Search results for: fused deep representations

Authors: Ajay Kumar Choubey, Geeta Agnihotri, C. Sasikumar, Rashmi Dwivedi

Abstract:

Deep-drawing operations are performed widely in industrial applications. It is very important for efficiency to achieve parts with no or minimum defects. Deep drawn parts are used in high performance, high strength and high reliability applications where tension, stress, load and human safety are critical considerations. Wrinkling is a kind of defect caused by stresses in the flange part of the blank during metal forming operations. To avoid wrinkling appropriate blank-holder pressure/force or drawbead can be applied. Now-a-day computer simulation plays a vital role in the field of manufacturing process. So computer simulation of manufacturing has much advantage over previous conventional process i.e. mass production, good quality of product, fast working etc. In this study, a two dimensional elasto-plastic Finite Element (F.E.) model for Mild Steel material blank has been developed to study the behavior of the flange wrinkling and deep drawing parameters under different Blank-Holder Pressure (B.H.P.). For this, commercially available Finite Element software ANSYS 14 has been used in this study. Simulation results are critically studied and salient conclusions have been drawn.

Keywords: ANSYS, deep drawing, BHP, finite element simulation, wrinkling

Procedia PDF Downloads 449

Authors: Bandhan Dey, Muhsina Bintoon Yiasha, Gulam Sulaman Choudhury

Abstract:

Chest disease is one of the most problematic ailments in our regular life. There are many known chest diseases out there. Diagnosing them correctly plays a vital role in the process of treatment. There are many methods available explicitly developed for different chest diseases. But the most common approach for diagnosing these diseases is through X-ray. In this paper, we proposed a multi-classification deep learning model for diagnosing COVID-19, lung cancer, pneumonia, tuberculosis, and atelectasis from chest X-rays. In the present work, we used the transfer learning method for better accuracy and fast training phase. The performance of three architectures is considered: InceptionV3, VGG-16, and VGG-19. We evaluated these deep learning architectures using public digital chest x-ray datasets with six classes (i.e., COVID-19, lung cancer, pneumonia, tuberculosis, atelectasis, and normal). The experiments are conducted on six-classification, and we found that VGG16 outperforms other proposed models with an accuracy of 95%.

Keywords: deep learning, image classification, X-ray images, Tensorflow, Keras, chest diseases, convolutional neural networks, multi-classification

Procedia PDF Downloads 92

Authors: Hesheng Wang, Haoyu Wang, Chungang Zhuang

Abstract:

Estimating the 6D pose of objects is a core step for robot bin-picking tasks. The problem is that various objects are usually randomly stacked with heavy occlusion in real applications. In this work, we propose a method to regress 6D poses by predicting three points for each object in the 3D point cloud through deep learning. To solve the ambiguity of symmetric pose, we propose a labeling method to help the network converge better. Based on the predicted pose, an iterative method is employed for pose optimization. In real-world experiments, our method outperforms the classical approach in both precision and recall.

Keywords: pose estimation, deep learning, point cloud, bin-picking, 3D computer vision

Procedia PDF Downloads 161

Authors: Soofiyan Atar, Adil Shaikh, Sahil Rajpurkar, Pragnesh Bhalala, Aniket Desai, Irfan Siddavatam

Abstract:

Deep reinforcement learning (deep RL) algorithms leverage the symbolic power of complex controllers by automating it by mapping sensory inputs to low-level actions. Deep RL eliminates the complex robot dynamics with minimal engineering. Deep RL provides high-risk involvement by directly implementing it in real-world scenarios and also high sensitivity towards hyperparameters. Tuning of hyperparameters on a pneumatic quadruped robot becomes very expensive through trial-and-error learning. This paper presents an automated learning control for a pneumatic quadruped robot using sample efficient deep Q learning, enabling minimal tuning and very few trials to learn the neural network. Long training hours may degrade the pneumatic cylinder due to jerk actions originated through stochastic weights. We applied this method to the pneumatic quadruped robot, which resulted in a hopping gait. In our process, we eliminated the use of a simulator and acquired a stable gait. This approach evolves so that the resultant gait matures more sturdy towards any stochastic changes in the environment. We further show that our algorithm performed very well as compared to programmed gait using robot dynamics.

Keywords: model-based reinforcement learning, gait stability, supervised learning, pneumatic quadruped

Procedia PDF Downloads 316

Authors: Ahmed Krobba, Meriem Touzene, Mohamed Debeyche

Abstract:

The wireless communications system (5G) will provide more diverse applications and higher quality services for users compared to the long-term evolution 4G (LTE). 5G uses a higher carrier frequency, which suffers from information loss in 5G coverage. Most 5G users often cannot obtain high-quality communications due to transmission channel noise and channel complexity. Physical Uplink Control Channel (PUCCH-NR: Physical Uplink Control Channel New Radio) plays a crucial role in 5G NR telecommunication technology, which is mainly used to transmit link control information uplink (UCI: Uplink Control Information. This study based of evaluating the performance of channel physical uplink control PUCCH-NR under low Signal-to-Noise Ratios with various antenna numbers reception. We propose the artificial intelligence approach based on deep neural networks (Deep Learning) to estimate the PUCCH-NR channel in comparison with this approach with different conventional methods such as least-square (LS) and minimum-mean-square-error (MMSE). To evaluate the channel performance we use the block error rate (BLER) as an evaluation criterion of the communication system. The results show that the deep neural networks method gives best performance compared with MMSE and LS

Keywords: 5G network, uplink (Uplink), PUCCH channel, NR-PUCCH channel, deep learning

Procedia PDF Downloads 82

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 153

Authors: Timothy Mossman

Abstract:

The number of adolescent children accompanying their immigrant parents to Canada has steadily increased since the 1990s. Much of the applied linguistics literature on these so-called ‘Generation 1.5’ youth has focused on their deficiencies as academic writers in US Rhetoric and Composition and ESL contexts in higher education and the stigma of ESL in US K-12 contexts. However, the literature on Generation 1.5 students and identity in Canadian higher education is limited. This qualitative study investigates the processes of identity construction of three Generation 1.5 students studying at a university in Metro Vancouver to find out what types of identities and representations of self and other they make relevant, the meanings they attribute to their identities, and what motivates them to construct these identities. The study analyzes the accounts and experiences of the participants in interviews, focus groups, and texts and as ‘culture-in-action,’ positing that they constructed identities as social categories associated with the languages and social practices of their countries of birth, in liminal spaces among a continuum between Canada and their countries of birth, and a spectrum of related cultural representations. Ideas and beliefs associated with broader ‘macro’ social structures in Canadian society related to language, culture, legitimacy, immigration, power, distinction, and racism were shown to be transcended in and through their representations of themselves and others. Data suggest that moving to Canada caused participants to experience discontinuities between their cultures, languages, and social practices, and in some cases a conflicting sense of self. The study brings implications for finding ways to understand the complexity of immigrant students, avoid reifying and generalizing about them, and not see them as stuck-in-between or lacking.

Keywords: culture-in-action, generation 1.5, identity, membership categorization analysis

Procedia PDF Downloads 148

Authors: Amal Khalifa, Nicolas Vana Santos

Abstract:

Steganography has been known for centuries as an efficient approach for covert communication. Due to its popularity and ease of access, image steganography has attracted researchers to find secure techniques for hiding information within an innocent looking cover image. In this research, we propose a novel deep-learning approach to digital image steganography. The proposed method, DeepWaveletFusion, uses convolutional neural networks (CNN) to hide a secret image into a cover image of the same size. Two CNNs are trained back-to-back to merge the Discrete Wavelet Transform (DWT) of both colored images and eventually be able to blindly extract the hidden image. Based on two different image similarity metrics, a weighted gain function is used to guide the learning process and maximize the quality of the retrieved secret image and yet maintaining acceptable imperceptibility. Experimental results verified the high recoverability of DeepWaveletFusion which outperformed similar deep-learning-based methods.

Keywords: deep learning, steganography, image, discrete wavelet transform, fusion

Procedia PDF Downloads 90

Authors: Mohd Javaid, Shahbaz Khan, Abid Haleem

Abstract:

Purpose: Large numbers of 3D printing technologies are now available for sophisticated applications in different fields. Additive manufacturing has established its dominance in design, development, and customisation of the product. In the era of developing technologies, there is a need to identify the appropriate technology for different application. In order to fulfil this need, two widely used printing technologies such as Fused Deposition Modeling (FDM), and Binding-Jet 3D Printing are compared for effective utilisation in the current scenario for different applications. Methodology: Systematic literature review conducted for both technologies with applications and associated factors enabling for the same. Appropriate MCDM tool is used to compare critical factors for both the technologies. Findings: Both technologies have their potential and capabilities to provide better direction to the industry. Additionally, this paper is helpful to develop a decision support system for the proper selection of technologies according to their continuum of applications and associated research and development capability. The vital issue is raw materials, and research-based material development is key to the sustainability of the developed technologies. FDM is a low-cost technology which provides high strength product as compared to binding jet technology. Researcher and companies can take benefits of this study to achieve the required applications in lesser resources. Limitations: Study has undertaken the comparison with the opinion of experts, which may not always be free from bias, and some own limitations of each technology. Originality: Comparison between these technologies will help to identify best-suited technology as per the customer requirements. It also provides development in this different field as per their extensive capability where these technologies can be successfully adopted. Conclusion: FDM and binding jet technology play an active role in industrial development. These help to assist the customisation and production of personalised parts cost-effectively. So, there is a need to understand how these technologies can provide these developments rapidly. These technologies help in easy changes or in making revised versions of the product, which is not easily possible in the conventional manufacturing system. High machine cost, the requirement of skilled human resources, low surface finish, and mechanical strength of product and material changing option is the main limitation of this technology. However, these limitations vary from technology to technology. In the future, these technologies are to be commercially viable for efficient usage in direct manufacturing of varied parts.

Keywords: 3D printing, comparison, fused deposition modeling, FDM, binding jet technology

Procedia PDF Downloads 105

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 86

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 662

Authors: Barbara Klimek

Abstract:

Wolves are one of the most misrepresented species in literature and the media. They’re often portrayed as vicious, man-eating beasts whose main life goal is to hunt and kill people. Many movie directors use wolves as their main characters in different types of films, especially horror, thriller and science fiction movies to create gore and fear. This, in turn, results in people being afraid of wolves and wanting to destroy them. Such cultural creations caused wolves being stalked, abused and killed by people and in many areas they were completely destroyed. This paper analyzes the representations of wolves in the chosen films in the four main portrayed aspects: 1. the overall picture – true versus false, positive versus negative, based on stereotypes or realistic, displaying wolf behavior typical of the species or fake 2. subjectivity – how humans treat and talk about the animals – as subjects or as objects 3. animal welfare – how humans treat wolves and nature, are the human – animal relations positive and appropriate or negative and abusive 4. empathy – are human characters shown to co-feel the suffering with the wolves, do they display signs of empathy towards the animals, do the animals empathize with humans? The detailed analysis of the text and pictures presented in the chosen films concludes that wolves are especially misrepresented in the movies. Their behavior is shown as fake and negative, based on stereotypes and myths, the human – animal relations are shown mainly as negative where people fear the animals and hunt them and wolves stalk, follow, attack and kill humans. It shows that people do not understand the needs of these animals and are unable to show empathy towards them. The article will discuss the above-mentioned study results in detail and will present many examples. Animal representations in cultural creations, including film have a great impact on how people treat particular species of animals. The media shape people’s attitudes, what in turn results in people either respecting and protecting the animals or fearing, disliking and destroying the particular species.

Keywords: film, movies, representations, wolves

Procedia PDF Downloads 213

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 101

Authors: Eric Bonetto, Anthony Piermatteo, Fabien Girandola, Gregory Lo Monaco

Abstract:

The present contribution focuses on the effect of the structure of social representations on group identification. A social representation (SR) is defined as an organized and structured set of cognitions, produced and shared by members of a same group about a same social object. Within this framework, the central core theory establishes a structural distinction between central cognitions – or 'core' – and peripheral ones: the former are theoretically considered as more connected than the later to group members’ social identity and may play a greater role in SRs’ ability to allow group identification by means of a common vision of the object of representation. Indeed, the central core provides a reference point for the in-group as it constitutes a consensual vision that gives meaning to a social object particularly important to individuals and to the group. However, while numerous contributions clearly refer to the underlying role of SRs in group identification, there are only few empirical evidences of this aspect. Thus, we hypothesize an effect of the structure of SRs on group identification. More precisely, central cognitions (vs. peripheral ones) will lead to a stronger group identification. In addition, we hypothesize that the refutation of a cognition will lead to a stronger group identification than its activation. The SR mobilized here is that of 'studying' among a population of first-year undergraduate psychology students. Thus, a pretest (N = 82), using an Attribute-Challenge Technique, was designed in order to identify the central and the peripheral cognitions to use in the primings of our main study. The results of this pretest are in line with previous studies. Then, the main study (online; N = 184), using a social priming methodology, was based on a 2 (Structural status of the cognitions belonging to the prime: central vs. peripheral) x 2 (Type of prime: activation vs. refutation) experimental design in order to test our hypotheses. Results revealed, as expected, the main effect of the structure of the SR on group identification. Indeed, central cognitions trigger a higher level of identification than the peripheral ones. However, we observe neither effect of the type of prime, nor interaction effect. These results experimentally demonstrate for the first time the effect of the structure of SRs on group identification and indicate that central cognitions are more connected than peripheral ones to group members’ social identity. These results will be discussed considering the importance of understanding identity as a function of SRs and on their ability to potentially solve the lack of consideration of the definition of the group in Social Representations Theory.

Keywords: group identification, social identity, social representations, structural approach

Procedia PDF Downloads 191

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

Abstract:

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

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

Procedia PDF Downloads 99

Authors: 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 420

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 148

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 79

Authors: Waranya Imprasittichai, Patsarawadee Paojinda, Sudaratana R. Krungkrai, Nirianne Marie Q. Palacpac, Toshihiro Horii, Jerapan Krungkrai

Abstract:

Fusion of the last two enzymes in the pyrimidine biosynthetic pathway in the inversed order by having COOH-terminal orotate phosphoribosyltransferase (OPRT) and NH2-terminal orotidine 5'-monophosphate decarboxylase (OMPDC), as OMPDC-OPRT, are described in many organisms. In this study, we constructed gene fusions of Plasmodium falciparum OMPDC-OPRT (1,836 bp) in pTrcHisA vector and expressed as an 6xHis-tag bifunctional protein in three Escherichia coli strains (BL21, Rosetta, TOP10) at 18 °C, 25 °C and 37 °C. The recombinant bifunctional protein was partially purified by Ni-Nitrilotriacetic acid-affinity chromatography. Specific activities of OPRT and OMPDC domains in the bifunctional enzyme expressed in E. coli TOP10 cells were approximately 3-4-fold higher than those in BL21 cells. There were no enzymatic activities when the construct vector expressed in Rosetta cells. Maximal expression of the fused gene was observed at 18 °C and the bifunctional enzyme had specific activities of OPRT and OMPDC domains in a ratio of 1:2. These results provide greater yields and better catalytic activities of the bifunctional OMPDC-OPRT enzyme for further purification and kinetic study.

Keywords: bifunctional enzyme, orotate phosphoribosyltransferase, orotidine 5'-monophosphate decarboxylase, plasmodium falciparum

Procedia PDF Downloads 354

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 72

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 54

Authors: Kaustubh Chakradeo, Michael Delves, Sofya Titarenko

Abstract:

Malaria is a serious disease which affects hundreds of millions of people around the world, each year. If not treated in time, it can be fatal. Despite recent developments in malaria diagnostics, the microscopy method to detect malaria remains the most common. Unfortunately, the accuracy of microscopic diagnostics is dependent on the skill of the microscopist and limits the throughput of malaria diagnosis. With the development of Artificial Intelligence tools and Deep Learning techniques in particular, it is possible to lower the cost, while achieving an overall higher accuracy. In this paper, we present a VGG-based model and compare it with previously developed models for identifying infected cells. Our model surpasses most previously developed models in a range of the accuracy metrics. The model has an advantage of being constructed from a relatively small number of layers. This reduces the computer resources and computational time. Moreover, we test our model on two types of datasets and argue that the currently developed deep-learning-based methods cannot efficiently distinguish between infected and contaminated cells. A more precise study of suspicious regions is required.

Keywords: convolution neural network, deep learning, malaria, thin blood smears

Procedia PDF Downloads 130

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 306

Authors: Dajana Gašo-Sokač, Valentina Bušić

Abstract:

Deep eutectic solvents (DES) are liquids composed of two or three safe, inexpensive components, often interconnected by noncovalent hydrogen bonds which produce eutectic mixture whose melting point is lower than that of each component. No data in literature have been found on the quaternization reaction in DES. The use of DES have several advantages: they are environmentally benign and biodegradable, easy for purification and simple for preparation. An environmentally sustainable method for preparing quaternary salts of izonicotinamide and substituted 2-bromoacetophenones was demonstrated here using choline chloride-based DES. The quaternization reaction was carried out by three synthetic approaches: conventional method, microwave and ultrasonic irradiation. We showed that the highest yields were obtained by the microwave method.

Keywords: deep eutectic solvents, izonicotinamide salts, microwave synthesis, ultrasonic irradiation

Procedia PDF Downloads 130

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 433

Authors: Khitem Amiri, Mohamed Farah

Abstract:

Image classification is a challenging task and is gaining lots of interest since it helps us to understand the content of images. Recently Deep Learning (DL) based methods gave very interesting results on several benchmarks. For Hyperspectral images (HSI), the application of DL techniques is still challenging due to the scarcity of labeled data and to the curse of dimensionality. Among other approaches, Deep Belief Network (DBN) based approaches gave a fair classification accuracy. In this paper, we address the problem of the curse of dimensionality by reducing the number of bands and replacing the HSI channels by the channels representing radiometric indices. Therefore, instead of using all the HSI bands, we compute the radiometric indices such as NDVI (Normalized Difference Vegetation Index), NDWI (Normalized Difference Water Index), etc, and we use the combination of these indices as input for the Deep Belief Network (DBN) based classification model. Thus, we keep almost all the pertinent spectral information while reducing considerably the size of the image. In order to test our image representation, we applied our method on several HSI datasets including the Indian pines dataset, Jasper Ridge data and it gave comparable results to the state of the art methods while reducing considerably the time of training and testing.

Keywords: hyperspectral images, deep belief network, radiometric indices, image classification

Procedia PDF Downloads 280

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 78

Authors: Srinidhi. A, Naveed Ahmed, Twinkle Hareendran, Vriksha Prakash

Abstract:

This work reviews some of the advanced image processing techniques for deep learning applications. Object detection by template matching, image denoising, edge detection, and super-resolution modelling are but a few of the tasks. The paper looks in into great detail, given that such tasks are crucial preprocessing steps that increase the quality and usability of image datasets in subsequent deep learning tasks. We review some of the methods for the assessment of image quality, more specifically sharpness, which is crucial to ensure a robust performance of models. Further, we will discuss the development of deep learning models specific to facial emotion detection, age classification, and gender classification, which essentially includes the preprocessing techniques interrelated with model performance. Conclusions from this study pinpoint the best practices in the preparation of image datasets, targeting the best trade-off between computational efficiency and retaining important image features critical for effective training of deep learning models.

Keywords: image processing, machine learning applications, template matching, emotion detection

Procedia PDF Downloads 13

Authors: Abe D. Desta

Abstract:

This study suggests a deep learning-based method for identifying and following moving objects in surveillance video. The proposed method uses a fast regional convolution neural network (F-RCNN) trained on a substantial dataset of vehicle images to first detect vehicles. A Kalman filter and a data association technique based on a Hungarian algorithm are then used to monitor the observed vehicles throughout time. However, in general, F-RCNN algorithms have been shown to be effective in achieving high detection accuracy and robustness in this research study. For example, in one study The study has shown that the vehicle detection and tracking, the system was able to achieve an accuracy of 97.4%. In this study, the F-RCNN algorithm was compared to other popular object detection algorithms and was found to outperform them in terms of both detection accuracy and speed. The presented system, which has application potential in actual surveillance systems, shows the usefulness of deep learning approaches in vehicle detection and tracking.

Keywords: artificial intelligence, computer vision, deep learning, fast-regional convolutional neural networks, feature extraction, vehicle tracking

Procedia PDF Downloads 126

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 75