Search results for: deep graphical model

Authors: Maulik Parmar, Sumeet Sandhu

Abstract:

The online fashion industry experiences high product return rates. Many returns are because of size/fit mismatches -the size scale on labels can vary across brands, the size parameters may not capture all fit measurements, or the product may have manufacturing defects. Warehouse quality check of garment sizes can be semi-automated to improve speed and accuracy. This paper presents an approach for automatically measuring garment sizes from a single image of the garment -using Deep Learning to learn garment keypoints. The paper focuses on the waist size measurement of jeans and can be easily extended to other garment types and measurements. Experimental results show that this approach can greatly improve the speed and accuracy of today’s manual measurement process.

Keywords: convolutional neural networks, deep learning, distortion, garment measurements, image warping, keypoints

Procedia PDF Downloads 308

Authors: Vidhu Mitha Goutham, Ruma Mukherjee

Abstract:

The low availability of well-trained, unlimited, dynamic-access models for specific languages makes it hard for corporate users to adopt quick translation techniques and incorporate them into product solutions. As translation tasks increasingly require a dynamic sequence learning curve; stable, cost-free opensource models are scarce. We survey and compare current translation techniques and propose a modified sequence to sequence model repurposed with attention techniques. Sequence learning using an encoder-decoder model is now paving the path for higher precision levels in translation. Using a Convolutional Neural Network (CNN) encoder and a Recurrent Neural Network (RNN) decoder background, we use Fairseq tools to produce an end-to-end bilingually trained Spanish-English machine translation model including source language detection. We acquire competitive results using a duo-lingo-corpus trained model to provide for prospective, ready-made plug-in use for compound sentences and document translations. Our model serves a decent system for large, organizational data translation needs. While acknowledging its shortcomings and future scope, it also identifies itself as a well-optimized deep neural network model and solution.

Keywords: attention, encoder-decoder, Fairseq, Seq2Seq, Spanish, translation

Procedia PDF Downloads 175

Authors: Maham Malik, Amjad Ali, Muhammad Asif

Abstract:

Current study aims to examine the relationship of emotional labor strategies - deep acting and surface acting - with employees' job satisfaction, organizational commitment and intentions to quit. The study also examines the mediating role of job satisfaction and organizational commitment for relationship of emotional labor strategies with intentions to quit. Data were conveniently collected from 307 nurses by using self-administered questionnaire. Linear regression test was applied to find the relationship between the variables. Mediation was checked through Baron and Kenny Model and Sobel test. Results prove the existence of partial mediation of job satisfaction between the emotional labor strategies and quitting intentions. The study recommends that deep acting should be promoted because it is positively associated with quality of work life, work engagement and organizational citizenship behavior of employees.

Keywords: emotional labor strategies, intentions to quit, job satisfaction, organizational commitment, nursing

Procedia PDF Downloads 147

Authors: Carlos Roncero-Parra, Alfonso Parreño-Torres, Jorge Mateo Sotos, Alejandro L. Borja

Abstract:

In this research, different methods based on machine/deep learning algorithms are presented for the classification and diagnosis of patients with mental disorders such as alzheimer. For this purpose, the signals obtained from 32 unipolar electrodes identified by non-invasive EEG were examined, and their basic properties were obtained. More specifically, different well-known machine learning based classifiers have been used, i.e., support vector machine (SVM), Bayesian linear discriminant analysis (BLDA), decision tree (DT), Gaussian Naïve Bayes (GNB), K-nearest neighbor (KNN) and Convolutional Neural Network (CNN). A total of 668 patients from five different hospitals have been studied in the period from 2011 to 2021. The best accuracy is obtained was around 93 % in both ADM and ADA classifications. It can be concluded that such a classification will enable the training of algorithms that can be used to identify and classify different mental disorders with high accuracy.

Keywords: alzheimer, machine learning, deep learning, EEG

Procedia PDF Downloads 126

Authors: Mahdi Akhbardeh

Abstract:

Synchronization of neuronal firing is a hallmark of several neurological diseases. Recently, stimulation techniques have been developed which make it possible to desynchronize oscillatory neuronal activity in a mild and effective way, without suppressing the neurons' firing. As yet, these techniques are being used to establish demand-controlled deep brain stimulation (DBS) techniques for the therapy of movement disorders like severe Parkinson's disease or essential tremor. We here present a first conceptualization suggesting that the nucleus accumbens is a promising target for the standard, that is, permanent high-frequency, DBS in patients with severe and chronic obsessive-compulsive disorder (OCD). In addition, we explain how demand-controlled DBS techniques may be applied to the therapy of OCD in those cases that are refractory to behavioral therapies and pharmacological treatment.

Keywords: stereotactic neurosurgery, deep brain stimulation, obsessive-compulsive disorder, phase resetting

Procedia PDF Downloads 512

Authors: A. Degale Desta, Tamirat Kebamo

Abstract:

Background: Recent advances in computer vision and pattern recognition have significantly improved activity recognition through video analysis, particularly with the application of Deep Convolutional Neural Networks (CNNs). One-stage detectors now enable efficient video-based recognition by simultaneously predicting object categories and locations. Such advancements are highly relevant in educational settings where CCTV surveillance could automatically monitor academic activities, enhancing security and classroom management. However, current datasets and recognition systems lack the specific focus on campus environments necessary for practical application in these settings.Objective: This study aims to address this gap by developing a dataset and testing an automated activity recognition system specifically tailored for educational campuses. The EthioCAD dataset was created to capture various classroom activities and teacher-student interactions, facilitating reliable recognition of academic activities using deep learning models. Method: EthioCAD, a novel video-based dataset, was created with a design science research approach to encompass teacher-student interactions across three domains and 18 distinct classroom activities. Using the Roboflow AI framework, the data was processed, with 4.224 KB of frames and 33.485 MB of images managed for frame extraction, labeling, and organization. The Ultralytics YOLOv8 model was then implemented within Google Colab to evaluate the dataset’s effectiveness, achieving high mean Average Precision (mAP) scores. Results: The YOLOv8 model demonstrated robust activity recognition within campus-like settings, achieving an mAP50 of 90.2% and an mAP50-95 of 78.6%. These results highlight the potential of EthioCAD, combined with YOLOv8, to provide reliable detection and classification of classroom activities, supporting automated surveillance needs on educational campuses. Discussion: The high performance of YOLOv8 on the EthioCAD dataset suggests that automated activity recognition for surveillance is feasible within educational environments. This system addresses current limitations in campus-specific data and tools, offering a tailored solution for academic monitoring that could enhance the effectiveness of CCTV systems in these settings. Conclusion: The EthioCAD dataset, alongside the YOLOv8 model, provides a promising framework for automated campus activity recognition. This approach lays the groundwork for future advancements in CCTV-based educational surveillance systems, enabling more refined and reliable monitoring of classroom activities.

Keywords: deep CNN, EthioCAD, deep learning, YOLOv8, activity recognition

Procedia PDF Downloads 12

Authors: Nalinee B. Suryawanshi, Vinay M. Bhandari, Laxmi Gayatri Sorokhaibam, Vivek V. Ranade

Abstract:

Deep desulphurization of transportation fuels is a major environmental concern all over the world and recently prescribed norms for the sulphur content require below 10 ppm sulphur concentrations in fuels such as diesel and gasoline. The existing technologies largely based on catalytic processes such as hydrodesulphurization, oxidation require newer catalysts and demand high cost of deep desulphurization whereas adsorption based processes have limitations due to lower capacity of sulphur removal. The present work is an attempt to provide alternatives for the existing methodologies using a newer non-catalytic process based on hydrodynamic cavitation. The developed process requires appropriate combining of organic and aqueous phases under ambient conditions and passing through a cavitating device such as orifice, venturi or vortex diode. The implosion of vapour cavities formed in the cavitating device generates (in-situ) oxidizing species which react with the sulphur moiety resulting in the removal of sulphur from the organic phase. In this work, orifice was used as a cavitating device and deep desulphurization was demonstrated for removal of thiophene as a model sulphur compound from synthetic fuel of n-octane, toluene and n-octanol. The effect of concentration of sulphur (up to 300 ppm), nature of organic phase and effect of pressure drop (0.5 to 10 bar) was discussed. A very high removal of sulphur content of more than 90% was demonstrated. The process is easy to operate, essentially works at ambient conditions and the ratio of aqueous to organic phase can be easily adjusted to maximise sulphur removal. Experimental studies were also carried out using commercial diesel as a solvent and the results substantiate similar high sulphur removal. A comparison of the two cavitating devices- one with a linear flow and one using vortex flow for effecting pressure drop and cavitation indicates similar trends in terms of sulphur removal behaviour. The developed process is expected to provide an attractive environmental engineering alternative for deep desulphurization of transportation fuels.

Keywords: cavitation, petroleum, separation, sulphur removal

Procedia PDF Downloads 379

Authors: Praveen S. Muthukumarana, Achala C. Aponso

Abstract:

A large percentage of global crop harvest is lost due to crop diseases. Timely identification and treatment of crop diseases is difficult in many developing nations due to insufficient trained professionals in the field of agriculture. Many crop diseases can be accurately diagnosed by visual symptoms. In the past decade, deep learning has been successfully utilized in domains such as healthcare but adoption in agriculture for plant disease detection is rare. The literature shows that models trained with popular datasets such as PlantVillage does not generalize well on real world images. This paper attempts to find out how to make plant disease identification models that generalize well with real world images.

Keywords: agriculture, convolutional neural network, deep learning, plant disease classification, plant disease detection, plant disease diagnosis

Procedia PDF Downloads 146

Authors: Weiwei Xie, Yichao Li

Abstract:

The initial installation of the umbilical can affect the subsequent installation process and final installation. Meanwhile, the design of both ends of the ultra-deep water dynamic umbilical (UDWDU), as well as the design of the surface unit and the subsea production system connected by UDWDU,], varies in different oil and gas fields. To optimize the installation process of UDWDU, on the basis of the summary and analysis of the surface-end and the subsea-end design of UDWDU and the mainstream construction resources, the method of initial installation from the surface unit side or the subsea production system side of UDWDU is studied, and each initiation installation method is pointed out if some difficulties that may be encountered.

Keywords: dynamic umbilical, ultra-deep-water, initial installation, installation process

Procedia PDF Downloads 155

Authors: Bin Feng, Zhulin Zong

Abstract:

Radar systems are critical in the modern military, aviation, and maritime operations, and their proper functioning is essential for the success of these operations. However, due to the complexity and sensitivity of radar systems, they are susceptible to various faults that can significantly affect their performance. Traditional radar fault diagnosis strategies rely on expert knowledge and rule-based approaches, which are often limited in effectiveness and require a lot of time and resources. Deep learning has recently emerged as a promising approach for fault diagnosis due to its ability to learn features and patterns from large amounts of data automatically. In this paper, we propose a radar fault diagnosis strategy based on deep learning that can accurately identify and classify faults in radar systems. Our approach uses convolutional neural networks (CNN) to extract features from radar signals and fault classify the features. The proposed strategy is trained and validated on a dataset of measured radar signals with various types of faults. The results show that it achieves high accuracy in fault diagnosis. To further evaluate the effectiveness of the proposed strategy, we compare it with traditional rule-based approaches and other machine learning-based methods, including decision trees, support vector machines (SVMs), and random forests. The results demonstrate that our deep learning-based approach outperforms the traditional approaches in terms of accuracy and efficiency. Finally, we discuss the potential applications and limitations of the proposed strategy, as well as future research directions. Our study highlights the importance and potential of deep learning for radar fault diagnosis. It suggests that it can be a valuable tool for improving the performance and reliability of radar systems. In summary, this paper presents a radar fault diagnosis strategy based on deep learning that achieves high accuracy and efficiency in identifying and classifying faults in radar systems. The proposed strategy has significant potential for practical applications and can pave the way for further research.

Keywords: radar system, fault diagnosis, deep learning, radar fault

Procedia PDF Downloads 90

Authors: Lorenzo Gontrani, Marilena Carbone, Domenica Tommasa Donia, Elvira Maria Bauer, Pietro Tagliatesta

Abstract:

One of the fields where DES shows remarkable added values is the synthesis Of inorganic materials, in particular nanoparticles. In this field, the higher- ent and highly-tunable nano-homogeneities of DES structure give origin to a marked templating effect, a precious role that has led to the recent bloom of a vast number of studies exploiting these new synthesis media to prepare Nanomaterials and composite structures of various kinds. In this contribution, the most recent developments in the field will be reviewed, and some ex-citing examples of novel metal oxide nanoparticles syntheses using non-toxic type-IV Deep Eutectic Solvents will be described. The prepared materials possess nanometric dimensions and show flower-like shapes. The use of the pre- pared nanoparticles as fluorescent materials for the detection of various contaminants is under development.

Keywords: metal deep eutectic solvents, nanoparticles, inorganic synthesis, type IV DES, lamellar

Procedia PDF Downloads 135

Authors: Richard O’Riordan, Saritha Unnikrishnan

Abstract:

Autonomous Vehicles (AVs) are incorporating an increasing number of ADAS features, including automated lane-keeping systems. In recent years, many research papers into lane detection algorithms have been published, varying from computer vision techniques to deep learning methods. The transition from lower levels of autonomy defined in the SAE framework and the progression to higher autonomy levels requires increasingly complex models and algorithms that must be highly reliable in their operation and functionality capacities. Furthermore, these algorithms have no room for error when operating at high levels of autonomy. Although the current research details existing computer vision and deep learning algorithms and their methodologies and individual results, the research also details challenges faced by the algorithms and the resources needed to operate, along with shortcomings experienced during their detection of lanes in certain weather and lighting conditions. This paper will explore these shortcomings and attempt to implement a lane detection algorithm that could be used to achieve improvements in AV lane detection systems. This paper uses a pre-trained LaneNet model to detect lane or non-lane pixels using binary segmentation as the base detection method using an existing dataset BDD100k followed by a custom dataset generated locally. The selected roads will be modern well-laid roads with up-to-date infrastructure and lane markings, while the second road network will be an older road with infrastructure and lane markings reflecting the road network's age. The performance of the proposed method will be evaluated on the custom dataset to compare its performance to the BDD100k dataset. In summary, this paper will use Transfer Learning to provide a fast and robust lane detection algorithm that can handle various road conditions and provide accurate lane detection.

Keywords: ADAS, autonomous vehicles, deep learning, LaneNet, lane detection

Procedia PDF Downloads 104

Authors: Koray U. Erbas

Abstract:

Neural networks are appealing for many applications since they are able to learn complex non-linear relationships between input and output data. As the number of neurons and layers in a neural network increase, it is possible to represent more complex relationships with automatically extracted features. Nowadays Deep Neural Networks (DNNs) are widely used in Computer Vision problems such as; classification, object detection, segmentation image editing etc. In this work, Facial Emotion Recognition task is performed by proposed Convolutional Neural Network (CNN)-based DNN architecture using FER2013 Dataset. Moreover, the effects of different hyperparameters (activation function, kernel size, initializer, batch size and network size) are investigated and ablation study results for Pooling Layer, Dropout and Batch Normalization are presented.

Keywords: convolutional neural network, deep learning, deep learning based FER, facial emotion recognition

Procedia PDF Downloads 274

Authors: Yitao Lei, Xingxiang Zhai, Burra Venkata Durga Kumar

Abstract:

As the quantity and complexity of computing in large-scale software systems increase, distributed system computing becomes increasingly important. The distributed system realizes high-performance computing by collaboration between different computing resources. If there are no efficient resource scheduling resources, the abuse of distributed computing may cause resource waste and high costs. However, resource scheduling is usually an NP-hard problem, so we cannot find a general solution. However, some optimization algorithms exist like genetic algorithm, ant colony optimization, etc. The large scale of distributed systems makes this traditional optimization algorithm challenging to work with. Heuristic and machine learning algorithms are usually applied in this situation to ease the computing load. As a result, we do a review of traditional resource scheduling optimization algorithms and try to introduce a deep reinforcement learning method that utilizes the perceptual ability of neural networks and the decision-making ability of reinforcement learning. Using the machine learning method, we try to find important factors that influence the performance of distributed system computing and help the distributed system do an efficient computing resource scheduling. This paper surveys the application of deep reinforcement learning on distributed system computing resource scheduling proposes a deep reinforcement learning method that uses a recurrent neural network to optimize the resource scheduling, and proposes the challenges and improvement directions for DRL-based resource scheduling algorithms.

Keywords: resource scheduling, deep reinforcement learning, distributed system, artificial intelligence

Procedia PDF Downloads 111

Authors: Diego Roberto Goncalves De Pontes, Sergio Donizetti Zorzo

Abstract:

Studies show that most users do not read privacy policies from the online services they use. Some authors claim that one of the main causes of this is that policies are long and usually hard to understand, which make users lose interest in reading them. In this scenario, users may agree with terms without knowing what kind of data is being collected and why. Given that, we aimed to develop a model that would present the privacy policies contents in an easy and graphical way for the user to understand. We call it the Privacy Label. Using information recovery techniques, we propose an architecture that is able to extract information about what kind of data is being collected and to what end in the policies and show it to the user in an automated way. To assess our model, we calculated the precision, recall and f-measure metrics on the information extracted by our technique. The results for each metric were 68.53%, 85.61% e 76,13%, respectively, making it possible for the final user to understand which data was being collected without reading the whole policy. Also, our proposal can facilitate the notice-and-choice by presenting privacy policy information in an alternative way for online users.

Keywords: privacy, policies, user behavior, computer human interaction

Procedia PDF Downloads 307

Authors: Adamu Zubairu Mohammed, Fransis Oforum Arimoro, Salihu Maikudi Ibrahim, Y. I. Auta, T. I. Arowosegbe, Y. Abdullahi

Abstract:

The present study was conducted to evaluate the effect of depth on the distribution of zooplankton and some physicochemical parameters in Tungan Kawo Lake (Wushishi dam). Water and zooplankton samples were collected from the surface, 3.0 meters deep and 6.0 meters deep, for a period of 24 hours for six months. Standard procedures were adopted for the determination of physicochemical parameters. Results have shown significant differences in the pH, DO, BOD Hardness, Na, and Mg. A total of 1764 zooplankton were recorded, comprising 35 species, with cladocera having 18 species (58%), 14 species of copepoda (41%), 3 species of diptera (1.0%). Results show that more of the zooplankton were recorded in the 3.0 meters-deep region compared to the two other depts and a significant difference was observed in the distribution of Ceriodaphnia dubia, Daphnia laevis, and Leptodiaptomus coloradensis. Though the most abundant zooplankton was recorded in the 3.0 meters deep, Leptodiaptomus coloradesnsis, which was observed in the 6.0 meters deep as the most individual observed, this was followed by Daphnia laevis. Canonical correspondence analysis between physicochemical parameters and the zooplankton indicated a good relationship in the Lake. Ceriodaphnia dubia was found to have a good association with oxygen, sodium, and potassium, while Daphnia laevis and Leptodiaptomus coloradensis are in good relationship with magnesium and phosphorus. It was generally observed that this depth does not have much influence on the distribution of zooplankton in Wushishi Lake.

Keywords: zooplankton, standard procedures, canonical correspondence analysis, Wushishi, canonical, physicochemical parameter

Procedia PDF Downloads 90

Authors: Ali Berkan Ural

Abstract:

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

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

Procedia PDF Downloads 95

Authors: Almutasim Billa A. Alanazi, Hal S. Tharp

Abstract:

Safe performance and efficient energy consumption are essential factors for designing a control system. This paper presents a reinforcement learning (RL) model that can be applied to control applications to improve safety and reduce energy consumption. As hardware constraints and environmental disturbances are imprecise and unpredictable, conventional control methods may not always be effective in optimizing control designs. However, RL has demonstrated its value in several artificial intelligence (AI) applications, especially in the field of control systems. The proposed model intelligently monitors a system's success by observing the rewards from the environment, with positive rewards counting as a success when the controlled reference is within the desired operating zone. Thus, the model can determine whether the system is safe to continue operating based on the designer/user specifications, which can be adjusted as needed. Additionally, the controller keeps track of energy consumption to improve energy efficiency by enabling the idle mode when the controlled reference is within the desired operating zone, thus reducing the system energy consumption during the controlling operation. Water temperature control for a hydroponic system is taken as a case study for the RL model, adjusting the variance of disturbances to show the model’s robustness and efficiency. On average, the model showed safety improvement by up to 15% and energy efficiency improvements by 35%- 40% compared to a traditional RL model.

Keywords: control system, hydroponics, machine learning, reinforcement learning

Procedia PDF Downloads 185

Authors: Chad Brown

Abstract:

This paper establishes general conditions for the convergence rates of nonparametric sieve estimators with dependent data. We present two key results: one for nonstationary data and another for stationary mixing data. Previous theoretical results often lack practical applicability to deep neural networks (DNNs). Using these conditions, we derive convergence rates for DNN sieve estimators in nonparametric regression settings with both nonstationary and stationary mixing data. The DNN architectures considered adhere to current industry standards, featuring fully connected feedforward networks with rectified linear unit activation functions, unbounded weights, and a width and depth that grows with sample size.

Keywords: sieve extremum estimates, nonparametric estimation, deep learning, neural networks, rectified linear unit, nonstationary processes

Procedia PDF Downloads 41

Authors: Maria Amodeo, Pasquale Arpaia, Marco Buzio, Vincenzo Di Capua, Francesco Donnarumma

Abstract:

Different deep neural network architectures have been compared and tested to predict magnetic hysteresis in the context of pulsed electromagnets for experimental physics applications. Modelling quasi-static or dynamic major and especially minor hysteresis loops is one of the most challenging topics for computational magnetism. Recent attempts at mathematical prediction in this context using Preisach models could not attain better than percent-level accuracy. Hence, this work explores neural network approaches and shows that the architecture that best fits the measured magnetic field behaviour, including the effects of hysteresis and eddy currents, is the nonlinear autoregressive exogenous neural network (NARX) model. This architecture aims to achieve a relative RMSE of the order of a few 100 ppm for complex magnetic field cycling, including arbitrary sequences of pseudo-random high field and low field cycles. The NARX-based architecture is compared with the state-of-the-art, showing better performance than the classical operator-based and differential models, and is tested on a reference quadrupole magnetic lens used for CERN particle beams, chosen as a case study. The training and test datasets are a representative example of real-world magnet operation; this makes the good result obtained very promising for future applications in this context.

Keywords: deep neural network, magnetic modelling, measurement and empirical software engineering, NARX

Procedia PDF Downloads 130

Authors: Walid El Kamash

Abstract:

Sand columns (or granular piles) can be employed as soil strengthening for flexible constructions such as road embankments, oil storage tanks in addition to multistory structures. The challenge of embedding the sand columns in soft soil is that the surrounding soft soil cannot avail the enough confinement stress in order to keep the form of the sand column. Therefore, the sand columns which were installed in such soil will lose their ability to perform needed load-bearing capacity. The encasement, besides increasing the strength and stiffness of the sand column, prevents the lateral squeezing of sands when the column is installed even in extremely soft soils, thus enabling quicker and more economical installation. This paper investigates the improvement in load capacity of the sand column by encasement through a comprehensive parametric study using the 3-D finite difference analysis for the soft clay of soil in Egypt. Moreover, the study was extended to include a comparison study between encased sand column and Deep Mixed columns (DM). The study showed that confining the sand by geosynthetic resulted in an increment of shear strength. That result paid the attention to use encased sand stone rather than deep mixed columns due to relative high permeability of the first material.

Keywords: encased sand column, Deep mixed column, numerical analysis, improving soft soil

Procedia PDF Downloads 378

Authors: Isaac K. E. Ampomah, Seong-Bae Park, Sang-Jo Lee

Abstract:

Over the past decade, there have been promising developments in Natural Language Processing (NLP) with several investigations of approaches focusing on Recognizing Textual Entailment (RTE). These models include models based on lexical similarities, models based on formal reasoning, and most recently deep neural models. In this paper, we present a sentence encoding model that exploits the sentence-to-sentence relation information for RTE. In terms of sentence modeling, Convolutional neural network (CNN) and recurrent neural networks (RNNs) adopt different approaches. RNNs are known to be well suited for sequence modeling, whilst CNN is suited for the extraction of n-gram features through the filters and can learn ranges of relations via the pooling mechanism. We combine the strength of RNN and CNN as stated above to present a unified model for the RTE task. Our model basically combines relation vectors computed from the phrasal representation of each sentence and final encoded sentence representations. Firstly, we pass each sentence through a convolutional layer to extract a sequence of higher-level phrase representation for each sentence from which the first relation vector is computed. Secondly, the phrasal representation of each sentence from the convolutional layer is fed into a Bidirectional Long Short Term Memory (Bi-LSTM) to obtain the final sentence representations from which a second relation vector is computed. The relations vectors are combined and then used in then used in the same fashion as attention mechanism over the Bi-LSTM outputs to yield the final sentence representations for the classification. Experiment on the Stanford Natural Language Inference (SNLI) corpus suggests that this is a promising technique for RTE.

Keywords: deep neural models, natural language inference, recognizing textual entailment (RTE), sentence-to-sentence relation

Procedia PDF Downloads 348

Authors: Sajeeha Ansar, Asad Ali Safi, Sheikh Ziauddin, Ahmad R. Shahid, Faraz Ahsan

Abstract:

The most aggressive form of brain tumor is called glioma. Glioma is kind of tumor that arises from glial tissue of the brain and occurs quite often. A fully automatic 2D-CNN model for brain tumor segmentation is presented in this paper. We performed pre-processing steps to remove noise and intensity variances using N4ITK and standard intensity correction, respectively. We used Keras open-source library with Theano as backend for fast implementation of CNN model. In addition, we used BRATS 2015 MRI dataset to evaluate our proposed model. Furthermore, we have used SimpleITK open-source library in our proposed model to analyze images. Moreover, we have extracted random 2D patches for proposed 2D-CNN model for efficient brain segmentation. Extracting 2D patched instead of 3D due to less dimensional information present in 2D which helps us in reducing computational time. Dice Similarity Coefficient (DSC) is used as performance measure for the evaluation of the proposed method. Our method achieved DSC score of 0.77 for complete, 0.76 for core, 0.77 for enhanced tumor regions. However, these results are comparable with methods already implemented 2D CNN architecture.

Keywords: brain tumor segmentation, convolutional neural networks, deep learning, LGG

Procedia PDF Downloads 182

Authors: Fatemeh Saadat Ghareh Bagh, Srimanta Ray, Jerald Lalman

Abstract:

Lignin, the largest inventory of organic carbon with a high caloric energy value is a major component in woody and non-woody biomass. In pulping mills, a large amount of the lignin is burned for energy. At the same time, the phenolic structure of lignin enables it to be converted to value-added compounds.This study has focused on extracting lignin from black liquor using deep eutectic solvents (DESs). Therefore, three choline chloride (ChCl)-DESs paired with lactic acid (LA) (1:11), oxalic acid.2H₂O (OX) (1:4), and malic acid (MA) (1:3) were synthesized at 90oC and atmospheric pressure. The kinetics of lignin recovery from black liquor using DES was investigated at three moderate temperatures (338, 353, and 368 K) at time intervals from 30 to 210 min. The extracted lignin (acid soluble lignin plus Klason lignin) was characterized by Fourier transform infrared spectroscopy (FTIR). The FTIR studies included comparing the extracted lignin with a model Kraft lignin. The extracted lignin was characterized spectrophotometrically to determine the acid soluble lignin (ASL) [TAPPI UM 250] fraction and Klason lignin was determined gravimetrically using TAPPI T 222 om02. The lignin extraction reaction using DESs was modeled by first-order reaction kinetics and the activation energy of the process was determined. The ChCl:LA-DES recovered lignin was 79.7±2.1% at 368K and a DES:BL ratio of 4:1 (v/v). The quantity of lignin extracted for the control solvent, [emim][OAc], was 77.5+2.2%. The activation energy measured for the LA-DES system was 22.7 KJ mol⁻¹, while the activation energy for the OX-DES and MA-DES systems were 7.16 KJ·mol⁻¹ and 8.66 KJ·mol⁻¹ when the total lignin recovery was 75.4 ±0.9% and 62.4 ±1.4, % respectively.

Keywords: black liquor, deep eutectic solvents, kinetics, lignin

Procedia PDF Downloads 148

Authors: Jie Zhang, Qianyu Guo, Tieyi Zhang, Zhiyong Feng, Xiaohong Li

Abstract:

With the widespread popularity of mobile devices and the development of artificial intelligence (AI), deep learning (DL) has been extensively applied in Android apps. Compared with traditional Android apps (traditional apps), deep learning based Android apps (DL-based apps) need to use more third-party application programming interfaces (APIs) to complete complex DL inference tasks. However, existing methods (e.g., FlowDroid) for detecting sensitive information leakage in Android apps cannot be directly used to detect DL-based apps as they are difficult to detect third-party APIs. To solve this problem, we design DLtrace; a new static information flow analysis tool that can effectively recognize third-party APIs. With our proposed trace and detection algorithms, DLtrace can also efficiently detect privacy leaks caused by sensitive APIs in DL-based apps. Moreover, using DLtrace, we summarize the non-sequential characteristics of DL inference tasks in DL-based apps and the specific functionalities provided by DL models for such apps. We propose two formal definitions to deal with the common polymorphism and anonymous inner-class problems in the Android static analyzer. We conducted an empirical assessment with DLtrace on 208 popular DL-based apps in the wild and found that 26.0% of the apps suffered from sensitive information leakage. Furthermore, DLtrace has a more robust performance than FlowDroid in detecting and identifying third-party APIs. The experimental results demonstrate that DLtrace expands FlowDroid in understanding DL-based apps and detecting security issues therein.

Keywords: mobile computing, deep learning apps, sensitive information, static analysis

Procedia PDF Downloads 179

Authors: Bharatendra Rai

Abstract:

The sequence of words in text data has long-term dependencies and is known to suffer from vanishing gradient problems when developing deep learning models. Although recurrent networks such as long short-term memory networks help to overcome this problem, achieving high text classification performance is a challenging problem. Convolutional recurrent networks that combine the advantages of long short-term memory networks and convolutional neural networks can be useful for text classification performance improvements. However, arriving at suitable hyperparameter values for convolutional recurrent networks is still a challenging task where fitting a model requires significant computing resources. This paper illustrates the advantages of using convolutional recurrent networks for text classification with the help of statistically planned computer experiments for hyperparameter tuning.

Keywords: long short-term memory networks, convolutional recurrent networks, text classification, hyperparameter tuning, Tukey honest significant differences

Procedia PDF Downloads 129

Authors: Lin Li, Farshad Amini

Abstract:

The flipped classroom has been introduced to promote collaborative learning and higher-order learning objectives. In contrast to the traditional classroom, the flipped classroom has students watch prerecorded lecture videos before coming to class and then “class becomes the place to work through problems, advance concepts, and engage in collaborative learning”. In this paper, the active flipped learning combines flipped classroom with active learning that is to establish an active flipped learning (AFL) model, aiming to promote active learning, stress deep learning, encourage student engagement and highlight data-driven personalized learning. Because students have watched the lecture prior to class, contact hours can be devoted to problem-solving and gain a deeper understanding of the subject matter. The instructor is able to provide students with a wide range of learner-centered opportunities in class for greater mentoring and collaboration, increasing the possibility to engage students. Currently, little is known about the extent to which AFL improves engineering students’ performance. This paper presents the preliminary study on the core course of sophomore students in Engineering Mechanics. A series of survey and interviews have been conducted to compare students’ learning engagement, empowerment, self-efficacy, and satisfaction with the AFL. It was found that the AFL model taking advantage of advanced technology is a convenient and professional avenue for engineering students to strengthen their academic confidence and self-efficacy in the Engineering Mechanics by actively participating in learning and fostering their deep understanding of engineering statics and dynamics

Keywords: active learning, engineering mechanics, flipped classroom, performance

Procedia PDF Downloads 294

Authors: Lihong Wu, Raymond Young

Abstract:

The ability to learn is one of the most critical skills in the information age. However, many students do not have a clear understanding of what learning is, what they are learning, and why they are learning. Many students study simply to pass rather than to learn something useful for their career and their life. They have a misconception about learning and a wrong attitude towards learning. This research explores student attitudes to study in management education and explores how to intercede to lead students from shallow to deeper modes of learning.

Keywords: knowledge, surface learning, deep learning, education

Procedia PDF Downloads 501

Authors: Yong Zhang

Abstract:

Light has proven to be useful in a wide range of biomedical applications such as fluorescence imaging, photoacoustic imaging, optogenetics, photodynamic therapy, photothermal therapy, and light controlled drug/gene delivery. Taking photodynamic therapy (PDT) as an example, PDT has been proven clinically effective in early lung cancer, bladder cancer, head, and neck cancer and is the primary treatment for skin cancer as well. However, clinical use of PDT is severely constrained by the low penetration depth of visible light through thick tissue, limiting its use to target regions only a few millimeters deep. One way to enhance the range is to use invisible near-infrared (NIR) light within the optical window (700–1100nm) for biological tissues, extending the depth up to 1cm with no observable damage to the intervening tissue. We have demonstrated use of NIR-to-visible upconversion fluorescent nanoparticles (UCNPs), emitting visible fluorescence when excited by a NIR light at 980nm, as a nanotransducer for PDT to convert deep tissue-penetrating NIR light to visible light suitable for activating photosensitizers. The unique optical properties of UCNPs enable the upconversion wavelength to be tuned and matched to the activation absorption wavelength of the photosensitizer. At depths beyond 1cm, however, tissue remains inaccessible to light even within the NIR window, and this critical depth limitation renders existing phototherapy ineffective against most deep-seated cancers. We have demonstrated some new treatment modalities for deep-seated cancers based on UCNP hydrogel implants and miniaturized, wirelessly powered optoelectronic devices for light delivery to deep tissues.

Keywords: upconversion, fluorescent, nanoparticle, bioimaging, photodynamic therapy

Procedia PDF Downloads 161

Authors: Ksenia Volkova, Artur Petrosyan, Ignatii Dubyshkin, Alexei Ossadtchi

Abstract:

Brain-computer interfaces are a growing research field producing many implementations that find use in different fields and are used for research and practical purposes. Despite the popularity of the implementations using non-invasive neuroimaging methods, radical improvement of the state channel bandwidth and, thus, decoding accuracy is only possible by using invasive techniques. Electrocorticography (ECoG) is a minimally invasive neuroimaging method that provides highly informative brain activity signals, effective analysis of which requires the use of machine learning methods that are able to learn representations of complex patterns. Deep learning is a family of machine learning algorithms that allow learning representations of data with multiple levels of abstraction. This study explores the potential of deep learning approaches for ECoG processing, decoding movement intentions and the perception of proprioceptive information. To obtain synchronous recording of kinematic movement characteristics and corresponding electrical brain activity, a series of experiments were carried out, during which subjects performed finger movements at their own pace. Finger movements were recorded with a three-axis accelerometer, while ECoG was synchronously registered from the electrode strips that were implanted over the contralateral sensorimotor cortex. Then, multichannel ECoG signals were used to track finger movement trajectory characterized by accelerometer signal. This process was carried out both causally and non-causally, using different position of the ECoG data segment with respect to the accelerometer data stream. The recorded data was split into training and testing sets, containing continuous non-overlapping fragments of the multichannel ECoG. A deep convolutional neural network was implemented and trained, using 1-second segments of ECoG data from the training dataset as input. To assess the decoding accuracy, correlation coefficient r between the output of the model and the accelerometer readings was computed. After optimization of hyperparameters and training, the deep learning model allowed reasonably accurate causal decoding of finger movement with correlation coefficient r = 0.8. In contrast, the classical Wiener-filter like approach was able to achieve only 0.56 in the causal decoding mode. In the noncausal case, the traditional approach reached the accuracy of r = 0.69, which may be due to the presence of additional proprioceptive information. This result demonstrates that the deep neural network was able to effectively find a representation of the complex top-down information related to the actual movement rather than proprioception. The sensitivity analysis shows physiologically plausible pictures of the extent to which individual features (channel, wavelet subband) are utilized during the decoding procedure. In conclusion, the results of this study have demonstrated that a combination of a minimally invasive neuroimaging technique such as ECoG and advanced machine learning approaches allows decoding motion with high accuracy. Such setup provides means for control of devices with a large number of degrees of freedom as well as exploratory studies of the complex neural processes underlying movement execution.

Keywords: brain-computer interface, deep learning, ECoG, movement decoding, sensorimotor cortex

Procedia PDF Downloads 177