Search results for: convolutional long short-term memory

Authors: Koray U. Erbas

Abstract:

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

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

Procedia PDF Downloads 228

Authors: Jianhong Xiang, Rui Sun, Linyu Wang

Abstract:

In recent years, due to the continuous improvement of deep learning theory, Convolutional Neural Network (CNN) has played a great superior performance in the research of Hyperspectral Image (HSI) classification. Since HSI has rich spatial-spectral information, only utilizing a single dimensional or single size convolutional kernel will limit the detailed feature information received by CNN, which limits the classification accuracy of HSI. In this paper, we design a multi-scale CNN with MLP based on residual and attention modules (INRAM-3DCNN) for the HSI classification task. We propose to use multiple 3D convolutional kernels to extract the packet feature information and fully learn the spatial-spectral features of HSI while designing residual 3D convolutional branches to avoid the decline of classification accuracy due to network degradation. Secondly, we also design the 2D Inception module with a joint channel attention mechanism to quickly extract key spatial feature information at different scales of HSI and reduce the complexity of the 3D model. Due to the high parallel processing capability and nonlinear global action of the Multilayer Perceptron (MLP), we use it in combination with the previous CNN structure for the final classification process. The experimental results on two HSI datasets show that the proposed INRAM-3DCNN method has superior classification performance and can perform the classification task excellently.

Keywords: INRAM-3DCNN, residual, channel attention, hyperspectral image classification

Procedia PDF Downloads 34

Authors: Hamdi Amroun, Yacine Benziani, Mehdi Ammi

Abstract:

In this paper, we want to determine whether the accurate prediction of nicotine concentration can be obtained by using a network of smart objects and an e-cigarette. The approach consists of, first, the recognition of factors influencing smoking cessation such as physical activity recognition and participant’s behaviors (using both smartphone and smartwatch), then the prediction of the configuration of the e-cigarette (in terms of nicotine concentration, power, and resistance of e-cigarette). The study uses a network of commonly connected objects; a smartwatch, a smartphone, and an e-cigarette transported by the participants during an uncontrolled experiment. The data obtained from sensors carried in the three devices were trained by a Long short-term memory algorithm (LSTM). Results show that our LSTM-based model allows predicting the configuration of the e-cigarette in terms of nicotine concentration, power, and resistance with a root mean square error percentage of 12.9%, 9.15%, and 11.84%, respectively. This study can help to better control consumption of nicotine and offer an intelligent configuration of the e-cigarette to users.

Keywords: Iot, activity recognition, automatic classification, unconstrained environment

Procedia PDF Downloads 200

Authors: Mohamed Raouf Benmakrelouf, Wafa Karouche, Joseph Rynkiewicz

Abstract:

In this paper, we propose an alternative method to construct a Bayesian Network (BN). This method relies on a convolutional neural network (CNN classifier), which determinates the edges of the network skeleton. We train a CNN on a normalized empirical probability density distribution (NEPDF) for predicting causal interactions and relationships. We have to find the optimal Bayesian network structure for causal inference. Indeed, we are undertaking a search for pair-wise causality, depending on considered causal assumptions. In order to avoid unreasonable causal structure, we consider a blacklist and a whitelist of causality senses. We tested the method on real data to assess the influence of education on the voting intention for the extreme right-wing party. We show that, with this method, we get a safer causal structure of variables (Bayesian Network) and make to identify a variable that satisfies the backdoor criterion.

Keywords: Bayesian network, structure learning, optimal search, convolutional neural network, causal inference

Procedia PDF Downloads 141

Authors: Jamshaid Ul Rahman, Faiza Makhdoom, Dianchen Lu

Abstract:

Activation functions play a decisive role in determining the capacity of Deep Neural Networks (DNNs) as they enable neural networks to capture inherent nonlinearities present in data fed to them. The prior research on activation functions primarily focused on the utility of monotonic or non-oscillatory functions, until Growing Cosine Unit (GCU) broke the taboo for a number of applications. In this paper, a Convolutional Neural Network (CNN) model named as ASU-CNN is proposed which utilizes recently designed activation function ASU across its layers. The effect of this non-monotonic and oscillatory function is inspected through feature map visualizations from different convolutional layers. The optimization of proposed network is offered by Adam with a fine-tuned adjustment of learning rate. The network achieved promising results on both training and testing data for the classification of CIFAR-10. The experimental results affirm the computational feasibility and efficacy of the proposed model for performing tasks related to the field of computer vision.

Keywords: amplifying sine unit, activation function, convolutional neural networks, oscillatory activation, image classification, CIFAR-10

Procedia PDF Downloads 63

Authors: Q. B. Maria de la Luz Ortega Juárez, Saúl Rojas Hernández, Itzel Berenice Rodríguez Mera, María Maricela Carrasco Yépez, Mara Gutierrez Sánchez

Abstract:

Naegleria fowleri is a free-living amoeba found mainly in temperate freshwater and is the etiologic agent of primary amebic meningoencephalitis (PAM), a fatal acute disease with a mortality rate greater than 95%. At present, there are no treatments available for MAP, and the development of effective vaccines that generate long-term immunological memory allowing protection against MAP would be of great importance. The objective of this work was to analyze the effector and memory immune response in BALB/c mice immunized with total extract of N. fowleri co-administered with cholera toxin. In this study, BALB/c mice were immunized four times intranasally with ET of N. fowleri adjuvanted with CT with or without booster at three months and were challenged or not with the lethal dose of N. fowleri, determining survival, the humoral, effector and memory response, by ELISA and flow cytometry techniques. The results obtained showed that the survival of mice immunized with booster had 60% protection compared to the group without booster, which obtained 20% protection. Evaluating the humoral response, it was found that both IgG and IgA levels were higher in sera than in nasal washes in both treatments. In the cellular response, the increase in the percentage of positive cells was found for effector T and B lymphocytes in the nasal passages (NP) in the group with boost and nasopharynx-associated lymphoid tissue (NALT) in the group without boost and lymphocytes only. B in both treatments, as well as in memory cells treatment with boost T lymphocytes in PN and NALT and without boost in cervical lymph nodes (CG) with respect to B lymphocytes, in PN, GC and NALT in treatment with boost and NALT in treatment without booster. Therefore, the involvement of the effector immune response and memory play a fundamental role for protection against N. fowleri and for the development of vaccine candidates.

Keywords: immune response, immunological memory, naegleria fowleri, primary amebic meningoencephalitis

Procedia PDF Downloads 46

Authors: Yolina A. Petrova, Georgi I. Petkov

Abstract:

The paper presents a symbolic model for category learning and categorization (called RoleMap). Unlike the other models which implement learning in a separate working mode, role-governed category learning and categorization emerge in RoleMap while it does its usual reasoning. The model is based on several basic mechanisms known as reflecting the sub-processes of analogy-making. It steps on the assumption that in their everyday life people constantly compare what they experience and what they know. Various commonalities between the incoming information (current experience) and the stored one (long-term memory) emerge from those comparisons. Some of those commonalities are considered to be highly important, and they are transformed into concepts for further use. This process denotes the category learning. When there is missing knowledge in the incoming information (i.e. the perceived object is still not recognized), the model makes anticipations about what is missing, based on the similar episodes from its long-term memory. Various such anticipations may emerge for different reasons. However, with time only one of them wins and is transformed into a category member. This process denotes the act of categorization.

Keywords: analogy-making, categorization, category learning, cognitive modeling, role-governed categories

Procedia PDF Downloads 117

Authors: Francesco Scarpati

Abstract:

Because of their long history, ranging from ancient times to the present day, European cities feature many historical layers, whose single identities are represented by traces surviving in the urban design. However, urban transformations, in particular, the ones that have been produced by the property speculation phenomena of the 20th century, often compromised the readability of these traces, resulting in a loss of the historical identities of the single layers. The purpose of this research is, therefore, a reflection on the theme of the reenactment of the historical memory in the stratified European contexts and on how contemporary architecture can help to reveal past signs of the cities. The research work starts from an analysis of a series of emblematic examples that have already provided an original solution to the described problem, going from the architectural detail scale to the urban and landscape scale. The results of these analyses are then applied to the case study of the city of Naples, as an emblematic example of a stratified city, with an ancient Greek origin; a city where it is possible to read most of the traces of its transformations. Particular consideration is given to the trace of the medieval walls of the city, which a long time ago clearly divided the city itself from the outer fields, and that is no longer readable at the current time. Finally, solutions and methods of intervention are proposed to ensure that the trace of the walls, read as a boundary, can be revealed through the contemporary project.

Keywords: contemporary project, historic memory, historic urban contexts, medieval walls, naples, stratified cities, urban traces

Procedia PDF Downloads 235

Authors: Akiko Kondo

Abstract:

Although the effects of working memory capacity on second/foreign language speaking skills have been researched in depth, few studies have focused on Japanese English as a foreign language (EFL) learners as compared to other languages (Indo-European languages), and the sample sizes of the relevant Japanese studies have been relatively small. Furthermore, comparing the effects of working memory capacity and motivation which is another kind of frequently researched individual factor on L2 speaking skills would add to the scholarly literature in the field of second language acquisition research. Therefore, the purposes of this study were to investigate whether working memory capacity and motivation have significant relationships with Japanese EFL learners’ speaking skills and to investigate the degree to which working memory capacity and motivation contribute to their English speaking skills. One-hundred and ten Japanese EFL students aged 18 to 26 years participated in this study. All of them are native Japanese speakers and have learned English as s foreign language for 6 to 15. They completed the Versant English speaking test, which has been widely used to measure non-native speakers’ English speaking skills, two types of working memory tests (the L1-based backward digit span test and the L1-based listening span test), and the language learning motivation survey. The researcher designed the working memory tests and the motivation survey. To investigate the relationship between the variables (English speaking skills, working memory capacity, and language learning motivation), a correlation analysis was conducted, which showed that L2 speaking test scores were significantly related to both working memory capacity and language learning motivation, although the correlation coefficients were weak. Furthermore, a multiple regression analysis was performed, with L2 speaking skills as the dependent variable and working memory capacity and language learning motivation as the independent variables. The results showed that working memory capacity and motivation significantly explained the variance in L2 speaking skills and that the L2 motivation had slightly larger effects on the L2 speaking skills than the working memory capacity. Although this study includes several limitations, the results could contribute to the generalization of the effects of individual differences, such as working memory and motivation on L2 learning, in the literature.

Keywords: individual differences, motivation, speaking skills, working memory

Procedia PDF Downloads 137

Authors: Ana B. Vivas, Antonia Ypsilanti, Aristea I. Ladas, Angeles F. Estevez

Abstract:

Mild Cognitive Impairment (MCI) is considered an intermediate stage between normal and pathological aging, as a substantial percentage of people diagnosed with MCI converts later to dementia of the Alzheimer’s type. Memory is of the first cognitive processes to deteriorate in this condition. In the present study we employed the differential outcomes procedure (DOP) to improve visuospatial memory in a group of participants with MCI. The DOP requires the structure of a conditional discriminative learning task in which a correct choice response to a specific stimulus-stimulus association is reinforced with a particular reinforcer or outcome. A group of 10 participants with MCI, and a matched control group had to learn and keep in working memory four target locations out of eight possible locations where a shape could be presented. Results showed that participants with MCI had a statistically significant better terminal accuracy when a unique outcome was paired with a location (76% accuracy) as compared to a non differential outcome condition (64%). This finding suggests that the DOP is useful in improving working memory in MCI patients, which may delay their conversion to dementia.

Keywords: mild cognitive impairment, working memory, differential outcomes, cognitive process

Procedia PDF Downloads 433

Authors: Kirsten A. Bartels

Abstract:

'Never again' and 'Lest we forget' have long been messages associated with the events of the Shoah. Yet as we attempt to learn from the past, we must find new ways to engage with its memories. The preservation of the culture and the value of tradition are critical factors in Jane Yolen's works of Holocaust fiction, The Devil's Arithmetic and Mapping the Bones, emphasized through the importance of remembering. That word, in its multitude of forms (remember, remembering, memories), occurs no less than ten times in the first four pages and over one hundred times in the one hundred and sixty-four-page narrative The Devil’s Arithmetic. While Yolen takes a different approach to showcasing the importance of memory in Mapping the Bones, it is of equal import in this work and arguably to the future of Holocaust knowing. The idea of remembering, the desire to remember, and the ability to remember, are explored in three divergent ways in The Devil’s Arithmetic. First, in the importance to remember a past which is not her own – to understand history or acquired memories. Second, in the protagonist's actual or initial memories, those of her life in modern-day New York. Third, in a reverse mode of forgetting and trying to reacquire that which has been lost -- as Hannah is processed in the camp and she forgets everything, all worlds prior to the camp are lost to her. As numbers replace names, Yolen stresses the importance of self-identity or owned memories. In addition, the importance of relaying memory, the transitions of memory from perspective, and the ideas of reflective telling are explored in Mapping the Bones -- through the telling of the story through the lens of one of the twins as the events are unfolding; and then the through the reflective telling from the lens of the other twin. Parallel to the exploration of the intersemiosis of memory is the discussion of literary shadows (foreshadowing, backshadowing, and side-shadowing) and their impact on the reader's experience with Yolen's narrative. For in this type of exploration, one cannot look at the events described in Yolen's work and not also contemplate the figurative shadows cast.

Keywords: holocaust literature, memory, narrative, Yolen

Procedia PDF Downloads 206

Authors: Yueying Chen

Abstract:

A city can be developed through memory, and memory is one of the most important elements for urban contexts. Collective memory is a collection of personal memories that can be preserved with objects, places, and events of heritage, expressing culture through spatial changes. These preserved forms can evoke a sense of community and certain emotions. Collective memory in cities reflects urban spatial alterations and historical developments. It can be preserved and reflected by revitalisation projects. A major current focus in collective memory research is how to identify and preserve memory in an intangible way. The influential elements within the preservation of collective memory mainly include institutions and objects. However, current research lacks the assessment of the collective memory after alterations of urban heritage. The assessment of urban heritage lacks visualization and qualitative methods. The emergence of the application of space syntax can fill in this gap. Hengshan Mansions was a new project in 2015. The original residential area has been replaced with a comprehensive commercial area integrating boutique shopping, upscale restaurants, and creative offices. Hengshan Mansions is located in the largest historic area in Shanghai, and its development is the epitome of the traditional culture in Shanghai. Its alteration is the newest project in this area and presents the new concept of revitalisation of urban heritage. For its physical parts, modern vitality is created, and historical information is preserved at the same time. However, most of the local people are moved away, and its functions are altered a lot. The preservation of its collective memory needs to discuss furtherly. Thus, the article builds a framework to assess the collective memory of urban heritage, including spatial configuration, spatial interaction, and cultural cognition. Then, it selects Hengshan Mansions in Shanghai as a case to analyse the assessed framework. Space syntax can be applied to visualize the assessment. Based on the analysis, the article will explore the influential reasons for the collective memory after alterations and proposes relevant advice for the preservation of the collective memory of urban heritage.

Keywords: collective memory, alternation of urban heritage, space syntax, Hengshan Mansions

Procedia PDF Downloads 100

Authors: Asher John Mohan, Krishna K. L.

Abstract:

Objectives: (1) To assess the extent of memory impairment induced by Phenytoin (PHT) at normal and reduced dose on temporal lobe epileptic mice. (2) To evaluate the protective effect of Levetiracetam (LEV) on aggravation of memory impairment in temporal lobe epileptic mice by PHT. Materials and Methods: Albino mice of either sex (n=36) were used for the study for a period of 64 days. Convulsions were induced by intraperitoneal administration of pilocarpine 280 mg/kg on every 6th day. Radial arm maze (RAM) was employed to evaluate the memory impairment activity on every 7th day. The anticonvulsant and memory impairment activity were assessed in PHT normal and reduced doses both alone and in combination with LEV. RAM error scores and convulsive scores were the parameters considered for this study. Brain acetylcholine esterase and glutamate were determined along with histopathological studies of frontal cortex. Results: Administration of PHT for 64 days on mice has shown aggravation of memory impairment activity on temporal lobe epileptic mice. Although the reduction in PHT dose was found to decrease the degree of memory impairment the same decreased the anticonvulsant potency. The combination with LEV not only brought about the correction of impaired memory but also replaced the loss of potency due to the reduction of the dose of the antiepileptic drug employed. These findings were confirmed with enzyme and neurotransmitter levels in addition to histopathological studies. Conclusion: This study thus builds a foundation in combining a nootropic anticonvulsant with an antiepileptic drug to curb the adverse effect of memory impairment associated with temporal lobe epilepsy. However further extensive research is a must for the practical incorporation of this approach into disease therapy.

Keywords: anti-epileptic drug, Phenytoin, memory impairment, Pilocarpine

Procedia PDF Downloads 290

Authors: Kamyar Moradi

Abstract:

Background: There is mixed evidence regarding the association between recreational cannabinoid use and memory performance. One of the major reasons for the present controversy is different cannabinoid use-related covariates that influence the cognitive status of an individual. Adjustment of these confounding variables provides accurate insight into the real effects of cannabinoid use on memory status. In this study, we sought to investigate the association between recent recreational cannabinoid use and memory performance while correcting the model for other possible covariates such as demographic characteristics and duration, and amount of cannabinoid use. Methods: Cannabinoid users were assigned to two groups based on the results of THC urine drug screen test (THC+ group: n = 110, THC- group: n = 410). THC urine drug screen test has a high sensitivity and specificity in detecting cannabinoid use in the last 3-4 weeks. The memory domain of NIH Toolbox battery and brain MRI volumetric measures were compared between the groups while adjusting for confounding variables. Results: After Benjamini-Hochberg p-value correction, the performance in all of the measured memory outcomes, including vocabulary comprehension, episodic memory, executive function/cognitive flexibility, processing speed, reading skill, working memory, and fluid cognition, were significantly weaker in THC+ group (p values less than 0.05). Also, volume of gray matter, left supramarginal, right precuneus, right inferior/middle temporal, right hippocampus, left entorhinal, and right pars orbitalis regions were significantly smaller in THC+ group. Conclusions: this study provides evidence regarding the acute effect of recreational cannabis use on memory performance. Further studies are warranted to confirm the results.

Keywords: brain MRI, cannabis, memory, recreational use, THC urine test

Procedia PDF Downloads 160

Authors: Parisa Golbayani, Dan Wang, Ionut¸ Florescu

Abstract:

In this work we implement machine learning techniques to financial statement reports in order to asses company’s credit rating. Specifically, the work analyzes the performance of four neural network architectures (MLP, CNN, CNN2D, LSTM) in predicting corporate credit rating as issued by Standard and Poor’s. The paper focuses on companies from the energy, financial, and healthcare sectors in the US. The goal of this analysis is to improve application of machine learning algorithms to credit assessment. To accomplish this, the study investigates three questions. First, we investigate if the algorithms perform better when using a selected subset of important features or whether better performance is obtained by allowing the algorithms to select features themselves. Second, we address the temporal aspect inherent in financial data and study whether it is important for the results obtained by a machine learning algorithm. Third, we aim to answer if one of the four particular neural network architectures considered consistently outperforms the others, and if so under which conditions. This work frames the problem as several case studies to answer these questions and analyze the results using ANOVA and multiple comparison testing procedures.

Keywords: convolutional neural network, long short term memory, multilayer perceptron, credit rating

Procedia PDF Downloads 207

Authors: Bing Li, Zhi Li, Yilong Yang

Abstract:

Web classification can promote the quality of service discovery and management in the service repository. It is widely used to locate developers desired services. Although traditional classification methods based on supervised learning models can achieve classification tasks, developers need to manually mark web services, and the quality of these tags may not be enough to establish an accurate classifier for service classification. With the doubling of the number of web services, the manual tagging method has become unrealistic. In recent years, the attention mechanism has made remarkable progress in the field of deep learning, and its huge potential has been fully demonstrated in various fields. This paper designs a multi-head attention graph convolutional network (MHAGCN) service classification method, which can assign different weights to the neighborhood nodes without complicated matrix operations or relying on understanding the entire graph structure. The framework combines the advantages of the attention mechanism and graph convolutional neural network. It can classify web services through automatic feature extraction. The comprehensive experimental results on a real dataset not only show the superior performance of the proposed model over the existing models but also demonstrate its potentially good interpretability for graph analysis.

Keywords: attention mechanism, graph convolutional network, interpretability, service classification, service discovery

Procedia PDF Downloads 110

Authors: S. Rozhkova, O. Rozhkova, A. Harlova, V. Lasukov

Abstract:

We have conducted the optimal synthesis of root-mean-squared objective filter to estimate the state vector in the case if within the observation channel with memory the anomalous noises with unknown mathematical expectation are complement in the function of the regular noises. The synthesis has been carried out for linear stochastic systems of continuous-time.

Keywords: mathematical expectation, filtration, anomalous noise, memory

Procedia PDF Downloads 211

Authors: Saed Khawaldeh, Mohamed Elsharnouby, Alaa Eddin Alchalabi, Usama Pervaiz, Tajwar Aleef, Vu Hoang Minh

Abstract:

Taxonomic classification has a wide-range of applications such as finding out more about the evolutionary history of organisms that can be done by making a comparison between species living now and species that lived in the past. This comparison can be made using different kinds of extracted species’ data which include DNA sequences. Compared to the estimated number of the organisms that nature harbours, humanity does not have a thorough comprehension of which specific species they all belong to, in spite of the significant development of science and scientific knowledge over many years. One of the methods that can be applied to extract information out of the study of organisms in this regard is to use the DNA sequence of a living organism as a marker, thus making it available to classify it into a taxonomy. The classification of living organisms can be done in many machine learning techniques including Neural Networks (NNs). In this study, DNA sequences classification is performed using Convolutional Neural Networks (CNNs) which is a special type of NNs.

Keywords: deep networks, convolutional neural networks, taxonomic classification, DNA sequences classification

Procedia PDF Downloads 404

Authors: Amjad Nusayr

Abstract:

Software security is a general term used to any type of software architecture or model in which security aspects are incorporated in this architecture. These aspects are not part of the main logic of the underlying program. Software security can be achieved using a combination of approaches, including but not limited to secure software designs, third part component validation, and secure coding practices. Memory safety is one feature in software security where we ensure that any object in memory has a valid pointer or a reference with a valid type. Aspect-Oriented Programming (AOP) is a paradigm that is concerned with capturing the cross-cutting concerns in code development. AOP is generally used for common cross-cutting concerns like logging and DB transaction managing. In this paper, we introduce the concepts that enable AOP to be used for the purpose of memory and type safety. We also present ideas for extending AOP in software security practices.

Keywords: aspect oriented programming, programming languages, software security, memory and type safety

Procedia PDF Downloads 99

Authors: Getaneh Berie Tarekegn

Abstract:

A precise localization system is crucial for many artificial intelligence Internet of Things (AI-IoT) applications in the era of smart cities. Their applications include traffic monitoring, emergency alarming, environmental monitoring, location-based advertising, intelligent transportation, and smart health care. The most common method for providing continuous positioning services in outdoor environments is by using a global navigation satellite system (GNSS). Due to nonline-of-sight, multipath, and weather conditions, GNSS systems do not perform well in dense urban, urban, and suburban areas.This paper proposes a generative AI-based positioning scheme for large-scale wireless settings using fingerprinting techniques. In this article, we presented a semi-supervised deep convolutional generative adversarial network (S-DCGAN)-based radio map construction method for real-time device localization. It also employed a reliable signal fingerprint feature extraction method with t-distributed stochastic neighbor embedding (t-SNE), which extracts dominant features while eliminating noise from hybrid WLAN and long-term evolution (LTE) fingerprints. The proposed scheme reduced the workload of site surveying required to build the fingerprint database by up to 78.5% and significantly improved positioning accuracy. The results show that the average positioning error of GAILoc is less than 0.39 m, and more than 90% of the errors are less than 0.82 m. According to numerical results, SRCLoc improves positioning performance and reduces radio map construction costs significantly compared to traditional methods.

Keywords: location-aware services, feature extraction technique, generative adversarial network, long short-term memory, support vector machine

Procedia PDF Downloads 17

Authors: Kemka C. Ihemelandu, Chukwuemeka U. Ihemelandu

Abstract:

The incidence of melanoma has been increasing rapidly over the past two decades, making melanoma a current public health crisis. Unfortunately, even as screening efforts continue to expand in an effort to ameliorate the death rate from melanoma, there is a need to improve diagnostic accuracy to decrease misdiagnosis. Artificial intelligence (AI) a new frontier in patient care has the ability to improve the accuracy of melanoma diagnosis. Convolutional neural network (CNN) a form of deep neural network, most commonly applied to analyze visual imagery, has been shown to outperform the human brain in pattern recognition. However, there are noted limitations with the accuracy of the CNN models. Our aim in this study was the optimization of convolutional neural network algorithms for the automated diagnosis of melanoma. We hypothesized that Optimal selection of the momentum and batch hyperparameter increases model accuracy. Our most successful model developed during this study, showed that optimal selection of momentum of 0.25, batch size of 2, led to a superior performance and a faster model training time, with an accuracy of ~ 83% after nine hours of training. We did notice a lack of diversity in the dataset used, with a noted class imbalance favoring lighter vs. darker skin tone. Training set image transformations did not result in a superior model performance in our study.

Keywords: melanoma, convolutional neural network, momentum, batch hyperparameter

Procedia PDF Downloads 78

Authors: Samuel Kaspi, Sitalakshmi Venkatraman

Abstract:

In-memory database systems are becoming popular due to the availability and affordability of sufficiently large RAM and processors in modern high-end servers with the capacity to manage large in-memory database transactions. While fast and reliable in-memory systems are still being developed to overcome cache misses, CPU/IO bottlenecks and distributed transaction costs, disk-based data stores still serve as the primary persistence. In addition, with the recent growth in multi-tenancy cloud applications and associated security concerns, many organisations consider the trade-offs and continue to require fast and reliable transaction processing of disk-based database systems as an available choice. For these organizations, the only way of increasing throughput is by improving the performance of disk-based concurrency control. This warrants a hybrid database system with the ability to selectively apply an enhanced disk-based data management within the context of in-memory systems that would help improve overall throughput. The general view is that in-memory systems substantially outperform disk-based systems. We question this assumption and examine how a modified variation of access invariance that we call enhanced memory access, (EMA) can be used to allow very high levels of concurrency in the pre-fetching of data in disk-based systems. We demonstrate how this prefetching in disk-based systems can yield close to in-memory performance, which paves the way for improved hybrid database systems. This paper proposes a novel EMA technique and presents a comparative study between disk-based EMA systems and in-memory systems running on hardware configurations of equivalent power in terms of the number of processors and their speeds. The results of the experiments conducted clearly substantiate that when used in conjunction with all concurrency control mechanisms, EMA can increase the throughput of disk-based systems to levels quite close to those achieved by in-memory system. The promising results of this work show that enhanced disk-based systems facilitate in improving hybrid data management within the broader context of in-memory systems.

Keywords: in-memory database, disk-based system, hybrid database, concurrency control

Procedia PDF Downloads 386

Authors: M. K. Wijayarathna, S. M. Buddika Harshanath

Abstract:

Monitoring student engagement has become a crucial part of the educational process and a reliable indicator of the capacity to retain information. As online learning classrooms are now more common these days, students' attention levels have become increasingly important, making it more difficult to check each student's concentration level in an online classroom setting. To profile student attention to various gradients of engagement, a study is a plan to conduct using machine learning models. Using a convolutional neural network, the findings and confidence score of the high accuracy model are obtained. In this research, convolutional neural networks are using to help discover essential emotions that are critical in defining various levels of participation. Students' attention levels were shown to be influenced by emotions such as calm, enjoyment, surprise, and fear. An improved virtual learning system was created as a result of these data, which allowed teachers to focus their support and advise on those students who needed it. Student participation has formed as a crucial component of the learning technique and a consistent predictor of a student's capacity to retain material in the classroom. Convolutional neural networks have a plan to implement the platform. As a preliminary step, a video of the pupil would be taken. In the end, researchers used a convolutional neural network utilizing the Keras toolkit to take pictures of the recordings. Two convolutional neural network methods are planned to use to determine the pupils' attention level. Finally, those predicted student attention level results plan to display on the graphical user interface of the System.

Keywords: HTML5, JavaScript, Python flask framework, AI, graphical user

Procedia PDF Downloads 68

Authors: Mahsa Mousavi, Hamid Reza Pourshaghaghi, Mohammad Tahghighi, Henk Corporaal

Abstract:

Recently, Statistic Random-Access Memory-based (SRAM-based) Field-Programmable Gate Arrays (FPGAs) are widely used in aeronautics and space systems where high dependability is demanded and considered as a mandatory requirement. Since design’s circuit is stored in configuration memory in SRAM-based FPGAs; they are very sensitive to Single Event Upsets (SEUs). In addition, the adverse effects of SEUs on the electronics used in space are much higher than in the Earth. Thus, developing fault tolerant techniques play crucial roles for the use of SRAM-based FPGAs in space. However, fault tolerance techniques introduce additional penalties in system parameters, e.g., area, power, performance and design time. In this paper, an accurate estimation of configuration memory vulnerability to SEUs is proposed for approximate-tolerant applications. This vulnerability estimation is highly required for compromising between the overhead introduced by fault tolerance techniques and system robustness. In this paper, we study applications in which the exact final output value is not necessarily always a concern meaning that some of the SEU-induced changes in output values are negligible. We therefore define and propose Approximate-based Configuration Memory Vulnerability Factor (ACMVF) estimation to avoid overestimating configuration memory vulnerability to SEUs. In this paper, we assess the vulnerability of configuration memory by injecting SEUs in configuration memory bits and comparing the output values of a given circuit in presence of SEUs with expected correct output. In spite of conventional vulnerability factor calculation methods, which accounts any deviations from the expected value as failures, in our proposed method a threshold margin is considered depending on user-case applications. Given the proposed threshold margin in our model, a failure occurs only when the difference between the erroneous output value and the expected output value is more than this margin. The ACMVF is subsequently calculated by acquiring the ratio of failures with respect to the total number of SEU injections. In our paper, a test-bench for emulating SEUs and calculating ACMVF is implemented on Zynq-7000 FPGA platform. This system makes use of the Single Event Mitigation (SEM) IP core to inject SEUs into configuration memory bits of the target design implemented in Zynq-7000 FPGA. Experimental results for 32-bit adder show that, when 1% to 10% deviation from correct output is considered, the counted failures number is reduced 41% to 59% compared with the failures number counted by conventional vulnerability factor calculation. It means that estimation accuracy of the configuration memory vulnerability to SEUs is improved up to 58% in the case that 10% deviation is acceptable in output results. Note that less than 10% deviation in addition result is reasonably tolerable for many applications in approximate computing domain such as Convolutional Neural Network (CNN).

Keywords: fault tolerance, FPGA, single event upset, approximate computing

Procedia PDF Downloads 159

Authors: Gagnesh Kumar, Nitin Gupta

Abstract:

Ternary Content Addressable Memory cells are mainly popular in network routers for packet forwarding and packet classification, but they are also useful in a variety of other applications that require high-speed table look-up. The main TCAM-design challenge is to decrease the power consumption associated with the large amount of parallel active circuitry, without compromising with speed or memory density. Furthermore, when the channel length decreases, leakage power becomes more significant, and it can even dominate dynamic power at lower technologies. In this paper, we propose a TCAM-design technique, called Virtual Power Supply technique that reduces the leakage by a substantial amount.

Keywords: match line (ML), search line (SL), ternary content addressable memory (TCAM), Leakage power (LP)

Procedia PDF Downloads 269

Authors: Mahdi Bazarganigilani

Abstract:

Aortic enlargement, also known as an aortic aneurysm, can occur when the walls of the aorta become weak. This disease can become deadly if overlooked and undiagnosed. In this paper, a computer-aided diagnosis (CAD) system was introduced to accurately diagnose aortic enlargement from chest x-ray images. An enhanced convolutional neural network (CNN) was employed and then trained by transfer learning by using three different main areas from the original images. The areas included the left lung, heart, and right lung. The accuracy of the system was then evaluated on 1001 samples by using 4-fold cross-validation. A promising accuracy of 90% was achieved in terms of the F-measure indicator. The results showed using different areas from the original image in the training phase of CNN could increase the accuracy of predictions. This encouraged the author to evaluate this method on a larger dataset and even on different CAD systems for further enhancement of this methodology.

Keywords: computer-aided diagnosis systems, aortic enlargement, chest X-ray, image processing, convolutional neural networks

Procedia PDF Downloads 126

Authors: Subodh Chandra Shakya, Badal Shrestha, Suni Thapa, Ashutosh Chauhan, Saugat Adhikari

Abstract:

To tackle our problem of clothes identification, we used different architectures of Convolutional Neural Networks. Among different architectures, the outcome from Inception ResNet V2 and MobileNet V2 seemed promising. On comparison of the metrices, we observed that the Inception ResNet V2 slightly outperforms MobileNet V2 for this purpose. So this paper of ours proposes the cloth identifier using Inception ResNet V2 and also contains the comparison between the outcome of ResNet V2 and MobileNet V2. The document here contains the results and findings of the research that we performed on the DeepFashion Dataset. To improve the dataset, we used different image preprocessing techniques like image shearing, image rotation, and denoising. The whole experiment was conducted with the intention of testing the efficiency of convolutional neural networks on cloth identification so that we could develop a reliable system that is good enough in identifying the clothes worn by the users. The whole system can be integrated with some kind of recommendation system.

Keywords: inception ResNet, convolutional neural net, deep learning, confusion matrix, data augmentation, data preprocessing

Procedia PDF Downloads 148

Authors: Jayati Bhattacharjee

Abstract:

Teaching is a very dynamic profession. Teaching Science is as much challenging as Learning the subject if not more. For instance teaching of Chemistry. From the introductory concepts of subatomic particles to atoms of elements and their symbols and further presenting the chemical equation and so forth is a challenge on both side of the equation Teaching Learning. This paper combines the Neuroscience of Learning and memory with the knowledge of Learning style (VAK) and presents an effective tool for the teacher to authenticate Learning. The model of ‘Working Memory’, the Visio-spatial sketchpad, the central executive and the phonological loop that transforms short-term memory to long term memory actually supports the psychological theory of Learning style i.e. Visual –Auditory-Kinesthetic. A closer examination of David Kolbe’s learning model suggests that learning requires abilities that are polar opposites, and that the learner must continually choose which set of learning abilities he or she will use in a specific learning situation. In grasping experience some of us perceive new information through experiencing the concrete, tangible, felt qualities of the world, relying on our senses and immersing ourselves in concrete reality. Others tend to perceive, grasp, or take hold of new information through symbolic representation or abstract conceptualization – thinking about, analyzing, or systematically planning, rather than using sensation as a guide. Similarly, in transforming or processing experience some of us tend to carefully watch others who are involved in the experience and reflect on what happens, while others choose to jump right in and start doing things. The watchers favor reflective observation, while the doers favor active experimentation. Any lesson plan based on the model of Prescriptive design: C+O=M (C: Instructional condition; O: Instructional Outcome; M: Instructional method). The desired outcome and conditions are independent variables whereas the instructional method is dependent hence can be planned and suited to maximize the learning outcome. The assessment for learning rather than of learning can encourage, build confidence and hope amongst the learners and go a long way to replace the anxiety and hopelessness that a student experiences while learning Science with a human touch in it. Application of this model has been tried in teaching chemistry to high school students as well as in workshops with teachers. The response received has proven the desirable results.

Keywords: working memory model, learning style, prescriptive design, assessment for learning

Procedia PDF Downloads 312

Authors: Douglas Rossi Ramos

Abstract:

The current digital conjuncture, called by some authors as 'Internet of Things' (IoT), 'Web 2.0' or even 'Web 3.0', consists of a network that encompasses any communication of objects and entities, such as data, information, technologies, and people. At this juncture, especially characterized by an "object socialization," communication can no longer be represented as a simple informational flow of messages from a sender, crossing a channel or medium, reaching a receiver. The idea of communication must, therefore, be thought of more broadly in which it is possible to analyze the process communicative from interactions between humans and nonhumans. To think about this complexity, a communicative process that encompasses both humans and other beings or entities communicating (objects and things), it is necessary to constitute a new epistemology of communication to rethink concepts and notions commonly attributed to humans such as 'memory.' This research aims to contribute to this epistemological constitution from the discussion about the notion of memory according to the complex ontology of Henri Bergson. Among the results (the notion of memory in Bergson presents itself as a conceptual tool for the analysis of posthumanism and the anthropomorphic conjuncture of the new advent of digital), there was the need to think about an ontological memory, analyzed as a being itself (being itself of memory), as a strategy for understanding the forms of interaction and communication that constitute the new digital conjuncture, in which communicating beings or entities tend to interact with each other. Rethinking the idea of communication beyond the dimension of transmission in informative sequences paves the way for an ecological perspective of the digital dwelling condition.

Keywords: communication, digital, Henri Bergson, memory

Procedia PDF Downloads 129

Authors: Bhaumik Tyagi, Mandeep Kaur, Kanika Singla

Abstract:

The advancement of blockchain has facilitated scholars to remodel e-voting systems for future generations. Server-side attacks like SQL injection attacks and DOS attacks are the most common attacks nowadays, where malicious codes are injected into the system through user input fields by illicit users, which leads to data leakage in the worst scenarios. Besides, quantum attacks are also there which manipulate the transactional data. In order to deal with all the above-mentioned attacks, integration of blockchain, convolutional neural network (CNN), and Quantum Key Distribution is done in this very research. The utilization of blockchain technology in e-voting applications is not a novel concept. But privacy and security issues are still there in a public and private blockchains. To solve this, the use of a hybrid blockchain is done in this research. This research proposed cryptographic signatures and blockchain algorithms to validate the origin and integrity of the votes. The convolutional neural network (CNN), a normalized version of the multilayer perceptron, is also applied in the system to analyze visual descriptions upon registration in a direction to enhance the privacy of voters and the e-voting system. Quantum Key Distribution is being implemented in order to secure a blockchain-based e-voting system from quantum attacks using quantum algorithms. Implementation of e-voting blockchain D-app and providing a proposed solution for the privacy of voters in e-voting using Blockchain, CNN, and Quantum Key Distribution is done.

Keywords: hybrid blockchain, secure e-voting system, convolutional neural networks, quantum key distribution, one-time pad

Procedia PDF Downloads 54