Search results for: masked data

Authors: Ling Qi, Matloob Khushi, Josiah Poon

Abstract:

This paper introduces a pre-trained Masked Candlestick Model (MCM) for trading time-series data. The pre-trained model is based on three core designs. First, we convert trading price data at each data point as a set of normalized elements and produce embeddings of each element. Second, we generate a masked sequence of such embedded elements as inputs for self-supervised learning. Third, we use the encoder mechanism from the transformer to train the inputs. The masked model learns the contextual relations among the sequence of embedded elements, which can aid downstream classification tasks. To evaluate the performance of the pre-trained model, we fine-tune MCM for three different downstream classification tasks to predict future price trends. The fine-tuned models achieved better accuracy rates for all three tasks than the baseline models. To better analyze the effectiveness of MCM, we test the same architecture for three currency pairs, namely EUR/GBP, AUD/USD, and EUR/JPY. The experimentation results demonstrate MCM’s effectiveness on all three currency pairs and indicate the MCM’s capability for signal extraction from trading data.

Keywords: masked language model, transformer, time series prediction, trading prediction, embedding, transfer learning, self-supervised learning

Procedia PDF Downloads 127

Authors: Tingting Lin, Manfred von Willich, Dafu Lou, Phil Eisen

Abstract:

A white-box implementation of a cryptographic algorithm is a software implementation intended to resist extraction of the secret key by an adversary. To date, most of the white-box techniques are used to protect block cipher implementations. However, a large proportion of the white-box implementations are proven to be vulnerable to affine equivalence attacks and other algebraic attacks, as well as differential computation analysis (DCA). In this paper, we identify a class of block ciphers for which we propose a method of constructing white-box implementations. Our method is based on threshold implementations and operations in composite fields. The resulting implementations consist of lookup tables and few exclusive OR operations. All intermediate values (inputs and outputs of the lookup tables) are masked. The threshold implementation makes the distribution of the masked values uniform and independent of the original inputs, and the operations in composite fields reduce the size of the lookup tables. The white-box implementations can provide resistance against algebraic attacks and DCA-like attacks.

Keywords: white-box, block cipher, composite field, threshold implementation

Procedia PDF Downloads 168

Authors: Oladapo Tolulope Ibitoye

Abstract:

Neural networks have become prominent and widely engaged in algorithmic-based machine learning networks. They are perfect in solving day-to-day issues to a certain extent. Neural networks are computing systems with several interconnected nodes. One of the numerous areas of application of neural networks is object detection. This is a prominent area due to the coronavirus disease pandemic and the post-pandemic phases. Wearing a face mask in public slows the spread of the virus, according to experts’ submission. This calls for the development of a reliable and effective model for detecting face masks on people's faces during compliance checks. The existing neural network models for facemask detection are characterized by their black-box nature and large dataset requirement. The highlighted challenges have compromised the performance of the existing models. The proposed model utilized Faster R-CNN Model on Inception V3 backbone to reduce system complexity and dataset requirement. The model was trained and validated with very few datasets and evaluation results shows an overall accuracy of 96% regardless of skin tone.

Keywords: convolutional neural network, face detection, face mask, masked faces

Procedia PDF Downloads 68

Authors: Soad Ali Yehia, Mohamed Shafik El-Ridi, Mina Ibrahim Tadros, Nolwa Gamal El-Sherif

Abstract:

Fexofenadine hydrochloride (FXD) is a slightly soluble, bitter-tasting, drug having an oral bioavailability of 35%. The maximum plasma concentration is reached 2.6 hours (Tmax) post-dose. The current work aimed to develop taste-masked FXD orodispersible tablets (ODTs) to increase extent of drug absorption and reduce Tmax. Taste masking was achieved via solid dispersion (SD) with chitosan (CS) or sodium alginate (ALG). FT-IR, DSC and XRD were performed to identify physicochemical interactions and FXD crystallinity. Taste-masked FXD-ODTs were developed via addition of superdisintegrants (crosscarmelose sodium or sodium starch glycolate, 5% and 10%, w/w) or sublimable agents (camphor, menthol or thymol; 10% and 20%, w/w) to FXD-SDs. ODTs were evaluated for weight variation, drug-content, friability, wetting time, disintegration time and drug release. Camphor-based (20%, w/w) FXD-ODT (F12) was optimized (F23) by incorporation of a more hydrophilic lubricant, sodium stearyl fumarate (Pruv®). The topography of the latter formula was examined via scanning electron microscopy (SEM). The in vivo estimation of FXD pharmacokinetics, relative to Allegra® tablets, was evaluated in healthy human volunteers. Based on the gustatory sensation test in healthy volunteers, FXD:CS (1:1) and FXD:ALG (1:0.5) SDs were selected. Taste-masked FXD-ODTs had appropriate physicochemical properties and showed short wetting and disintegration times. Drug release profiles of F23 and phenylalanine-containing Allegra® ODT were similar (f2 = 96) showing a complete release in two minutes. SEM micrographs revealed pores following camphor sublimation. Compared to Allegra® tablets, pharmacokinetic studies in healthy volunteers proved F23 ability to increase extent of FXD absorption (14%) and reduce Tmax to 1.83 h.

Keywords: fexofenadine hydrochloride, taste masking, chitosan, orodispersible

Procedia PDF Downloads 344

Authors: Abdullah H. Özcan, Dilara Hisar, Yetkin Sayar, Cem Ünsalan

Abstract:

In this study, an automated building and tree detection method is proposed using DSM data and true orthophoto image. A multiscale matched filtering is used on DSM data. Therefore, first watershed transform is applied. Then, Otsu’s thresholding method is used as an adaptive threshold to segment each watershed region. Detected objects are masked with NDVI to separate buildings and trees. The proposed method is able to detect buildings and trees without entering any elevation threshold. We tested our method on ISPRS semantic labeling dataset and obtained promising results.

Keywords: building detection, local maximum filtering, matched filtering, multiscale

Procedia PDF Downloads 320

Authors: Shrabani Ghosh

Abstract:

Automatic offensive language detection in social media has become a stirring task in today's NLP. Manual Offensive language detection is tedious and laborious work where automatic methods based on machine learning are only alternatives. Previous works have done sentiment analysis over social media in different ways such as supervised, semi-supervised, and unsupervised manner. Domain adaptation in a semi-supervised way has also been explored in NLP, where the source domain and the target domain are different. In domain adaptation, the source domain usually has a large amount of labeled data, while only a limited amount of labeled data is available in the target domain. Pretrained transformers like BERT, RoBERTa models are fine-tuned to perform text classification in an unsupervised manner to perform further pre-train masked language modeling (MLM) tasks. In previous work, hate speech detection has been explored in Gab.ai, which is a free speech platform described as a platform of extremist in varying degrees in online social media. In domain adaptation process, Twitter data is used as the source domain, and Gab data is used as the target domain. The performance of domain adaptation also depends on the cross-domain similarity. Different distance measure methods such as L2 distance, cosine distance, Maximum Mean Discrepancy (MMD), Fisher Linear Discriminant (FLD), and CORAL have been used to estimate domain similarity. Certainly, in-domain distances are small, and between-domain distances are expected to be large. The previous work finding shows that pretrain masked language model (MLM) fine-tuned with a mixture of posts of source and target domain gives higher accuracy. However, in-domain performance of the hate classifier on Twitter data accuracy is 71.78%, and out-of-domain performance of the hate classifier on Gab data goes down to 56.53%. Recently self-supervised learning got a lot of attention as it is more applicable when labeled data are scarce. Few works have already been explored to apply self-supervised learning on NLP tasks such as sentiment classification. Self-supervised language representation model ALBERTA focuses on modeling inter-sentence coherence and helps downstream tasks with multi-sentence inputs. Self-supervised attention learning approach shows better performance as it exploits extracted context word in the training process. In this work, a self-supervised attention mechanism has been proposed to detect hate speech on Gab.ai. This framework initially classifies the Gab dataset in an attention-based self-supervised manner. On the next step, a semi-supervised classifier trained on the combination of labeled data from the first step and unlabeled data. The performance of the proposed framework will be compared with the results described earlier and also with optimized outcomes obtained from different optimization techniques.

Keywords: attention learning, language model, offensive language detection, self-supervised learning

Procedia PDF Downloads 105

Authors: Leila Baghaarabani, Parvin Razzaghi, Mennatolla Magdy Mostafa, Ahmad Albaqsami, Al Warith Al Rushaidi, Masoud Al Rawahi

Abstract:

Predicting the interaction between drugs and their molecular targets is pivotal for advancing drug development processes. Due to the time and cost limitations, computational approaches have emerged as an effective approach to drug-target interaction (DTI) prediction. Most of the introduced computational based approaches utilize the drug molecule and protein sequence as input. This study does not only utilize these inputs, it also introduces a protein representation developed using a masked protein language model. In this representation, for every individual amino acid residue within the protein sequence, there exists a corresponding probability distribution that indicates the likelihood of each amino acid being present at that particular position. Then, the similarity between each pair of amino-acids is computed to create similarity matrix. To encode the knowledge of the similarity matrix, Bi-Level Routing Attention (BiFormer) is utilized, which combines aspects of transformer-based models with protein sequence analysis and represents a significant advancement in the field of drug-protein interaction prediction. BiFormer has the ability to pinpoint the most effective regions of the protein sequence that are responsible for facilitating interactions between the protein and drugs, thereby enhancing the understanding of these critical interactions. Thus, it appears promising in its ability to capture the local structural relationship of the proteins by enhancing the understanding of how it contributes to drug protein interactions, thereby facilitating more accurate predictions. To evaluate the proposed method, it was tested on two widely recognized datasets: Davis and KIBA. A comprehensive series of experiments was conducted to illustrate its effectiveness in comparison to cuttingedge techniques.

Keywords: BiFormer, transformer, protein language processing, self-attention mechanism, binding affinity, drug target interaction, similarity matrix, protein masked representation, protein language model

Procedia PDF Downloads 7

Authors: KuiDong Kang, Hye Bin Yim, Su Ah Kim

Abstract:

Purpose: Tectorigenin is an isoflavone derived from the rhizome of Belamacanda chinensis. In this study, oxygen-induced retinopathy was used to characterize the anti-angiogenic properties of tectorigenin in mice. Methods: ICR neonatal mice were exposed to 75% oxygen from postnatal day P7 until P12 and returned to room air (21% oxygen) for five days (P12 to P17). Mice were subjected to daily intraperitoneal injection of tectorigenin (1 mg/kg, 10 mg/kg) and vehicle from P12 to P17. Retro-orbital injection of FITC-dextran was performed and retinal flat mounts were viewed by fluorescence microscopy. The Central avascular area was quantified from the digital images in a masked fashion using image analysis software (NIH ImageJ). Neovascular tufts were quantified by using SWIFT_NV and neovascular lumens were quantified from a histologic section in a masked fashion. Immunohistochemistry and Western blot analysis were also performed to demonstrate the anti-angiogenic activity of this compound in vivo. Results: In the retina of tectorigenin injected mouse (10mg/kg), the central non-perfusion area was significantly decreased compared to the vehicle injected group (1.76±0.5 mm2 vs 2.85±0.6 mm2, P<0.05). In vehicle-injected group, 33.45 ± 5.51% of the total retinal area was avascular, whereas the retinas of pups treated with high-dose (10 mg/kg) tectorigenin showed avascular retinal areas of 21.25 ±4.34% (P<0.05). High dose of tectorigenin also significantly reduced the number of vascular lumens in the histologic section. Tectorigenin (10 mg/kg) significantly reduced the expression of vascular endothelial growth factor (VEGF), matrix metalloproteinase-2 (MMP-2), MMP-9, and angiotensin II compared to the vehicle injected group. Tectorigenin did not affect CD31 abundance at any tested dose. Conclusions: Our results show that tectorigenin possesses powerful anti-angiogenic properties and can attenuate new vessel formation in the retina after systemic administration. These results imply that this compound can be considered as a candidate substance for therapeutic inhibition of retinal angiogenesis.

Keywords: tectorigenin, anti-angiogenic, retinopathy, Belamacanda chinensis

Procedia PDF Downloads 267

Authors: Vaishnavi Shivde, Shrishti Sinha, Trapti Mishra

Abstract:

Traffic light detection from a moving vehicle is an important technology both for driver safety assistance functions as well as for autonomous driving in the city. This paper proposed a deep-learning-based traffic light recognition method that consists of a pixel-wise image segmentation technique and a fully convolutional network i.e., UNET architecture. This paper has used a method for detecting the position and recognizing the state of the traffic lights in video sequences is presented and evaluated using Traffic Light Dataset which contains masked traffic light image data. The first stage is the detection, which is accomplished through image processing (image segmentation) techniques such as image cropping, color transformation, segmentation of possible traffic lights. The second stage is the recognition, which means identifying the color of the traffic light or knowing the state of traffic light which is achieved by using a Convolutional Neural Network (UNET architecture).

Keywords: traffic light detection, image segmentation, machine learning, classification, convolutional neural networks

Procedia PDF Downloads 173

Authors: Jinwon Kang, Seonghak Jo, Joohee Ahn, Junghye Choi, Sun-Young Lee

Abstract:

A morphological priming has proved its importance by showing that segmentation occurs in morphemes when visual words are recognized within a noticeably short time. Regarding Sino-Korean prefixes, this study conducted an experiment on visual masked priming tasks with 57 ms stimulus-onset asynchrony (SOA) to see how individual differences in the amount of morphological knowledge affect morphological priming. The relationship between the prime and target words were classified as morphological (e.g., 미개척 migaecheog [unexplored] – 미해결 mihaegyel [unresolved]), semantical (e.g., 친환경 chinhwangyeong [eco-friendly]) – 무공해 mugonghae [no-pollution]), and orthographical (e.g., 미용실 miyongsil [beauty shop] – 미확보 mihwagbo [uncertainty]) conditions. We then compared the priming by configuring irrelevant paired stimuli for each condition’s control group. As a result, in the behavioral data, we observed facilitatory priming from a group with high morphological knowledge only under the morphological condition. In contrast, a group with low morphological knowledge showed the priming only under the orthographic condition. In the event-related potential (ERP) data, the group with high morphological knowledge presented the N250 only under the morphological condition. The findings of this study imply that individual differences in morphological knowledge in Korean may have a significant influence on the segmental processing of Korean word recognition.

Keywords: ERP, individual differences, morphological priming, sino-Korean prefixes

Procedia PDF Downloads 214

Authors: Yanjie Zhu, André Jesus, Irwanda Laory

Abstract:

Structural Health Monitoring (SHM), involving data acquisition, data interpretation and decision-making system aim to continuously monitor the structural performance of civil infrastructures under various in-service circumstances. The main value and purpose of SHM is identifying damages through data interpretation system. Research on SHM has been expanded in the last decades and a large volume of data is recorded every day owing to the dramatic development in sensor techniques and certain progress in signal processing techniques. However, efficient and reliable data interpretation for damage detection under environmental variations is still a big challenge. Structural damages might be masked because variations in measured data can be the result of environmental variations. This research reports a novel method based on single-channel Blind Signal Separation (BSS), which extracts environmental effects from measured data directly without any prior knowledge of the structure loading and environmental conditions. Despite the successful application in audio processing and bio-medical research fields, BSS has never been used to detect damage under varying environmental conditions. This proposed method optimizes and combines Ensemble Empirical Mode Decomposition (EEMD), Principal Component Analysis (PCA) and Independent Component Analysis (ICA) together to separate structural responses due to different loading conditions respectively from a single channel input signal. The ICA is applying on dimension-reduced output of EEMD. Numerical simulation of a truss bridge, inspired from New Joban Line Arakawa Railway Bridge, is used to validate this method. All results demonstrate that the single-channel BSS-based method can recover temperature effects from mixed structural response recorded by a single sensor with a convincing accuracy. This will be the foundation of further research on direct damage detection under varying environment.

Keywords: damage detection, ensemble empirical mode decomposition (EEMD), environmental variations, independent component analysis (ICA), principal component analysis (PCA), structural health monitoring (SHM)

Procedia PDF Downloads 304

Authors: Vikrant Gupta, Amrit Goswami

Abstract:

The fixed income market forms the basis of the modern financial market. All other assets in financial markets derive their value from the bond market. Owing to its over-the-counter nature, corporate bonds have relatively less data publicly available and thus is researched upon far less compared to Equities. Bond price prediction is a complex financial time series forecasting problem and is considered very crucial in the domain of finance. The bond prices are highly volatile and full of noise which makes it very difficult for traditional statistical time-series models to capture the complexity in series patterns which leads to inefficient forecasts. To overcome the inefficiencies of statistical models, various machine learning techniques were initially used in the literature for more accurate forecasting of time-series. However, simple machine learning methods such as linear regression, support vectors, random forests fail to provide efficient results when tested on highly complex sequences such as stock prices and bond prices. hence to capture these intricate sequence patterns, various deep learning-based methodologies have been discussed in the literature. In this study, a recurrent neural network-based deep learning model using long short term networks for prediction of corporate bond prices has been discussed. Long Short Term networks (LSTM) have been widely used in the literature for various sequence learning tasks in various domains such as machine translation, speech recognition, etc. In recent years, various studies have discussed the effectiveness of LSTMs in forecasting complex time-series sequences and have shown promising results when compared to other methodologies. LSTMs are a special kind of recurrent neural networks which are capable of learning long term dependencies due to its memory function which traditional neural networks fail to capture. In this study, a simple LSTM, Stacked LSTM and a Masked LSTM based model has been discussed with respect to varying input sequences (three days, seven days and 14 days). In order to facilitate faster learning and to gradually decompose the complexity of bond price sequence, an Empirical Mode Decomposition (EMD) has been used, which has resulted in accuracy improvement of the standalone LSTM model. With a variety of Technical Indicators and EMD decomposed time series, Masked LSTM outperformed the other two counterparts in terms of prediction accuracy. To benchmark the proposed model, the results have been compared with traditional time series models (ARIMA), shallow neural networks and above discussed three different LSTM models. In summary, our results show that the use of LSTM models provide more accurate results and should be explored more within the asset management industry.

Keywords: bond prices, long short-term memory, time series forecasting, empirical mode decomposition

Procedia PDF Downloads 136

Authors: Fariba Azizi, Firoozeh Haghighi, Viliam Makis

Abstract:

In this paper, we propose a method to model the relationship between failure time and degradation for a simple step stress test where underlying degradation path is linear and different causes of failure are possible. It is assumed that the intensity function depends only on the degradation value. No assumptions are made about the distribution of the failure times. A simple step-stress test is used to shorten failure time of products and a tampered failure rate (TFR) model is proposed to describe the effect of the changing stress on the intensities. We assume that some of the products that fail during the test have a cause of failure that is only known to belong to a certain subset of all possible failures. This case is known as masking. In the presence of masking, the maximum likelihood estimates (MLEs) of the model parameters are obtained through an expectation-maximization (EM) algorithm by treating the causes of failure as missing values. The effect of incomplete information on the estimation of parameters is studied through a Monte-Carlo simulation. Finally, a real example is analyzed to illustrate the application of the proposed methods.

Keywords: cause of failure, linear degradation path, reliability function, expectation-maximization algorithm, intensity, masked data

Procedia PDF Downloads 334

Authors: Jean-Pierre Dubois, Jihad S. Daba, H. Karam, J. Abdallah

Abstract:

Tsunami early detection and warning systems have proved to be of ultimate importance, especially after the destructive tsunami that hit Japan in March 2012. Such systems are crucial to inform the authorities of any risk of a tsunami and of the degree of its danger in order to make the right decision and notify the public of the actions they need to take to save their lives. The purpose of this research is to enhance existing tsunami detection and warning systems. We first propose an automated and miniaturized model of an early tsunami detection and warning system. The model for the operation of a tsunami warning system is simulated using the data acquisition toolbox of Matlab and measurements acquired from specified internet pages due to the lack of the required real-life sensors, both seismic and hydrologic, and building a graphical user interface for the system. In the second phase of this work, we implement various satellite image filtering schemes to enhance the acquired synthetic aperture radar images of the tsunami affected region that are masked by speckle noise. This enables us to conduct a post-tsunami damage extent study and calculate the percentage damage. We conclude by proposing improvements to the existing telecommunication infrastructure of existing warning tsunami systems using a migration to IP-based networks and fiber optics links.

Keywords: detection, GIS, GSN, GTS, GPS, speckle noise, synthetic aperture radar, tsunami, wiener filter

Procedia PDF Downloads 392

Authors: Paris Binos

Abstract:

The present work investigates developmental aspects of the duration of isolated vowels in infants with normal hearing compared to those who received cochlear implants (CIs) before two years of age. Infants with normal hearing produced shorter vowel duration since this find related with more mature production abilities. First isolated vowels are transparent during the protophonic stage as evidence of an increased motor and linguistic control. Vowel duration is a crucial factor for the transition of prelexical speech to normal adult speech. Despite current knowledge of data for infants with normal hearing more research is needed to unravel productions skills in early implanted children. Thus, isolated vowel productions by two congenitally hearing-impaired Greek infants (implantation ages 1:4-1:11; post-implant ages 0:6-1:3) were recorded and sampled for six months after implantation with a Nucleus-24. The results compared with the productions of three normal hearing infants (chronological ages 0:8-1:1). Vegetative data and vocalizations masked by external noise or sounds were excluded. Participants had no other disabilities and had unknown deafness etiology. Prior to implantation the infants had an average unaided hearing loss of 95-110 dB HL while the post-implantation PTA decreased to 10-38 dB HL. The current research offers a methodology for the processing of the prelinguistic productions based on a combination of acoustical and auditory analyses. Based on the current methodological framework, duration measured through spectrograms based on wideband analysis, from the voicing onset to the end of the vowel. The end marked by two co-occurring events: 1) The onset of aperiodicity with a rapid change in amplitude in the waveform and 2) a loss in formant’s energy. Cut-off levels of significance were set at 0.05 for all tests. Bonferroni post hoc tests indicated that difference was significant between the mean duration of vowels of infants wearing CIs and their normal hearing peers. Thus, the mean vowel duration of CIs measured longer compared to the normal hearing peers (0.000). The current longitudinal findings contribute to the existing data for the performance of children wearing CIs at a very young age and enrich also the data of the Greek language. The above described weakness for CI’s performance is a challenge for future work in speech processing and CI’s processing strategies.

Keywords: cochlear implant, duration, spectrogram, vowel

Procedia PDF Downloads 261

Authors: Siddharth Krishnaswamy

Abstract:

Problem Statement: Currently, when analyzing household food security, the most commonly studied food access indicators are household income and expenditure. Larger studies do take into account other indices such as credit and employment. But these are baselines studies and by definition are conducted infrequently. Food security analysis for access is usually dedicated to analyzing income and expenditure indicators. And both these indicators are notoriously inconsistent. Yet this data can very often end up being the basis on which household food access is calculated; and by extension, be used for decision making. Objectives: This paper argues that along with income and expenditure, credit and debit information should be collected so that an accurate analysis of household food security (and in particular) food access can be determined. The lack of collection and analysis of this information routinely means that there is often a “masking” of the actual situation; a household’s food access and food availability patterns may be adequate mainly as a result of borrowing and may even be due to a long- term dependency (a debt cycle). In other words, such a household is, in reality, worse off than it appears a factor masked by its performance on basic access indicators. Procedures/methodologies/approaches: Existing food security data sets collected in 2005 in Azerbaijan, 2010 across Myanmar and 2014-15 across Uganda were used to support the theory that analyzing income and expenditure of a HHs and analyzing the same in addition to data on credit & borrowing patterns will result in an entirely different scenario of food access of the household. Furthermore, the data analyzed depicts food consumption patterns across groups of households and then relates this to the extent of dependency on credit, i.e. households borrowing money in order to meet food needs. Finally, response options that were based on analyzing only income and expenditure; and response options based on income, expenditure, credit, and borrowing – from the same geographical area of operation are studied and discussed. Results: The purpose of this work was to see if existing methods of household food security analysis could be improved. It is hoped that food security analysts will collect household level information on credit and debit and analyze them against income, expenditure and consumption patterns. This will help determine if a household’s food access and availability are dependent on unsustainable strategies such as borrowing money for food or undertaking sustained debts. Conclusions: The results clearly show the amount of relevant information that is missing in Food Access analysis if debit and borrowing of the household is not analyzed along with the typical Food Access indicators that are usually analyzed. And the serious repercussions this has on Programmatic response and interventions.

Keywords: analysis, food security indicators, response, resilience analysis

Procedia PDF Downloads 331

Authors: Zhipeng Chen, Peng Zhang, Qingyun Liu, Li Guo

Abstract:

With the Internet becoming the dominant channel for business and life, many IPs are increasingly masked using web proxies for illegal purposes such as propagating malware, impersonate phishing pages to steal sensitive data or redirect victims to other malicious targets. Moreover, as Internet traffic continues to grow in size and complexity, it has become an increasingly challenging task to detect the proxy service due to their dynamic update and high anonymity. In this paper, we present an approach based on behavioral graph analysis to study the behavior similarity of web proxy users. Specifically, we use bipartite graphs to model host communications from network traffic and build one-mode projections of bipartite graphs for discovering social-behavior similarity of web proxy users. Based on the similarity matrices of end-users from the derived one-mode projection graphs, we apply a simple yet effective spectral clustering algorithm to discover the inherent web proxy users behavior clusters. The web proxy URL may vary from time to time. Still, the inherent interest would not. So, based on the intuition, by dint of our private tools implemented by WebDriver, we examine whether the top URLs visited by the web proxy users are web proxies. Our experiment results based on real datasets show that the behavior clusters not only reduce the number of URLs analysis but also provide an effective way to detect the web proxies, especially for the unknown web proxies.

Keywords: bipartite graph, one-mode projection, clustering, web proxy detection

Procedia PDF Downloads 245

Authors: Jamal Takhchi

Abstract:

The understanding of vibration propagation in complex structures such as automotive body in white remains a challenging issue in car design regarding NVH performances. The current analysis is limited to the low frequency range where modal concepts are dominant. Higher frequencies, between 200 and 1000 Hz, will become critical With the rise of electrification. EVs annoying sounds are mostly whines created by either Gears or e-motors between 300 Hz and 2 kHz. Structural intensity analysis was Experienced a few years ago on finite element models. The application was promising but limited by the fact that the propagating 3D intensity vector field is masked by a rotational Intensity field. This rotational field should be filtered using a differential operator. The expression of this operator in the framework of finite element modeling is not yet known. The aim of the proposed work is to implement this operator in the current dynamic solver (NASTRAN) of Stellantis and develop the Expected methodology for the mid-frequency structural analysis of electrified vehicles.

Keywords: structural intensity, NVH, body in white, irrotatational intensity

Procedia PDF Downloads 155

Authors: X. Wang

Abstract:

Timely and accurate information on urban building damage caused by earthquake is important basis for disaster assessment and emergency relief. Very high resolution (VHR) remotely sensed imagery containing abundant fine-scale information offers a large quantity of data for detecting and assessing urban building damage in the aftermath of earthquake disasters. However, the accuracy obtained using spectral features alone is comparatively low, since building damage, intact buildings and pavements are spectrally similar. Therefore, it is of great significance to detect urban building damage effectively using multi-source data. Considering that in general height or geometric structure of buildings change dramatically in the devastated areas, a novel multi-stage urban building damage detection method, using bi-temporal spectral, height and corner information, was proposed in this study. The pre-event height information was generated using stereo VHR images acquired from two different satellites, while the post-event height information was produced from airborne LiDAR data. The corner information was extracted from pre- and post-event panchromatic images. The proposed method can be summarized as follows. To reduce the classification errors caused by spectral similarity and errors in extracting height information, ground surface, shadows, and vegetation were first extracted using the post-event VHR image and height data and were masked out. Two different types of building damage were then extracted from the remaining areas: the height difference between pre- and post-event was used for detecting building damage showing significant height change; the difference in the density of corners between pre- and post-event was used for extracting building damage showing drastic change in geometric structure. The initial building damage result was generated by combining above two building damage results. Finally, a post-processing procedure was adopted to refine the obtained initial result. The proposed method was quantitatively evaluated and compared to two existing methods in Port au Prince, Haiti, which was heavily hit by an earthquake in January 2010, using pre-event GeoEye-1 image, pre-event WorldView-2 image, post-event QuickBird image and post-event LiDAR data. The results showed that the method proposed in this study significantly outperformed the two comparative methods in terms of urban building damage extraction accuracy. The proposed method provides a fast and reliable method to detect urban building collapse, which is also applicable to relevant applications.

Keywords: building damage, corner, earthquake, height, very high resolution (VHR)

Procedia PDF Downloads 213

Authors: X. S. Wu, H. Jia, P. H. Qian, Z. Zhang, H. L. Cai, F. M. Zhang

Abstract:

A bipolar resistance switching behaviour is detected for a Ti/TiO2-x/Au memristor device, which is fabricated by a masked designed magnetic sputtering. The current dependence of voltage indicates the curve changes slowly and continuously. When voltage pulses are applied to the device, the set and reset processes maintains linearity, which is used to simulate the synapses. We argue that the conduction mechanism of the device is from the oxygen vacancy channel model, and the resistance of the device change slowly due to the reaction between the titanium electrode and the intermediate layer and the existence of a large number of oxygen vacancies in the intermediate layer. Then, Hopfield neural network is constructed to simulate the behaviour of neural network in image processing, and the accuracy rate is more than 98%. This shows that titanium dioxide memristor has a broad application prospect in high performance neural network simulation.

Keywords: memristor fabrication, neuromorphic computing, bionic synaptic application, TiO₂-based

Procedia PDF Downloads 90

Authors: Zhenxiang Zhou

Abstract:

The triose phosphate utilisation (TPU) limitation to leaf photosynthesis is a biochemical process concerning the sub-foliar carbon sink-source (im)balance, in which photorespiration-associated amino acids exports provide an additional outlet for carbon and increases leaf photosynthetic rate. However, whether this process is regulated by whole-plant sink-source relations and nitrogen budgets remains unclear. We address this question by model analyses of gas-exchange data measured on leaves at three growth stages of rice plants grown at two-nitrogen levels, where three means (leaf-colour modification, adaxial vs abaxial measurements, and panicle pruning) were explored to alter source-sink ratios. Higher specific leaf nitrogen (SLN) resulted in higher rates of TPU and also led to the TPU limitation occurring at a lower intercellular CO2 concentration. Photorespiratory nitrogen assimilation was greater in higher-nitrogen leaves but became smaller in cases associated with yellower-leaf modification, abaxial measurement, or panicle pruning. The feedback inhibition of panicle pruning on rates of TPU was not always observed because panicle pruning blocked nitrogen remobilisation from leaves to grains, and the increased SLN masked the feedback inhibition. The (sub)foliar TPU limitation can be modulated by whole-plant source-sink ratios and nitrogen budgets during rice grain filling, suggesting a close link between sub-foliar and whole-plant sink limitations.

Keywords: triose phosphate utilization, sink limitation, panicle pruning, oryza sativa

Procedia PDF Downloads 90

Authors: Mansour Mohammadpour

Abstract:

Data transformation refers to the modification of any point in a data set by a mathematical function. When applying transformations, the measurement scale of the data is modified. Data transformations are commonly employed to turn data into the appropriate form, which can serve various functions in the quantitative analysis of the data. This study addresses the investigation of the use of data transformations in Data Envelopment Analysis (DEA). Although data transformations are important options for analysis, they do fundamentally alter the nature of the variable, making the interpretation of the results somewhat more complex.

Keywords: data transformation, data envelopment analysis, undesirable data, negative data

Procedia PDF Downloads 20

Authors: Shorena Pharjiani

Abstract:

The Present empirical paper investigates the relationship between FDI and economic growth by 10 selected industries in 10 Central and Eastern European countries from the period 1995 to 2012. Different estimation approaches were used to explore the connection between FDI and economic growth, for example OLS, RE, FE with and without time dummies. Obtained empirical results leads to some main consequences: First, the Central and East European countries (CEEC) attracted foreign direct investment, which raised the productivity of industries they entered in. It should be concluded that the linkage between FDI and output growth by industries is positive and significant enough to suggest that foreign firm’s participation enhanced the productivity of the industries they occupied. There had been an endogeneity problem in the regression and fixed effects estimation approach was used which partially corrected the regression analysis in order to make the results less biased. Second, it should be stressed that the results show that time has an important role in making FDI operational for enhancing output growth by industries via total factor productivity. Third, R&D positively affected economic growth and at the same time, it should take some time for research and development to influence economic growth. Fourth, the general trends masked crucial differences at the country level: over the last 20 years, the analysis of the tables and figures at the country level show that the main recipients of FDI of the 11 Central and Eastern European countries were Hungary, Poland and the Czech Republic. The main reason was that these countries had more open door policies for attracting the FDI. Fifth, according to the graphical analysis, while Hungary had the highest FDI inflow in this region, it was not reflected in the GDP growth as much as in other Central and Eastern European countries.

Keywords: central and East European countries (CEEC), economic growth, FDI, panel data

Procedia PDF Downloads 237

Authors: Utpal Das, Sona Das

Abstract:

InAs/GaSb type-II superlattice (T2SL) Mid-wave infrared (MWIR) focal plane arrays (FPAs) have recently seen rapid development. However, in small pixel size large format FPAs, the occurrence of high mesa sidewall surface leakage current is a major constraint necessitating proper surface passivation. A simple pixel isolation technique in InAs/GaSb T2SL detector arrays without the conventional mesa etching has been proposed to isolate the pixels by forming a more resistive higher band gap material from the SL, in the inter-pixel region. Here, a single step femtosecond (fs) laser anneal of the T2SL structure of the inter-pixel T2SL regions, have been used to increase the band gap between the pixels by QW-intermixing and hence increase isolation between the pixels. The p-i-n photodiode structure used here consists of a 506nm, (10 monolayer {ML}) InAs:Si (1x10¹⁸cm⁻³)/(10ML) GaSb SL as the bottom n-contact layer grown on an n-type GaSb substrate. The undoped absorber layer consists of 1.3µm, (10ML)InAs/(10ML)GaSb SL. The top p-contact layer is a 63nm, (10ML)InAs:Be(1x10¹⁸cm⁻³)/(10ML)GaSb T2SL. In order to improve the carrier transport, a 126nm of graded doped (10ML)InAs/(10ML)GaSb SL layer was added between the absorber and each contact layers. A 775nm 150fs-laser at a fluence of ~6mJ/cm² is used to expose the array where the pixel regions are masked by a Ti(200nm)-Au(300nm) cap. Here, in the inter-pixel regions, the p+ layer have been reactive ion etched (RIE) using CH₄+H₂ chemistry and removed before fs-laser exposure. The fs-laser anneal isolation improvement in 200-400μm pixels due to spatially selective quantum well intermixing for a blue shift of ~70meV in the inter-pixel regions is confirmed by FTIR measurements. Dark currents are measured between two adjacent pixels with the Ti(200nm)-Au(300nm) caps used as contacts. The T2SL quality in the active photodiode regions masked by the Ti-Au cap is hardly affected and retains the original quality of the detector. Although, fs-laser anneal of p+ only etched p-i-n T2SL diodes show a reduction in the reverse dark current, no significant improvement in the full RIE-etched mesa structures is noticeable. Hence for a 128x128 array fabrication of 8μm square pixels and 10µm pitch, SU8 polymer isolation after RIE pixel delineation has been used. X-n+ row contacts and Y-p+ column contacts have been used to measure the optical response of the individual pixels. The photo-response of these 8μm and other 200μm pixels under a 2ns optical pulse excitation from an Optical-Parametric-Oscillator (OPO), shows a peak responsivity of ~0.03A/W and 0.2mA/W, respectively, at λ~3.7μm. Temporal response of this detector array is seen to have a fast response ~10ns followed typical slow decay with ringing, attributed to impedance mismatch of the connecting co-axial cables. In conclusion, response times of a few ns have been measured in 8µm pixels of a 128x128 array. Although fs-laser anneal has been found to be useful in increasing the inter-pixel isolation in InAs/GaSb T2SL arrays by QW inter-mixing, it has not been found to be suitable for passivation of full RIE etched mesa structures with vertical walls on InAs/GaSb T2SL.

Keywords: band-gap blue-shift, fs-laser-anneal, InAs/GaSb T2SL, Inter-pixel isolation, ns-Response, photodiode array

Procedia PDF Downloads 152

Authors: Yibeltal T. Bayou, Yohana S. Mashalla, Gloria Thupayagale-Tshweneagae

Abstract:

Background: Maternal mortality has been shown to be lower in urban areas than in rural areas. However, disparities for the fast-growing population of urban poor who struggle as much their rural counterparts to access quality healthcare are masked by the urban averages. The aim of this paper is to report on the findings of antenatal adequacy among slum residents in Addis Ababa, Ethiopia. Methods and Materials: A quantitative and cross-sectional community-based study design was employed. A stratified two-stage cluster sampling technique was used to determine the sample and data was collected using structured questionnaire administered to 837 women aged 15-49 years. Binary logistic regression models were employed to identify predictors of adequacy of antenatal care. Results: The majority of slum residents did not have adequate antenatal care services i.e., only 50.7%, 19.3% and 10.2% of the slum resident women initiated early antenatal care, received adequate antenatal care service contents and had overall adequate antenatal care services. Pregnancy intention, educational status and place of ANC visits were important determinant factors for adequacy of ANC in the study area. Women with secondary and above educational status were 2.9 times more likely to have overall adequate care compared to those with no formal education. Similarly, women whose last pregnancy was intended and clients of private healthcare facilities were 1.8 and 2.8 times more likely to have overall adequate antenatal care compared to those whose last pregnancy was unintended and clients of public healthcare facilities respectively. Conclusion: In order to improve ANC adequacy in the study area, the policymaking, planning, and implementation processes should focus on the poor adequacy of ANC among the disadvantaged groups in particular and the slum residents in general.

Keywords: Addis Ababa, adequacy of antenatal care, slum residents, maternal mortality

Procedia PDF Downloads 423

Authors: Venkateswar Pujari

Abstract:

This study tries to investigate the complex interplay between control, awareness, and attention in human cognitive processes. The fundamental elements of cognitive functioning that play a significant role in influencing perception, decision-making, and behavior are attention, awareness, and control. Understanding how they interact can help us better understand how our minds work and may even increase our understanding of cognitive science and its therapeutic applications. The study uses an empirical methodology to examine the relationships between attention, awareness, and control by integrating different experimental paradigms and neuropsychological tests. To ensure the generalizability of findings, a wide sample of participants is chosen, including people with various cognitive profiles and ages. The study is structured into four primary parts, each of which focuses on one component of how attention, awareness, and control interact: 1. Evaluation of Attentional Capacity and Selectivity: In this stage, participants complete established attention tests, including the Stroop task and visual search tasks. 2. Evaluation of Awareness Degrees: In the second stage, participants' degrees of conscious and unconscious awareness are assessed using perceptual awareness tasks such as masked priming and binocular rivalry tasks. 3. Investigation of Cognitive Control Mechanisms: In the third phase, reaction inhibition, cognitive flexibility, and working memory capacity are investigated using exercises like the Wisconsin Card Sorting Test and the Go/No-Go paradigm. 4. Results Integration and Analysis: Data from all phases are integrated and analyzed in the final phase. To investigate potential links and prediction correlations between attention, awareness, and control, correlational and regression analyses are carried out. The study's conclusions shed light on the intricate relationships that exist between control, awareness, and attention throughout cognitive function. The findings may have consequences for cognitive psychology, neuroscience, and clinical psychology by providing new understandings of cognitive dysfunctions linked to deficiencies in attention, awareness, and control systems.

Keywords: attention, awareness, control, cognitive functioning, neuropsychological assessment

Procedia PDF Downloads 91

Authors: Nikat Parveen, M. Ananthi

Abstract:

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

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

Procedia PDF Downloads 341

Authors: Anshika Kankane, Dongshik Kang

Abstract:

Marine debris has a significant influence on coastal environments, damaging biodiversity, and causing loss and damage to marine and ocean sector. A functional cost-effective and automatic approach has been used to look up at this problem. Computer vision combined with a deep learning-based model is being proposed to identify and categorize marine debris of seven kinds on different beach locations of Japan. This research compares state-of-the-art deep learning models with a suggested model architecture that is utilized as a feature extractor for debris categorization. The model is being proposed to detect seven categories of litter using a manually constructed debris dataset, with the help of Mask R-CNN for instance segmentation and a shape matching network called HOGShape, which can then be cleaned on time by clean-up organizations using warning notifications of the system. The manually constructed dataset for this system is created by annotating the images taken by fixed KaKaXi camera using CVAT annotation tool with seven kinds of category labels. A pre-trained HOG feature extractor on LIBSVM is being used along with multiple templates matching on HOG maps of images and HOG maps of templates to improve the predicted masked images obtained via Mask R-CNN training. This system intends to timely alert the cleanup organizations with the warning notifications using live recorded beach debris data. The suggested network results in the improvement of misclassified debris masks of debris objects with different illuminations, shapes, viewpoints and litter with occlusions which have vague visibility.

Keywords: computer vision, debris, deep learning, fixed live camera images, histogram of gradients feature extractor, instance segmentation, manually annotated dataset, multiple template matching

Procedia PDF Downloads 106

Authors: Faisal Kalota

Abstract:

Big Data and analytics have gained a huge momentum in recent years. Big Data feeds into the field of Learning Analytics (LA) that may allow academic institutions to better understand the learners’ needs and proactively address them. Hence, it is important to have an understanding of Big Data and its applications. The purpose of this descriptive paper is to provide an overview of Big Data, the technologies used in Big Data, and some of the applications of Big Data in education. Additionally, it discusses some of the concerns related to Big Data and current research trends. While Big Data can provide big benefits, it is important that institutions understand their own needs, infrastructure, resources, and limitation before jumping on the Big Data bandwagon.

Keywords: big data, learning analytics, analytics, big data in education, Hadoop

Procedia PDF Downloads 426

Authors: Burak Oksuzoglu, Savas Yildirim, Ferhat Kutlu

Abstract:

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

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

Procedia PDF Downloads 146