Search results for: deep mixing method

Authors: Azene Zenebe

Abstract:

Deep learning is a subset of machine learning which incorporates techniques for the construction of artificial neural networks and found to be useful for modeling complex problems with large dataset. Deep learning requires a very high power computational and longer time for training. By aggregating computing power, high performance computer (HPC) has emerged as an approach to resolving advanced problems and performing data-driven research activities. Cyber threat intelligence (CIT) is actionable information or insight an organization or individual uses to understand the threats that have, will, or are currently targeting the organization. Results of review of literature will be presented along with results of experimental study that compares the performance of tree-based and function-base machine learning including deep learning algorithms using secondary dataset collected from darknet.

Keywords: deep-learning, cyber security, cyber threat modeling, tree-based machine learning, function-based machine learning, data science

Procedia PDF Downloads 120

Authors: A. C. Blaga, A. Cârlescu, M. Turnea, A. I. Galaction, D. Caşcaval

Abstract:

The performance of an aerobic stirred bioreactor for fungal fermentation was analyzed on the basis of mixing time and oxygen mass transfer coefficient, by quantifying the influence of some specific geometrical and operational parameters of the bioreactor, as well as the rheological behavior of Penicillium chrysogenum broth (free mycelia and mycelia aggregates). The rheological properties of the fungus broth, controlled by the biomass concentration, its growth rate, and morphology strongly affect the performance of the bioreactor. Experimental data showed that for both morphological structures the accumulation of fungus biomass induces a significant increase of broths viscosity and modifies the rheological behavior. For lower P. chrysogenum concentrations (both morphological conformations), the mixing time initially increases with aeration rate, reaches a maximum value and decreases. This variation can be explained by the formation of small bubbles, due to the presence of solid phase which hinders the bubbles coalescence, the rising velocity of bubbles being reduced by the high apparent viscosity of fungus broths. By biomass accumulation, the variation of mixing time with aeration rate is gradually changed, the continuous reduction of mixing time with air input flow increase being obtained for 33.5 g/l d.w. P. chrysogenum. Owing to the superior apparent viscosity, which reduces considerably the relative contribution of mechanical agitation to the broths mixing, these phenomena are more pronounced for P. chrysogenum free mycelia. Due to the increase of broth apparent viscosity, the biomass accumulation induces two significant effects on oxygen transfer rate: the diminution of turbulence and perturbation of bubbles dispersion - coalescence equilibrium. The increase of P. chrysogenum free mycelia concentration leads to the decrease of kla values. Thus, for the considered variation domain of the main parameters taken into account, namely air superficial velocity from 8.36 10-4 to 5.02 10-3 m/s and specific power input from 100 to 500 W/m3, kla was reduced for 3.7 times for biomass concentration increase from 4 to 36.5 g/l d.w. The broth containing P. crysogenum mycelia aggregates exhibits a particular behavior from the point of view of oxygen transfer. Regardless of bioreactor operating conditions, the increase of biomass concentration leads initially to the increase of oxygen mass transfer rate, the phenomenon that can be explained by the interaction of pellets with bubbles. The results are in relation with the increase of apparent viscosity of broths corresponding to the variation of biomass concentration between the mentioned limits. Thus, the apparent viscosity of the suspension of fungus mycelia aggregates increased for 44.2 times and fungus free mycelia for 63.9 times for CX increase from 4 to 36.5 g/l d.w. By means of the experimental data, some mathematical correlations describing the influences of the considered factors on mixing time and kla have been proposed. The proposed correlations can be used in bioreactor performance evaluation, optimization, and scaling-up.

Keywords: biomass concentration, mixing time, oxygen mass transfer, P. chrysogenum broth, stirred bioreactor

Procedia PDF Downloads 305

Authors: Wei Li, Tuo Yang

Abstract:

In order to satisfy the real-time and accurate requirements of cigarette smoke detection in complex scenes, a cigarette smoke detection technology based on the combination of deep learning and color features was proposed. Firstly, based on the color features of cigarette smoke, the suspicious cigarette smoke area in the image is extracted. Secondly, combined with the efficiency of cigarette smoke detection and the problem of network overfitting, a network model for cigarette smoke detection was designed according to YOLOV3 algorithm to reduce the false detection rate. The experimental results show that the method is feasible and effective, and the accuracy of cigarette smoke detection is up to 99.13%, which satisfies the requirements of real-time cigarette smoke detection in complex scenes.

Keywords: deep learning, computer vision, cigarette smoke detection, YOLOV3, color feature extraction

Procedia PDF Downloads 55

Authors: Hillary Mwongyera

Abstract:

The Semliki basin has become a frontier for petroleum exploration in recent years. Exploration efforts have resulted into extensive seismic data acquisition and drilling of three wells namely; Turaco 1, Turaco 2 and Turaco 3. A petrophysical analysis of the Turaco 1 well was carried out to identify two reservoir zones on which AVO modeling was performed. A combination of seismic modeling and rock physics modeling was applied during reservoir characterization and monitoring to determine variations of seismic responses with amplitude characteristics. AVO intercept gradient analysis applied on AVO synthetic CDP gathers classified AVO anomalies associated with both reservoir zones as Class 1 AVO anomalies. Fluid replacement modeling was carried out on both reservoir zones using homogeneous mixing and patchy saturation patterns to determine effects of fluid substitution on rock property interactions. For both homogeneous mixing and saturation patterns, density (ρ) showed an increasing trend with increasing brine substitution while Shear wave velocity (Vs) decreased with increasing brine substitution. A study of compressional wave velocity (Vp) with increasing brine substitution for both homogeneous mixing and patchy saturation gave quite interesting results. During patchy saturation, Vp increased with increasing brine substitution. During homogeneous mixing however, Vp showed a slightly decreasing trend with increasing brine substitution but increased tremendously towards and at full brine saturation. A sensitivity analysis carried out showed that density was a very sensitive rock property responding to brine saturation except at full brine saturation during homogeneous mixing where Vp showed greater sensitivity with brine saturation. Rock physics modeling was performed to predict diagnostics of reservoir quality using an inverse deterministic approach which showed low shale content and a high degree of shale stiffness within reservoir zones.

Keywords: Amplitude Versus Offset (AVO), fluid replacement modelling, reservoir characterization, AVO attributes, rock physics modelling, reservoir monitoring

Procedia PDF Downloads 504

Authors: Maryam Zarabian, Hector Guzman, Pedro Pereira-Almao, Abraham Fapojuwo

Abstract:

Dry reforming of methane (DRM) has sparked significant industrial and scientific interest not only as a viable alternative for addressing the environmental concerns of two main contributors of the greenhouse effect, i.e., carbon dioxide (CO₂) and methane (CH₄), but also produces syngas, i.e., a mixture of hydrogen (H₂) and carbon monoxide (CO) utilized by a wide range of downstream processes as a feedstock for other chemical productions. In this study, we develop an AI-enable syngas production model to tackle the problem of achieving an equivalent H₂/CO ratio [1:1] with respect to the most efficient conversion. Firstly, the unsupervised density-based spatial clustering of applications with noise (DBSAN) algorithm removes outlier data points from the original experimental dataset. Then, random forest (RF) and deep neural network (DNN) models employ the error-free dataset to predict the DRM results. DNN models inherently would not be able to obtain accurate predictions without a huge dataset. To cope with this limitation, we employ reusing pre-trained layers’ approaches such as transfer learning and greedy layer-wise pretraining. Compared to the other deep models (i.e., pure deep model and transferred deep model), the greedy layer-wise pre-trained deep model provides the most accurate prediction as well as similar accuracy to the RF model with R² values 1.00, 0.999, 0.999, 0.999, 0.999, and 0.999 for the total outlet flow, H₂/CO ratio, H₂ yield, CO yield, CH₄ conversion, and CO₂ conversion outputs, respectively.

Keywords: artificial intelligence, dry reforming of methane, artificial neural network, deep learning, machine learning, transfer learning, greedy layer-wise pretraining

Procedia PDF Downloads 58

Authors: Yong Wee Foo, Lai Meng Tang

Abstract:

Artificial Intelligence (AI), particularly the usage of deep neural networks for hierarchical representations from data, has found numerous complex applications across various domains, including computer vision, robotics, autonomous vehicles, and other scientific fields. However, their inherent “black box” nature can sometimes make it challenging for early researchers or school students of various levels to comprehend and trust the results they produce. Consequently, there has been a growing demand for reliable visualization tools in engineering and science education to help learners understand, trust, and explain a deep learning network. This has led to a notable emphasis on the visualization of AI in the research community in recent years. AI visualization tools are increasingly being adopted to significantly improve the comprehension of complex topics in deep learning. This paper proposes a novel approach to empower students to actively explore the inner workings of deep neural networks by combining the student-centered learning approach of flipped classroom models with the investigative power of AI visualization tools, namely, the TensorFlow Playground, the Local Interpretable Model-agnostic Explanations (LIME), and the SHapley Additive exPlanations (SHAP), for delivering an AI education curriculum. Combining the two factors is vital in fostering ownership, responsibility, and critical thinking skills in the age of AI.

Keywords: deep learning, explainable AI, AI visualization, representation learning

Procedia PDF Downloads 33

Authors: Azubuike Ekwere

Abstract:

The shallow and deep aquiferous horizons of the fractured and weathered crystalline basement Oban Massif of south-eastern Nigeria were studied during the dry and wet seasons. The criteria were ascertaining hydrochemistry relative to seasonal and spatial variations across the study area. Results indicate that concentrations of major cations and anions exhibit the order of abundance; Ca>Na>Mg>K and HCO3>SO4>Cl respectively, with minor variations across sampling seasons. Major elements Ca, Mg, Na and K were higher for the shallow aquifers than the deep aquifers across seasons. The major anions Cl, SO4, HCO3, and NO3 were higher for the deep aquifers compared to the shallow ones. Two water types were identified for both aquifer types: Ca-Mg-HCO3 and Ca-Na-Cl-SO4. Most of the parameters considered were within the international limits for drinking, domestic and irrigation purposes. Assessment by use of sodium absorption ratio (SAR), percent sodium (%Na) and the wilcox diagram reveals that the waters are suitable for irrigation purposes.

Keywords: shallow aquifer, deep aquifer, seasonal variation, hydrochemistry, Oban massif, Nigeria

Procedia PDF Downloads 623

Authors: Hao Li, Guy Y. Cornejo Maceda, Yiqing Li, Jianguo Tan, Marek Morzynski, Bernd R. Noack

Abstract:

We propose an automated analysis of the flow control behaviour from an ensemble of control laws and associated time-resolved flow snapshots. The input may be the rich database of machine learning control (MLC) optimizing a feedback law for a cost function in the plant. The proposed methodology provides (1) insights into the control landscape, which maps control laws to performance, including extrema and ridge-lines, (2) a catalogue of representative flow states and their contribution to cost function for investigated control laws and (3) visualization of the dynamics. Key enablers are classification and feature extraction methods of machine learning. The analysis is successfully applied to the stabilization of a mixing layer with sensor-based feedback driving an upstream actuator. The fluctuation energy is reduced by 26%. The control replaces unforced Kelvin-Helmholtz vortices with subsequent vortex pairing by higher-frequency Kelvin-Helmholtz structures of lower energy. These efforts target a human interpretable, fully automated analysis of MLC identifying qualitatively different actuation regimes, distilling corresponding coherent structures, and developing a digital twin of the plant.

Keywords: machine learning control, mixing layer, feedback control, model-free control

Procedia PDF Downloads 192

Authors: Alessandro Marano

Abstract:

The author describes the use of deep plane face lifting and platysmaplasty to treat sagging neck with minimal scars. Series of case study. The author uses a selective deep plane face lift with a minimal access scar that not extend behind the ear lobe, neck liposuction and platysmaplasty to restore the sagging neck; the scars are minimal and no require drainage post-op. The deep plane face lifting can achieve a good result restoring vertical vectors in aging and sagging face, neck district can be treated without cutting the skin behind the ear lobe combining the SMAS vertical suspension and platysmaplasty; surgery can be performed in local anesthesia with sedation in day surgery and fast recovery. Restoring neck sagging without extend scars behind ear lobe is possible in selected patients, procedure is fast, safe, no drainage required, patients are satisfied and healing time is fast and comfortable.

Keywords: face lifting, aesthetic, face, neck, platysmaplasty, deep plane

Procedia PDF Downloads 70

Authors: Jean Marriz M. Manzano, Marc D. Rosales, Magdaleno R. Vasquez Jr., Maria Theresa G. De Leon

Abstract:

This paper discusses the effects of surface roughness on a cantilever beam vibrational energy harvester. A silicon sample was fabricated using MEMS fabrication processes. When etching silicon using deep reactive ion etching (DRIE) at large etch depths, rougher surfaces are observed as a result of increased response in process pressure, amount of coil power and increased helium backside cooling readings. To account for the effects of surface roughness on the characteristics of the cantilever beam, finite element method (FEM) modeling was performed using actual roughness data from fabricated samples. It was found that when etching about 550um of silicon, root mean square roughness parameter, Sq, varies by 1 to 3 um (at 100um thick) across a 6-inch wafer. Given this Sq variation, FEM simulations predict an 8 to148 Hz shift in the resonant frequency while having no significant effect on the output power. The significant shift in the resonant frequency implies that careful consideration of surface roughness from fabrication processes must be done when designing energy harvesters.

Keywords: deep reactive ion etching, finite element method, microelectromechanical systems, multiphysics analysis, surface roughness, vibrational energy harvester

Procedia PDF Downloads 99

Authors: SKhan Park, Seok Jin Lee, Jong Sun Kim, Jun Ho Lee, Bong Chan Kim

Abstract:

Because of the large economic losses caused by traffic congestion in metropolitan areas, various studies on the underground network design and construction techniques has been performed various studies in the developed countries. In Korea, it has performed a study to develop a versatile double-deck of deep tunnel model. This paper is an introduction to develop a ground reinforcement method to enable the safe tunnel construction in the weakened pillar section like as junction of tunnel. Applicable ground reinforcement method in the weakened section is proposed and it is expected to verify the method by the field application tests.

Keywords: double-deck tunnel, ground reinforcement, tunnel construction, weakened pillar section

Procedia PDF Downloads 369

Authors: Omar Masaud Almrhag, Frage Lhadi Abookleesh

Abstract:

Different types of food like banana, potato and chicken affect the quality of oil during deep fat frying. The changes in the quality of oil were evaluated and compared. Four different types of edible oils, namely, corn oil, soybean, canola, and palm oil were used for deep fat frying at 180°C ± 5°C for 5 h/d for six consecutive days. A potato was sliced into 7-8 cm length wedges and chicken was cut into uniform pieces of 100 g each. The parameters used to assess the quality of oil were total polar compound (TPC), iodine value (IV), specific extinction E1% at 233 nm and 269 nm, fatty acid composition (FAC), free fatty acids (FFA), viscosity (cp) and changes in the thermal properties. Results showed that, TPC, IV, FAC, Viscosity (cp) and FFA composition changed significantly with time (P< 0.05) and type of food. Significant differences (P< 0.05) were noted for the used parameters during frying of the above mentioned three products.

Keywords: frying potato, chicken, frying deterioration, quality of oil

Procedia PDF Downloads 391

Authors: Firas Gerges, Frank Y. Shih

Abstract:

Malignant melanoma, known simply as melanoma, is a type of skin cancer that appears as a mole on the skin. It is critical to detect this cancer at an early stage because it can spread across the body and may lead to the patient's death. When detected early, melanoma is curable. In this paper, we propose a deep learning model (convolutional neural networks) in order to automatically classify skin lesion images as malignant or benign. Images underwent certain pre-processing steps to diminish the effect of the normal skin region on the model. The result of the proposed model showed a significant improvement over previous work, achieving an accuracy of 97%.

Keywords: deep learning, skin cancer, image processing, melanoma

Procedia PDF Downloads 111

Authors: Uma Maheshwari V., Rajanikanth Aluvalu, Kumar Gautam

Abstract:

The COVID-19 disease is a highly contagious viral infection with major worldwide health implications. The global economy suffers as a result of COVID. The spread of this pandemic disease can be slowed if positive patients are found early. COVID-19 disease prediction is beneficial for identifying patients' health problems that are at risk for COVID. Deep learning and machine learning algorithms for COVID prediction using X-rays have the potential to be extremely useful in solving the scarcity of doctors and clinicians in remote places. In this paper, a convolutional neural network (CNN) with deep layers is presented for recognizing COVID-19 patients using real-world datasets. We gathered around 6000 X-ray scan images from various sources and split them into two categories: normal and COVID-impacted. Our model examines chest X-ray images to recognize such patients. Because X-rays are commonly available and affordable, our findings show that X-ray analysis is effective in COVID diagnosis. The predictions performed well, with an average accuracy of 99% on training photographs and 88% on X-ray test images.

Keywords: deep CNN, COVID–19 analysis, feature extraction, feature map, accuracy

Procedia PDF Downloads 46

Authors: Weirong Wang, Shenghong Huang, Xisheng Luo, Zhenyu Li

Abstract:

Material mixing process and related dynamic issues at extreme compressing conditions have gained more and more concerns in last ten years because of the engineering appealings in inertial confinement fusion (ICF) and hypervelocity aircraft developments. However, there lacks models and methods that can handle fully coupled turbulent material mixing and complex fluid evolution under conditions of high energy density regime up to now. In aspects of macro hydrodynamics, three numerical methods such as direct numerical simulation (DNS), large eddy simulation (LES) and Reynolds-averaged Navier–Stokes equations (RANS) has obtained relative acceptable consensus under the conditions of low energy density regime. However, under the conditions of high energy density regime, they can not be applied directly due to occurrence of dissociation, ionization, dramatic change of equation of state, thermodynamic properties etc., which may make the governing equations invalid in some coupled situations. However, in view of micro/meso scale regime, the methods based on Molecular Dynamics (MD) as well as Monte Carlo (MC) model are proved to be promising and effective ways to investigate such issues. In this study, both classical MD and first-principle based electron force field MD (eFF-MD) methods are applied to investigate Richtmyer-Meshkov Instability of metal Lithium and gas Hydrogen (Li-H2) interface mixing at different shock loading speed ranging from 3 km/s to 30 km/s. It is found that: 1) Classical MD method based on predefined potential functions has some limits in application to extreme conditions, since it cannot simulate the ionization process and its potential functions are not suitable to all conditions, while the eFF-MD method can correctly simulate the ionization process due to its ‘ab initio’ feature; 2) Due to computational cost, the eFF-MD results are also influenced by simulation domain dimensions, boundary conditions and relaxation time choices, etc., in computations. Series of tests have been conducted to determine the optimized parameters. 3) Ionization induced by strong shock compression has important effects on Li-H2 interface evolutions of RMI, indicating a new micromechanism of RMI under conditions of high energy density regime.

Keywords: first-principle, ionization, molecular dynamics, material mixture, Richtmyer-Meshkov instability

Procedia PDF Downloads 206

Authors: Jovana Nikolov, Natasa Todorovic, Ivana Stojkovic

Abstract:

Monitoring of 222Rn in drinking or surface waters, as well as in groundwater has been performed in connection with geological, hydrogeological and hydrological surveys and health hazard studies. Liquid scintillation counting (LSC) is often preferred analytical method for 222Rn measurements in waters because it allows multiple-sample automatic analysis. LSC method implies mixing of water samples with organic scintillation cocktail, which triggers radon diffusion from the aqueous into organic phase for which it has a much greater affinity, eliminating possibility of radon emanation in that manner. Two direct LSC methods that assume different sample composition have been presented, optimized and evaluated in this study. One-phase method assumed direct mixing of 10 ml sample with 10 ml of emulsifying cocktail (Ultima Gold AB scintillation cocktail is used). Two-phase method involved usage of water-immiscible cocktails (in this study High Efficiency Mineral Oil Scintillator, Opti-Fluor O and Ultima Gold F are used). Calibration samples were prepared with aqueous 226Ra standard in glass 20 ml vials and counted on ultra-low background spectrometer Quantulus 1220TM equipped with PSA (Pulse Shape Analysis) circuit which discriminates alpha/beta spectra. Since calibration procedure is carried out with 226Ra standard, which has both alpha and beta progenies, it is clear that PSA discriminator has vital importance in order to provide reliable and precise spectra separation. Consequentially, calibration procedure was done through investigation of PSA discriminator level influence on 222Rn efficiency detection, using 226Ra calibration standard in wide range of activity concentrations. Evaluation of presented methods was based on obtained efficiency detections and achieved Minimal Detectable Activity (MDA). Comparison of presented methods, accuracy and precision as well as different scintillation cocktail’s performance was considered from results of measurements of 226Ra spiked water samples with known activity and environmental samples.

Keywords: 222Rn in water, Quantulus1220TM, scintillation cocktail, PSA parameter

Procedia PDF Downloads 170

Authors: Mohammad Saleem, Neeta Kumar, Anita Sharma, Sazina Muzammil

Abstract:

It is observed that some of the dental students in our setting take less interest in medical subjects. Various teaching methods are focus of research interest currently and being tried to generate interest among students. An approach of interactive integrated tutorial was used to assess its feasibility in teaching medical subjects to dental undergraduates. The aim was to generate interest and promote active self-learning among students. The objectives were to (1) introduce the integrated interactive learning method through two departments, (2) get feedback from the students and faculty on feasibility and effectiveness of this method. Second-year students in Bachelor of Dental Surgery course were divided into two groups. Each group was asked to study physiology and pathology of a common and important condition (anemia and hypertension) in a week’s time. During the tutorial, students asked questions on physiology and pathology of that condition from each other in the presence of teachers of both physiology and pathology departments. The teachers acted only as facilitators. After the session, the feedback from students and faculty on this alternative learning method was obtained. Results: Majority of the students felt that this method of learning is enjoyable, helped to develop reasoning skills and ability to correlate and integrate the knowledge from two related fields. Majority of the students felt that this kind of learning led to better understanding of the topic and motivated them towards deep learning. Teachers observed that the study promoted interdepartmental cross-discipline collaboration and better students’ linkages. Conclusion: Interactive integrated tutorial is effective in motivating dental students for better and deep learning of medical subjects.

Keywords: active learning, education, integrated, interactive, self-learning, tutorials

Procedia PDF Downloads 283

Authors: H. Idmoussi, L. Somoue, O. Ettahiri, A. Makaoui, S. Charib, A. Agouzouk, A. Ben Mhamed, K. Hilmi, A. Errhif

Abstract:

The study on the composition, abundance, and distribution of phytoplankton was conducted along the Moroccan coast of the Mediterranean Sea (Saiidia - Three Forks Cape) in April 2018. Samples were collected at thirteen stations using Niskin bottles within two layers (surface and deep layers). The identification and enumeration of phytoplankton were carried out according to the Utermöhl method (1958). A total number of 54 phytoplankton species were identified over the entire survey area. Thirty-six species could be found both in the surface and the deep layers while eleven species were observed only in the surface layer and seven in the deep layer. The phytoplankton throughout the study area was dominated by diatoms represented mainly by Nitzschia sp., Pseudonitzschia sp., Chaetoceros sp., Cylindrotheca closterium, Leptocylindrus minimus, Leptocylindrus danicus, Dactyliosolen fragilissimus. Dinoflagellates were dominated by Gymnodinium sp., Scrippsiella sp., Gyrodinium spirale, Noctulica sp, Prorocentrum micans. Euglenophyceae, Silicoflagellates and Raphidophyceae were present in low numbers. Most of the phytoplankton were concentrated in the surface layer, particularly towards the Three Forks Cape (25200 cells·l⁻¹). Shannon species diversity (ranging from 2 and 4 Bits) and evenness index (broadly > 0.7) suggested that phytoplankton community is generally diversified and structured in the studied area.

Keywords: abundance, diversity, Mediterranean Sea, phytoplankton

Procedia PDF Downloads 129

Authors: Ammarah Irum, Muhammad Ali Tahir

Abstract:

Document-level sentiment analysis in Urdu is a challenging Natural Language Processing (NLP) task due to the difficulty of working with lengthy texts in a language with constrained resources. Deep learning models, which are complex neural network architectures, are well-suited to text-based applications in addition to data formats like audio, image, and video. To investigate the potential of deep learning for Urdu sentiment analysis, we implemented five different deep learning models, including Bidirectional Long Short Term Memory (BiLSTM), Convolutional Neural Network (CNN), Convolutional Neural Network with Bidirectional Long Short Term Memory (CNN-BiLSTM), and Bidirectional Encoder Representation from Transformer (BERT). In this study, we developed a hybrid deep learning model called BiLSTM-Single Layer Multi Filter Convolutional Neural Network (BiLSTM-SLMFCNN) by fusing BiLSTM and CNN architecture. The proposed and baseline techniques are applied on Urdu Customer Support data set and IMDB Urdu movie review data set by using pre-trained Urdu word embedding that are suitable for sentiment analysis at the document level. Results of these techniques are evaluated and our proposed model outperforms all other deep learning techniques for Urdu sentiment analysis. BiLSTM-SLMFCNN outperformed the baseline deep learning models and achieved 83%, 79%, 83% and 94% accuracy on small, medium and large sized IMDB Urdu movie review data set and Urdu Customer Support data set respectively.

Keywords: urdu sentiment analysis, deep learning, natural language processing, opinion mining, low-resource language

Procedia PDF Downloads 36

Authors: Arian Hosseini, Mahmudul Hasan

Abstract:

To address the increasing need for efficient and accurate content moderation, we propose an efficient and lightweight deep classification ensemble structure. Our approach is based on a combination of simple visual features, designed for high-accuracy classification of violent content with low false positives. Our ensemble architecture utilizes a set of lightweight models with narrowed-down color features, and we apply it to both images and videos. We evaluated our approach using a large dataset of explosion and blast contents and compared its performance to popular deep learning models such as ResNet-50. Our evaluation results demonstrate significant improvements in prediction accuracy, while benefiting from 7.64x faster inference and lower computation cost. While our approach is tailored to explosion detection, it can be applied to other similar content moderation and violence detection use cases as well. Based on our experiments, we propose a "think small, think many" philosophy in classification scenarios. We argue that transforming a single, large, monolithic deep model into a verification-based step model ensemble of multiple small, simple, and lightweight models with narrowed-down visual features can possibly lead to predictions with higher accuracy.

Keywords: deep classification, content moderation, ensemble learning, explosion detection, video processing

Procedia PDF Downloads 21

Authors: Seyed Abolhasan Naeini, M. Mortezaee

Abstract:

Various factors such as the method of installation, the pile type, the pile material and the pile shape, can affect the final bearing capacity of a pile executed in the soil; among them, the method of installation is of special importance. The physical modeling is among the best options in the laboratory study of the piles behavior. Therefore, the current paper first presents and reviews the frustum confining vesel (FCV) as a suitable tool for physical modeling of deep foundations. Then, by describing the loading tests of two open-ended and closed-end steel piles, each of which has been performed in two methods, “with displacement" and "without displacement", the effect of end conditions and installation method on the final bearing capacity of the pile is investigated. The soil used in the current paper is silty sand of Firoozkooh. The results of the experiments show that in general the without displacement installation method has a larger bearing capacity in both piles, and in a specific method of installation the closed ended pile shows a slightly higher bearing capacity.

Keywords: physical modeling, frustum confining vessel, pile, bearing capacity, installation method

Procedia PDF Downloads 107

Authors: S. K. Verma, S. L. Sinha, D. K. Chandraker

Abstract:

The Advanced Heavy Water Reactor (AHWR) is a vertical pressure tube type, heavy water moderated and boiling light water cooled natural circulation based reactor. The fuel bundle of AHWR contains 54 fuel rods arranged in three concentric rings of 12, 18 and 24 fuel rods. This fuel bundle is divided into a number of imaginary interacting flow passage called subchannels. Single phase flow condition exists in reactor rod bundle during startup condition and up to certain length of rod bundle when it is operating at full power. Prediction of the thermal margin of the reactor during startup condition has necessitated the determination of the turbulent mixing rate of coolant amongst these subchannels. Thus, it is vital to evaluate turbulent mixing between subchannels of AHWR rod bundle. With the remarkable progress in the computer processing power, the computational fluid dynamics (CFD) methodology can be useful for investigating the thermal–hydraulic characteristics phenomena in the nuclear fuel assembly. The present report covers the results of simulation of pressure drop, velocity variation and turbulence intensity on single rod bundle with 54 rods in circular arrays. In this investigation, 54-rod assemblies are simulated with ANSYS Fluent 15 using steady simulations with an ANSYS Workbench meshing. The simulations have been carried out with water for Reynolds number 9861.83. The rod bundle has a mean flow area of 4853.0584 mm2 in the bare region with the hydraulic diameter of 8.105 mm. In present investigation, a benchmark k-ε model has been used as a turbulence model and the symmetry condition is set as boundary conditions. Simulation are carried out to determine the turbulent mixing rate in the simulated subchannels of the reactor. The size of rod and the pitch in the test has been same as that of actual rod bundle in the prototype. Water has been used as the working fluid and the turbulent mixing tests have been carried out at atmospheric condition without heat addition. The mean velocity in the subchannel has been varied from 0-1.2 m/s. The flow conditions are found to be closer to the actual reactor condition.

Keywords: AHWR, CFD, single-phase turbulent mixing rate, thermal–hydraulic

Procedia PDF Downloads 300

Authors: Li Yu, Chenlu Jiao, Hongrun Xin, Yan Wang, Kaiyang Wang

Abstract:

In order to study the impact of various factors on the housing price, we propose to build different prediction models based on deep learning to determine the existing data of the real estate in order to more accurately predict the housing price or its changing trend in the future. Considering that the factors which affect the housing price vary widely, the proposed prediction models include two categories. The first one is based on multiple characteristic factors of the real estate. We built Convolution Neural Network (CNN) prediction model and Long Short-Term Memory (LSTM) neural network prediction model based on deep learning, and logical regression model was implemented to make a comparison between these three models. Another prediction model is time series model. Based on deep learning, we proposed an LSTM-1 model purely regard to time series, then implementing and comparing the LSTM model and the Auto-Regressive and Moving Average (ARMA) model. In this paper, comprehensive study of the second-hand housing price in Beijing has been conducted from three aspects: crawling and analyzing, housing price predicting, and the result comparing. Ultimately the best model program was produced, which is of great significance to evaluation and prediction of the housing price in the real estate industry.

Keywords: deep learning, convolutional neural network, LSTM, housing prediction

Procedia PDF Downloads 275

Authors: Ahmed Hammed, Wady Naanaa

Abstract:

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

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

Procedia PDF Downloads 298

Authors: Kishore Kumar R., Kaustav Sengupta, Shalini Sood Sehgal, Poornima Santhanam

Abstract:

Fashion is a human expression that is constantly changing. One of the prime factors that consistently influences fashion is the change in colour preferences. The role of colour in our everyday lives is very significant. It subconsciously explains a lot about one’s mindset and mood. Analyzing the colours by extracting them from the outfit images is a critical study to examine the individual’s/consumer behaviour. Several research works have been carried out on extracting colours from images, but to the best of our knowledge, there were no studies that extract colours to specific apparel and identify colour patterns geographically. This paper proposes a framework for accurately extracting colours from T-shirt images and predicting dominant colours geographically. The proposed method consists of two stages: first, a U-Net deep learning model is adopted to segment the T-shirts from the images. Second, the colours are extracted only from the T-shirt segments. The proposed method employs the iMaterialist (Fashion) 2019 dataset for the semantic segmentation task. The proposed framework also includes a mechanism for gathering data and analyzing India’s general colour preferences. From this research, it was observed that black and grey are the dominant colour in different regions of India. The proposed method can be adapted to study fashion’s evolving colour preferences.

Keywords: colour analysis in t-shirts, convolutional neural network, encoder-decoder, k-means clustering, semantic segmentation, U-Net model

Procedia PDF Downloads 79

Authors: Lidia Dzierzbicka-Glowacka, Anna Lemieszek, Mariusz Figiela

Abstract:

In 2010-2011, the research on zooplankton was conducted in the southern part of the Baltic Sea to determine seasonal variability in changes occurring throughout the zooplankton in 2010 and 2011, both in the region of Gdańsk Deep, and in the western part of Gdańsk Bay. The research in the sea showed that the taxonomic composition of holoplankton in the southern part of the Baltic Sea was similar to that recorded in this region for many years. The maximum values of abundance and biomass of zooplankton both in the Deep and the Bay of Gdańsk were observed in the summer season. Copepoda dominated in the composition of zooplankton for almost the entire study period, while rotifers occurred in larger numbers only in the summer 2010 in the Gdańsk Deep as well as in May and July 2010 in the western part of Gdańsk Bay, and meroplankton – in April 2011.

Keywords: Baltic Sea, composition, Gdańsk Bay, zooplankton

Procedia PDF Downloads 397

Authors: Harish Kumar Sharma, Garima Sengar

Abstract:

Rice bran oil is considered comparatively nutritionally superior than different fats/oils. Therefore, model blends prepared from pure rice bran oil (RBO) and sunflower oil (SFO) were explored for changes in the different physicochemical parameters. Repeated deep fat frying process was carried out by using dried potato in order to study the thermal behaviour of pure rice bran oil, sunflower oil and their model blends. Pure rice bran oil and sunflower oil had shown good thermal stability during the repeated deep fat frying cycles. Although, the model blends constituting 60% RBO + 40% SFO showed better suitability during repeated deep fat frying than the remaining blended oils. The quantification of pure rice bran oil in the blended oils, physically refined rice bran oil (PRBO): SnF (sunflower oil) was carried by different methods. The study revealed that regression equations based on the oryzanol content, palmitic acid composition and iodine value can be used for the quantification. The rice bran oil can easily be quantified in the blended oils based on the oryzanol content by HPLC even at 1% level. The palmitic acid content in blended oils can also be used as an indicator to quantify rice bran oil at or above 20% level in blended oils whereas the method based on ultrasonic velocity, acoustic impedance and relative association showed initial promise in the quantification.

Keywords: rice bran oil, sunflower oil, frying, quantification

Procedia PDF Downloads 277

Authors: Taha Benarbia

Abstract:

The advent of automated and connected vehicles has revolutionized the transportation industry, presenting new opportunities for enhancing the efficiency, safety, and sustainability of our transportation networks. This paper explores the integration of automated and connected vehicles into a smart transportation framework, leveraging the power of deep learning techniques to optimize the overall network performance. The first aspect addressed in this paper is the deployment of automated vehicles (AVs) within the transportation system. AVs offer numerous advantages, such as reduced congestion, improved fuel efficiency, and increased safety through advanced sensing and decisionmaking capabilities. The paper delves into the technical aspects of AVs, including their perception, planning, and control systems, highlighting the role of deep learning algorithms in enabling intelligent and reliable AV operations. Furthermore, the paper investigates the potential of connected vehicles (CVs) in creating a seamless communication network between vehicles, infrastructure, and traffic management systems. By harnessing real-time data exchange, CVs enable proactive traffic management, adaptive signal control, and effective route planning. Deep learning techniques play a pivotal role in extracting meaningful insights from the vast amount of data generated by CVs, empowering transportation authorities to make informed decisions for optimizing network performance. The integration of deep learning with automated and connected vehicles paves the way for advanced transportation network optimization. Deep learning algorithms can analyze complex transportation data, including traffic patterns, demand forecasting, and dynamic congestion scenarios, to optimize routing, reduce travel times, and enhance overall system efficiency. The paper presents case studies and simulations demonstrating the effectiveness of deep learning-based approaches in achieving significant improvements in network performance metrics

Keywords: automated vehicles, connected vehicles, deep learning, smart transportation network

Procedia PDF Downloads 41

Authors: Muhammad Zubair Khan, Yugyung Lee

Abstract:

Deep learning has recently achieved enormous response in semantic image segmentation. The previously developed U-Net inspired architectures operate with continuous stride and pooling operations, leading to spatial data loss. Also, the methods lack establishing long-term pixels connection to preserve context knowledge and reduce spatial loss in prediction. This article developed encoder-decoder architecture with bi-directional LSTM embedded in long skip-connections and densely connected convolution blocks. The network non-linearly combines the feature maps across encoder-decoder paths for finding dependency and correlation between image pixels. Additionally, the densely connected convolutional blocks are kept in the final encoding layer to reuse features and prevent redundant data sharing. The method applied batch-normalization for reducing internal covariate shift in data distributions. The empirical evidence shows a promising response to our method compared with other semantic segmentation techniques.

Keywords: deep learning, semantic segmentation, image analysis, pixels connection, convolution neural network

Procedia PDF Downloads 76

Authors: Leah Lee

Abstract:

This paper examines the correlation between deep learning models and emotions with noises to see whether or not noises mask emotions. The deep learning models used are plain convolutional neural networks (CNN), auto-encoder, long short-term memory (LSTM), and Visual Geometry Group-16 (VGG-16). Emotion datasets used are Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS), Crowd-sourced Emotional Multimodal Actors Dataset (CREMA-D), Toronto Emotional Speech Set (TESS), and Surrey Audio-Visual Expressed Emotion (SAVEE). To make it four times bigger, audio set files, stretch, and pitch augmentations are utilized. From the augmented datasets, five different features are extracted for inputs of the models. There are eight different emotions to be classified. Noise variations are white noise, dog barking, and cough sounds. The variation in the signal-to-noise ratio (SNR) is 0, 20, and 40. In summation, per a deep learning model, nine different sets with noise and SNR variations and just augmented audio files without any noises will be used in the experiment. To compare the results of the deep learning models, the accuracy and receiver operating characteristic (ROC) are checked.

Keywords: auto-encoder, convolutional neural networks, long short-term memory, speech emotion recognition, visual geometry group-16

Procedia PDF Downloads 38