Search results for: RSC neural classifier

Authors: Salima Smiti, Ines Gasmi, Makram Soui

Abstract:

Credit risk is the most important issue for financial institutions. Its assessment becomes an important task used to predict defaulter customers and classify customers as good or bad payers. To this objective, numerous techniques have been applied for credit risk assessment. However, to our knowledge, several evaluation techniques are black-box models such as neural networks, SVM, etc. They generate applicants’ classes without any explanation. In this paper, we propose to assess credit risk using rules classification method. Our output is a set of rules which describe and explain the decision. To this end, we will compare seven classification algorithms (JRip, Decision Table, OneR, ZeroR, Fuzzy Rule, PART and Genetic programming (GP)) where the goal is to find the best rules satisfying many criteria: accuracy, sensitivity, and specificity. The obtained results confirm the efficiency of the GP algorithm for German and Australian datasets compared to other rule-based techniques to predict the credit risk.

Keywords: credit risk assessment, classification algorithms, data mining, rule extraction

Procedia PDF Downloads 145

Authors: Sarita Agarwal, Deepika Delsa Dean

Abstract:

Like the task of transferring photo images to artistic images, image-to-image translation aims to translate the data to the imitated data which belongs to the target domain. Neural Style Transfer and CycleGAN are two well-known deep learning architectures used for photo image-to-art image transfer. However, studies involving these two models concentrate on one-to-one domain translation, not one-to-multi domains translation. Our study tries to investigate deep learning architectures, which can be controlled to yield multiple artistic style translation only by adding a conditional vector. We have expanded CycleGAN and constructed Conditional CycleGAN for 5 kinds of categories translation. Our study found that the architecture inserting conditional vector into the middle layer of the Generator could output multiple artistic images.

Keywords: genetic counseling, FMR1 gene, fragile x-associated primary ovarian insufficiency, premutation

Procedia PDF Downloads 87

Authors: Saba Rahimi, Ozan Oktay, Javier Alvarez-Valle, Sujeeth Bharadwaj

Abstract:

Successful application of deep learning in medical image analysis necessitates unprecedented amounts of labeled training data. Unlike conventional 2D applications, radiological images can be three-dimensional (e.g., CT, MRI), consisting of many instances within each image. The problem is exacerbated when expert annotations are required for effective pixel-wise labeling, which incurs exorbitant labeling effort and cost. Active learning is an established research domain that aims to reduce labeling workload by prioritizing a subset of informative unlabeled examples to annotate. Our contribution is a cost-effective approach for U-Net 3D models that uses Monte Carlo sampling to analyze pixel-wise uncertainty. Experiments on the AAPM 2017 lung CT segmentation challenge dataset show that our proposed framework can achieve promising segmentation results by using only 42% of the training data.

Keywords: image segmentation, active learning, convolutional neural network, 3D U-Net

Procedia PDF Downloads 119

Authors: Samiah Alammari, Nassim Ammour

Abstract:

When providing a massive number of tasks successively to a deep learning process, a good performance of the model requires preserving the previous tasks data to retrain the model for each upcoming classification. Otherwise, the model performs poorly due to the catastrophic forgetting phenomenon. To overcome this shortcoming, we developed a successful continual learning deep model for remote sensing hyperspectral image regions classification. The proposed neural network architecture encapsulates two trainable subnetworks. The first module adapts its weights by minimizing the discrimination error between the land-cover classes during the new task learning, and the second module tries to learn how to replicate the data of the previous tasks by discovering the latent data structure of the new task dataset. We conduct experiments on HSI dataset Indian Pines. The results confirm the capability of the proposed method.

Keywords: continual learning, data reconstruction, remote sensing, hyperspectral image segmentation

Procedia PDF Downloads 216

Authors: Shishay Kidanu, Abdullah Alhaj

Abstract:

Sinkholes in the karst terrain of Greene County, Missouri, pose significant geohazards, imposing challenges on construction and infrastructure development, with potential threats to lives and property. To address these issues, understanding the influencing factors and modeling sinkhole susceptibility is crucial for effective mitigation through strategic changes in land use planning and practices. This study utilizes geographic information system (GIS) software to collect and process diverse data, including topographic, geologic, hydrogeologic, and anthropogenic information. Nine key sinkhole influencing factors, ranging from slope characteristics to proximity to geological structures, were carefully analyzed. The Frequency Ratio method establishes relationships between attribute classes of these factors and sinkhole events, deriving class weights to indicate their relative importance. Weighted integration of these factors is accomplished using the Analytic Hierarchy Process (AHP) and the Weighted Linear Combination (WLC) method in a GIS environment, resulting in a comprehensive sinkhole susceptibility index (SSI) model for the study area. Employing Jenk's natural break classifier method, the SSI values are categorized into five distinct sinkhole susceptibility zones: very low, low, moderate, high, and very high. Validation of the model, conducted through the Area Under Curve (AUC) and Sinkhole Density Index (SDI) methods, demonstrates a robust correlation with sinkhole inventory data. The prediction rate curve yields an AUC value of 74%, indicating a 74% validation accuracy. The SDI result further supports the success of the sinkhole susceptibility model. This model offers reliable predictions for the future distribution of sinkholes, providing valuable insights for planners and engineers in the formulation of development plans and land-use strategies. Its application extends to enhancing preparedness and minimizing the impact of sinkhole-related geohazards on both infrastructure and the community.

Keywords: sinkhole, GIS, analytical hierarchy process, frequency ratio, susceptibility, Missouri

Procedia PDF Downloads 36

Authors: Amanina Iymia Jeffree, Reena Thriumani, Mohammad Iqbal Omar, Ammar Zakaria, Yumi Zuhanis Has-Yun Hashim, Ali Yeon Md Shakaff

Abstract:

Metabolite profiling is a strategy to be approached in the pattern recognition method focused on three types of cancer cell line that driving the most to death specifically lung, breast, and colon cancer. The purpose of this study was to discriminate the VOCs pattern among cancerous and control group based on metabolite profiling. The sampling was executed utilizing the cell culture technique. All culture flasks were incubated till 72 hours and data collection started after 24 hours. Every running sample took 24 minutes to be completed accordingly. The comparative metabolite patterns were identified by the implementation of headspace-solid phase micro-extraction (HS-SPME) sampling coupled with gas chromatography-mass spectrometry (GCMS). The optimizations of the main experimental variables such as oven temperature and time were evaluated by response surface methodology (RSM) to get the optimal condition. Volatiles were acknowledged through the National Institute of Standards and Technology (NIST) mass spectral database and retention time libraries. To improve the reliability of significance, it is of crucial importance to eliminate background noise which data from 3rd minutes to 17th minutes were selected for statistical analysis. Targeted metabolites, of which were annotated as known compounds with the peak area greater than 0.5 percent were highlighted and subsequently treated statistically. Volatiles produced contain hundreds to thousands of compounds; therefore, it will be optimized by chemometric analysis, such as principal component analysis (PCA) as a preliminary analysis before subjected to a pattern classifier for identification of VOC samples. The volatile organic compound profiling has shown to be significantly distinguished among cancerous and control group based on metabolite profiling.

Keywords: in vitro cancer cell line, metabolite profiling, pattern recognition, volatile organic compounds

Procedia PDF Downloads 343

Authors: Jiahui Song, Ravindra P. Joshi

Abstract:

The use of high-intensity, short-duration electric pulses is a promising development with many biomedical applications. The uses include irreversible electroporation for killing abnormal cells, reversible poration for drug and gene delivery, neuromuscular manipulation, and the shrinkage of tumors, etc. High intensity, short-duration electric pulses result in the creation of high-density, nanometer-sized pores in the cellular membrane. This electroporation amounts to localized modulation of the transverse membrane conductance, and effectively provides a voltage shunt. The electrically controlled changes in the trans-membrane conductivity could be used to affect neural traffic and action potential propagation. A rat was taken as the representative example in this research. The simulation study shows the pathway from the sensorimotor cortex down to the spinal motoneurons, and effector muscles could be reversibly blocked by using high-intensity, short-duration electrical pulses. Also, actual experimental observations were compared against simulation predictions.

Keywords: action potential, electroporation, high-intensity, short-duration

Procedia PDF Downloads 240

Authors: Jia-Hong Lee, Mei-Yi Wu, Hsien-Tsung Kuo

Abstract:

Texture is an important characteristic in real and synthetic scenes. Texture analysis plays a critical role in inspecting surfaces and provides important techniques in a variety of applications. Although several descriptors have been presented to extract texture features, the development of object recognition is still a difficult task due to the complex aspects of texture. Recently, many robust and scaling-invariant image features such as SIFT, SURF and ORB have been successfully used in image retrieval and object recognition. In this paper, we have tried to compare the performance for texture classification using these feature descriptors with k-means clustering. Different classifiers including K-NN, Naive Bayes, Back Propagation Neural Network , Decision Tree and Kstar were applied in three texture image sets － UIUCTex, KTH-TIPS and Brodatz, respectively. Experimental results reveal SIFTS as the best average accuracy rate holder in UIUCTex, KTH-TIPS and SURF is advantaged in Brodatz texture set. BP neuro network works best in the test set classification among all used classifiers.

Keywords: texture classification, texture descriptor, SIFT, SURF, ORB

Procedia PDF Downloads 333

Authors: Yuanjin Liu

Abstract:

Retirement withdrawal strategies are very important to minimize the probability of ruin in retirement. The ruin probability is modeled as a function of initial withdrawal age, gender, asset allocation, inflation rate, and initial withdrawal rate. The ruin probability is obtained based on the 2019 period life table for the Social Security, IRS Required Minimum Distribution (RMD) Worksheets, US historical bond and equity returns, and inflation rates using simulation. Several popular machine learning algorithms of the generalized additive model, random forest, support vector machine, extreme gradient boosting, and artificial neural network are built. The model validation and selection are based on the test errors using hyperparameter tuning and train-test split. The optimal model is recommended for retirees to monitor the ruin probability. The optimal withdrawal strategy can be obtained based on the optimal predictive model.

Keywords: ruin probability, retirement withdrawal strategies, predictive models, optimal model

Procedia PDF Downloads 41

Authors: Edgardo V. Gubatanga Jr., Mark Joshua Salvacion

Abstract:

Most aerial LiDAR systems have accompanying aerial cameras in order to capture not only the terrain of the surveyed area but also its true-color appearance. However, the presence of atmospheric clouds, poor lighting conditions, and aerial camera problems during an aerial survey may cause absence of aerial photographs. These leave areas having terrain information but lacking aerial photographs. Intensity images can be derived from LiDAR data but they are only grayscale images. A deep learning model is developed to create a complex function in a form of a deep neural network relating the pixel values of LiDAR-derived intensity images and true-color images. This complex function can then be used to predict the true-color images of a certain area using intensity images from LiDAR data. The predicted true-color images do not necessarily need to be accurate compared to the real world. They are only intended to look realistic so that they can be used as base maps.

Keywords: aerial LiDAR, colorization, deep learning, intensity images

Procedia PDF Downloads 129

Authors: Shweta Singh, Dipali Bansal, Rashima Mahajan

Abstract:

Psychoacoustics has become a potential area of research due to the growing interest of both laypersons and medical and mental health professionals. Non-invasive brain computer interface like Electroencephalography (EEG) is widely being used in this field. An attempt has been made in this paper to examine the response of EEG signals to acoustic stimuli further analysing the brain electrical activity. The real time EEG is acquired for 6 participants using a cost effective and portable EMOTIV EEG neuron headset. EEG data analysis is further done using EMOTIV test bench, EDF browser and EEGLAB (MATLAB Tool) application software platforms. Spectral analysis of acquired neural signals (AF3 channel) using these software platforms are clearly indicative of increased brain activity in various bands. The inferences drawn from such an analysis have significant correlation with subject’s subjective reporting of the experiences. The results suggest that the methodology adopted can further be used to assist patients with sleeping and depressive disorders.

Keywords: OM chant, spectral analysis, EDF browser, EEGLAB, EMOTIV, real time acquisition

Procedia PDF Downloads 252

Authors: N. Ploysook, R. Rugsaj, C. Suvanjumrat

Abstract:

The characteristic requirement for producing rectangular shape bottles was a uniform thickness of the plastic bottle wall. Die shaping was a good technique which controlled the wall thickness of bottles. An advance technology which was the finite element method (FEM) for blowing parison to be a rectangular shape bottle was conducted to reduce waste plastic from a trial and error method of a die shaping and parison control method. The artificial intelligent (AI) comprised of artificial neural network and genetic algorithm was selected to optimize the die gap shape from the FEM results. The application of AI technique could optimize the suitable die gap shape for the parison blow molding which did not depend on the parison control method to produce rectangular bottles with the uniform wall. Particularly, this application can be used with cheap blow molding machines without a parison controller therefore it will reduce cost of production in the bottle blow molding process.

Keywords: AI, bottle, die shaping, FEM

Procedia PDF Downloads 212

Authors: Rana I. Abdulghani, Amera I. Melhum

Abstract:

With the abnormal growth of the usage of computers over networks and under the consideration or agreement of most of the computer security experts who said that the goal of building a secure system is never achieved effectively, all these points led to the design of the intrusion detection systems(IDS). This research adopts a comparison between two techniques for network intrusion detection, The first one used the (Particles Swarm Optimization) that fall within the field (Swarm Intelligence). In this Act, the algorithm Enhanced for the purpose of obtaining the minimum error rate by amending the cluster centers when better fitness function is found through the training stages. Results show that this modification gives more efficient exploration of the original algorithm. The second algorithm used a (Back propagation NN) algorithm. Finally a comparison between the results of two methods used were based on (NSL_KDD) data sets for the construction and evaluation of intrusion detection systems. This research is only interested in clustering the two categories (Normal and Abnormal) for the given connection records. Practices experiments result in intrude detection rate (99.183818%) for EPSO and intrude detection rate (69.446416%) for BP neural network.

Keywords: IDS, SI, BP, NSL_KDD, PSO

Procedia PDF Downloads 357

Authors: The Danh Phan

Abstract:

House price forecasting is a main topic in the real estate market research. Effective house price prediction models could not only allow home buyers and real estate agents to make better data-driven decisions but may also be beneficial for the property policymaking process. This study investigates the housing market by using machine learning techniques to analyze real historical house sale transactions in Australia. It seeks useful models which could be deployed as an application for house buyers and sellers. Data analytics show a high discrepancy between the house price in the most expensive suburbs and the most affordable suburbs in the city of Melbourne. In addition, experiments demonstrate that the combination of Stepwise and Support Vector Machine (SVM), based on the Mean Squared Error (MSE) measurement, consistently outperforms other models in terms of prediction accuracy.

Keywords: house price prediction, regression trees, neural network, support vector machine, stepwise

Procedia PDF Downloads 186

Authors: Katleho Daniel Makatjane, Diteboho Lawrence Xaba, Ntebogang Dinah Moroke

Abstract:

The current study investigates the behaviour of time-varying parameters that are based on the score function of the predictive model density at time t. The mechanism to update the parameters over time is the scaled score of the likelihood function. The results revealed that there is high persistence of time-varying, as the location parameter is higher and the skewness parameter implied the departure of scale parameter from the normality with the unconditional parameter as 1.5. The results also revealed that there is a perseverance of the leptokurtic behaviour in stock returns which implies the returns are heavily tailed. Prior to model estimation, the White Neural Network test exposed that the stock price can be modelled by a GAS model. Finally, we proposed further researches specifically to model the existence of time-varying parameters with a more detailed model that encounters the heavy tail distribution of the series and computes the risk measure associated with the returns.

Keywords: generalized autoregressive score model, South Africa, stock returns, time-varying

Procedia PDF Downloads 475

Authors: Michal Krecichwost, Zauzanna Miodonska, Pawel Badura

Abstract:

The diagnosis of sigmatism is mostly based on the observation of articulatory organs. It is, however, not always possible to precisely observe the vocal apparatus, in particular in the oral cavity of the patient. Speech processing can allow to objectify the therapy and simplify the verification of its progress. In the described study the methodology for classification of incorrectly pronounced phoneme [s] is proposed. The recordings come from adults. They were registered with the speech recorder at the sampling rate of 44.1 kHz and the resolution of 16 bit. The database of pathological and normative speech has been collected for the study including reference assessments provided by the speech therapy experts. Ten adult subjects were asked to simulate a certain type of stigmatism under the speech therapy expert supervision. In the recordings, the analyzed phone [s] was surrounded by vowels, viz: ASA, ESE, ISI, SPA, USU, YSY. Thirteen MFCC (mel-frequency cepstral coefficients) and RMS (root mean square) values are calculated within each frame being a part of the analyzed phoneme. Additionally, 3 fricative formants along with corresponding amplitudes are determined for the entire segment. In order to aggregate the information within the segment, the average value of each MFCC coefficient is calculated. All features of other types are aggregated by means of their 75th percentile. The proposed method of features aggregation reduces the size of the feature vector used in the classification. Binary SVM (support vector machine) classifier is employed at the phoneme recognition stage. The first group consists of pathological phones, while the other of the normative ones. The proposed feature vector yields classification sensitivity and specificity measures above 90% level in case of individual logo phones. The employment of a fricative formants-based information improves the sole-MFCC classification results average of 5 percentage points. The study shows that the employment of specific parameters for the selected phones improves the efficiency of pathology detection referred to the traditional methods of speech signal parameterization.

Keywords: computer-aided pronunciation evaluation, sibilants, sigmatism diagnosis, speech processing

Procedia PDF Downloads 256

Authors: Frederic Jumelle, Kelvin So, Didan Deng

Abstract:

A method and system for neuropsychological performance test, comprising a mobile terminal, used to interact with a cloud server which stores user information and is logged into by the user through the terminal device; the user information is directly accessed through the terminal device and is processed by artificial neural network, and the user information comprises user facial emotions information, performance test answers information and user chronometrics. This assessment is used to evaluate the cognitive performance and emotional response of the subject to a series of dichotomous questions describing various situations of daily life and challenging the users' knowledge, values, ethics, and principles. In industrial applications, the timing of this assessment will depend on the users' need to obtain a service from a provider, such as opening a bank account, getting a mortgage or an insurance policy, authenticating clearance at work, or securing online payments.

Keywords: artificial intelligence, neurofinance, neuropsychology, risk management

Procedia PDF Downloads 110

Authors: Anas H. Aljemely, Jianping Xuan

Abstract:

Rolling bearing fault diagnosis plays a pivotal issue in the rotating machinery of modern manufacturing. In this research, a raw vibration signal and improved deep learning method for bearing fault diagnosis are proposed. The multi-dimensional scales of raw vibration signals are selected for evaluation condition monitoring system, and the deep learning process has shown its effectiveness in fault diagnosis. In the proposed method, employing an Exponential linear unit (ELU) layer in a convolutional neural network (CNN) that conducts the identical function on positive data, an exponential nonlinearity on negative inputs, and a particular convolutional operation to extract valuable features. The identification results show the improved method has achieved the highest accuracy with a 100-dimensional scale and increase the training and testing speed.

Keywords: bearing fault prognostics, developed CNN model, multiple-scale evaluation, deep learning features

Procedia PDF Downloads 170

Authors: Lai Yi-Hsiu

Abstract:

The present paper aims to examine the language processing of Chinese-speaking seniors with Alzheimer’s disease (AD) from the perspective of temporal cues. Twenty healthy adults, 17 healthy seniors, and 13 seniors with AD in Taiwan participated in this study to tell stories based on two sets of pictures. Nine temporal cues were fetched and analyzed. Oral productions in Mandarin Chinese were compared and discussed to examine to what extent and in what way these three groups of participants performed with significant differences. Results indicated that the age effects were significant in filled pauses. The dementia effects were significant in mean duration of pauses, empty pauses, filled pauses, lexical pauses, normalized mean duration of filled pauses and lexical pauses. The findings reported in the current paper help characterize the nature of language processing in seniors with or without AD, and contribute to the interactions between the AD neural mechanism and their temporal parameters.

Keywords: language processing, Alzheimer’s disease, Mandarin Chinese, temporal cues

Procedia PDF Downloads 418

Authors: Hamed Saremi, Suzan Taghavy, Seyed Mohammad Hanif Sanjari, Mostafa Kahali

Abstract:

One of the challenges in manufacturing and service companies to provide a product or service is recognized Brand to consumers in target markets. They provide most of their processes under the same capacity. But the constant threat of devastating internal and external resources to prevent a rise Brands and more companies are recognizing the stages are bankrupt. This paper has tried to identify and analyze effective indicators of brand equity and focuses on indicators and presents a model of intelligent create a model to prevent possible damage. In this study, the identified indicators of brand equity are based on literature study and according to expert opinions, set of indicators By techniques DEMATEL Then to used Multi-Step Adaptive Neural-Fuzzy Inference system (ANFIS) to design a multi-stage intelligent system for assessment of brand equity.

Keywords: brand, cosmetic product, ANFIS, DEMATEL

Procedia PDF Downloads 389

Authors: Khalak Bin Khair, Saqib Jahir, Mohammed Ibrahim, Fahad Bin, Debajyoti Karmaker

Abstract:

Object detection is a computer technology that deals with searching through digital images and videos for occurrences of semantic elements of a particular class. It is associated with image processing and computer vision. On top of object detection, we detect camouflage objects within an image using Deep Learning techniques. Deep learning may be a subset of machine learning that's essentially a three-layer neural network Over 6500 images that possess camouflage properties are gathered from various internet sources and divided into 4 categories to compare the result. Those images are labeled and then trained and tested using vgg16 architecture on the jupyter notebook using the TensorFlow platform. The architecture is further customized using Transfer Learning. Methods for transferring information from one or more of these source tasks to increase learning in a related target task are created through transfer learning. The purpose of this transfer of learning methodologies is to aid in the evolution of machine learning to the point where it is as efficient as human learning.

Keywords: deep learning, transfer learning, TensorFlow, camouflage, object detection, architecture, accuracy, model, VGG16

Procedia PDF Downloads 102

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

Abstract:

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

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

Procedia PDF Downloads 58

Authors: Jarek Krajewski, Andre Wittenborn, Martin Sauerland

Abstract:

This abstract describes a promising approach for estimating post-traumatic stress disorder (PTSD) based on prosodic speech characteristics. It illustrates the validity of this method by briefly discussing results from an Arabic refugee sample (N= 47, 32 m, 15 f). A well-established standardized self-report scale “Reaction of Adolescents to Traumatic Stress” (RATS) was used to determine the ground truth level of PTSD. The speech material was prompted by telling about autobiographical related sadness inducing experiences (sampling rate 16 kHz, 8 bit resolution). In order to investigate PTSD-induced speech changes, a self-developed set of 136 prosodic speech features was extracted from the .wav files. This set was adapted to capture traumatization related speech phenomena. An artificial neural network (ANN) machine learning model was applied to determine the PTSD level and reached a correlation of r = .37. These results indicate that our classifiers can achieve similar results to those seen in speech-based stress research.

Keywords: speech prosody, PTSD, machine learning, feature extraction

Procedia PDF Downloads 64

Authors: L. S. Chathurika

Abstract:

Early prediction of student performance is an important factor to be gained academic excellence. Whatever the study stream in secondary education, students lay the foundation for higher studies during the first year of their degree or diploma program in Sri Lanka. The information technology (IT) field has certain improvements in the education domain by selecting specialization areas to show the talents and skills of students. These specializations can be software engineering, network administration, database administration, multimedia design, etc. After completing the first-year, students attempt to select the best path by considering numerous factors. The purpose of this experiment is to predict the best study path using machine learning algorithms. Five classification algorithms: decision tree, support vector machine, artificial neural network, Naïve Bayes, and logistic regression are selected and tested. The support vector machine obtained the highest accuracy, 82.4%. Then affecting features are recognized to select the best study path.

Keywords: algorithm, classification, evaluation, features, testing, training

Procedia PDF Downloads 96

Authors: Ci Lin, Tet Yeap, Iluju Kiringa

Abstract:

This paper introduces the subspace rotation algorithm (SRA) to train the Restricted Hopfield Network (RHN) as an auto-associative memory. Subspace rotation algorithm is a gradient-free subspace tracking approach based on the singular value decomposition (SVD). In comparison with Backpropagation Through Time (BPTT) on training RHN, it is observed that SRA could always converge to the optimal solution and BPTT could not achieve the same performance when the model becomes complex, and the number of patterns is large. The AUTS case study showed that the RHN model trained by SRA could achieve a better structure of attraction basin with larger radius(in general) than the Hopfield Network(HNN) model trained by Hebbian learning rule. Through learning 10000 patterns from MNIST dataset with RHN models with different number of hidden nodes, it is observed that an several components could be adjusted to achieve a balance between recovery accuracy and noise resistance.

Keywords: hopfield neural network, restricted hopfield network, subspace rotation algorithm, hebbian learning rule

Procedia PDF Downloads 88

Authors: Armineh Nourbakhsh, Sameena Shah, Carolyn Rose

Abstract:

Layout-aware language models have been used to create multimodal representations for documents that are in image form, achieving relatively high accuracy in document understanding tasks. However, the large number of parameters in the resulting models makes building and using them prohibitive without access to high-performing processing units with large memory capacity. We propose an alternative approach that can create efficient representations without the need for a neural visual backbone. This leads to an 80% reduction in the number of parameters compared to the smallest SOTA model, widely expanding applicability. In addition, our layout embeddings are pre-trained on spatial and visual cues alone and only fused with text embeddings in downstream tasks, which can facilitate applicability to low-resource of multi-lingual domains. Despite using 2.5% of training data, we show competitive performance on two form understanding tasks: semantic labeling and link prediction.

Keywords: layout understanding, form understanding, multimodal document understanding, bias-augmented attention

Procedia PDF Downloads 115

Authors: Monica Gonzalez Machorro

Abstract:

Dementia is hard to diagnose because of the lack of early physical symptoms. Early dementia recognition is key to improving the living condition of patients. Speech technology is considered a valuable biomarker for this challenge. Recent works have utilized conventional acoustic features and machine learning methods to detect dementia in speech. BERT-like classifiers have reported the most promising performance. One constraint, nonetheless, is that these studies are either based on human transcripts or on transcripts produced by automatic speech recognition (ASR) systems. This research contribution is to explore a method that does not require transcriptions to detect early Alzheimer’s disease (AD) and mild cognitive impairment (MCI). This is achieved by fine-tuning a pre-trained ASR model for the downstream early AD and MCI tasks. To do so, a subset of the thoroughly studied Pitt Corpus is customized. The subset is balanced for class, age, and gender. Data processing also involves cropping the samples into 10-second segments. For comparison purposes, a baseline model is defined by training and testing a Random Forest with 20 extracted acoustic features using the librosa library implemented in Python. These are: zero-crossing rate, MFCCs, spectral bandwidth, spectral centroid, root mean square, and short-time Fourier transform. The baseline model achieved a 58% accuracy. To fine-tune HuBERT as a classifier, an average pooling strategy is employed to merge the 3D representations from audio into 2D representations, and a linear layer is added. The pre-trained model used is ‘hubert-large-ls960-ft’. Empirically, the number of epochs selected is 5, and the batch size defined is 1. Experiments show that our proposed method reaches a 69% balanced accuracy. This suggests that the linguistic and speech information encoded in the self-supervised ASR-based model is able to learn acoustic cues of AD and MCI.

Keywords: automatic speech recognition, early Alzheimer’s recognition, mild cognitive impairment, speech impairment

Procedia PDF Downloads 97

Authors: Bharatendra Rai

Abstract:

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

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

Procedia PDF Downloads 86

Authors: M. Hilani, B. Nassih

Abstract:

Phishing is one of the oldest and best known scams on the Internet. It can be defined as any type of telecommunications fraud that uses social engineering tricks to obtain confidential data from its victims. It’s a cybercrime aimed at stealing your sensitive information. Phishing is generally done via private email, so scammers impersonate large companies or other trusted entities to encourage victims to voluntarily provide information such as login credentials or, worse yet, credit card numbers. The COVID-19 theme is used by cybercriminals in multiple malicious campaigns like phishing. In this environment, messaging filtering solutions have become essential to protect devices that will now be used outside of the secure perimeter. Despite constantly updating methods to avoid these cyberattacks, the end result is currently insufficient. Many researchers are looking for optimal solutions to filter phishing emails, but we still need good results. In this work, we concentrated on solving the problem of detecting phishing emails using the different steps of NLP preprocessing, and we proposed and trained a model using one-dimensional CNN. Our study results show that our model obtained an accuracy of 99.99%, which demonstrates how well our model is working.

Keywords: phishing, e-mail, NLP preprocessing, CNN, e-mail filtering

Procedia PDF Downloads 81

Authors: S. Kawther, C. Marshall

Abstract:

Educational neuroscience has the intention of transforming research findings of the underpinning neural processes of learning to educational practices. A main criticism of the field, hitherto, is that less focus has been put on studying the in-progress practical application of these findings. Therefore, this study aims to gain a better understanding of teachers’ perceptions of the practical application and utilization of brain knowledge. This was approached by investigating the answer to 'What are the facilitators and barriers for bringing research from neuroscience to bear on education?'. Following a qualitative design, semi-structured interviews were conducted with 12 teachers who had a proficient course in educational neuroscience. Thematic analysis was performed on the transcribed data applying Braun & Clark’s steps. Findings emerged with four main themes: time, knowledge, teacher’s involvement, and system. These themes revealed that some effective brain-based practices are being engaged in by the teachers. However, the lack of guidance and challenges regarding this implementation were also found. This study discusses findings in light of the development of educational neuroscience implementation.

Keywords: brain-based, educational neuroscience, neuroeducation, neuroscience-informed

Procedia PDF Downloads 130