Search results for: convolutional long short-term memory

Authors: Muhammad Nooraiman bin Noorashid, Mohd Sharizuan bin Mohd Omar, Mohd Zabri Adil bin Talib, Aswami Fadillah bin Mohd Ariffin

Abstract:

Nowadays cryptocurrency has become a global phenomenon known to most people. People using this alternative digital money to do a transaction in many ways (e.g. Used for online shopping, wealth management, and fundraising). However, this digital asset also widely used in criminal activities since its use decentralized control as opposed to centralized electronic money and central banking systems and this makes a user, who used this currency invisible. The high-value exchange of these digital currencies also has been a target to criminal activities. The cryptocurrency crimes have become a challenge for the law enforcement to analyze and to proof the evidence as criminal devices. In this paper, our focus is more on bitcoin cryptocurrency and the possible artifacts that can be obtained from the different type of digital wallet, which is software and browser-based application. The process memory and physical hard disk are examined with the aims of identifying and recovering potential digital evidence. The stage of data acquisition divided by three states which are the initial creation of the wallet, transaction that consists transfer and receiving a coin and the last state is after the wallet is being deleted. Findings from this study suggest that both data from software and browser type of wallet process memory is a valuable source of evidence, and many of the artifacts found in process memory are also available from the application and wallet files on the client computer storage.

Keywords: cryptocurrency, bitcoin, digital wallet, digital forensics

Procedia PDF Downloads 340

Authors: Jaspal Rana, Varinder Singh

Abstract:

Oxidative stress has been identified as an underlying cause of ischemia-reperfusion (IR) related cognitive dysfunction and brain damage. Therefore, antioxidant based therapies to treat IR injury are being investigated. Allium cepa L. (onion) is used as culinary medicine and is documented to have marked antioxidant effects. Hence, the present study was designed to evaluate the effect of A. cepa outer scale extract (ACE) against IR induced cognition and biochemical deficit in mice. ACE was prepared by maceration with 70% methanol and fractionated into ethylacetate and aqueous fractions. Bilateral common carotid artery occlusion for 10 min, followed by 24 h reperfusion, was used to induce cerebral IR injury. Following IR injury, ACE (100 and 200 mg/kg) was administered orally to animals for 7 days once daily. Behavioral outcomes (memory and sensorimotor functions) were evaluated using Morris water maze and neurological severity score. Cerebral infarct size, brain thiobarbituric acid reactive species, reduced glutathione, and superoxide dismutase activity were also determined. Treatment with ACE significantly ameliorated IR mediated deterioration of memory and sensorimotor functions and rose in brain oxidative stress in animals. The results of the present investigation revealed that ACE improved functional outcomes after cerebral IR injury which may be attributed to its antioxidant properties.

Keywords: allium cepa, cerebral ischemia, memory, sensorimotor

Procedia PDF Downloads 113

Authors: Jingting Luo, Yong Wang, Ying Wang

Abstract:

Pedestrian detection in image or video data is a very important and challenging task in security surveillance. The difficulty of this task is to locate and detect pedestrians of different scales in complex scenes accurately. To solve these problems, a deep neural network (RT-YOLOv3) is proposed to realize real-time pedestrian detection at different scales in security monitoring. RT-YOLOv3 improves the traditional YOLOv3 algorithm. Firstly, the deep residual network is added to extract vehicle features. Then six convolutional neural networks with different scales are designed and fused with the corresponding scale feature maps in the residual network to form the final feature pyramid to perform pedestrian detection tasks. This method can better characterize pedestrians. In order to further improve the accuracy and generalization ability of the model, a hybrid pedestrian data set training method is used to extract pedestrian data from the VOC data set and train with the INRIA pedestrian data set. Experiments show that the proposed RT-YOLOv3 method achieves 93.57% accuracy of mAP (mean average precision) and 46.52f/s (number of frames per second). In terms of accuracy, RT-YOLOv3 performs better than Fast R-CNN, Faster R-CNN, YOLO, SSD, YOLOv2, and YOLOv3. This method reduces the missed detection rate and false detection rate, improves the positioning accuracy, and meets the requirements of real-time detection of pedestrian objects.

Keywords: pedestrian detection, feature detection, convolutional neural network, real-time detection, YOLOv3

Procedia PDF Downloads 141

Authors: Jyoti Rani, Ashima Anand, Shivendra Shivani

Abstract:

In recent years, physiological signals obtained in telemedicine have been stored independently from patient information. In addition, people have increasingly turned to mobile devices for information on health-related topics. Major authentication and security issues may arise from this storing, degrading the reliability of diagnostics. This study introduces an approach to reversible watermarking, which ensures security by utilizing the electrocardiogram (ECG) signal as a carrier for embedding patient information. In the proposed work, Pan-Tompkins++ is employed to convert the 1D ECG signal into a 2D signal. The frequency subbands of a signal are extracted using RDWT(Redundant discrete wavelet transform), and then one of the subbands is subjected to MSVD (Multiresolution singular valued decomposition for masking. Finally, the encrypted watermark is embedded within the signal. The experimental results show that the watermarked signal obtained is indistinguishable from the original signals, ensuring the preservation of all diagnostic information. In addition, the DnCNN (Denoising convolutional neural network) concept is used to denoise the retrieved watermark for improved accuracy. The proposed ECG signal-based watermarking method is supported by experimental results and evaluations of its effectiveness. The results of the robustness tests demonstrate that the watermark is susceptible to the most prevalent watermarking attacks.

Keywords: ECG, VMD, watermarking, PanTompkins++, RDWT, DnCNN, MSVD, chaotic encryption, attacks

Procedia PDF Downloads 101

Authors: Rumeysa Gunduz, Dirk Koester, Thomas Schack

Abstract:

Previous behavioral studies have shown that working memory (WM) and manual actions share limited capacity cognitive resources, which in turn results in execution costs of manual actions in WM. However, to the best of our knowledge, there is no study investigating the neurophysiology of execution costs. The current study aims to fill this research gap investigating the neurophysiology of execution costs of grasping in WM phases (encoding, maintenance, retrieval) considering verbal and visuospatial domains of WM. A WM-grasping dual task paradigm was implemented to examine execution costs. Baseline single task required performing verbal or visuospatial version of a WM task. Dual task required performing the WM task embedded in a high precision grasp to place task. 30 participants were tested in a 2 (single vs. dual task) x 2 (visuo-spatial vs. verbal WM) within subject design. Event related potentials (ERPs) were extracted for each WM phase separately in the single and dual tasks. Memory performance for visuospatial WM, but not for verbal WM, was significantly lower in the dual task compared to the single task. Encoding related ERPs in the single task revealed different ERPs of verbal WM and visuospatial WM at bilateral anterior sites and right posterior site. In the dual task, bilateral anterior difference disappeared due to bilaterally increased anterior negativities for visuospatial WM. Maintenance related ERPs in the dual task revealed different ERPs of verbal WM and visuospatial WM at bilateral posterior sites. There was also anterior negativity for visuospatial WM. Retrieval related ERPs in the single task revealed different ERPs of verbal WM and visuospatial WM at bilateral posterior sites. In the dual task, there was no difference between verbal WM and visuospatial WM. Behavioral and ERP findings suggest that execution of grasping shares cognitive resources only with visuospatial WM, which in turn results in domain specific execution costs. Moreover, ERP findings suggest unique patterns of costs in each WM phase, which supports the idea that each WM phase reflects a separate cognitive process. This study not only contributes to the understanding of cognitive principles of manual action control, but also contributes to the understanding of WM as an entity consisting of separate modalities and cognitive processes.

Keywords: dual task, grasping execution, neurophysiology, working memory domains, working memory phases

Procedia PDF Downloads 426

Authors: Yao Fu, Xingli Zhang, Jiannong Shi

Abstract:

Visual working memory (VWM) capacity is the ability to maintain and manipulate short-term information which is not currently available. It is well known for its significance to form the basis of numerous cognitive abilities and its limitation in holding information. VWM span, the most popular measurable indicator, is found to reach the adult level (3-4 items) around 12-13 years’ old, while less is known about the precision development of the VWM capacity. By using simultaneously delayed responses paradigm, the present study investigates the development of VWM precision among 6-18-year-old children and young adults, besides its possible relationships with fluid intelligence and span. Results showed that precision and span both increased with age, and precision reached the maximum in 16-17 age-range. Moreover, when remembering 3 simultaneously presented items, the probability of remembering target item correlated with fluid intelligence and the probability of wrap errors (misbinding target and non-target items) correlated with age. When remembering more items, children had worse performance than adults due to their wrap errors. Compared to span, VWM precision was effective predictor of intelligence even after controlling for age. These results suggest that unlike VWM span, precision developed in a slow, yet longer fashion. Moreover, decreasing probability of wrap errors might be the main reason for the development of precision. Last, precision correlated more closely with intelligence than span in childhood and adolescence, which might be caused by the probability of remembering target item.

Keywords: fluid intelligence, precision, visual working memory, wrap errors

Procedia PDF Downloads 276

Authors: Birge Yildirim Okta

Abstract:

This paper aims to narrate the story of Atatürk Cultural Center in Taksim Square, which was demolished in 2018 and discuss its architectonic as a social place of memory and its existence and demolishment as the space of politics. The paper uses narrative discourse analysis to research Atatürk Cultural Center (AKM) as a place of memory and space of politics from the establishment of the Turkish Republic (1923) until today. After the establishment of the Turkish Republic, one of the most important implementations in Taksim Square, reflecting the internationalist style, was the construction of the Opera Building in Prost Plan. The first design of the opera building belonged to Aguste Perret, which could not be implemented due to economic hardship during World War II. Later the project was designed by architects Feridun Kip and Rüknettin Güney in 1946 but could not be completed due to the 1960 military coup. Later the project was shifted to another architect Hayati Tabanlıoglu, with a change in its function as a cultural center. Eventually, the construction of the building was completed in 1969 in a completely different design. AKM became a symbol of republican modernism not only with its modern architectural style but also with it is function as the first opera building of the Republic, reflecting the western, modern cultural heritage by professional groups, artists, and the intelligentsia. In 2005, Istanbul’s council for the protection of cultural heritage decided to list AKM as a grade 1 cultural heritage, ending a period of controversy which saw calls for the demolition of the center as it was claimed, it ended its useful lifespan. In 2008 the building was announced to be closed for repairs and restoration. Over the following years, the building was demolished piece by piece silently while the Taksim mosque has been built just in front of Atatürk Cultural Center. Belonging to the early republican period AKM was a representation of the cultural production of modern society for the emergence and westward looking, secular public space in Turkey. Its erasure from the Taksim scene under the rule of the conservative government, Justice, and Development Party, and the construction of the Taksim mosque in front of AKM’s parcel is also representational. The question of governing the city through space has always been an important aspect for governments, those holding political power since cities are the chaotic environments that are seen as a threat for the governments, carrying the tensions of the proletariat or the contradictory groups. The story of AKM as a dispositive or a regulatory apparatus demonstrates how space itself is becoming a political medium, to transform the socio-political condition. The paper narrates the existence and demolishment of the Atatürk Cultural Center by discussing the constructed and demolished building as a place of memory and space of politics.

Keywords: space of politics, place of memory, Atatürk Cultural Center, Taksim square, collective memory

Procedia PDF Downloads 140

Authors: Celine Davis

Abstract:

The novel coronavirus 2019 (COVID-19) is an infectious disease caused by the virus SARS-CoV-2, which has detrimental respiratory, cardiovascular, and neurological effects impacting over one million lives in the United States. New researches has emerged indicating long-term neurologic consequences in those who survive COVID-19 infections, including more than seven million Americans and another 27 million people worldwide. These consequences include attentional deficits, memory impairments, executive function deficits and aphasia-like symptoms which fall within the purview of speech-language pathology. The National Health Interview Survey (NHIS) is a comprehensive annual survey conducted by the National Center for Health Statistics (NCHS), a branch of the Centers for Disease Control and Prevention (CDC) in the United States. The NHIS is one of the most significant sources of health-related data in the country and has been conducted since 1957. The longitudinal nature of the study allows for analysis of trends in various variables over the years, which can be essential for understanding societal changes and making treatment recommendations. This current study will utilize NHIS data from 2020-2022 which contained interview questions specifically related to COVID-19. Adult cases of individuals between the ages of 18-50 diagnosed with COVID-19 in the United States during 2020-2022 will be identified using the National Health Interview Survey (NHIS). Multiple regression analysis of self-reported data confirming COVID-19 infection status and challenges with concentration, communication, and memory will be performed. Latent class analysis will be utilized to identify subgroups in the population to indicate whether certain demographic groups have higher susceptibility to cognitive-linguistic deficits associated with COVID-19. Completion of this study will reveal whether there is an association between confirmed COVID-19 diagnosis and heightened incidence of cognitive deficits and subsequent implications, if any, on activities of daily living. This study is distinct in its aim to utilize national survey data to explore the relationship between confirmed COVID-19 diagnosis and the prevalence of cognitive-communication deficits with a secondary focus on resulting activity limitations. To the best of the author’s knowledge, this will be the first large-scale epidemiological study investigating the associations between cognitive-linguistic deficits, COVID-19 and implications on activities of daily living in the United States population. These findings will highlight the need for targeted interventions and support services to address the cognitive-communication needs of individuals recovering from COVID-19, thereby enhancing their overall well-being and functional outcomes.

Keywords: cognition, COVID-19, language, limitations, memory, NHIS

Procedia PDF Downloads 53

Authors: A. M. John-Otumu, M. M. Rahman, M. C. Onuoha, E. P. Ojonugwa

Abstract:

A Convolutional Neural Network (CNN) model for predicting Lassa fever was built using Python 3.8.0 programming language, alongside Keras 2.2.4 and TensorFlow 2.6.1 libraries as the development environment in order to reduce the current high risk of Lassa fever in West Africa, particularly in Nigeria. The study was prompted by some major flaws in existing conventional laboratory equipment for diagnosing Lassa fever (RT-PCR), as well as flaws in AI-based techniques that have been used for probing and prognosis of Lassa fever based on literature. There were 15,679 blood smear microscopic image datasets collected in total. The proposed model was trained on 70% of the dataset and tested on 30% of the microscopic images in avoid overfitting. A 3x3x3 convolution filter was also used in the proposed system to extract features from microscopic images. The proposed CNN-based model had a recall value of 96%, a precision value of 93%, an F1 score of 95%, and an accuracy of 94% in predicting and accurately classifying the images into clean or infected samples. Based on empirical evidence from the results of the literature consulted, the proposed model outperformed other existing AI-based techniques evaluated. If properly deployed, the model will assist physicians, medical laboratory scientists, and patients in making accurate diagnoses for Lassa fever cases, allowing the mortality rate due to the Lassa fever virus to be reduced through sound decision-making.

Keywords: artificial intelligence, ANN, blood smear, CNN, deep learning, Lassa fever

Procedia PDF Downloads 120

Authors: Yuanqing Li, Changyi Lei, Zhaopeng Xue, Zhuo Zheng, Yanbo Long

Abstract:

In agricultural production and breeding, implementing automatic picking robot in orchard farming to reduce human labour and error is challenging. The core function of it is automatic identification based on machine vision. This paper focuses on apple detection and counting in orchards and implements several deep learning methods. Extensive datasets are used and a semi-automatic annotation method is proposed. The proposed deep learning models are in state-of-the-art YOLO family. In view of the essence of the models with various backbones, a multi-dimensional comparison in details is made in terms of counting accuracy, mAP and model memory, laying the foundation for realising automatic precision agriculture.

Keywords: agricultural object detection, deep learning, machine vision, YOLO family

Procedia PDF Downloads 197

Authors: Felipe A. Guth, Shane Ward, Kevin McDonnell

Abstract:

The assessment of disease levels in crop fields is an important and time-consuming task that generally relies on expert knowledge of trained individuals. Image classification in agriculture problems historically has been based on classical machine learning strategies that make use of hand-engineered features in the top of a classification algorithm. This approach tends to not produce results with high accuracy and generalization to the classes classified by the system when the nature of the elements has a significant variability. The advent of deep convolutional neural networks has revolutionized the field of machine learning, especially in computer vision tasks. These networks have great resourcefulness of learning and have been applied successfully to image classification and object detection tasks in the last years. The objective of this work was to propose a new method based on deep learning convolutional neural networks towards the task of disease level monitoring. Common RGB images of winter wheat were obtained during a growing season. Five categories of disease levels presence were produced, in collaboration with agronomists, for the algorithm classification. Disease level tasks performed by experts provided ground truth data for the disease score of the same winter wheat plots were RGB images were acquired. The system had an overall accuracy of 84% on the discrimination of the disease level classes.

Keywords: crop disease assessment, deep learning, precision agriculture, residual neural networks

Procedia PDF Downloads 331

Authors: Aleksander Veraksa, Alla Tvardovskaya, Margarita Gavrilova, Vera Yakupova, Martin Musálek

Abstract:

Considering the current agreement on the significance of executive functions, there is growing interest in determining factors that contribute to the development of these skills, especially during the preschool period. Although multiple studies have been focusing on links between physical activity, physical fitness and executive functions, this topic was more investigated in schoolchildren and adults than in preschoolers. The aim of the current study was to identify different levels of physical fitness among pre-schoolers, followed by an analysis of differences in their executive functions. Participants were 261 5-6-years old children. Inhibitory control and working memory were positively linked with physical fitness. Cognitive flexibility was not associated with physical fitness. The research findings are considered from neuropsychological grounds, Jean Piaget's theory of cognitive development, and the cultural-historical approach.

Keywords: cognitive flexibility, inhibitory control, physical activity, physical fitness, working memory.

Procedia PDF Downloads 97

Authors: Zhicheng Han

Abstract:

This study examines the correlation between knowledge of formulaic language, working memory (WM), and phonological short-term memory (PSTM) in Chinese L2 learners of English. This study investigates if WM and PSTM correlate differently to the acquisition of formulaic language, which may be relevant for the discourse around the conceptualization of formulas. Connectionist approaches have lead scholars to argue that formulas are form-meaning connections stored whole, making PSTM significant in the acquisitional process as it pertains to the storage and retrieval of chunk information. Generativist scholars, on the other hand, argued for active participation of interlanguage grammar in the acquisition and use of formulaic language, where formulas are represented in the mind but retain the internal structure built around a lexical core. This would make WM, especially the processing component of WM an important cognitive factor since it plays a role in processing and holding information for further analysis and manipulation. The current study asked L1 Chinese learners of English enrolled in graduate programs in China to complete a preference raking task where they rank their preference for formulas, grammatical non-formulaic expressions, and ungrammatical phrases with and without the lexical core in academic contexts. Participants were asked to rank the options in order of the likeliness of them encountering these phrases in the test sentences within academic contexts. Participants’ syntactic proficiency is controlled with a cloze test and grammar test. Regression analysis found a significant relationship between the processing component of WM and preference of formulaic expressions in the preference ranking task while no significant correlation is found for PSTM or syntactic proficiency. The correlational analysis found that WM, PSTM, and the two proficiency test scores have significant covariates. However, WM and PSTM have different predictor values for participants’ preference for formulaic language. Both storage and processing components of WM are significantly correlated with the preference for formulaic expressions while PSTM is not. These findings are in favor of the role of interlanguage grammar and syntactic knowledge in the acquisition of formulaic expressions. The differing effects of WM and PSTM suggest that selective attention to and processing of the input beyond simple retention play a key role in successfully acquiring formulaic language. Similar correlational patterns were found for preferring the ungrammatical phrase with the lexical core of the formula over the ones without the lexical core, attesting to learners’ awareness of the lexical core around which formulas are constructed. These findings support the view that formulaic phrases retain internal syntactic structures that are recognized and processed by the learners.

Keywords: formulaic language, working memory, phonological short-term memory, academic language

Procedia PDF Downloads 62

Authors: Changshan Zhang, Zhijin Yu, Shixing Fan

Abstract:

A comprehensive hazard evaluation for coal self-heating in composite long-wall gobs is heavily dependent on computational simulation. In this study, the spatial distributions of cracks which caused significant air leakage were simulated by universal distinct element code (UDEC) simulation. Based on the main routes of air leakage and characteristics of coal self-heating, a computational fluid dynamics (CFD) modeling was conducted to model the coal spontaneous combustion dangerous area in composite long-wall gobs. The results included the oxygen concentration distributions and temperature profiles showed that the numerical approach is validated by comparison with the test data. Furthermore, under the conditions of specific engineering, the major locations where some techniques for extinguishing and preventing long-wall gob fires need to be put into practice were also examined.

Keywords: computational simulation, UDEC simulation, coal self-heating, CFD modeling, long-wall gobs

Procedia PDF Downloads 313

Authors: Hong Fan, Lifang Gao, Feng Zhan

Abstract:

This paper examines the influence of local gambling attitudes on a firm's long-term financial performance. Firms located in gambling-prone regions may be more willing to take risks, thus spending more on innovative projects. However, firms in such regions may also be likely to choose projects impulsively and allocate resources inefficiently. By studying Chinese publicly listed firms from 2010 to 2017, we find that firms in more gambling-prone regions invest more in R&D. Both local gambling attitudes and firms’ R&D spending are positively associated with firms’ long-term financial performance. More importantly, our study reveals that the positive impact of R&D spending on firms’ long-term financial performance is weakened by gambling-friendly attitudes, probably because firms in gambling-prone regions are more likely to overinvest in risky projects. This effect is stronger for larger firms, state-owned enterprises (SOEs), firms with more government subsidies, and firms with weaker internal control.

Keywords: regional gambling attitudes, long-term financial performance, R&D, risk, local bias

Procedia PDF Downloads 114

Authors: Duygu Kan, Mehmet Cayoren

Abstract:

Sommerfeld-integrals (SIs) are commonly encountered in electromagnetics problems involving analysis of antennas and scatterers embedded in planar multilayered media. Generally speaking, the analytical solution of SIs is unavailable, and it is well known that numerical evaluation of SIs is very time consuming and computationally expensive due to the highly oscillating and slowly decaying nature of the integrands. Therefore, fast computation of SIs has a paramount importance. In this paper, a parallel code has been developed to speed up the computation of SI in the framework of calculation of dyadic Green’s function in multilayered media. OpenMP shared memory approach is used to parallelize the SI algorithm and resulted in significant time savings. Moreover accelerating the computation of dyadic Green’s function is discussed based on the parallel SI algorithm developed.

Keywords: Sommerfeld-integrals, multilayer dyadic Green’s function, OpenMP, shared memory parallel programming

Procedia PDF Downloads 247

Authors: Felib Ayman Shawky Salem

Abstract:

Nowadays crypto currency has become a global phenomenon known to most people. People using this alternative digital money to do a transaction in many ways (e.g. Used for online shopping, wealth management, and fundraising). However, this digital asset also widely used in criminal activities since its use decentralized control as opposed to centralized electronic money and central banking systems and this makes a user, who used this currency invisible. The high-value exchange of these digital currencies also has been a target to criminal activities. The crypto currency crimes have become a challenge for the law enforcement to analyze and to proof the evidence as criminal devices. In this paper, our focus is more on bitcoin crypto currency and the possible artifacts that can be obtained from the different type of digital wallet, which is software and browser-based application. The process memory and physical hard disk are examined with the aims of identifying and recovering potential digital evidence. The stage of data acquisition divided by three states which are the initial creation of the wallet, transaction that consists transfer and receiving a coin and the last state is after the wallet is being deleted. Findings from this study suggest that both data from software and browser type of wallet process memory is a valuable source of evidence, and many of the artifacts found in process memory are also available from the application and wallet files on the client computer storage.

Keywords: cryptocurrency, bitcoin, payment methods, blockchain, appropriation, online retailers, TOE framework, disappropriation, non-appropriationBitCoin, financial protection, crypto currency, money laundering cryptocurrency, digital wallet, digital forensics

Procedia PDF Downloads 41

Authors: Victor N. Anisimov, Igor E. Serov, Ksenia M. Kolkova, Natalia V. Galkina

Abstract:

The problem of memorability of the advertising content is closely connected with the key issues of neuromarketing. The memorability of the advertising content contributes to the marketing effectiveness of the promoted product. Significant directions of studying the phenomenon of memorability are the memorability of the brand (detected through the memorability of the logo) and the memorability of the product offer (detected through the memorization of dynamic audiovisual advertising content - commercial). The aim of this work is to reveal the predictors of memorization of static and dynamic audiovisual stimuli (logos and commercials). An important direction of the research was revealing differences in psychophysiological correlates of memorability between static and dynamic audiovisual stimuli. We assumed that static and dynamic images are perceived in different ways and may have a difference in the memorization process. Objective methods of recording psychophysiological parameters while watching static and dynamic audiovisual materials are well suited to achieve the aim. The electroencephalography (EEG) method was performed with the aim of identifying correlates of the memorability of various stimuli in the electrical activity of the cerebral cortex. All stimuli (in the groups of statics and dynamics separately) were divided into 2 groups – remembered and not remembered based on the results of the questioning method. The questionnaires were filled out by survey participants after viewing the stimuli not immediately, but after a time interval (for detecting stimuli recorded through long-term memorization). Using statistical method, we developed the classifier (statistical model) that predicts which group (remembered or not remembered) stimuli gets, based on psychophysiological perception. The result of the statistical model was compared with the results of the questionnaire. Conclusions: Predictors of the memorability of static and dynamic stimuli have been identified, which allows prediction of which stimuli will have a higher probability of remembering. Further developments of this study will be the creation of stimulus memory model with the possibility of recognizing the stimulus as previously seen or new. Thus, in the process of remembering the stimulus, it is planned to take into account the stimulus recognition factor, which is one of the most important tasks for neuromarketing.

Keywords: memory, commercials, neuromarketing, EEG, branding

Procedia PDF Downloads 251

Authors: Deokho Kim, Wonwoo Lee, Jaewoong Lee, Teresa Ng, Gun-Ill Lee, Jiwon Jeong

Abstract:

This paper presents a method for improving object search accuracy using a deep learning model. A major limitation to provide accurate similarity with deep learning is the requirement of huge amount of data for training pairwise similarity scores (metrics), which is impractical to collect. Thus, similarity scores are usually trained with a relatively small dataset, which comes from a different domain, causing limited accuracy on measuring similarity. For this reason, this paper proposes a deep learning model that can be trained with a significantly small amount of data, a clustered data which of each cluster contains a set of visually similar images. In order to measure similarity distance with the proposed method, visual features of two images are extracted from intermediate layers of a convolutional neural network with various pooling methods, and the network is trained with pairwise similarity scores which is defined zero for images in identical cluster. The proposed method outperforms the state-of-the-art object similarity scoring techniques on evaluation for finding exact items. The proposed method achieves 86.5% of accuracy compared to the accuracy of the state-of-the-art technique, which is 59.9%. That is, an exact item can be found among four retrieved images with an accuracy of 86.5%, and the rest can possibly be similar products more than the accuracy. Therefore, the proposed method can greatly reduce the amount of training data with an order of magnitude as well as providing a reliable similarity metric.

Keywords: visual search, deep learning, convolutional neural network, machine learning

Procedia PDF Downloads 215

Authors: Mohamed Lotfy, Ghada Soliman

Abstract:

Recognizing Arabic dot-matrix digits is a challenging problem due to the unique characteristics of dot-matrix fonts, such as irregular dot spacing and varying dot sizes. This paper presents an approach for recognizing Arabic digits printed in dot matrix format. The proposed model is based on Convolutional Neural Networks (CNN) that take the dot matrix as input and generate embeddings that are rounded to generate binary representations of the digits. The binary embeddings are then used to perform Optical Character Recognition (OCR) on the digit images. To overcome the challenge of the limited availability of dotted Arabic expiration date images, we developed a True Type Font (TTF) for generating synthetic images of Arabic dot-matrix characters. The model was trained on a synthetic dataset of 3287 images and 658 synthetic images for testing, representing realistic expiration dates from 2019 to 2027 in the format of yyyy/mm/dd. Our model achieved an accuracy of 98.94% on the expiry date recognition with Arabic dot matrix format using fewer parameters and less computational resources than traditional CNN-based models. By investigating and presenting our findings comprehensively, we aim to contribute substantially to the field of OCR and pave the way for advancements in Arabic dot-matrix character recognition. Our proposed approach is not limited to Arabic dot matrix digit recognition but can also be extended to text recognition tasks, such as text classification and sentiment analysis.

Keywords: computer vision, pattern recognition, optical character recognition, deep learning

Procedia PDF Downloads 93

Authors: Goutam Kumar Ghorai, Sandip Sadhukhan, Arpita Sarkar, Debprasad Sinha, G. Sarkar, Ashis K. Dhara

Abstract:

Diabetes mellitus is one of the most common chronic diseases in all countries and continues to increase in numbers significantly. Diabetic retinopathy (DR) is damage to the retina that occurs with long-term diabetes. DR is a major cause of blindness in the Indian population. Therefore, its early diagnosis is of utmost importance towards preventing progression towards imminent irreversible loss of vision, particularly in the huge population across rural India. The barriers to eye examination of all diabetic patients are socioeconomic factors, lack of referrals, poor access to the healthcare system, lack of knowledge, insufficient number of ophthalmologists, and lack of networking between physicians, diabetologists and ophthalmologists. A few diabetic patients often visit a healthcare facility for their general checkup, but their eye condition remains largely undetected until the patient is symptomatic. This work aims to focus on the design and development of a fully automated intelligent decision system for screening retinal fundus images towards detection of the pathophysiology caused by microaneurysm in the early stage of the diseases. Automated detection of microaneurysm is a challenging problem due to the variation in color and the variation introduced by the field of view, inhomogeneous illumination, and pathological abnormalities. We have developed aconvolutional neural network for efficient detection of microaneurysm. A loss function is also developed to handle severe class imbalance due to very small size of microaneurysms compared to background. The network is able to locate the salient region containing microaneurysms in case of noisy images captured by non-mydriatic cameras. The ground truth of microaneurysms is created by expert ophthalmologists for MESSIDOR database as well as private database, collected from Indian patients. The network is trained from scratch using the fundus images of MESSIDOR database. The proposed method is evaluated on DIARETDB1 and the private database. The method is successful in detection of microaneurysms for dilated and non-dilated types of fundus images acquired from different medical centres. The proposed algorithm could be used for development of AI based affordable and accessible system, to provide service at grass root-level primary healthcare units spread across the country to cater to the need of the rural people unaware of the severe impact of DR.

Keywords: retinal fundus image, deep convolutional neural network, early detection of microaneurysms, screening of diabetic retinopathy

Procedia PDF Downloads 141

Authors: Zhanfeng Ma, Zhiping Xiong, Hu Yin, Zhengwei She, Aditya P. Gurajada, Tianlun Chen, Ying Li

Abstract:

Many RDBMS vendors use B-tree index to achieve high performance for point queries and range queries, and some of them also employ hash index to further enhance the performance as hash table is more efficient for point queries. However, there are extra overheads to maintain a separate hash index, for example, hash mapping for all data records must always be maintained, which results in more memory space consumption; locking, logging and other mechanisms are needed to guarantee ACID, which affects the concurrency and scalability of the system. To relieve the overheads, Hash Cached B-tree (HCB) index is proposed in this paper, which consists of a standard disk-based B-tree index and an additional in-memory lock-free hash table. Initially, only the B-tree index is constructed for all data records, the hash table is built on the fly based on runtime workload, only data records accessed by point queries are indexed using hash table, this helps reduce the memory footprint. Changes to hash table are done using compare-and-swap (CAS) without performing locking and logging, this helps improve the concurrency and avoid contention. The hash table is also optimized to be cache conscious. HCB index is implemented in SAP ASE database, compared with the standard B-tree index, early experiments and customer adoptions show significant performance improvement. This paper provides an overview of the design of HCB index and reports the experimental results.

Keywords: B-tree, compare-and-swap, lock-free hash table, point queries, range queries, SAP ASE database

Procedia PDF Downloads 286

Authors: Gulfam Haider, sana danish

Abstract:

Convolutional Neural Networks (CNNs) have emerged as powerful tools for image classification, and the choice of optimizers profoundly affects their performance. The study of optimizers and their adaptations remains a topic of significant importance in machine learning research. While numerous studies have explored and advocated for various optimizers, the efficacy of these optimization techniques is still subject to scrutiny. This work aims to address the challenges surrounding the effectiveness of optimizers by conducting a comprehensive analysis and evaluation. The primary focus of this investigation lies in examining the performance of different optimizers when employed in conjunction with the popular activation function, Rectified Linear Unit (ReLU). By incorporating ReLU, known for its favorable properties in prior research, the aim is to bolster the effectiveness of the optimizers under scrutiny. Specifically, we evaluate the adjustment of these optimizers with both the original Softmax activation function and the modified ReLU activation function, carefully assessing their impact on overall performance. To achieve this, a series of experiments are conducted using a well-established benchmark dataset for image classification tasks, namely the Canadian Institute for Advanced Research dataset (CIFAR-10). The selected optimizers for investigation encompass a range of prominent algorithms, including Adam, Root Mean Squared Propagation (RMSprop), Adaptive Learning Rate Method (Adadelta), Adaptive Gradient Algorithm (Adagrad), and Stochastic Gradient Descent (SGD). The performance analysis encompasses a comprehensive evaluation of the classification accuracy, convergence speed, and robustness of the CNN models trained with each optimizer. Through rigorous experimentation and meticulous assessment, we discern the strengths and weaknesses of the different optimization techniques, providing valuable insights into their suitability for image classification tasks. By conducting this in-depth study, we contribute to the existing body of knowledge surrounding optimizers in CNNs, shedding light on their performance characteristics for image classification. The findings gleaned from this research serve to guide researchers and practitioners in making informed decisions when selecting optimizers and activation functions, thus advancing the state-of-the-art in the field of image classification with convolutional neural networks.

Keywords: deep neural network, optimizers, RMsprop, ReLU, stochastic gradient descent

Procedia PDF Downloads 125

Authors: Belbaly Nassim

Abstract:

Virtual teams (VT) initiatives, in which teams are geographically dispersed and communicate via modern computer-driven technologies, have attracted increasing attention from researchers and professionals. The growing need to examine how to balance and optimize VT is particularly important given the exposure experienced by companies when their employees encounter globalization and decentralization pressures to monitor VT performance. Hence, organization is regularly limited due to misalignment between the behavioral capabilities of the team’s dispersed competences and knowledge capabilities and how trust issues interplay and influence these VT dimensions and the effects of such exchanges. In fact, the future success of business depends on the extent to which VTs are managing efficiently their dispersed expertise, skills and knowledge to stimulate VT creativity. Transactive memory system (TMS) may enhance VT creativity using its three dimensons: knowledge specialization, credibility and knowledge coordination. TMS can be understood as a composition of both a structural component residing of individual knowledge and a set of communication processes among individuals. The individual knowledge is shared while being retrieved, applied and the learning is coordinated. TMS is driven by the central concept that the system is built on the distinction between internal and external memory encoding. A VT learns something new and catalogs it in memory for future retrieval and use. TMS uses the role of information technology to explain VT behaviors by offering VT members the possibility to encode, store, and retrieve information. TMS considers the members of a team as a processing system in which the location of expertise both enhances knowledge coordination and builds trust among members over time. We build on TMS dimensions to hypothesize the effects of specialization, coordination, and credibility on VT creativity. In fact, VTs consist of dispersed expertise, skills and knowledge that can positively enhance coordination and collaboration. Ultimately, this team composition may lead to recognition of both who has expertise and where that expertise is located; over time, the team composition may also build trust among VT members over time developing the ability to coordinate their knowledge which can stimulate creativity. We also assess the reciprocal relationship between TMS dimensions and VT creativity. We wish to use TMS to provide researchers with a theoretically driven model that is empirically validated through survey evidence. We propose that TMS provides a new way to enhance and balance VT creativity. This study also provides researchers insight into the use of TMS to influence positively VT creativity. In addition to our research contributions, we provide several managerial insights into how TMS components can be used to increase performance within dispersed VTs.

Keywords: virtual team creativity, transactive memory systems, specialization, credibility, coordination

Procedia PDF Downloads 172

Authors: Mazlynda Md Yusuf, Wafa' Mahadzir, Mohamad Yazis Ali Basah

Abstract:

Nowadays, financing long-term care for elderly people is a crucial issue, either towards the family members or the care institution. Corresponding with the growing number of ageing population in Malaysia, there’s a need of concern on the uncertaintiness of future family care and the need for long-term care services. Moreover, with the increasing cost of living, children feels the urge of needing to work and receive a fixed monthly income that results to sending their elderly parents to care institutions. Currently, in Malaysia, the rates for private nursing homes can amount up to RM 4,000 per month excluding medical treatments and other recurring expenses. These costs are expected to be paid using their Employees Provident Fund (EPF) savings that they accumulate during their working years, especially for those working under private sectors. Hence, this study identifies the adequacy of EPF in funding the cost of long-term care service during old age. This study used a hypothetical simulation model to simulate different scenarios. The findings of this study could be used for individuals to prepare on the importance of planning for retirement, especially with the increasing cost of long-term care services.

Keywords: long-term care cost, employees provident fund Malaysia, ageing population, Malaysian elderly

Procedia PDF Downloads 340

Authors: Masood Varshosaz, Kamyar Hasanpour

Abstract:

In recent years, we have seen growing interest in recognizing humans in drone images for post-disaster search and rescue operations. Deep learning algorithms have shown great promise in this area, but they often require large amounts of labeled data to train the models. To keep the data acquisition cost low, augmentation techniques can be used to create additional data from existing images. There are many techniques of such that can help generate variations of an original image to improve the performance of deep learning algorithms. While data augmentation is potentially assumed to improve the accuracy and robustness of the models, it is important to ensure that the performance gains are not outweighed by the additional computational cost or complexity of implementing the techniques. To this end, it is important to evaluate the impact of data augmentation on the performance of the deep learning models. In this paper, we evaluated the most currently available 2D data augmentation techniques on a standard convolutional network which was trained for recognizing humans in drone images. The techniques include rotation, scaling, random cropping, flipping, shifting, and their combination. The results showed that the augmented models perform 1-3% better compared to a base network. However, as the augmented images only contain the human parts already visible in the original images, a new data augmentation approach is needed to include the invisible parts of the human body. Thus, we suggest a new method that employs simulated 3D human models to generate new data for training the network.

Keywords: human recognition, deep learning, drones, disaster mitigation

Procedia PDF Downloads 93

Authors: Kayode A. Olaniyi, Olabanji F. Omotoye, Adeola A. Ogunleye

Abstract:

The skew detection and correction form an important part of digital document analysis. This is because uncompensated skew can deteriorate document features and can complicate further document image processing steps. Efficient text document analysis and digitization can rarely be achieved when a document is skewed even at a small angle. Once the documents have been digitized through the scanning system and binarization also achieved, document skew correction is required before further image analysis. Research efforts have been put in this area with algorithms developed to eliminate document skew. Skew angle correction algorithms can be compared based on performance criteria. Most important performance criteria are accuracy of skew angle detection, range of skew angle for detection, speed of processing the image, computational complexity and consequently memory space used. The standard Hough Transform has successfully been implemented for text documentation skew angle estimation application. However, the standard Hough Transform algorithm level of accuracy depends largely on how much fine the step size for the angle used. This consequently consumes more time and memory space for increase accuracy and, especially where number of pixels is considerable large. Whenever the Hough transform is used, there is always a tradeoff between accuracy and speed. So a more efficient solution is needed that optimizes space as well as time. In this paper, an improved Hough transform (HT) technique that optimizes space as well as time to robustly detect document skew is presented. The modified algorithm of Hough Transform presents solution to the contradiction between the memory space, running time and accuracy. Our algorithm starts with the first step of angle estimation accurate up to zero decimal place using the standard Hough Transform algorithm achieving minimal running time and space but lacks relative accuracy. Then to increase accuracy, suppose estimated angle found using the basic Hough algorithm is x degree, we then run again basic algorithm from range between ±x degrees with accuracy of one decimal place. Same process is iterated till level of desired accuracy is achieved. The procedure of our skew estimation and correction algorithm of text images is implemented using MATLAB. The memory space estimation and process time are also tabulated with skew angle assumption of within 00 and 450. The simulation results which is demonstrated in Matlab show the high performance of our algorithms with less computational time and memory space used in detecting document skew for a variety of documents with different levels of complexity.

Keywords: hough-transform, skew-detection, skew-angle, skew-correction, text-document

Procedia PDF Downloads 158

Authors: Cristina Greco

Abstract:

The spread of the digital and we-based technologies has led to a transformation process, which has coincided with an increase in the number of cases who are beyond the mainstream storytelling and its codes on the interaction with the user. On the base of a previous research on i-docs and virtual museums, this study analyses interactive and immersive online Graphic Novel – one-page, animated, illustrated, and hybrid – to reflect on the transformational implications of this expressive form on the user perception, remembrance, and awareness. The way in which the user experiences a certain level of interaction with the story and immersion in the semantic and figurative universe would bring user’s attention, activating introspection and self-reflection processes, perception, imagination, and creativity. This would have to do with the involvement of different senses – visual, proprioceptive, tactile, auditory, and vestibular – and the activation of a phenomenon of synaesthesia (involuntary cross-modal sensory association) – where, for example, the aural reconnect the user to another sense, providing a multisensory experience. The case studies show specific forms of interactive and immersive graphic novel and reflect on application that has sought to engage innovative ways to communicate different messages and stimulate cultural memory and collective awareness. The visual semiotic and narrative analysis of the distinctive traits of such a complex textuality, along with a study of the user’s experience through observation in naturalistic settings and interviews, allows us to question the functioning of these configurations, with regard to the relationships between the figurative dimension, the perceptive activity, and their impact on the user’s engagement.

Keywords: collective awareness, cultural memory, graphic novel, interactive and immersive storytelling

Procedia PDF Downloads 149

Authors: Ying Ying Liu, Austin Cooke, Parimala Thulasiraman

Abstract:

Internet of Things (IoT) has attracted a recent spark in research on Internet of Vehicles (IoV). In this paper, we focus on one research area in IoV: preserving location privacy of vehicle data. We discuss existing location privacy preserving techniques and provide a scheme for evaluating these techniques under IoV traffic condition. We propose a different strategy in applying Differential Privacy using k-d tree data structure to preserve location privacy and experiment on real world Gowalla data set. We show that our strategy produces differentially private data, good preservation of utility by achieving similar regression accuracy to the original dataset on an LSTM (Long Term Short Term Memory) neural network traffic predictor.

Keywords: differential privacy, internet of things, internet of vehicles, location privacy, privacy preservation scheme

Procedia PDF Downloads 179

Authors: Arpan Bera, Rini Ganguly, Raja Chakraborty, Amlan J. Pal

Abstract:

To deal with the increasing demands for the high-density non-volatile memory devices, we need nano-sites with efficient and stable charge storage capabilities. We prepared nanocrystals (NCs) of inorganic perovskite, CsPbCl₃ coated with Cs₄PbCl₆, by colloidal synthesis. Due to the type-I band alignment at the junction, this core-shell composite is expected to behave as a charge trapping site. Using Scanning Tunneling Spectroscopy (STS), we investigated voltage-controlled resistive switching in this heterostructure by tracking the change in its current-voltage (I-V) characteristics. By applying voltage pulse of appropriate magnitude on the NCs through this non-invasive method, different resistive states of this system were systematically accessed. For suitable pulse-magnitude, the response jumped to a branch with enhanced current indicating a high-resistance state (HRS) to low-resistance state (LRS) switching in the core-shell NCs. We could reverse this process by using a pulse of opposite polarity. These two distinct resistive states can be considered as two logic states, 0 and 1, which are accessible by varying voltage magnitude and polarity. STS being a local probe in space enabled us to capture this switching at individual NC site. Hence, we claim a bright prospect of these core-shell NCs made of inorganic halide perovskites in future high density memory application.

Keywords: Core-shell perovskite, CsPbCl₃-Cs₄PbCl₆, resistive switching, Scanning Tunneling Spectroscopy

Procedia PDF Downloads 89