patient (especially in women) as possible as early and fast. In the study, a new algorithm is developed using advanced image processing and deep learning method to detect and classify the problem at earlystagewithmoreaccuracy. This system first works with image processing methods (Image acquisition, Noiseremoval, Region Growing Segmentation, Morphological Operations, Breast BorderExtraction, Advanced Segmentation, ObtainingRegion Of Interests (ROIs), etc.) and segments the area of interest of the breast and then analyzes these partly obtained area for cancer detection/lumps in order to diagnosis the disease. After segmentation, with using the Spectrogramimages, 5 different deep learning based methods (specified Convolutional Neural Network (CNN) basedAlexNet, ResNet50, VGG16, DenseNet, Xception) are applied to classify the breast based problems.

Keywords: computer aided diagnosis, breast cancer, region growing, segmentation, deep learning

Procedia PDF Downloads 63

Authors: Sheldon McCall, Miao Yu, Liyun Gong, Shigang Yue, Stefanos Kollias

Abstract:

Falls are a significant health concern for older adults globally, and prompt identification is critical to providing necessary healthcare support. Our study proposes a new fall detection method using computer vision based on modern deep learning techniques. Our approach involves training a trans- former model on a large 2D pose dataset for general action recognition, followed by transfer learning. Specifically, we freeze the first few layers of the trained transformer model and train only the last two layers for fall detection. Our experimental results demonstrate that our proposed method outperforms both classical machine learning and deep learning approaches in fall/non-fall classification. Overall, our study suggests that our proposed methodology could be a valuable tool for identifying falls.

Keywords: healthcare, fall detection, transformer, transfer learning

Procedia PDF Downloads 97

Authors: Vasupradaa Manivannan, Santosh Maruthy

Abstract:

Background/Aims: Preliminary evidence suggests that code-switching and code-mixing may act as one of the voluntary coping behavior to avoid the stuttering characteristics in children and adults; however, less is known about the types and patterns of code-mixing (CM) and code-switching (CS). Further, it is not known how it is different between children to adults who stutter. This study aimed to identify and compare the CM and CS patterns between Kannada-English bilingual children and adults who stutter. Method: A standard group comparison was made between five children who stutter (CWS) in the age range of 9-13 years and five adults who stutter (AWS) in the age range of 20-25 years. The participants who are proficient in Kannada (first language- L1) and English (second language- L2) were considered for the study. There were two tasks given to both the groups, a) General conversation (GC) with 10 random questions, b) Narration task (NAR) (Story / General Topic, for example., A Memorable Life Event) in three different conditions {Mono Kannada (MK), Mono English (ME), and Bilingual (BIL) Condition}. The children and adults were assessed online (via Zoom session) with a high-quality internet connection. The audio and video samples of the full assessment session were auto-recorded and manually transcribed. The recorded samples were analyzed for the percentage of dysfluencies using SSI-4 and CM, and CS exhibited in each participant using Matrix Language Frame (MLF) model parameters. The obtained data were analyzed using the Statistical Package for the Social Sciences (SPSS) software package (Version 20.0). Results: The mean, median, and standard deviation values were obtained for the percentage of dysfluencies (%SS) and frequency of CM and CS in Kannada-English bilingual children and adults who stutter for various parameters obtained through the MLF model. The inferential results indicated that %SS significantly varied between population (AWS vs CWS), languages (L1 vs L2), and tasks (GC vs NAR) but not across free (BIL) and bound (MK, ME) conditions. It was also found that the frequency of CM and CS patterns varies between CWS and AWS. The AWS had a lesser %SS but greater use of CS patterns than CWS, which is due to their excessive coping skills. The language mixing patterns were more observed in L1 than L2, and it was significant in most of the MLF parameters. However, there was a significantly higher (P<0.05) %SS in L2 than L1. The CS and CS patterns were more in conditions 1 and 3 than 2, which may be due to the higher proficiency of L2 than L1. Conclusion: The findings highlight the importance of assessing the CM and CS behaviors, their patterns, and the frequency of CM and CS between CWS and AWS on MLF parameters in two different tasks across three conditions. The results help us to understand CM and CS strategies in bilingual persons who stutter.

Keywords: bilinguals, code mixing, code switching, stuttering

Procedia PDF Downloads 50

Authors: N. Yang, R. Linforth, I. Fisk

Abstract:

The influence of food processing and choice of flavour solvent was investigated using biscuits prepared with vanillin flavour as an example. Powder vanillin either was added directly into the dough or dissolved into flavour solvent then mixed into the dough. The impact of two commonly used flavour solvents on food quality was compared: propylene glycol (PG) or triacetin (TA). The analytical approach for vanillin detection was developed by chromatography (HPLC-PDA), and the standard extraction method for vanillin was also established. The results indicated the impact of solvent choice on vanillin level during biscuit preparation. After baking, TA as a more heat resistant solvent retained more vanillin than PG, so TA is a better solvent for products that undergo a heating process. The results also illustrated the impact of mixing and baking on vanillin stability in the matrices. The average loss of vanillin was 33% during mixing and 13% during baking, which indicated that the binding of vanillin to fat or flour before baking might cause larger loss than evaporation loss during baking.

Keywords: biscuit, flavour stability, food quality, vanillin

Procedia PDF Downloads 487

Authors: Ksheeraj Sai Vepuri, Nada Attar

Abstract:

We as humans use words with accompanying visual and facial cues to communicate effectively. Classifying facial emotion using computer vision methodologies has been an active research area in the computer vision field. In this paper, we propose a simple method for facial expression recognition that enhances accuracy. We tested our method on the FER-2013 dataset that contains static images. Instead of using Histogram equalization to preprocess the dataset, we used Unsharp Mask to emphasize texture and details and sharpened the edges. We also used ImageDataGenerator from Keras library for data augmentation. Then we used Convolutional Neural Networks (CNN) model to classify the images into 7 different facial expressions, yielding an accuracy of 69.46% on the test set. Our results show that using image preprocessing such as the sharpening technique for a CNN model can improve the performance, even when the CNN model is relatively simple.

Keywords: facial expression recognittion, image preprocessing, deep learning, CNN

Procedia PDF Downloads 103

Authors: Amos Olajide Oluyege, Emmanuel Uchechukwu Opara, Sunday Adeniyi Adedutan, Joseph Adeola Fuwape

Abstract:

This study was conducted to determine the durability of wood-cement particleboards when exposed to attack by subterranean termites, Macrotermes subhylinus. The boards were made from Terminalia superba and Gmelina arborea wood sawdust at nominal board densities (BD) of 1000, 900, and 800 kg/m³ using wood-cement mixing ratios (MR) of 3:1, 2.5:1, 2:1, and 1:1. Above ground durability tests against termite attack were carried out according to ASTM D 2017 for 14 weeks. Results of visual assessment of the wood cement particleboards show that all the board samples had a visual rating that was not less than 7 (i.e., moderate attack) for both species irrespective of the MR and BD. T. superba boards were found to have higher resistance to termite attack compared to their G. arborea counterparts. The mean values for weight loss following exposure ranged from 1.93 to 6.13% and 3.24 to 12.44%. Analysis of variance (ANOVA) results of the weight loss assessment revealed a significant (p < 0.05) effect of species and mixing ratio on the weight loss of the boards due to termite attack with F(₁,₇₂) = 92.890 and P = 0.000 and F(₃,₇₂) = 8.318 and p = 0.000, while board density did not have any significant effect (p > 0.05) with F (₂,₇₂) = 1.307 and p = 0.277. Thus, boards made from a higher mixing ratio had better resistance against termite attacks. Thus, it can be concluded that the durability of cement-bonded particleboards when exposed to subterranean termite attack is not only dependent on the quality of the wood raw material (species) but also on the enhanced protection imparted by the cement matrix; the protection increased with increase in cement/wood mixing ratio.

Keywords: cement-bonded particleboard, mixing ratio, board density, Gmelina arborea, Terminalia superba

Procedia PDF Downloads 179

Authors: A. P. Joshi, H. V. Warrior, J. P. Panda

Abstract:

This paper is a continuation of the work carried out by various turbulence modelers in Oceanography on the topic of oceanic turbulent mixing. It evaluates the evolution of ocean water temperature and salinity by the appropriate modeling of turbulent mixing utilizing proper prescription of eddy viscosity. Many modelers in past have suggested including terms like shear, buoyancy and vorticity to be the parameters that decide the slow pressure strain correlation. We add to it the fact that dissipation anisotropy also modifies the correlation through eddy viscosity parameterization. This recalibrates the established correlation constants slightly and gives improved results. This anisotropization of dissipation implies that the critical Richardson’s number increases much beyond unity (to 1.66) to accommodate enhanced mixing, as is seen in reality. The model is run for a couple of test cases in the General Ocean Turbulence Model (GOTM) and the results are presented here.

Keywords: Anisotropy, GOTM, pressure-strain correlation, Richardson critical number

Procedia PDF Downloads 143

Authors: Naoum Abderrahmane, Boumehed Meriem, Alshaqaqi Belal

Abstract:

Background subtraction algorithm is a larger used technique for detecting moving objects in video surveillance to extract the foreground objects from a reference background image. There are many challenges to test a good background subtraction algorithm, like changes in illumination, dynamic background such as swinging leaves, rain, snow, and the changes in the background, for example, moving and stopping of vehicles. In this paper, we propose an efficient and accurate background subtraction method for moving object detection in video surveillance. The main idea is to use a developed fast-independent component analysis (ICA) algorithm to separate background, noise, and foreground masks from an image sequence in practical environments. The fast-ICA algorithm is adapted and adjusted with a matrix calculation and searching for an optimum non-quadratic function to be faster and more robust. Moreover, in order to estimate the de-mixing matrix and the denoising de-mixing matrix parameters, we propose to convert all images to YCrCb color space, where the luma component Y (brightness of the color) gives suitable results. The proposed technique has been verified on the publicly available datasets CD net 2012 and CD net 2014, and experimental results show that our algorithm can detect competently and accurately moving objects in challenging conditions compared to other methods in the literature in terms of quantitative and qualitative evaluations with real-time frame rate.

Keywords: background subtraction, moving object detection, fast-ICA, de-mixing matrix

Procedia PDF Downloads 68

Authors: Anupriya, Bikramjit Sinfh, Radhay Shyam

Abstract:

In order to improve mixing phenomena and combustion processes in supersonic flow, the current work has concentrated on identifying the ideal cavity parameters using CFD ANSYS Fluent. Offset ratios (OR) and aft ramp angles () have been manipulated in simulations of several models, but the length-to-depth ratio has remained the same. The length-to-depth ratio of all cavity flows is less than 10, making them all open. Hydrogen fuel was injected into a supersonic air flow with a Mach number of 3.75 using a chamber with a 1 mm diameter and a transverse slot nozzle. The free stream had conditions of a pressure of 1.2 MPa, a temperature of 299K, and a Reynolds number of 2.07x107. This method has the ability to retain a flame since the cavity facilitates rapid mixing of fuel and oxidizer and decreases total pressure losses. The impact of the cavity on combustion efficiency and total pressure loss is discussed, and the results are compared to those of a model without a cavity. Both the mixing qualities and the combustion processes were enhanced in the model with the cavity. The overall pressure loss as well as the effectiveness of the combustion process both increase with the increase in the ramp angle to the rear. When OR is increased, however, resistance to the supersonic flow field is reduced, which has a detrimental effect on both parameters. For a given ramp height, larger pressure losses were observed at steeper ramp angles due to increased eddy-viscous turbulent flow and increased wall drag.

Keywords: total pressure loss, flame holder, supersonic combustion, combustion efficiency, cavity, nozzle

Procedia PDF Downloads 63

Authors: Achouri Fatima, Chouicha Kaddour

Abstract:

The main parameters affecting the workability are the water content, particle size, and the total surface of the grains, as long as the mixing water begins by wetting the surface of the grains and then fills the voids between the grains to form entrapped water, the quantity of water remaining is called free water. The aim is to undertake a fractal approach through the relationship between the concrete formulation parameters and workability, to develop this approach a series of concrete taken from the literature was investigated by varying formulation parameters such as G / S, the quantity of cement C and the quantity of mixing water E. We also call on other model as the model for the thickness of the water layer and model of the thickness of the paste layer to judge their relevance, hence the following results : the relevance of the model of the thickness of the water layer is considered relevant when there is a variation in the water quantity, the model of the thickness of the layer of the paste is only applicable if we consider that the paste is made with the grain value Dmax = 2.85: value from which we see a stable model.

Keywords: concrete, fractal method, paste thickness, water thickness, workability

Procedia PDF Downloads 347

Authors: Akshat Mathur, Sunil Kumar Khatri

Abstract:

This paper presents brief about how the use of Artificial intelligence in respect to GUI testing can reduce workload by using DL-fueled method. This paper also discusses about how graphical user interface and event driven software testing can derive benefits from the use of AI techniques. The use of AI techniques not only reduces the task and work load but also helps in getting better output than manual testing. Although results are same, but the use of Artifical intelligence techniques for GUI testing has proven to provide ideal results. DL-fueled framework helped us to find imperfections of the entire webpage and provides test failure result in a score format between 0 and 1which signifies that are test meets it quality criteria or not. This paper proposes DL-fueled method which helps us to find the genuine GUI bugs and defects and also helped us to scale the existing labour-intensive and skill-intensive methodologies.

Keywords: graphical user interface, GUI, artificial intelligence, deep learning, ML technology

Procedia PDF Downloads 133

Authors: Xulu Yao, Moi Hoon Yap, Yanlong Zhang

Abstract:

As a branch of artificial neural network, deep learning is widely used in the field of image recognition, but the lack of its dataset leads to imperfect model learning. By analysing the data scale requirements of deep learning and aiming at the application in GUI generation, it is found that the collection of GUI dataset is a time-consuming and labor-consuming project, which is difficult to meet the needs of current deep learning network. To solve this problem, this paper proposes a semi-supervised deep learning model that relies on the original small-scale datasets to produce a large number of reliable data sets. By combining the cyclic neural network with the generated countermeasure network, the cyclic neural network can learn the sequence relationship and characteristics of data, make the generated countermeasure network generate reasonable data, and then expand the Rico dataset. Relying on the network structure, the characteristics of collected data can be well analysed, and a large number of reasonable data can be generated according to these characteristics. After data processing, a reliable dataset for model training can be formed, which alleviates the problem of dataset shortage in deep learning.

Keywords: GUI, deep learning, GAN, data augmentation

Procedia PDF Downloads 147

Authors: Mária Csernoch, Piroska Biró

Abstract:

The legends about “user-friendly” and “easy-to-use” birotical tools (computer-related office tools) have been spreading and misleading end-users. This approach has led us to the extremely high number of incorrect documents, causing serious financial losses in the creating, modifying, and retrieving processes. Our research proved that there are at least two sources of this underachievement: (1) The lack of the definition of the correctly edited, formatted documents. Consequently, end-users do not know whether their methods and results are correct or not. They are not aware of their ignorance. They are so ignorant that their ignorance does not allow them to realize their lack of knowledge. (2) The end-users’ problem-solving methods. We have found that in non-traditional programming environments end-users apply, almost exclusively, surface approach metacognitive methods to carry out their computer related activities, which are proved less effective than deep approach methods. Based on these findings we have developed deep approach methods which are based on and adapted from traditional programming languages. In this study, we focus on the most popular type of birotical documents, the text-based documents. We have provided the definition of the correctly edited text, and based on this definition, adapted the debugging method known in programming. According to the method, before the realization of text editing, a thorough debugging of already existing texts and the categorization of errors are carried out. With this method in advance to real text editing users learn the requirements of text-based documents and also of the correctly formatted text. The method has been proved much more effective than the previously applied surface approach methods. The advantages of the method are that the real text handling requires much less human and computer sources than clicking aimlessly in the GUI (Graphical User Interface), and the data retrieval is much more effective than from error-prone documents.

Keywords: deep approach metacognitive methods, error-prone birotical documents, financial losses, human and computer resources

Procedia PDF Downloads 359

Authors: Salamatu Sani

Abstract:

This study is an investigation of how code-mixing manifests in the language development of a Nigerian child, especially in the Hausa speaking environment. It is hinged on the fact that the environment influences the first language acquired by a child regardless of the cultural and/or linguistic background of the parents. The child under investigation has been subjected to close monitoring on her speech hitherto. It is a longitudinal study covering a period of twelve months (January 2018 to December 2018); that was when the subject was between twenty-four and thirty months of age. The speeches have been recorded by means of a tape recorder, video, and a diary. The study employs as a theoretical framework, emergentism, which is an eclectic of the behaviourist and the mentalist theories to the study of language development, for analysis. This is in agreement with the positions of Skinner and Watson. Sequel to this investigation, it was discovered the environment is a major factor that influences the exposure of a child to a language more than the other factors and that, if a child is exposed to more than one language, there is a great tendency for such a child to code-mix and code-switch in her speech production. The child under investigation, in spite of the linguistic background of her parents, speaks the Hausa Language much better than the other languages around her though with remarkable code-mixing with other languages around her such as English and Ebira languages. The study concludes that although a child is born with the innate ability to acquire a particular language, the environment plays a key role to trigger the innate ability and consequently, the child is exposed to the acquisition of the dominant language around her at a particular given time.

Keywords: bilingual, code-mixing, emergentism, environment, Hausa

Procedia PDF Downloads 129

Authors: S. J. Kim, Y. J. Yoo

Abstract:

Slack-tide sampling was carried out at seven stations at high and low tides for a tidal cycle, in summer (7, 8, 9) and fall (10), 2016 to determine the differences of water quality according to tides in Masan Bay. The data were analyzed by Pearson correlation and factor analysis. The mixing state of all the water quality components investigated is well explained by the correlation with salinity (SAL). Turbidity (TURB), dissolved silica (DSi), nitrite and nitrate nitrogen (NNN) and total nitrogen (TN), which find their way into the bay from the streams and have no internal source and sink reaction, showed a strong negative correlation with SAL at low tide, indicating the property of conservative mixing. On the contrary, in summer and fall, dissolved oxygen (DO), hydrogen sulfide (H2S) and chemical oxygen demand with KMnO4 (CODMn) of the surface and bottom water, which were sensitive to an internal source and sink reaction, showed no significant correlation with SAL at high and low tides. The remaining water quality parameters showed a conservative or a non-conservative mixing pattern depending on the mixing characteristics at high and low tides, determined by the functional relationship between the changes of the flushing time and the changes of the characteristics of water quality components of the end-members in the bay. Factor analysis performed on the concentration difference data sets between high and low tides helped in identifying the principal latent variables for them. The concentration differences varied spatially and temporally. Principal factors (PFs) scores plots for each monitoring situation showed high associations of the variations to the monitoring sites. At sampling station 1 (ST1), temperature (TEMP), SAL, DSi, TURB, NNN and TN of the surface water in summer, TEMP, SAL, DSi, DO, TURB, NNN, TN, reactive soluble phosphorus (RSP) and total phosphorus (TP) of the bottom water in summer, TEMP, pH, SAL, DSi, DO, TURB, CODMn, particulate organic carbon (POC), ammonia nitrogen (AMN), NNN, TN and fecal coliform (FC) of the surface water in fall, TEMP, pH, SAL, DSi, H2S, TURB, CODMn, AMN, NNN and TN of the bottom water in fall commonly showed up as the most significant parameters and the large concentration differences between high and low tides. At other stations, the significant parameters showed differently according to the spatial and temporal variations of mixing pattern in the bay. In fact, there is no estuary that always maintains steady-state flow conditions. The mixing regime of an estuary might be changed at any time from linear to non-linear, due to the change of flushing time according to the combination of hydrogeometric properties, inflow of freshwater and tidal action, And furthermore the change of end-member conditions due to the internal sinks and sources makes the occurrence of concentration difference inevitable. Therefore, when investigating the water quality of the estuary, it is necessary to take a sampling method considering the tide to obtain average water quality data.

Keywords: conservative mixing, end-member, factor analysis, flushing time, high and low tide, latent variables, non-conservative mixing, slack-tide sampling, spatial and temporal variations, surface and bottom water

Procedia PDF Downloads 101

Authors: Azeddine El-Hassouny, Chandrashekhar Meshram, Geraldin Nanfack

Abstract:

In recent years, learning from data with noisy labels (Label Noise) has been a major concern in supervised learning. This problem has become even more worrying in Deep Learning, where the generalization capabilities have been questioned lately. Indeed, deep learning requires a large amount of data that is generally collected by search engines, which frequently return data with unreliable labels. In this paper, we investigate the Label Noise in Deep Learning using variational inference. Our contributions are : (1) exploiting Label Noise concept where the true labels are learnt using reparameterization variational inference, while observed labels are learnt discriminatively. (2) the noise transition matrix is learnt during the training without any particular process, neither heuristic nor preliminary phases. The theoretical results shows how true label distribution can be learned by variational inference in any discriminate neural network, and the effectiveness of our approach is proved in several target datasets, such as MNIST and CIFAR32.

Keywords: label noise, deep learning, discrete latent variable, variational inference, MNIST, CIFAR32

Procedia PDF Downloads 87

Authors: Raquel Zydeck, Karina Azzolin, Luis Kosteski, Alisson Milani

Abstract:

This work presents numerical models in plane deformations (2D), using the Discrete Element Method formedbybars (LDEM) andtheFiniteElementMethod (FEM), in structuralmasonrywallswith horizontal chasesof 20%, 30%, and 50% deep, located in the central part and 1/3 oftheupperpartofthewall, withcenteredandeccentricloading. Differentcombinationsofboundaryconditionsandinteractionsbetweenthemethodswerestudied.

Keywords: chases in structural masonry walls, discrete element method formed by bars, finite element method, numerical models, boundary condition

Procedia PDF Downloads 134

Authors: Yanjun Chen, Chuanping Hu, Jie Shao, Lin Mei, Chongyang Zhang

Abstract:

Traditional image classification is based on encoding scheme (e.g. Fisher Vector, Vector of Locally Aggregated Descriptor) with low-level image features (e.g. SIFT, HoG). Compared to these low-level local features, deep convolutional features obtained at the mid-level layer of convolutional neural networks (CNN) have richer information but lack of geometric invariance. For scene classification, there are scattered objects with different size, category, layout, number and so on. It is crucial to find the distinctive objects in scene as well as their co-occurrence relationship. In this paper, we propose a method to take advantage of both deep convolutional features and the traditional encoding scheme while taking object-centric and scene-centric information into consideration. First, to exploit the object-centric and scene-centric information, two CNNs that trained on ImageNet and Places dataset separately are used as the pre-trained models to extract deep convolutional features at multiple scales. This produces dense local activations. By analyzing the performance of different CNNs at multiple scales, it is found that each CNN works better in different scale ranges. A scale-wise CNN adaption is reasonable since objects in scene are at its own specific scale. Second, a fisher kernel is applied to aggregate a global representation at each scale and then to merge into a single vector by using a post-processing method called scale-wise normalization. The essence of Fisher Vector lies on the accumulation of the first and second order differences. Hence, the scale-wise normalization followed by average pooling would balance the influence of each scale since different amount of features are extracted. Third, the Fisher vector representation based on the deep convolutional features is followed by a linear Supported Vector Machine, which is a simple yet efficient way to classify the scene categories. Experimental results show that the scale-specific feature extraction and normalization with CNNs trained on object-centric and scene-centric datasets can boost the results from 74.03% up to 79.43% on MIT Indoor67 when only two scales are used (compared to results at single scale). The result is comparable to state-of-art performance which proves that the representation can be applied to other visual recognition tasks.

Keywords: deep convolutional features, Fisher Vector, multiple scales, scale-specific normalization

Procedia PDF Downloads 301

Authors: Muhammad Ali Sarwar, Muhammad Farooq, Nayab Hassan, Hammad Hassan

Abstract:

Pakistan is highly recognized for its agriculture and is well known for producing substantial amounts of wheat, cotton, and sugarcane. However, some factors contribute to a decline in crop quality and a reduction in overall output. One of the main factors contributing to this decline is the presence of weed and its late detection. This process of detection is manual and demands a detailed inspection to be done by the farmer itself. But by the time detection of weed, the farmer will be able to save its cost and can increase the overall production. The focus of this research is to identify and classify the four main types of weeds (Small-Flowered Cranesbill, Chick Weed, Prickly Acacia, and Black-Grass) that are prevalent in our region’s major crops. In this work, we implemented three different deep learning techniques: YOLO-v5, Inception-v3, and Deep CNN on the same Dataset, and have concluded that deep convolutions neural network performed better with an accuracy of 97.45% for such classification. In relative to the state of the art, our proposed approach yields 2% better results. We devised the architecture in an efficient way such that it can be used in real-time.

Keywords: deep convolution networks, Yolo, machine learning, agriculture

Procedia PDF Downloads 70

Authors: Murad Almadani, Khalil Abu-Hantash, Xinyu Wang, Herbert Jelinek, Kinda Khalaf

Abstract:

Gait analysis is used by healthcare professionals as a tool to gain a better understanding of the movement impairment and track progress. In most circumstances, monitoring patients in their real-life environments with low-cost equipment such as cameras and wearable sensors is more important. Inertial sensors, on the other hand, cannot provide enough information on angular dynamics. This research offers a method for tracking 2D joint coordinates using cutting-edge vision algorithms and a single RGB camera. We provide an end-to-end comprehensive deep learning pipeline for marker-less gait parameter estimation, which, to our knowledge, has never been done before. To make our pipeline function in real-time for real-world applications, we leverage the AlphaPose human posture prediction model and a deep learning transformer. We tested our approach on the well-known GPJATK dataset, which produces promising results.

Keywords: gait analysis, human pose estimation, deep learning, real time gait estimation, AlphaPose, transformer

Procedia PDF Downloads 82

Authors: Ashkan Shafee, Ahmad Fahimifar

Abstract:

There is a growing demand for construction of high-rise buildings and infrastructures in large cities, which sometimes require deep excavations in the vicinity of pile foundations. In this study, a two-dimensional finite element analysis is used to gain insight into the response of pile groups adjacent to deep excavations in sand. The numerical code was verified by available experimental works, and a parametric study was performed on different working load combinations, excavation depth and supporting system. The results show that the simple two-dimensional plane strain model can accurately simulate the excavation induced changes on adjacent pile groups. It was found that further excavation than pile toe level and also inclined loading on adjacent pile group can severely affect the serviceability of the foundation.

Keywords: deep excavation, inclined loading, lateral deformation, pile group

Procedia PDF Downloads 235