Search results for: neural cellular automata

Authors: Adel Edwar Waheeb Louka

Abstract:

Purpose AI-driven solutions are at the forefront of many pathology and medical imaging methods. Using algorithms designed to better the experience of medical professionals within their respective fields, the efficiency and accuracy of diagnosis can improve. In particular, X-rays are a fast and relatively inexpensive test that can diagnose diseases. In recent years, X-rays have not been widely used to detect and diagnose COVID-19. The under use of Xrays is mainly due to the low diagnostic accuracy and confounding with pneumonia, another respiratory disease. However, research in this field has expressed a possibility that artificial neural networks can successfully diagnose COVID-19 with high accuracy. Models and Data The dataset used is the COVID-19 Radiography Database. This dataset includes images and masks of chest X-rays under the labels of COVID-19, normal, and pneumonia. The classification model developed uses an autoencoder and a pre-trained convolutional neural network (DenseNet201) to provide transfer learning to the model. The model then uses a deep neural network to finalize the feature extraction and predict the diagnosis for the input image. This model was trained on 4035 images and validated on 807 separate images from the ones used for training. The images used to train the classification model include an important feature: the pictures are cropped beforehand to eliminate distractions when training the model. The image segmentation model uses an improved U-Net architecture. This model is used to extract the lung mask from the chest X-ray image. The model is trained on 8577 images and validated on a validation split of 20%. These models are calculated using the external dataset for validation. The models’ accuracy, precision, recall, f1-score, IOU, and loss are calculated. Results The classification model achieved an accuracy of 97.65% and a loss of 0.1234 when differentiating COVID19-infected, pneumonia-infected, and normal lung X-rays. The segmentation model achieved an accuracy of 97.31% and an IOU of 0.928. Conclusion The models proposed can detect COVID-19, pneumonia, and normal lungs with high accuracy and derive the lung mask from a chest X-ray with similarly high accuracy. The hope is for these models to elevate the experience of medical professionals and provide insight into the future of the methods used.

Keywords: artificial intelligence, convolutional neural networks, deeplearning, image processing, machine learningSarapin, intraarticular, chronic knee pain, osteoarthritisFNS, trauma, hip, neck femur fracture, minimally invasive surgery

Procedia PDF Downloads 62

Authors: Ninlawat Phuangchoke, Waraporn Viyanon, Setta Sasananan

Abstract:

The most important process of the water treatment plant process is the coagulation using alum and poly aluminum chloride (PACL), and the value of usage per day is a hundred thousand baht. Therefore, determining the dosage of alum and PACL are the most important factors to be prescribed. Water production is economical and valuable. This research applies an artificial neural network (ANN), which uses the Levenberg–Marquardt algorithm to create a mathematical model (Soft Jar Test) for prediction chemical dose used to coagulation such as alum and PACL, which input data consists of turbidity, pH, alkalinity, conductivity, and, oxygen consumption (OC) of Bangkhen water treatment plant (BKWTP) Metropolitan Waterworks Authority. The data collected from 1 January 2019 to 31 December 2019 cover changing seasons of Thailand. The input data of ANN is divided into three groups training set, test set, and validation set, which the best model performance with a coefficient of determination and mean absolute error of alum are 0.73, 3.18, and PACL is 0.59, 3.21 respectively.

Keywords: soft jar test, jar test, water treatment plant process, artificial neural network

Procedia PDF Downloads 161

Authors: Nadia Masood Khan, Muhammad Salman Khan, Gul Muhammad Khan

Abstract:

Cardiologists perform cardiac auscultation to detect abnormalities in heart sounds. Since accurate auscultation is a crucial first step in screening patients with heart diseases, there is a need to develop computer-aided detection/diagnosis (CAD) systems to assist cardiologists in interpreting heart sounds and provide second opinions. In this paper different algorithms are implemented for automated heart sound classification using unsegmented phonocardiogram (PCG) signals. Support vector machine (SVM), artificial neural network (ANN) and cartesian genetic programming evolved artificial neural network (CGPANN) without the application of any segmentation algorithm has been explored in this study. The signals are first pre-processed to remove any unwanted frequencies. Both time and frequency domain features are then extracted for training the different models. The different algorithms are tested in multiple scenarios and their strengths and weaknesses are discussed. Results indicate that SVM outperforms the rest with an accuracy of 73.64%.

Keywords: pattern recognition, machine learning, computer aided diagnosis, heart sound classification, and feature extraction

Procedia PDF Downloads 255

Authors: Gabriele Borg, Alexei Debono, Charlie Abela

Abstract:

There on a constant rise in the availability of high volumes of data gathered from multiple sources, resulting in an abundance of unprocessed information that can be used to monitor patterns and trends in user behaviour. Similarly, year after year, Malta is also constantly experiencing ongoing population growth and an increase in mobilization demand. This research takes advantage of data which is continuously being sourced and converting it into useful information related to the traffic problem on the Maltese roads. The scope of this paper is to provide a methodology to create a custom dataset (MalTra - Malta Traffic) compiled from multiple participants from various locations across the island to identify the most common routes taken to expose the main areas of activity. This use of big data is seen being used in various technologies and is referred to as ITSs (Intelligent Transportation Systems), which has been concluded that there is significant potential in utilising such sources of data on a nationwide scale. Furthermore, a series of traffic prediction graph neural network models are conducted to compare MalTra to large-scale traffic datasets.

Keywords: graph neural networks, traffic management, big data, mobile data patterns

Procedia PDF Downloads 123

Authors: Gajaanuja Megalathan, Banuka Athuraliya

Abstract:

Crime is one of our society's most intimidating and threatening challenges. With the majority of the population residing in cities, many experts and data provided by local authorities suggest a rapid increase in the number of crimes committed in these cities in recent years. There has been an increasing graph in the crime rates. People living in Sri Lanka have the right to know the exact crime rates and the crime rates in the future of the place they are living in. Due to the current economic crisis, crime rates have spiked. There have been so many thefts and murders recorded within the last 6-10 months. Although there are many sources to find out, there is no solid way of searching and finding out the safety of the place. Due to all these reasons, there is a need for the public to feel safe when they are introduced to new places. Through this research, the author aims to develop a mobile application that will be a solution to this problem. It is mainly targeted at tourists, and people who recently relocated will gain advantage of this application. Moreover, the Arima Model combined with ANN is to be used to predict crime rates. From the past researchers' works, it is evidently clear that they haven’t used the Arima model combined with Artificial Neural Networks to forecast crimes.

Keywords: arima model, ANN, crime prediction, data analysis

Procedia PDF Downloads 124

Authors: Huy Hieu Pham, Houssam Salmane, Louahdi Khoudour, Alain Crouzil, Pablo Zegers, Sergio Velastin

Abstract:

We present a deep learning-based multitask framework for joint 3D human pose estimation and action recognition from color video sequences. Our approach proceeds along two stages. In the first, we run a real-time 2D pose detector to determine the precise pixel location of important key points of the body. A two-stream neural network is then designed and trained to map detected 2D keypoints into 3D poses. In the second, we deploy the Efficient Neural Architecture Search (ENAS) algorithm to find an optimal network architecture that is used for modeling the Spatio-temporal evolution of the estimated 3D poses via an image-based intermediate representation and performing action recognition. Experiments on Human3.6M, Microsoft Research Redmond (MSR) Action3D, and Stony Brook University (SBU) Kinect Interaction datasets verify the effectiveness of the proposed method on the targeted tasks. Moreover, we show that our method requires a low computational budget for training and inference.

Keywords: human action recognition, pose estimation, D-CNN, deep learning

Procedia PDF Downloads 140

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 122

Authors: L. Rakesh, T. Y. Heblekar

Abstract:

This study entails the development and optimization of a mathematical model for a floating drum biogas reactor from first principles using thermal and empirical considerations. The model was derived on the basis of mass conservation, lumped mass heat transfer formulations and empirical biogas formation laws. The treatment leads to a system of coupled nonlinear ordinary differential equations whose solution mapped four-time independent controllable parameters to five output variables which adequately serve to describe the reactor performance. These equations were solved numerically using fourth order Runge-Kutta method for a range of input parameter values. Using the data so obtained an Artificial Neural Network with a single hidden layer was trained using Levenberg-Marquardt Damped Least Squares (DLS) algorithm. This network was then fine-tuned for optimal mapping by varying hidden layer size. This fast forward model was then employed as a health score generator in the Bacterial Foraging Optimization code. The optimal operating state of the simplified Biogas reactor was thus obtained.

Keywords: biogas, floating drum reactor, neural network model, optimization

Procedia PDF Downloads 138

Authors: Hadeer R. M. Tawfik, Rania A. K. Birry, Amani A. Saad

Abstract:

Eyes are considered to be the most sensitive and important organ for human being. Thus, any eye disorder will affect the patient in all aspects of life. Cataract is one of those eye disorders that lead to blindness if not treated correctly and quickly. This paper demonstrates a model for automatic detection, classification, and grading of cataracts based on image processing techniques and artificial intelligence. The proposed system is developed to ease the cataract diagnosis process for both ophthalmologists and patients. The wavelet transform combined with 2D Log Gabor Wavelet transform was used as feature extraction techniques for a dataset of 120 eye images followed by a classification process that classified the image set into three classes; normal, early, and advanced stage. A comparison between the two used classifiers, the support vector machine SVM and the artificial neural network ANN were done for the same dataset of 120 eye images. It was concluded that SVM gave better results than ANN. SVM success rate result was 96.8% accuracy where ANN success rate result was 92.3% accuracy.

Keywords: cataract, classification, detection, feature extraction, grading, log-gabor, neural networks, support vector machines, wavelet

Procedia PDF Downloads 329

Authors: Vincent Murray

Abstract:

The glycopeptide bleomycin is used in the treatment of testicular cancer, Hodgkin's lymphoma, and squamous cell carcinoma. Bleomycin damages and cleaves DNA in human cells, and this is considered to be the main mode of action for bleomycin's anti-tumor activity. In particular, double-strand breaks are thought to be the main mechanism for the cellular toxicity of bleomycin. Using Illumina next-generation DNA sequencing techniques, the genome-wide sequence specificity of bleomycin-induced double-strand breaks was determined in human cells. The degree of bleomycin cleavage was also assessed at the transcription start sites (TSSs) of actively transcribed genes and compared with non-transcribed genes. It was observed that bleomycin preferentially cleaved at the TSSs of actively transcribed human genes. There was a correlation between the degree of this enhanced cleavage at TSSs and the level of transcriptional activity. Bleomycin cleavage is also affected by chromatin structure and at TSSs, the peaks of bleomycin cleavage were approximately 200 bp apart. This indicated that bleomycin was able to detect phased nucleosomes at the TSSs of actively transcribed human genes. The genome-wide cleavage pattern of the bleomycin analogues 6′-deoxy-BLM Z and zorbamycin was also investigated in human cells. As found for bleomycin, these bleomycin analogues also preferentially cleaved at the TSSs of actively transcribed human genes. The cytotoxicity (IC₅₀ values) of these bleomycin analogues was determined. It was found that the degree of enhanced cleavage at TSSs was inversely correlated with the IC₅₀ values of the bleomycin analogues. This suggested that the level of cleavage at the TSSs of actively transcribed human genes was important for the cytotoxicity of bleomycin and analogues. Hence this study provided a deeper understanding of the cellular processes involved in the cancer chemotherapeutic activity of bleomycin.

Keywords: anti-tumour activity, bleomycin analogues, chromatin structure, genome-wide study, Illumina DNA sequencing

Procedia PDF Downloads 116

Authors: Bowen Ding, Yihao Kuang

Abstract:

In recent years, with the development of large-scale pre-trained lan-guage models, building vector representations of text through deep neural network models has become a standard practice for natural language processing tasks. From the performance on downstream tasks, we can know that the text representation constructed by these models contains linguistic information, but its encoding mode and extent are unclear. In this work, a structural probe is proposed to detect whether the vector representation produced by a deep neural network is embedded with a syntax tree. The probe is trained with the deep metric learning method, so that the distance between word vectors in the metric space it defines encodes the distance of words on the syntax tree, and the norm of word vectors encodes the depth of words on the syntax tree. The experiment results on ELMo and BERT show that the syntax tree is encoded in their parameters and the word representations they produce.

Keywords: deep metric learning, syntax tree probing, natural language processing, word representations

Procedia PDF Downloads 62

Authors: Thauane Silva, Gabrielle do Vale, Andre Ferreira, Marilda Siqueira, Thiago Moreno L. Souza, Milene D. Miranda

Abstract:

The exposure of A(H1N1)pdm09-infected epithelial cells (HeLa) to HIV-1 viral particles, or its gp120, enhanced interferon-induced transmembrane protein (IFITM3) content, a viral restriction factor (RF), resulting in a decrease in influenza replication. The gp120 binds to CCR5 (R5) or CXCR4 (X4) cell receptors during HIV-1 infection. Then, it is possible that the endogenous ligands of these receptors also modulate the expression of IFITM3 and other cellular factors that restrict influenza virus replication. Thus, the aim of this study is to analyze the role of cellular receptors R5 and X4 in modulating RFs in order to inhibit the replication of the influenza virus. A549 cells were treated with 2x effective dose (ED50) of endogenous R5 or X4 receptor agonists, CCL3 (20 ng/ml), CCL4 (10 ng/ml), CCL5 (10 ng/ml) and CXCL12 (100 ng/mL) or exogenous agonists, gp120 Bal-R5, gp120 IIIB-X4 and its mutants (5 µg/mL). The interferon α (10 ng/mL) and oseltamivir (60 nM) were used as a control. After 24 h post agonists exposure, the cells were infected with virus influenza A(H3N2) at 2 MOI (multiplicity of infection) for 1 h. Then, 24 h post infection, the supernatant was harvested and, the viral titre was evaluated by qRT-PCR. To evaluate IFITM3 and SAM and HD domain containing deoxynucleoside triphosphate triphosphohydrolase 1 (SAMHD1) protein levels, A549 were exposed to agonists for 24 h, and the monolayer was lysed with Laemmli buffer for western blot (WB) assay or fixed for indirect immunofluorescence (IFI) assay. In addition to this, we analyzed other RFs modulation in A549, after 24 h post agonists exposure by customized RT² Profiler Polymerase Chain Reaction Array. We also performed a functional assay in which SAMHD1-knocked-down, by single-stranded RNA (siRNA), A549 cells were infected with A(H3N2). In addition, the cells were treated with guanosine to assess the regulatory role of dNTPs by SAMHD1. We found that R5 and X4 agonists inhibited influenza replication in 54 ± 9%. We observed a four-fold increase in SAMHD1 transcripts by RFs mRNA quantification panel. After 24 h post agonists exposure, we did not observe an increase in IFITM3 protein levels through WB or IFI assays, but we observed an upregulation up to three-fold in the protein content of SAMHD1, in A549 exposed to agonists. Besides this, influenza replication enhanced in 20% in cell cultures that SAMDH1 was knockdown. Guanosine treatment in cells exposed to R5 ligands further inhibited influenza virus replication, suggesting that the inhibitory mechanism may involve the activation of the SAMHD1 deoxynucleotide triphosphohydrolase activity. Thus, our data show for the first time a direct relationship of SAMHD1 and inhibition of influenza replication, and provides perspectives for new studies on the signaling modulation, through cellular receptors, to induce proteins of great importance in the control of relevant infections for public health.

Keywords: chemokine receptors, gp120, influenza, virus restriction factors

Procedia PDF Downloads 132

Authors: Muhamad Aris Burhanudin, Angga Firmansyas, Bagus Jaya Santosa

Abstract:

Earthquakes are natural hazard that can trigger the most dangerous hazard, tsunami. 26 December 2004, a giant earthquake occurred in north-west Andalas Island. It made giant tsunami which crushed Sumatra, Bangladesh, India, Sri Lanka, Malaysia and Singapore. More than twenty thousand people dead. The occurrence of earthquake and tsunami can not be avoided. But this hazard can be mitigated by earthquake forecasting. Early preparation is the key factor to reduce its damages and consequences. We aim to investigate quantitatively on pattern of earthquake. Then, we can know the trend. We study about earthquake which has happened in Andalas island, Indonesia one last decade. Andalas is island which has high seismicity, more than a thousand event occur in a year. It is because Andalas island is in tectonic subduction zone of Hindia sea plate and Eurasia plate. A tsunami forecasting is needed to mitigation action. Thus, a Tsunami Forecasting Method is presented in this work. Neutral Network has used widely in many research to estimate earthquake and it is convinced that by using Backpropagation Method, earthquake can be predicted. At first, ANN is trained to predict Tsunami 26 December 2004 by using earthquake data before it. Then after we get trained ANN, we apply to predict the next earthquake. Not all earthquake will trigger Tsunami, there are some characteristics of earthquake that can cause Tsunami. Wrong decision can cause other problem in the society. Then, we need a method to reduce possibility of wrong decision. Fuzzy TOPSIS is a statistical method that is widely used to be decision seconder referring to given parameters. Fuzzy TOPSIS method can make the best decision whether it cause Tsunami or not. This work combines earthquake prediction using neural network method and using Fuzzy TOPSIS to determine the decision that the earthquake triggers Tsunami wave or not. Neural Network model is capable to capture non-linear relationship and Fuzzy TOPSIS is capable to determine the best decision better than other statistical method in tsunami prediction.

Keywords: earthquake, fuzzy TOPSIS, neural network, tsunami

Procedia PDF Downloads 485

Authors: Han Xue, Zhang Lanyue

Abstract:

In order to seek more effective feature extraction technology, feature extraction method based on MFCC combined with vector hydrophone is exposed in the paper. The sound pressure signal and particle velocity signal of two kinds of ships are extracted by using MFCC and its evolution form, and the extracted features are fused by using fisher-ratio and correlated distance criterion. The features are then identified by BP neural network. The results showed that MFCC, First-Order Differential MFCC and Second-Order Differential MFCC features can be used as effective features for recognition of underwater targets, and the fusion feature can improve the recognition rate. Moreover, the results also showed that the recognition rate of the particle velocity signal is higher than that of the sound pressure signal, and it reflects the superiority of vector signal processing.

Keywords: vector information, MFCC, differential MFCC, fusion feature, BP neural network

Procedia PDF Downloads 524

Authors: Kouzi Katia

Abstract:

This paper proposes a Direct Torque Control (DTC) algorithm of dual Stator Induction Motor (DSIM) drive using two approach intelligent techniques: Artificial Neural Network (ANN) approach replaces the switching table selector block of conventional DTC and Mamdani Fuzzy Logic controller (FLC) is used for stator resistance estimation. The fuzzy estimation method is based on an online stator resistance correction through the variations of stator current estimation error and its variation. The fuzzy logic controller gives the future stator resistance increment at the output. The main advantage of suggested algorithm control is to reduce the hardware complexity of conventional selectors, to avoid the drive instability that may occur in certain situation and ensure the tracking of the actual of the stator resistance. The effectiveness of the technique and the improvement of the whole system performance are proved by results.

Keywords: artificial neural network, direct torque control, dual stator induction motor, fuzzy logic estimator, switching table

Procedia PDF Downloads 338

Authors: Zsolt János Viharos, Krisztián Balázs Kis, Imre Paniti, Gábor Belső, Péter Németh, János Farkas

Abstract:

The paper presents the results and industrial applications in the production setup period estimation based on industrial data inherited from the field of polymer cutting. The literature of polymer cutting is very limited considering the number of publications. The first polymer cutting machine is known since the second half of the 20th century; however, the production of polymer parts with this kind of technology is still a challenging research topic. The products of the applying industrial partner must met high technical requirements, as they are used in medical, measurement instrumentation and painting industry branches. Typically, 20% of these parts are new work, which means every five years almost the entire product portfolio is replaced in their low series manufacturing environment. Consequently, it requires a flexible production system, where the estimation of the frequent setup periods' lengths is one of the key success factors. In the investigation, several (input) parameters have been studied and grouped to create an adequate training information set for an artificial neural network as a base for the estimation of the individual setup periods. In the first group, product information is collected such as the product name and number of items. The second group contains material data like material type and colour. In the third group, surface quality and tolerance information are collected including the finest surface and tightest (or narrowest) tolerance. The fourth group contains the setup data like machine type and work shift. One source of these parameters is the Manufacturing Execution System (MES) but some data were also collected from Computer Aided Design (CAD) drawings. The number of the applied tools is one of the key factors on which the industrial partners’ estimations were based previously. The artificial neural network model was trained on several thousands of real industrial data. The mean estimation accuracy of the setup periods' lengths was improved by 30%, and in the same time the deviation of the prognosis was also improved by 50%. Furthermore, an investigation on the mentioned parameter groups considering the manufacturing order was also researched. The paper also highlights the manufacturing introduction experiences and further improvements of the proposed methods, both on the shop floor and on the quotation preparation fields. Every week more than 100 real industrial setup events are given and the related data are collected.

Keywords: artificial neural network, low series manufacturing, polymer cutting, setup period estimation

Procedia PDF Downloads 240

Authors: Justin Reverdi, Sixin Zhang, Saïd Aoues, Fabrice Gamboa, Serge Gratton, Thomas Pellegrini

Abstract:

In vapor cycle systems, the mass flow sensor plays a key role for different monitoring and control purposes. However, physical sensors can be inaccurate, heavy, cumbersome, expensive, or highly sensitive to vibrations, which is especially problematic when embedded into an aircraft. The conception of a virtual sensor, based on other standard sensors, is a good alternative. This paper has two main objectives. Firstly, a data-driven model using a convolutional neural network is proposed to estimate the mass flow of the compressor. We show that it significantly outperforms the standard polynomial regression model (thermodynamic maps) in terms of the standard MSE metric and engineer performance metrics. Secondly, a semi-automatic segmentation method is proposed to compute the engineer performance metrics for real datasets, as the standard MSE metric may pose risks in analyzing the dynamic behavior of vapor cycle systems.

Keywords: deep learning, convolutional neural network, vapor cycle system, virtual sensor

Procedia PDF Downloads 52

Authors: Vadim Kulikov

Abstract:

The classical Stroop effect is the phenomenon that it takes more time to name the ink color of a printed word if the word denotes a conflicting color than if it denotes the same color. Over the last 80 years, there have been many variations of the experiment revealing various mechanisms behind semantic, attentional, behavioral and perceptual processing. The Stroop task is known to exhibit asymmetry. Reading the words out loud is hardly dependent on the ink color, but naming the ink color is significantly influenced by the incongruent words. This asymmetry is reversed, if instead of naming the color, one has to point at a corresponding color patch. Another debated aspects are the notions of automaticity and how much of the effect is due to semantic and how much due to response stage interference. Is automaticity a continuous or an all-or-none phenomenon? There are many models and theories in the literature tackling these questions which will be discussed in the presentation. None of them, however, seems to capture all the findings at once. A computational model is proposed which is based on the philosophical idea developed by the author that the mind operates as a collection of different information processing modalities such as different sensory and descriptive modalities, which produce emergent phenomena through mutual interaction and coherence. This is the framework theory where ‘framework’ attempts to generalize the concepts of modality, perspective and ‘point of view’. The architecture of this computational model consists of blocks of neurons, each block corresponding to one framework. In the simplest case there are four: visual color processing, text reading, speech production and attention selection modalities. In experiments where button pressing or pointing is required, a corresponding block is added. In the beginning, the weights of the neural connections are mostly set to zero. The network is trained using Hebbian learning to establish connections (corresponding to ‘coherence’ in framework theory) between these different modalities. The amount of data fed into the network is supposed to mimic the amount of practice a human encounters, in particular it is assumed that converting written text into spoken words is a more practiced skill than converting visually perceived colors to spoken color-names. After the training, the network performs the Stroop task. The RT’s are measured in a canonical way, as these are continuous time recurrent neural networks (CTRNN). The above-described aspects of the Stroop phenomenon along with many others are replicated. The model is similar to some existing connectionist models but as will be discussed in the presentation, has many advantages: it predicts more data, the architecture is simpler and biologically more plausible.

Keywords: connectionism, Hebbian learning, artificial neural networks, philosophy of mind, Stroop

Procedia PDF Downloads 263

Authors: Aishatu Ibrahim Birma, Aminu Tukur, Abdulkarim Abbass Gora

Abstract:

Machine translation plays a vital role in the Field of Natural Language Processing (NLP), breaking down language barriers and enabling communication across diverse communities. In the context of Hausa, a widely spoken language in West Africa, mainly in Nigeria, effective translation systems are essential for enabling seamless communication and promoting cultural exchange. However, due to the unique linguistic characteristics of Hausa, accurate translation remains a challenging task. The research proposes an approach to improving the machine learning translation of Hausa by integrating Named Entity Recognition (NER) techniques. Named entities, such as person names, locations, organizations, and dates, are critical components of a language's structure and meaning. Incorporating NER into the translation process can enhance the quality and accuracy of translations by preserving the integrity of named entities and also maintaining consistency in translating entities (e.g., proper names), and addressing the cultural references specific to Hausa. The NER will be incorporated into Neural Machine Translation (NMT) for the Hausa to English Translation.

Keywords: machine translation, natural language processing (NLP), named entity recognition (NER), neural machine translation (NMT)

Procedia PDF Downloads 37

Authors: Sefik Can Karakaya, Ibrahim Demir

Abstract:

In this study, the relationship between musical preferences and personality traits has been investigated in terms of Spotify audio analysis features. The aim of this paper is to build such a classifier capable of segmenting people into their Myers-Briggs Type Index (MBTI) personality type based on their Spotify playlists. Music takes an important place in the lives of people all over the world and online music streaming platforms make it easier to reach musical contents. In this context, the motivation to build such a classifier is allowing people to gain access to their MBTI personality type and perhaps for more reliably and more quickly. For this purpose, logistic regression and deep neural networks have been selected for classifier and their performances are compared. In conclusion, it has been found that musical preferences differ statistically between personality traits, and evaluated models are able to distinguish personality types based on given musical data structure with over %60 accuracy rate.

Keywords: myers-briggs type indicator, music psychology, Spotify, behavioural user profiling, deep neural networks, logistic regression

Procedia PDF Downloads 139

Authors: Maad Kamal Al-Anni

Abstract:

This study is about an algorithmic dependence of Artificial Neural Network on Multilayer Perceptron (MPL) pertaining to the classification and clustering presentations for Mobile Adhoc Network vulnerabilities. Moreover, mobile ad hoc network (MANET) is ubiquitous intelligent internetworking devices in which it has the ability to detect their environment using an autonomous system of mobile nodes that are connected via wireless links. Security affairs are the most important subject in MANET due to the easy penetrative scenarios occurred in such an auto configuration network. One of the powerful techniques used for inspecting the network packets is Intrusion Detection System (IDS); in this article, we are going to show the effectiveness of artificial neural networks used as a machine learning along with stochastic approach (information gain) to classify the malicious behaviors in simulated network with respect to different IDS techniques. The monitoring agent is responsible for detection inference engine, the audit data is collected from collecting agent by simulating the node attack and contrasted outputs with normal behaviors of the framework, whenever. In the event that there is any deviation from the ordinary behaviors then the monitoring agent is considered this event as an attack , in this article we are going to demonstrate the  signature-based IDS approach in a MANET by implementing the back propagation algorithm over ensemble-based Traffic Table (TT), thus the signature of malicious behaviors or undesirable activities are often significantly prognosticated and efficiently figured out, by increasing the parametric set-up of Back propagation algorithm during the experimental results which empirically shown its effectiveness  for the ratio of detection index up to 98.6 percentage. Consequently it is proved in empirical results in this article, the performance matrices are also being included in this article with Xgraph screen show by different through puts like Packet Delivery Ratio (PDR), Through Put(TP), and Average Delay(AD).

Keywords: Intrusion Detection System (IDS), Mobile Adhoc Networks (MANET), Back Propagation Algorithm (BPA), Neural Networks (NN)

Procedia PDF Downloads 191

Authors: Basiliyos Tilahun Betru, Charles Awono Onana, Bernabe Batchakui

Abstract:

Recommender systems have become increasingly popular in recent years, and are utilized in numerous areas. Nowadays many web services provide several information for users and recommender systems have been developed as critical element of these web applications to predict choice of preference and provide significant recommendations. With the help of the advantage of deep learning in modeling different types of data and due to the dynamic change of user preference, building a deep model can better understand users demand and further improve quality of recommendation. In this paper, deep neural network models for recommender system are evaluated. Most of deep neural network models in recommender system focus on the classical collaborative filtering user-item setting. Deep learning models demonstrated high level features of complex data can be learned instead of using metadata which can significantly improve accuracy of recommendation. Even though deep learning poses a great impact in various areas, applying the model to a recommender system have not been fully exploited and still a lot of improvements can be done both in collaborative and content-based approach while considering different contextual factors.

Keywords: big data, decision making, deep learning, recommender system

Procedia PDF Downloads 474

Authors: Min L. Stewart, Patrick Johnston

Abstract:

Predictive coding has been proposed as a general explanatory framework for understanding the neural mechanisms of perception. As such, an underweighting of perceptual priors has been hypothesised to underpin a range of differences in inferential and sensory processing in autism spectrum disorders. However, empirical evidence to support this has not been well established. The present study uses an electroencephalography paradigm involving changes of facial identity and person category (actors etc.) to explore how levels of autistic traits (AT) affect predictive coding at multiple stages in the visual processing hierarchy. The study uses a rapid serial presentation of faces, with hierarchically structured sequences involving both periodic and aperiodic repetitions of different stimulus attributes (i.e., person identity and person category) in order to induce contextual expectations relating to these attributes. It investigates two main predictions: (1) significantly larger and late neural responses to change of expected visual sequences in high-relative to low-AT, and (2) significantly reduced neural responses to violations of contextually induced expectation in high- relative to low-AT. Preliminary frequency analysis data comparing high and low-AT show greater and later event-related-potentials (ERPs) in occipitotemporal areas and prefrontal areas in high-AT than in low-AT for periodic changes of facial identity and person category but smaller ERPs over the same areas in response to aperiodic changes of identity and category. The research advances our understanding of how abnormalities in predictive coding might underpin aberrant perceptual experience in autism spectrum. This is the first stage of a research project that will inform clinical practitioners in developing better diagnostic tests and interventions for people with autism.

Keywords: hierarchical visual processing, face processing, perceptual hierarchy, prediction error, predictive coding

Procedia PDF Downloads 107

Authors: Manuel A. Alonso-Tarajano, Roberto Mosca, Patrick Aloy

Abstract:

Protein kinases participate in a myriad of cellular processes of major biomedical interest. The in vivo substrate specificity of these enzymes is a process determined by several factors, and despite several years of research on the topic, is still far from being totally understood. In the present work, we have quantified the contributions to the kinase substrate specificity of i) the phosphorylation sites and their surrounding residues in the sequence and of ii) the association of kinases to adaptor or scaffold proteins. We have used position-specific scoring matrices (PSSMs), to represent the stretches of sequences phosphorylated by 93 families of kinases. We have found negative correlations between the number of sequences from which a PSSM is generated and the statistical significance and the performance of that PSSM. Using a subset of 22 statistically significant PSSMs, we have identified specificity determinant residues (SDRs) for 86% of the corresponding kinase families. Our results suggest that different SDRs can function as positive or negative elements of substrate recognition by the different families of kinases. Additionally, we have found that human proteins with known function as adaptors or scaffolds (kAS) tend to interact with a significantly large fraction of the substrates of the kinases to which they associate. Based on this characteristic we have identified a set of 279 potential adaptors/scaffolds (pAS) for human kinases, which is enriched in Pfam domains and functional terms tightly related to the proposed function. Moreover, our results show that for 74.6% of the kinase– pAS association found, the pAS colocalize with the substrates of the kinases they are associated to. Finally, we have found evidence suggesting that the association of kinases to adaptors and scaffolds, may contribute significantly to diminish the in vivo substrate crossed- specificity of protein kinases. In general, our results indicate the relevance of several SDRs for both the positive and negative selection of phosphorylation sites by kinase families and also suggest that the association of kinases to pAS proteins may be an important factor for the localization of the enzymes with their set of substrates.

Keywords: kinase, phosphorylation, substrate specificity, adaptors, scaffolds, cellular colocalization

Procedia PDF Downloads 338

Authors: Yakin Hajlaoui, Richard Labib, Jean-François Plante, Michel Gamache

Abstract:

This study introduces the Multi-Layer Inverse Distance Weighting Model (ML-IDW), inspired by the mathematical formulation of both multi-layer neural networks (ML-NNs) and Inverse Distance Weighting model (IDW). ML-IDW leverages ML-NNs' processing capabilities, characterized by compositions of learnable non-linear functions applied to input features, and incorporates IDW's ability to learn anisotropic spatial dependencies, presenting a promising solution for nonlinear spatial interpolation and learning from complex spatial data. it employ gradient descent and backpropagation to train ML-IDW, comparing its performance against conventional spatial interpolation models such as Kriging and standard IDW on regression and classification tasks using simulated spatial datasets of varying complexity. the results highlight the efficacy of ML-IDW, particularly in handling complex spatial datasets, exhibiting lower mean square error in regression and higher F1 score in classification.

Keywords: deep learning, multi-layer neural networks, gradient descent, spatial interpolation, inverse distance weighting

Procedia PDF Downloads 48

Authors: Edward Schwalb, Matthias Dehmer, Michael Schlenkrich, Farzaneh Taslimi, Ketron Mitchell-Wynne, Horen Kuecuekyan

Abstract:

We present a generalized feature extraction approach for supporting Machine Learning (ML) algorithms which perform tasks similar to Finite-Element Analysis (FEA). We report results for estimating the Head Injury Categorization (HIC) of vehicle engine compartments across various impact scenarios. Our experiments demonstrate that models learned using features derived with a simple discretization approach provide a reasonable approximation of a full simulation. We observe that Decision Trees could be as effective as Neural Networks for the HIC task. The simplicity and performance of the learned Decision Trees could offer a trade-off of a multiple order of magnitude increase in speed and cost improvement over full simulation for a reasonable approximation. When used as a complement to full simulation, the approach enables rapid approximate feedback to engineering teams before submission for full analysis. The approach produces mesh independent features and is further agnostic of the assembly structure.

Keywords: mechanical design validation, FEA, supervised decision tree, convolutional neural network.

Procedia PDF Downloads 138

Authors: Marisa Rio, Sharanya Bola, Richard H. W. Funk, Gerald Gerlach

Abstract:

Cell migration, wound healing and regeneration are some of the physiological phenomena in which electric fields (EFs) have proven to have an important function. Physiologically, cells experience electrical signals in the form of transmembrane potentials, ion fluxes through protein channels as well as electric fields at their surface. As soon as a wound is created, the disruption of the epithelial layers generates an electric field of ca. 40-200 mV/mm, directing cell migration towards the wound site, starting the healing process. In vitro electrotaxis, experiments have shown cells respond to DC EFs polarizing and migrating towards one of the poles (cathode or anode). A standard electrotaxis experiment consists of an electrotaxis chamber where cells are cultured, a DC power source and agar salt bridges that help delaying toxic products from the electrodes to attain the cell surface. The electric field strengths used in such an experiment are uniform and homogeneous. In contrast, the endogenous electric field strength around a wound tend to be multi-field and non-homogeneous. In this study, we present a custom device that enables electrotaxis experiments in non-homogeneous DC electric fields. Its main feature involves the replacement of conventional metallic electrodes, separated from the electrotaxis channel by agarose gel bridges, through electrolyte-filled microchannels. The connection to the DC source is made by Ag/AgCl electrodes, incased in agarose gel and placed at the end of each microfluidic channel. An SU-8 membrane closes the fluidic channels and simultaneously serves as the single connection from each of them to the central electrotaxis chamber. The electric field distribution and current density were numerically simulated with the steady-state electric conduction module from ANSYS 16.0. Simulation data confirms the application of nonhomogeneous EF of physiological strength. To validate the biocompatibility of the device cellular viability of the photoreceptor-derived 661W cell line was accessed. The cells have not shown any signs of apoptosis, damage or detachment during stimulation. Furthermore, immunofluorescence staining, namely by vinculin and actin labelling, allowed the assessment of adhesion efficiency and orientation of the cytoskeleton, respectively. Cellular motility in the presence and absence of applied DC EFs was verified. The movement of individual cells was tracked for the duration of the experiments, confirming the EF-induced, cathodal-directed motility of the studied cell line. The in vitro monolayer wound assay, or “scratch assay” is a standard protocol to quantitatively access cell migration in vitro. It encompasses the growth of a confluent cell monolayer followed by the mechanic creation of a scratch, representing a wound. Hence, wound dynamics was monitored over time and compared for control and applied the electric field to quantify cellular population motility.

Keywords: DC non-homogeneous electric fields, electrotaxis, microfluidic biochip, wound healing

Procedia PDF Downloads 268

Authors: Ozlem Oral, Seval Kilic, Ozlem Yedier, Serap Dokmeci, Devrim Gozuacik

Abstract:

Autophagy is a degradation pathway, activating under stress conditions. It digests macromolecules, such as abnormal proteins and long-lived organelles by engulfing them and by subsequent delivery of the cargo to lysosomes. The members of the phospholipid-dependent serine/threonine kinases, involved in many signaling pathways, which are necessary for the regulation of cellular metabolic activation. Previous studies implicate that, serine/threonine kinases have crucial roles in the mechanism of many diseases depend on the activated and/or inactivated signaling pathway. Data indicates, the signaling pathways activated by serine/threonine kinases are also involved in activation of autophagy mechanism. However, the information about the effect of serine/threonine kinases on autophagy mechanism and the roles of these effects in disease formation is limited. In this study, we investigated the effect of activated serine/threonine kinases on autophagic pathway. We performed a commonly used autophagy technique, GFP-LC3 dot formation and by using microscopy analyses, we evaluated promotion and/or inhibition of autophagy in serine/threonine kinase-overexpressed fibroblasts as well as cancer cells. In addition, we carried out confocal microscopy analyses and examined autophagic flux by utilizing the differential pH sensitivities of RFP and GFP in mRFP-GFP-LC3 probe. Based on the shRNA-library based screening, we identified autophagy-related proteins affected by serine/threonine kinases. We further studied the involvement of serine/threonine kinases on the molecular mechanism of newly identified autophagy proteins and found that, autophagic pathway is indirectly controlled by serine/threonine kinases via specific autophagic proteins. Our data indicate the molecular connection between two critical cellular mechanisms, which have important roles in the formation of many disease pathologies, particularly cancer. This project is supported by TUBITAK-1001-Scientific and Technological Research Projects Funding Program, Project No: 114Z836.

Keywords: autophagy, GFP-LC3 dot formation assay, serine/threonine kinases, shRNA-library screening

Procedia PDF Downloads 288

Authors: Sharmi Mukherjee, Anindita Chakraborty

Abstract:

Cellular irradiation incites complex responses including arrest of cell cycle progression. This article accentuates the effects of radiation on cell cycle status of radiation non-targeted cells. Human Hepatoma HepG2 cells were exposed to increasing doses of γ radiations (1, 2, 4, 6 Gy) and their cell culture media was transferred to non-targeted HepG2 cells cultured in other Petri plates. These radiation non-targeted cells cultured in the ICCM (Irradiated cell conditioned media) were the bystander cells on which cell cycle analysis was performed using flow cytometry. An apparent decrease in the distribution of bystander cells at G0/G1 phase was observed with increased radiation doses upto 4 Gy representing a linear relationship. This was accompanied by a gradual increase in cellular distribution at G2/M phase. Interestingly the number of cells in G2/M phase at 1 and 2 Gy irradiation was not significantly different from each other. However, the percentage of G2 phase cells at 4 and 6 Gy doses were significantly higher than 2 Gy dose indicating the IC50 dose to be between 2 and 4 Gy. Cell cycle arrest is an indirect indicator of genotoxic damage in cells. In this study, bystander stress signals through the cell culture media of irradiated cells disseminated the radiation induced DNA damages in the non-targeted cells which resulted in arrest of the cell cycle progression at G2/M phase checkpoint. This implies that actual radiation biological effects represent a penumbra with effects encompassing a larger area than the actual beam. This article highlights the existence of genotoxic damages as bystander effects of γ rays in human Hepatoma cells by cell cycle analysis and opens up avenues for appraisal of bystander stress communications between tumor cells. Contemplation of underlying signaling mechanisms can be manipulated to maximize damaging effects of radiation with minimum dose and thus has therapeutic applications.

Keywords: bystander effect, cell cycle, genotoxic damage, hepatoma

Procedia PDF Downloads 178

Authors: Ankit Kamboj, Shikha Talwar, Nilesh Powar

Abstract:

To successfully deliver our products in the market, the employees need to be in a safe environment, especially in an industrial and manufacturing environment. The consequences of delinquency in wearing safety glasses while working in industrial plants could be high risk to employees, hence the need to develop a real-time automatic detection system which detects the persons (violators) not wearing safety glasses. In this study a convolutional neural network (CNN) algorithm called faster region based CNN (Faster RCNN) with rotated bounding box has been used for detecting safety glasses on persons; the algorithm has an advantage of detecting safety glasses with different orientation angles on the persons. The proposed method of rotational bounding boxes with a convolutional neural network first detects a person from the images, and then the method detects whether the person is wearing safety glasses or not. The video data is captured at the entrance of restricted zones of the industrial environment (manufacturing plant), which is further converted into images at 2 frames per second. In the first step, the CNN with pre-trained weights on COCO dataset is used for person detection where the detections are cropped as images. Then the safety goggles are labelled on the cropped images using the image labelling tool called roLabelImg, which is used to annotate the ground truth values of rotated objects more accurately, and the annotations obtained are further modified to depict four coordinates of the rectangular bounding box. Next, the faster RCNN with rotated bounding box is used to detect safety goggles, which is then compared with traditional bounding box faster RCNN in terms of detection accuracy (average precision), which shows the effectiveness of the proposed method for detection of rotatory objects. The deep learning benchmarking is done on a Dell workstation with a 16GB Nvidia GPU.

Keywords: CNN, deep learning, faster RCNN, roLabelImg rotated bounding box, safety goggle detection

Procedia PDF Downloads 125