Search results for: neural machine translation

Authors: S. Hammoudeh, S. Ghuloum, A. Abdelhakam, A. AlMujalli, M. Opler, Y. Hani, A. Yehya, S. Mari, R. Elsherbiny, Z. Mahfoud, H. Al-Amin

Abstract:

Introduction: Suicidal ideation and attempts are very common in patients with schizophrenia and still contributes to the high mortality in this population. The InterSePT Scale for Suicidal Thinking (ISST) is a validated tool used to assess suicidal ideation in patients with schizophrenia. This research aims to validate the Arabic version of the ISST among the Arabs residing in Qatar. Methods: Patients diagnosed with schizophrenia were recruited from the department of Psychiatry, Rumailah Hospital, Doha, Qatar. Healthy controls were recruited from the primary health care centers in Doha, Qatar. The validation procedures including professional and expert translation, pilot survey and back translation of the ISST were implemented. Diagnosis of schizophrenia was confirmed using the validated Arabic version of Mini International Neuropsychiatric Interview (MINI 6, module K) for schizophrenia. The gold standard was the module B on suicidality from MINI 6 also. This module was administered by a rater who was blinded to the results of ISST. Results: Our sample (n=199) was composed of 98 patients diagnosed with schizophrenia (age 36.03 ± 9.88 years; M/F is 2/1) and 101 healthy participants (age 35.01 ± 8.23 years; M/F is 1/2). Among patients with schizophrenia: 26.5% were married, 17.3% had a college degree, 28.6% were employed, 9% had committed suicide once, and 4.4% had more than 4 suicide attempts. Among the control group: 77.2% were married, 57.4% had a college degree, and 99% were employed. The mean score on the ISST was 2.36 ± 3.97 vs. 0.47 ± 1.44 for the schizophrenia and control groups, respectively. The overall Cronbach’s alpha was 0.91. Conclusions: This is the first study in the Arab world to validate the ISST in an Arabic-based population. The psychometric properties indicate that the Arabic version of the ISST is a valid tool to assess the severity of suicidal ideation in Arabic speaking patients diagnosed with schizophrenia.

Keywords: mental health, Qatar, schizophrenia, suicide

Procedia PDF Downloads 541

Authors: Florin Leon, Silvia Curteanu

Abstract:

Developing complete mechanistic models for polymerization reactors is not easy, because complex reactions occur simultaneously; there is a large number of kinetic parameters involved and sometimes the chemical and physical phenomena for mixtures involving polymers are poorly understood. To overcome these difficulties, empirical models based on sampled data can be used instead, namely regression methods typical of machine learning field. They have the ability to learn the trends of a process without any knowledge about its particular physical and chemical laws. Therefore, they are useful for modeling complex processes, such as the free radical polymerization of methyl methacrylate achieved in a batch bulk process. The goal is to generate accurate predictions of monomer conversion, numerical average molecular weight and gravimetrical average molecular weight. This process is associated with non-linear gel and glass effects. For this purpose, an adaptive sampling technique is presented, which can select more samples around the regions where the values have a higher variation. Several machine learning methods are used for the modeling and their performance is compared: support vector machines, k-nearest neighbor, k-nearest neighbor and random forest, as well as an original algorithm, large margin nearest neighbor regression. The suggested method provides very good results compared to the other well-known regression algorithms.

Keywords: batch bulk methyl methacrylate polymerization, adaptive sampling, machine learning, large margin nearest neighbor regression

Procedia PDF Downloads 293

Authors: Artur Matuck, Guilherme F. Nobre

Abstract:

Machines can be either tool, media, or social agents. Advances in technology have been delivering machines capable of autonomous expression, both through communication and art. This paper deals with models (theoretical approach) and experiments (applied approach) related to artificial agents. On one hand it traces how social sciences' scholars have worked with topics such as text automatization, man-machine writing cooperation, and communication. On the other hand it covers how computer sciences' scholars have built communicative and artistic machines, including the programming of creativity. The aim is to present a brief survey on artificially intelligent communicators and artificially creative writers, and provide the basis to understand the meta-authorship and also to new and further man-machine co-authorship.

Keywords: artificial communication, artificial creativity, artificial writers, meta-authorship, robotic art

Procedia PDF Downloads 275

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 472

Authors: Kourosh Modarresi

Abstract:

The abundance of media channels and devices has given users a variety of options to extract, discover, and explore information in the digital world. Since, often, there is a long and complicated path that a typical user may venture before taking any (significant) action (such as purchasing goods and services), it is critical to know how each node (media channel) in the path of user has contributed to the final action. In this work, the significance of each media channel is computed using statistical analysis and machine learning techniques. More specifically, “Regularized Singular Value Decomposition”, and “Sparse Principal Component” has been used to compute the significance of each channel toward the final action. The results of this work are a considerable improvement compared to the present approaches.

Keywords: multimedia attribution, sparse principal component, regularization, singular value decomposition, feature significance, machine learning, linear systems, variable shrinkage

Procedia PDF Downloads 292

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 508

Authors: Burak Oksuzoglu, Savas Yildirim, Ferhat Kutlu

Abstract:

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

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

Procedia PDF Downloads 124

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 329

Authors: Aaditya U. Jhamb

Abstract:

Due to the current energy crisis that many countries are battling, energy-efficient buildings are the subject of extensive research in the modern technological era because of growing worries about energy consumption and its effects on the environment. The paper explores 8 factors that help determine energy efficiency for a building: (relative compactness, surface area, wall area, roof area, overall height, orientation, glazing area, and glazing area distribution), with Tsanas and Xifara providing a dataset. The data set employed 768 different residential building models to anticipate heating and cooling loads with a low mean squared error. By optimizing these characteristics, machine learning algorithms may assess and properly forecast a building's heating and cooling loads, lowering energy usage while increasing the quality of people's lives. As a result, the paper studied the magnitude of the correlation between these input factors and the two output variables using various statistical methods of analysis after determining which input variable was most closely associated with the output loads. The most conclusive model was the Decision Tree Regressor, which had a mean squared error of 0.258, whilst the least definitive model was the Isotonic Regressor, which had a mean squared error of 21.68. This paper also investigated the KNN Regressor and the Linear Regression, which had to mean squared errors of 3.349 and 18.141, respectively. In conclusion, the model, given the 8 input variables, was able to predict the heating and cooling loads of a residential building accurately and precisely.

Keywords: energy efficient buildings, heating load, cooling load, machine learning models

Procedia PDF Downloads 80

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 39

Authors: T. Asefi, J. Faiz, M. A. Khan

Abstract:

This paper introduces dual rotor axial flux machines with surface mounted and spoke type ferrite permanent magnets with concentrated windings; they are introduced as alternatives to a generator with surface mounted Nd-Fe-B magnets. The output power, voltage, speed and air gap clearance for all the generators are identical. The machine designs are optimized for minimum mass using a population-based algorithm, assuming the same efficiency as the Nd-Fe-B machine. A finite element analysis (FEA) is applied to predict the performance, emf, developed torque, cogging torque, no load losses, leakage flux and efficiency of both ferrite generators and that of the Nd-Fe-B generator. To minimize cogging torque, different rotor pole topologies and different pole arc to pole pitch ratios are investigated by means of 3D FEA. It was found that the surface mounted ferrite generator topology is unable to develop the nominal electromagnetic torque, and has higher torque ripple and is heavier than the spoke type machine. Furthermore, it was shown that the spoke type ferrite permanent magnet generator has favorable performance and could be an alternative to rare-earth permanent magnet generators, particularly in wind energy applications. Finally, the analytical and numerical results are verified using experimental results.

Keywords: axial flux, permanent magnet generator, dual rotor, ferrite permanent magnet generator, finite element analysis, wind turbines, cogging torque, population-based algorithms

Procedia PDF Downloads 133

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 252

Authors: Ahmed I. Alutabi, Naghmeh Dezhabad, Sudhakar Ganti

Abstract:

Data centers have been growing in size and dema nd continuously in the last two decades. Planning for the deployment of resources has been shallow and always resorted to over-provisioning. Data center operators try to maximize the availability of their services by allocating multiple of the needed resources. One resource that has been wasted, with little thought, has been energy. In recent years, programmable resource allocation has paved the way to allow for more efficient and robust data centers. In this work, we examine the predictability of resource usage in a data center environment. We use a number of models that cover a wide spectrum of machine learning categories. Then we establish a framework to guarantee the client service level agreement (SLA). Our results show that using prediction can cut energy loss by up to 55%.

Keywords: machine learning, artificial intelligence, prediction, data center, resource allocation, green computing

Procedia PDF Downloads 93

Authors: Todd Zhou, Mikhail Yurochkin

Abstract:

Out-of-distribution (OOD) detection is receiving increasing amounts of attention in the machine learning research community, boosted by recent technologies, such as autonomous driving and image processing. This newly-burgeoning field has called for the need for more effective and efficient methods for out-of-distribution generalization methods. Without accessing the label information, deploying machine learning models to out-of-distribution domains becomes extremely challenging since it is impossible to evaluate model performance on unseen domains. To tackle this out-of-distribution detection difficulty, we designed a model selection pipeline algorithm and developed a model selection framework with different impurity and randomness measurements to evaluate and choose the best-performing models for out-of-distribution data. By exploring different randomness scores based on predicted probabilities, we adopted the out-of-distribution entropy and developed a custom-designed score, ”CombinedScore,” as the evaluation criterion. This proposed score was created by adding labeled source information into the judging space of the uncertainty entropy score using harmonic mean. Furthermore, the prediction bias was explored through the equality of opportunity violation measurement. We also improved machine learning model performance through model calibration. The effectiveness of the framework with the proposed evaluation criteria was validated on the Folktables American Community Survey (ACS) datasets.

Keywords: model selection, domain generalization, model fairness, randomness measurements, bias index

Procedia PDF Downloads 111

Authors: S. Schröder, P. Ennen, T. Langer, S. Müller, M. Shehadeh, M. Haberstroh, F. Hees

Abstract:

Since a bit over a year ago, Festo AG and Co. KG, Festo Didactic SE, robomotion GmbH, the researchers of the Cybernetics-Lab IMA/ZLW and IfU, as well as the Human-Computer Interaction Center at the RWTH Aachen University, have been working together in the focal point of assembly competences to realize different scenarios in the field of human-machine interaction (HMI). In the framework of project ARIZ, questions concerning the future of production within the fourth industrial revolution are dealt with. There are many perspectives of human-robot collaboration that consist Industry 4.0 on an individual, organization and enterprise level, and these will be addressed in ARIZ. The aim of the ARIZ projects is to link AI-Approaches to assembly problems and to implement them as prototypes in demonstrators. To do so, island and flow based production scenarios will be simulated and realized as prototypes. These prototypes will serve as applications of flexible robotics as well as AI-based planning and control of production process. Using the demonstrators, human interaction strategies will be examined with an information system on one hand, and a robotic system on the other. During the tests, prototypes of workspaces that illustrate prospective production work forms will be represented. The human being will remain a central element in future productions and will increasingly be in charge of managerial tasks. Questions thus arise within the overall perspective, primarily concerning the role of humans within these technological revolutions, as well as their ability to act and design respectively to the acceptance of such systems. Roles, such as the 'Trainer' of intelligent systems may become a possibility in such assembly scenarios.

Keywords: human-machine interaction, information technology, island based production, assembly competences

Procedia PDF Downloads 188

Authors: Vesile Evrim, Aliyu Awwal

Abstract:

Today as in the other domains, there are an enormous number of political transcripts available in the Web which is waiting to be mined and used for various purposes such as statistics and recommendations. Therefore, automatically determining the political orientation on these transcripts becomes crucial. The methodologies used by machine learning algorithms to do the automatic classification are based on different features such as Linguistic. Considering the ideology differences between Liberals and Conservatives, in this paper, the effect of Personality Traits on political orientation classification is studied. This is done by considering the correlation between LIWC features and the BIG Five Personality Traits. Several experiments are conducted on Convote U.S. Congressional-Speech dataset with seven benchmark classification algorithms. The different methodologies are applied on selecting different feature sets that constituted by 8 to 64 varying number of features. While Neuroticism is obtained to be the most differentiating personality trait on classification of political polarity, when its top 10 representative features are combined with several classification algorithms, it outperformed the results presented in previous research.

Keywords: politics, personality traits, LIWC, machine learning

Procedia PDF Downloads 478

Authors: Hossein Ghadimi, Alireza Alizadeh, Oveis Abedinia, Noradin Ghadimi

Abstract:

This paper presents an enhanced Honey Bee Mating Optimization (HBMO) to solve the optimal design of multi machine power system stabilizer (PSSs) parameters, which is called the Interactive Honey Bee Mating Optimization (IHBMO). Power System Stabilizers (PSSs) are now routinely used in the industry to damp out power system oscillations. The design problem of the proposed controller is formulated as an optimization problem and IHBMO algorithm is employed to search for optimal controller parameters. The proposed method is applied to multi-machine power system (MPS). The method suggested in this paper can be used for designing robust power system stabilizers for guaranteeing the required closed loop performance over a prespecified range of operating and system conditions. The simplicity in design and implementation of the proposed stabilizers makes them better suited for practical applications in real plants. The non-linear simulation results are presented under wide range of operating conditions in comparison with the PSO and CPSS base tuned stabilizer one through FD and ITAE performance indices. The results evaluation shows that the proposed control strategy achieves good robust performance for a wide range of system parameters and load changes in the presence of system nonlinearities and is superior to the other controllers.

Keywords: power system stabilizer, IHBMO, multimachine, nonlinearities

Procedia PDF Downloads 487

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 125

Authors: João Rato, Nuno Costa

Abstract:

The human verbal communication is a two-way process which requires a mutual understanding that will result in some considerations. This kind of communication, also called dialogue, besides the supposed human agents it can also be performed between human agents and machines. The interaction between Men and Machines, by means of a natural language, has an important role concerning the improvement of the communication between each other. Aiming at knowing the performance of some speech recognition systems, this document shows the results of the accomplished tests according to the Word Error Rate evaluation method. Besides that, it is also given a set of information linked to the systems of Man-Machine communication. After this work has been made, conclusions were drawn regarding the Speech Recognition Systems, among which it can be mentioned their poor performance concerning the voice interpretation in noisy environments.

Keywords: automatic speech recognition, man-machine conversation, speech recognition, spoken dialogue systems, word error rate

Procedia PDF Downloads 306

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 458

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 97

Authors: Brian Tung, Yam Wing Siu, Tsun Se Cheong

Abstract:

Purpose: This research aims to explore how personal and environmental factors, especially the socio-economic changes and behavioral changes fostered by the COVID-19 outbreak pandemic, affect the financial vulnerability of a specific segment of people in financial distress. Innovative research methodology of machine learning will be applied to data collected from over 300 local individuals in Hong Kong seeking counseling or similar services in recent years. Results: First, machine learning has found that too much exposure to digital services and information on digitized services may lead to adverse effects on respondents’ financial vulnerability. Second, the improvement in financial literacy level provides benefits to the financially vulnerable group, especially those respondents who have started with a lower level. Third, serious addiction to digital technology can lead to worsened debt servicing ability. Machine learning also has found a strong correlation between debt servicing situations and income-seeking behavior as well as spending behavior. In addition, if the vulnerable groups are able to make appropriate investments, they can reduce the probability of incurring financial distress. Finally, being too active in borrowing and repayment can result in a higher likelihood of over-indebtedness. Conclusion: Findings can be employed in formulating a better counseling strategy for professionals. Debt counseling services can be more preventive in nature. For example, according to the findings, with a low level of financial literacy, the respondents are prone to overspending and unable to react properly to the e-marketing promotion messages pop-up from digital services or even falling into financial/investment scams. In addition, people with low levels of financial knowledge will benefit from financial education. Therefore, financial education programs could include tech-savvy matters as special features.

Keywords: personal finance, digitization of the economy, COVID-19 pandemic, addiction to digital technology, financial vulnerability

Procedia PDF Downloads 41

Authors: Youn-Hwan Kim, Jae-Won Moon, Hae-Joong Kim

Abstract:

This paper introduces the results of the study on the development of accelerated life test methods for the motor used in machine tools. In recent years, as well as efficiency for motors, there is a growing need for research on life expectancy of motors. It is considered impossible to calculate the acceleration coefficient by increasing the rotational load or temperature load as the acceleration stress in the motor system because the temperature of the copper exceeds the wire thermal class rating. This paper describes the equipment development procedure for the highly accelerated life test (HALT) of the 12kW three-phase squirrel-cage induction motors (SCIMs). After the test, the lifetime analysis was carried out, and it is compared with the life expectancy by finite element method (FEM) and bearing theory.

Keywords: acceleration coefficient, bearing, HALT, life expectancy, motor

Procedia PDF Downloads 262

Authors: Ehsan Mehryaar

Abstract:

The rate of penetration is (RoP) one of the vital factors in the cost and time of tunnel boring projects; therefore, predicting it can lead to a substantial increase in the efficiency of the project. RoP is heavily dependent geological properties of the project site and TBM properties. In this study, 151-point data from Queen’s water tunnel is collected, which includes unconfined compression strength, peak slope index, angle with weak planes, and distance between planes of weaknesses. Since the size of the data is small, it was observed that it is imbalanced. To solve that problem synthetic minority oversampling technique is utilized. The model based on the model tree is proposed, where each leaf consists of a support vector machine model. Proposed model performance is then compared to existing empirical equations in the literature.

Keywords: Model tree, SMOTE, rate of penetration, TBM(tunnel boring machine), SVM

Procedia PDF Downloads 165

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 28

Authors: Zhaoan Wang

Abstract:

Research in predictive maintenance modeling has improved in the recent years to predict failures and needed maintenance with high accuracy, saving cost and improving manufacturing efficiency. However, classic prediction models provide little valuable insight towards the most important features contributing to the failure. By analyzing and quantifying feature importance in predictive maintenance models, cost saving can be optimized based on business goals. First, multiple classifiers are evaluated with cross-validation to predict the multi-class of failures. Second, predictive performance with features provided by different feature selection algorithms are further analyzed. Third, features selected by different algorithms are ranked and combined based on their predictive power. Finally, linear explainer SHAP (SHapley Additive exPlanations) is applied to interpret classifier behavior and provide further insight towards the specific roles of features in both local predictions and global model behavior. The results of the experiments suggest that certain features play dominant roles in predictive models while others have significantly less impact on the overall performance. Moreover, for multi-class prediction of machine failures, the most important features vary with type of machine failures. The results may lead to improved productivity and cost saving by prioritizing sensor deployment, data collection, and data processing of more important features over less importance features.

Keywords: automated supply chain, intelligent manufacturing, predictive maintenance machine learning, feature engineering, model interpretation

Procedia PDF Downloads 115

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 120

Authors: Azita Ramezani, Ghazal Mashhadiagha, Bahareh Sanabakhsh

Abstract:

This study researches the combination of Random. Forest classifiers with large language models (LLMs) and natural language processing (NLP) to improve diagnostic accuracy in chest X-ray analysis using the Indiana University dataset. Utilizing advanced NLP techniques, the research preprocesses textual data from radiological reports to extract key features, which are then merged with image-derived data. This improved dataset is analyzed with Random Forest classifiers to predict specific clinical results, focusing on the identification of health issues and the estimation of case urgency. The findings reveal that the combination of NLP, LLMs, and machine learning not only increases diagnostic precision but also reliability, especially in quickly identifying critical conditions. Achieving an accuracy of 99.35%, the model shows significant advancements over conventional diagnostic techniques. The results emphasize the large potential of machine learning in medical imaging, suggesting that these technologies could greatly enhance clinician judgment and patient outcomes by offering quicker and more precise diagnostic approximations.

Keywords: natural language processing (NLP), large language models (LLMs), random forest classifier, chest x-ray analysis, medical imaging, diagnostic accuracy, indiana university dataset, machine learning in healthcare, predictive modeling, clinical decision support systems

Procedia PDF Downloads 20

Authors: Sehreen Moorat, Mussarat Lakho

Abstract:

A method of artificial intelligence using digital mammograms data has been proposed in this paper for detection of breast cancer. Many researchers have developed techniques for the early detection of breast cancer; the early diagnosis helps to save many lives. The detection of breast cancer through mammography is effective method which detects the cancer before it is felt and increases the survival rate. In this paper, we have purposed image processing technique for enhancing the image to detect the graphical table data and markings. Texture features based on Gray-Level Co-Occurrence Matrix and intensity based features are extracted from the selected region. For classification purpose, neural network based supervised classifier system has been used which can discriminate between benign and malignant. Hence, 68 digital mammograms have been used to train the classifier. The obtained result proved that automated detection of breast cancer is beneficial for early diagnosis and increases the survival rates of breast cancer patients. The proposed system will help radiologist in the better interpretation of breast cancer.

Keywords: medical imaging, cancer, processing, neural network

Procedia PDF Downloads 248

Authors: Houxiang Zhu, Chun Liang

Abstract:

The CRISPR-Cpf1 system has been successfully applied in genome editing. However, target efficiency of the CRISPR-Cpf1 system varies among different gRNA sequences. The published CRISPR-Cpf1 gRNA data was reanalyzed. Many sequences and structural features of gRNAs (e.g., the position-specific nucleotide composition, position-nonspecific nucleotide composition, GC content, minimum free energy, and melting temperature) correlated with target efficiency were found. Using machine learning technology, a support vector machine (SVM) model was created to predict target efficiency for any given gRNAs. The first web service application, CRISPR-DT (CRISPR DNA Targeting), has been developed to help users design optimal gRNAs for the CRISPR-Cpf1 system by considering both target efficiency and specificity. CRISPR-DT will empower researchers in genome editing.

Keywords: CRISPR-Cpf1, genome editing, target efficiency, target specificity

Procedia PDF Downloads 249