Search results for: automatic classification of tremor types

Authors: Mohammad Alawairdhi

Abstract:

Customer Relationship Management (CRM) started gaining attention as late as the 1990s, and since then efforts are ongoing to define the domain’s precise specifications. There is yet no single agreed upon definition. However, a predominant majority perceives CRM as a mechanism for enhancing interaction with customers, thereby strengthening the relationship between a business and its clients. From the perspective of Information Technology (IT) companies, CRM systems can be viewed as facilitating software products or services to automate the marketing, selling and servicing functions of an organization. In this paper, we have proposed a Bluetooth enabled CRM system for small- and medium-scale organizations. In the proposed system, Bluetooth technology works as an automatic identification token in addition to its common use as a communication channel. The system comprises a server side accompanied by a user-interface support for both client and server sides. The system has been tested in two environments and users have expressed ease of use, convenience and understandability as major advantages of the proposed solution.

Keywords: customer relationship management, CRM, bluetooth, automatic identification token

Procedia PDF Downloads 336

Authors: Benjamin Beltzung, Marie Pelé, Julien P. Renoult, Cédric Sueur

Abstract:

To this day, it is not known if drawing is specifically human behavior or if this behavior finds its origins in ancestor species. An interesting window to enlighten this question is to analyze the drawing behavior in genetically close to human species, such as non-human primate species. A good candidate for this approach is the orangutan, who shares 97% of our genes and exhibits multiple human-like behaviors. Focusing on figurative aspects may not be suitable for orangutans’ drawings, which may appear as scribbles but may have meaning. A manual feature selection would lead to an anthropocentric bias, as the features selected by humans may not match with those relevant for orangutans. In the present study, we used deep learning to analyze the drawings of a female orangutan named Molly († in 2011), who has produced 1,299 drawings in her last five years as part of a behavioral enrichment program at the Tama Zoo in Japan. We investigate multiple ways to decipher Molly’s drawings. First, we demonstrate the existence of differences between seasons by training a deep learning model to classify Molly’s drawings according to the seasons. Then, to understand and interpret these seasonal differences, we analyze how the information spreads within the network, from shallow to deep layers, where early layers encode simple local features and deep layers encode more complex and global information. More precisely, we investigate the impact of feature complexity on classification accuracy through features extraction fed to a Support Vector Machine. Last, we leverage style transfer to dissociate features associated with drawing style from those describing the representational content and analyze the relative importance of these two types of features in explaining seasonal variation. Content features were relevant for the classification, showing the presence of meaning in these non-figurative drawings and the ability of deep learning to decipher these differences. The style of the drawings was also relevant, as style features encoded enough information to have a classification better than random. The accuracy of style features was higher for deeper layers, demonstrating and highlighting the variation of style between seasons in Molly’s drawings. Through this study, we demonstrate how deep learning can help at finding meanings in non-figurative drawings and interpret these differences.

Keywords: cognition, deep learning, drawing behavior, interpretability

Procedia PDF Downloads 151

Authors: P. Bharathiraja

Abstract:

Computer Aided decision making system is used to enhance diagnosis and prognosis of diseases and also to assist clinicians and junior doctors in clinical decision making. Medical Data used for decision making should be definite and consistent. Data Mining and soft computing techniques are used for cleaning the data and for incorporating human reasoning in decision making systems. Fuzzy rule based inference technique can be used for classification in order to incorporate human reasoning in the decision making process. In this work, missing values are imputed using the mean or mode of the attribute. The data are normalized using min-ma normalization to improve the design and efficiency of the fuzzy inference system. The fuzzy inference system is used to handle the uncertainties that exist in the medical data. Equal-width-partitioning is used to partition the attribute values into appropriate fuzzy intervals. Fuzzy rules are generated using Class Based Associative rule mining algorithm. The system is trained and tested using heart disease data set from the University of California at Irvine (UCI) Machine Learning Repository. The data was split using a hold out approach into training and testing data. From the experimental results it can be inferred that classification using fuzzy inference system performs better than trivial IF-THEN rule based classification approaches. Furthermore it is observed that the use of fuzzy logic and fuzzy inference mechanism handles uncertainty and also resembles human decision making. The system can be used in the absence of a clinical expert to assist junior doctors and clinicians in clinical decision making.

Keywords: decision making, data mining, normalization, fuzzy rule, classification

Procedia PDF Downloads 507

Authors: Maryam Hoorzad, Narges Shokry, Mandan Momeni

Abstract:

According to importance of socialization in effectiveness of organizations and on the other hand assessing the impact of individual differences on socialization tactics by measuring employees satisfaction, can be assessed for each of the personality types which socialization tactics is the more effective. The aim of this paper is to investigate how organizational socialization tactics affect job satisfaction of employees according to personality types. A survey was conducted using a measurement tool based on Van Maanen and Schein’s theory on organizational socialization tactics and Myers Briggs’ measurement tools of personality types. The respondents were employees with more than 3 years backward in Tehran University of Medical Science. Data collection was performed using both library and field, the data collection instrument was questionnaires and data were analysed using the Spss and Lisrel programs. It was found that investiture and serial tactics has a significant effect on employees satisfaction, any increase in investiture and serial tactics led to increase in job satisfaction and any increase in divestiture and disjunctive tactics led to reduction of job satisfaction. Investiture tactic has the most effect on employees satisfaction. Also based on the results, personality types affect the relationship between socialization tactics and job satisfaction. In the ESFJ personality type the effect of investiture tactic on employee satisfaction is the most.

Keywords: organizational socialization, organizational socialization tactics, personality types, job satisfaction

Procedia PDF Downloads 432

Authors: Haonan Hu, Shuge Lei, Dasheng Sun, Huabin Zhang, Kehong Yuan, Jian Dai, Jijun Tang

Abstract:

This paper focuses on the classification task of breast ultrasound images and conducts research on the reliability measurement of classification results. A dual-channel evaluation framework was developed based on the proposed inference reliability and predictive reliability scores. For the inference reliability evaluation, human-aligned and doctor-agreed inference rationals based on the improved feature attribution algorithm SP-RISA are gracefully applied. Uncertainty quantification is used to evaluate the predictive reliability via the test time enhancement. The effectiveness of this reliability evaluation framework has been verified on the breast ultrasound clinical dataset YBUS, and its robustness is verified on the public dataset BUSI. The expected calibration errors on both datasets are significantly lower than traditional evaluation methods, which proves the effectiveness of the proposed reliability measurement.

Keywords: medical imaging, ultrasound imaging, XAI, uncertainty measurement, trustworthy AI

Procedia PDF Downloads 81

Authors: Jaiden Xuan Schraut, Leon Liu, Yiqiao Yin

Abstract:

Computer vision in medical diagnosis has achieved a high level of success in diagnosing diseases with high accuracy. However, conventional classifiers that produce an image to-label result provides insufficient information for medical professionals to judge and raise concerns over the trust and reliability of a model with results that cannot be explained. In order to gain local insight into cancerous regions, separate tasks such as imaging segmentation need to be implemented to aid the doctors in treating patients, which doubles the training time and costs which renders the diagnosis system inefficient and difficult to be accepted by the public. To tackle this issue and drive AI-first medical solutions further, this paper proposes a multi-output network that follows a U-Net architecture for image segmentation output and features an additional convolutional neural networks (CNN) module for auxiliary classification output. Class activation maps are a method of providing insight into a convolutional neural network’s feature maps that leads to its classification but in the case of lung diseases, the region of interest is enhanced by U-net-assisted Class Activation Map (CAM) visualization. Therefore, our proposed model combines image segmentation models and classifiers to crop out only the lung region of a chest X-ray’s class activation map to provide a visualization that improves the explainability and is able to generate classification results simultaneously which builds trust for AI-led diagnosis systems. The proposed U-Net model achieves 97.61% accuracy and a dice coefficient of 0.97 on testing data from the COVID-QU-Ex Dataset which includes both diseased and healthy lungs.

Keywords: multi-output network model, U-net, class activation map, image classification, medical imaging analysis

Procedia PDF Downloads 186

Authors: Huma Balouch

Abstract:

Menochilus sexmaculatus commonly known as six spotted zig zag ladybird, is an aphidophagus and the most misidentified Coccinellids due to the occurrence of numerous color variants. The correct identification of Menochilus sexmaculatus and its strains is necessary to implement the use of biological control. In the present study phenotypic and genotypic polymorphism was investigated in Menochilus sexmaculatus collected from Punjab, NWFP and Sindh provinces of Pakistan. Six different morphs of the species were distinguished by analyzing its Elytral color and spot pattern and then Polymerase Chain Reaction was used to generate random amplification of polymorphic DNA (RAPD) from six different types of Menochilus sexmaculatus. Forty primers (OPA & OPC Kit) were used to perform RAPD PCR on six different types of Menochilus sexmaculatus of which, seven primers revealed different patterns related to the Menochilus sexmaculatus types. These seven primers (OPA-04, OPA-09, OPA-18, OPC-04, OPC-12, OPC-15 and OPC-18) produced 111 clear polymorphic bands and 6 scorable strain specific markers. The cluster analysis applied to RAPD data showed high polymorphism among six types and it can be concluded that these six types are six polymorphic strains of the same species.

Keywords: Menochilus sexmaculatus, aphidophagus, coccinellids, phenotypic and genotypic polymorphism, RAPD-PCR, strain specific markers

Procedia PDF Downloads 482

Authors: Mrinal Kanti Bhowmik, Kakali Das Jr., Barin Kumar De, Debotosh Bhattacharjee

Abstract:

Breast cancer is the most common cancer and a leading cause of death for women in the 35 to 55 age group. Early detection of breast cancer can decrease the mortality rate of breast cancer. Mammography is considered as a ‘Gold Standard’ for breast cancer detection and a very popular modality, presently used for breast cancer screening and detection. The screening of digital mammograms often leads to over diagnosis and a consequence to unnecessary traumatic & painful biopsies. For that reason recent studies involving the use of thermal imaging as a screening technique have generated a growing interest especially in cases where the mammography is limited, as in young patients who have dense breast tissue. Tumor is a significant sign of breast cancer in both mammography and thermography. The tumors are complex in structure and they also exhibit a different statistical and textural features compared to the breast background tissue. Fractal geometry is a geometry which is used to describe this type of complex structure as per their main characteristic, where traditional Euclidean geometry fails. Over the last few years, fractal geometrics have been applied mostly in many medical image (1D, 2D, or 3D) analysis applications. In breast cancer detection using digital mammogram images, also it plays a significant role. Fractal is also used in thermography for early detection of the masses using the thermal texture. This paper presents an overview of the recent aspects and initiatives of fractals in breast cancer detection in both mammography and thermography. The scope of fractal geometry in automatic breast cancer detection using digital mammogram and thermogram images are analysed, which forms a foundation for further study on application of fractal geometry in medical imaging for improving the efficiency of automatic detection.

Keywords: fractal, tumor, thermography, mammography

Procedia PDF Downloads 376

Authors: Mpho Mokoatle, Darlington Mapiye, James Mashiyane, Stephanie Muller, Gciniwe Dlamini

Abstract:

Great advances in high-throughput sequencing technologies have resulted in availability of huge amounts of sequencing data in public and private repositories, enabling a holistic understanding of complex biological phenomena. Sequence data are used for a wide range of applications such as gene annotations, expression studies, personalized treatment and precision medicine. However, this rapid growth in sequence data poses a great challenge which calls for novel data processing and analytic methods, as well as huge computing resources. In this work, a machine and statistical learning approach for DNA sequence classification based on $k$-mer representation of sequence data is proposed. The approach is tested using whole genome sequences of Mycobacterium tuberculosis (MTB) isolates to (i) reduce the size of genomic sequence data, (ii) identify an optimum size of k-mers and utilize it to build classification models, (iii) predict the phenotype from whole genome sequence data of a given bacterial isolate, and (iv) demonstrate computing challenges associated with the analysis of whole genome sequence data in producing interpretable and explainable insights. The classification models were trained on 104 whole genome sequences of MTB isoloates. Cluster analysis showed that k-mers maybe used to discriminate phenotypes and the discrimination becomes more concise as the size of k-mers increase. The best performing classification model had a k-mer size of 10 (longest k-mer) an accuracy, recall, precision, specificity, and Matthews Correlation coeffient of 72.0%, 80.5%, 80.5%, 63.6%, and 0.4 respectively. This study provides a comprehensive approach for resampling whole genome sequencing data, objectively selecting a k-mer size, and performing classification for phenotype prediction. The analysis also highlights the importance of increasing the k-mer size to produce more biological explainable results, which brings to the fore the interplay that exists amongst accuracy, computing resources and explainability of classification results. However, the analysis provides a new way to elucidate genetic information from genomic data, and identify phenotype relationships which are important especially in explaining complex biological mechanisms.

Keywords: AWD-LSTM, bootstrapping, k-mers, next generation sequencing

Procedia PDF Downloads 158

Authors: Darlington Mapiye, Mpho Mokoatle, James Mashiyane, Stephanie Muller, Gciniwe Dlamini

Abstract:

Great advances in high-throughput sequencing technologies have resulted in availability of huge amounts of sequencing data in public and private repositories, enabling a holistic understanding of complex biological phenomena. Sequence data are used for a wide range of applications such as gene annotations, expression studies, personalized treatment and precision medicine. However, this rapid growth in sequence data poses a great challenge which calls for novel data processing and analytic methods, as well as huge computing resources. In this work, a machine and statistical learning approach for DNA sequence classification based on k-mer representation of sequence data is proposed. The approach is tested using whole genome sequences of Mycobacterium tuberculosis (MTB) isolates to (i) reduce the size of genomic sequence data, (ii) identify an optimum size of k-mers and utilize it to build classification models, (iii) predict the phenotype from whole genome sequence data of a given bacterial isolate, and (iv) demonstrate computing challenges associated with the analysis of whole genome sequence data in producing interpretable and explainable insights. The classification models were trained on 104 whole genome sequences of MTB isoloates. Cluster analysis showed that k-mers maybe used to discriminate phenotypes and the discrimination becomes more concise as the size of k-mers increase. The best performing classification model had a k-mer size of 10 (longest k-mer) an accuracy, recall, precision, specificity, and Matthews Correlation coeffient of 72.0 %, 80.5 %, 80.5 %, 63.6 %, and 0.4 respectively. This study provides a comprehensive approach for resampling whole genome sequencing data, objectively selecting a k-mer size, and performing classification for phenotype prediction. The analysis also highlights the importance of increasing the k-mer size to produce more biological explainable results, which brings to the fore the interplay that exists amongst accuracy, computing resources and explainability of classification results. However, the analysis provides a new way to elucidate genetic information from genomic data, and identify phenotype relationships which are important especially in explaining complex biological mechanisms

Keywords: AWD-LSTM, bootstrapping, k-mers, next generation sequencing

Procedia PDF Downloads 145

Authors: Chi-Wai Kan, Kam-Hong Chau, Ho-Shing Law

Abstract:

Wicking property is important for textile finishing and wears comfort. Good wicking properties can ensure uniformity and efficiency of the textiles treatment. In view of wear comfort, quick wicking fabrics facilitate the evaporation of sweat. Therefore, the wetness sensation of the skin is minimised to prevent discomfort. The testing method for vertical wicking was standardised by the American Association of Textile Chemists and Colorists (AATCC) in 2011. The traditional vertical wicking test involves human error to observe fast changing and/or unclear wicking height. This study introduces optoelectronic devices to achieve an automatic Vertical Wicking Tester (VWT) and reduce human error. The VWT can record the wicking time and wicking height of samples. By reducing the difficulties of manual judgment, the reliability of the vertical wicking experiment is highly increased. Furthermore, labour is greatly decreased by using the VWT. The automatic measurement of the VWT has optoelectronic devices to trace the liquid wicking with a simple operation procedure. The optoelectronic devices detect the colour difference between dry and wet samples. This allows high sensitivity to a difference in irradiance down to 10 μW/cm². Therefore, the VWT is capable of testing dark fabric. The VWT gives a wicking distance (wicking height) of 1 mm resolution and a wicking time of one-second resolution. Acknowledgment: This is a research project of HKRITA funded by Innovation and Technology Fund (ITF) with title “Development of an Automatic Measuring System for Vertical Wicking” (ITP/055/20TP). Author would like to thank the financial support by ITF. Any opinions, findings, conclusions or recommendations expressed in this material/event (or by members of the project team) do not reflect the views of the Government of the Hong Kong Special Administrative Region, the Innovation and Technology Commission or the Panel of Assessors for the Innovation and Technology Support Programme of the Innovation and Technology Fund and the Hong Kong Research Institute of Textiles and Apparel. Also, we would like to thank the support and sponsorship from Lai Tak Enterprises Limited, Kingis Development Limited and Wing Yue Textile Company Limited.

Keywords: AATCC method, comfort, textile measurement, wetness sensation

Procedia PDF Downloads 90

Authors: Didier Auroux, Vladimir Groza

Abstract:

This work is part of STEEP Marie-Curie ITN project, and it focuses on the identification of unknown parameters of the proposed generic Abrasive WaterJet Milling (AWJM) PDE model, that appears as an ill-posed inverse problem. The necessity of studying this problem comes from the industrial milling applications where the possibility to predict and model the final surface with high accuracy is one of the primary tasks in the absence of any knowledge of the model parameters that should be used. In this framework, we propose the identification of model parameters by minimizing a cost function, measuring the difference between experimental and numerical solutions. The adjoint approach based on corresponding Lagrangian gives the opportunity to find out the unknowns of the AWJM model and their optimal values that could be used to reproduce the required trench profile. Due to the complexity of the nonlinear problem and a large number of model parameters, we use an automatic differentiation software tool (TAPENADE) for the adjoint computations. By adding noise to the artificial data, we show that in fact the parameter identification problem is highly unstable and strictly depends on input measurements. Regularization terms could be effectively used to deal with the presence of data noise and to improve the identification correctness. Based on this approach we present results in 2D and 3D of the identification of the model parameters and of the surface prediction both with self-generated data and measurements obtained from the real production. Considering different types of model and measurement errors allows us to obtain acceptable results for manufacturing and to expect the proper identification of unknowns. This approach also gives us the ability to distribute the research on more complex cases and consider different types of model and measurement errors as well as 3D time-dependent model with variations of the jet feed speed.

Keywords: Abrasive Waterjet Milling, inverse problem, model parameters identification, regularization

Procedia PDF Downloads 308

Authors: Pavel Chmelar, Martin Dobrovolny

Abstract:

Laser projection or laser footprint detection is today widely used in many fields of robotics, measurement, or electronics. The system accuracy strictly depends on precise laser footprint detection on target objects. This article deals with the laser line detection based on the RGB segmentation and the component labeling. As a measurement device was used the developed optical rangefinder. The optical rangefinder is equipped with vertical sweeping of the laser beam and high quality camera. This system was developed mainly for automatic exploration and mapping of unknown spaces. In the first section is presented a new detection algorithm. In the second section are presented measurements results. The measurements were performed in variable light conditions in interiors. The last part of the article present achieved results and their differences between day and night measurements.

Keywords: color segmentation, component labelling, laser line detection, automatic mapping, distance measurement, vector map

Procedia PDF Downloads 421

Authors: Jonathan Sohn

Abstract:

Deep neural networks (DNNs) have shown state-of-the-art performance for many applications, including computer vision, natural language processing, and speech recognition. Recently, adversarial attacks have been studied in the context of deep neural networks, which aim to alter the results of deep neural networks by modifying the inputs slightly. For example, an adversarial attack on a DNN used for object detection can cause the DNN to miss certain objects. As a result, the reliability of DNNs is undermined by their lack of robustness against adversarial attacks, raising concerns about their use in safety-critical applications such as autonomous driving. In this paper, we focus on studying the adversarial attacks and defenses on DNNs for image classification. There are two types of adversarial attacks studied which are fast gradient sign method (FGSM) attack and projected gradient descent (PGD) attack. A DNN forms decision boundaries that separate the input images into different categories. The adversarial attack slightly alters the image to move over the decision boundary, causing the DNN to misclassify the image. FGSM attack obtains the gradient with respect to the image and updates the image once based on the gradients to cross the decision boundary. PGD attack, instead of taking one big step, repeatedly modifies the input image with multiple small steps. There is also another type of attack called the target attack. This adversarial attack is designed to make the machine classify an image to a class chosen by the attacker. We can defend against adversarial attacks by incorporating adversarial examples in training. Specifically, instead of training the neural network with clean examples, we can explicitly let the neural network learn from the adversarial examples. In our experiments, the digit recognition accuracy on the MNIST dataset drops from 97.81% to 39.50% and 34.01% when the DNN is attacked by FGSM and PGD attacks, respectively. If we utilize FGSM training as a defense method, the classification accuracy greatly improves from 39.50% to 92.31% for FGSM attacks and from 34.01% to 75.63% for PGD attacks. To further improve the classification accuracy under adversarial attacks, we can also use a stronger PGD training method. PGD training improves the accuracy by 2.7% under FGSM attacks and 18.4% under PGD attacks over FGSM training. It is worth mentioning that both FGSM and PGD training do not affect the accuracy of clean images. In summary, we find that PGD attacks can greatly degrade the performance of DNNs, and PGD training is a very effective way to defend against such attacks. PGD attacks and defence are overall significantly more effective than FGSM methods.

Keywords: deep neural network, adversarial attack, adversarial defense, adversarial machine learning

Procedia PDF Downloads 186

Authors: Sergey A. Burikov, Tatiana A. Dolenko, Kirill A. Gushchin, Sergey A. Dolenko

Abstract:

The paper presents the results of clusterization by Kohonen self-organizing maps (SOM) applied for analysis of array of Raman spectra of multi-component solutions of inorganic salts, for determination of types of salts present in the solution. It is demonstrated that use of SOM is a promising method for solution of clusterization and classification problems in spectroscopy of multi-component objects, as attributing a pattern to some cluster may be used for recognition of component composition of the object.

Keywords: Kohonen self-organizing maps, clusterization, multi-component solutions, Raman spectroscopy

Procedia PDF Downloads 434

Authors: Brahim-Fares Zaidi, Malika Boudraa, Sid-Ahmed Selouani

Abstract:

Our work aims to improve our Automatic Recognition System for Dysarthria Speech (ARSDS) based on the Hidden Models of Markov (HMM) and the Hidden Markov Model Toolkit (HTK) to help people who are sick. With pronunciation problems, we applied two techniques of speech parameterization based on Mel Frequency Cepstral Coefficients (MFCC's) and Perceptual Linear Prediction (PLP's) and concatenated them with JITTER and SHIMMER coefficients in order to increase the recognition rate of a dysarthria speech. For our tests, we used the NEMOURS database that represents speakers with dysarthria and normal speakers.

Keywords: hidden Markov model toolkit (HTK), hidden models of Markov (HMM), Mel-frequency cepstral coefficients (MFCC), perceptual linear prediction (PLP’s)

Procedia PDF Downloads 150

Authors: Rashi Bhalla, Russel Pears, M. Asif Naeem

Abstract:

In this 'Information Explosion Era' analyzing data 'a critical commodity' and mining knowledge from vertically distributed data stream incurs huge communication cost. However, an effort to decrease the communication in the distributed environment has an adverse influence on the classification accuracy; therefore, a research challenge lies in maintaining a balance between transmission cost and accuracy. This paper proposes a method based on Bayesian inference to reduce the communication volume in a heterogeneous distributed environment while retaining prediction accuracy. Our experimental evaluation reveals that a significant reduction in communication can be achieved across a diverse range of dataset types.

Keywords: big data, bayesian inference, distributed data stream mining, heterogeneous-distributed data

Procedia PDF Downloads 149

Authors: Zoran Šverko, Saša Vlahinić, Nino Stojković, Ivan Markovinović

Abstract:

In this article, the classification of target letters is performed using data from the EEG P300 Speller paradigm. Neural networks trained with the results of dynamic connectivity analysis between different brain regions are used for classification. Dynamic connectivity analysis is based on the adaptive window size and the imaginary part of the complex Pearson correlation coefficient. Brain dynamics are analysed using the relative intersection of confidence intervals for the imaginary component of the complex Pearson correlation coefficient method (RICI-imCPCC). The RICI-imCPCC method overcomes the shortcomings of currently used dynamical connectivity analysis methods, such as the low reliability and low temporal precision for short connectivity intervals encountered in constant sliding window analysis with wide window size and the high susceptibility to noise encountered in constant sliding window analysis with narrow window size. This method overcomes these shortcomings by dynamically adjusting the window size using the RICI rule. This method extracts information about brain connections for each time sample. Seventy percent of the extracted brain connectivity information is used for training and thirty percent for validation. Classification of the target word is also done and based on the same analysis method. As far as we know, through this research, we have shown for the first time that dynamic connectivity can be used as a parameter for classifying EEG signals.

Keywords: dynamic connectivity analysis, EEG, neural networks, Pearson correlation coefficients

Procedia PDF Downloads 201

Authors: Jae Ni Jang, Young Uk Kim

Abstract:

Background: Chat Generative Pre-training Transformer-3 (ChatGPT; San Francisco, California, Open Artificial Intelligence) is an artificial intelligence chatbot based on a large language model designed to generate human-like text. As the usage of ChatGPT is increasing among less knowledgeable patients, medical students, and anesthesia and pain medicine residents or trainees, we aimed to evaluate the accuracy of ChatGPT-3 responses to questions about the American Society of Anesthesiologists (ASA) classification based on patients’ underlying diseases and assess the quality of the generated responses. Methods: A total of 47 questions were submitted to ChatGPT using textual prompts. The questions were designed for ChatGPT-3 to provide answers regarding ASA classification in response to common underlying diseases frequently observed in adult patients. In addition, we created 18 questions regarding the ASA classification for pediatric patients and pregnant women. The accuracy of ChatGPT’s responses was evaluated by cross-referencing with Miller’s Anesthesia, Morgan & Mikhail’s Clinical Anesthesiology, and the American Society of Anesthesiologists’ ASA Physical Status Classification System (2020). Results: Out of the 47 questions pertaining to adults, ChatGPT -3 provided correct answers for only 23, resulting in an accuracy rate of 48.9%. Furthermore, the responses provided by ChatGPT-3 regarding children and pregnant women were mostly inaccurate, as indicated by a 28% accuracy rate (5 out of 18). Conclusions: ChatGPT provided correct responses to questions relevant to the daily clinical routine of anesthesiologists in approximately half of the cases, while the remaining responses contained errors. Therefore, caution is advised when using ChatGPT to retrieve anesthesia-related information. Although ChatGPT may not yet be suitable for clinical settings, we anticipate significant improvements in ChatGPT and other large language models in the near future. Regular assessments of ChatGPT's ASA classification accuracy are essential due to the evolving nature of ChatGPT as an artificial intelligence entity. This is especially important because ChatGPT has a clinically unacceptable rate of error and hallucination, particularly in pediatric patients and pregnant women. The methodology established in this study may be used to continue evaluating ChatGPT.

Keywords: American Society of Anesthesiologists, artificial intelligence, Chat Generative Pre-training Transformer-3, ChatGPT

Procedia PDF Downloads 34

Authors: Min Kyu Kim, Eun Young Lee, Dong Woo Son, Yoon Seok Chang

Abstract:

In this paper, we introduce a flexible box erecting machine (BEM) that swiftly and automatically transforms cardboard into a three dimensional box. Recently, the parcel service and home-shopping industries have grown rapidly, and there is an increasing need for various box types to ship various products. However, workers cannot fold thousands of boxes manually in a day. As such, automatic BEMs are garnering greater attention. This study takes equipment operation into consideration as well as mechanical improvements in order to design a BEM that is able to outperform its conventional counterparts. We analyzed six dispatching rules – First In First Out (FIFO), Shortest Processing Time (SPT), Earliest Due Date (EDD), Setup Avoidance, EDD + SPT, and EDD + Setup Avoidance – to determine which one was most suitable for BEM operation. Consequently, SPT and Setup Avoidance were found to be the most critical rules, followed by EDD + Setup Avoidance, EDD + SPT, EDD, and FIFO. This hierarchy was valid for both our conventional BEM and our new flexible BEM from the viewpoint of processing time. We believe that this research can contribute to flexible BEM management, which has the potential to increase productivity and convenience.

Keywords: automation, box erecting machine, dispatching rule, setup time

Procedia PDF Downloads 354

Authors: A. Casale, J. Alessi, C. N. Bianchi, G. Bozzini, M. Brunoldi, V. Cappanera, P. Corvisiero, G. Fanciulli, D. Grosso, N. Magnoli, A. Mandich, C. Melchiorre, C. Morri, P. Povero, N. Stasi, M. Taiuti, G. Viano, M. Wurtz

Abstract:

This work describes a real-time algorithm for detecting, tracking and classifying single motorboats, developed using the acoustic data recorded by a hydrophone array within the framework of EU LIFE + project ARION (LIFE09NAT/IT/000190). The project aims to improve the conservation status of bottlenose dolphins through a real-time simultaneous monitoring of their population and surface ship traffic. A Passive Acoustic Monitoring (PAM) system is installed on two autonomous permanent marine buoys, located close to the boundaries of the Marine Protected Area (MPA) of Portofino (Ligurian Sea- Italy). Detecting surface ships is also a necessity in many other sensible areas, such as wind farms, oil platforms, and harbours. A PAM system could be an effective alternative to the usual monitoring systems, as radar or active sonar, for localizing unauthorized ship presence or illegal activities, with the advantage of not revealing its presence. Each ARION buoy consists of a particular type of structure, named meda elastica (elastic beacon) composed of a main pole, about 30-meter length, emerging for 7 meters, anchored to a mooring of 30 tons at 90 m depth by an anti-twist steel wire. Each buoy is equipped with a floating element and a hydrophone tetrahedron array, whose raw data are send via a Wi-Fi bridge to a ground station where real-time analysis is performed. Bottlenose dolphin detection algorithm and ship monitoring algorithm are operating in parallel and in real time. Three modules were developed and commissioned for ship monitoring. The first is the detection algorithm, based on Time Difference Of Arrival (TDOA) measurements, i.e., the evaluation of angular direction of the target respect to each buoy and the triangulation for obtaining the target position. The second is the tracking algorithm, based on a Kalman filter, i.e., the estimate of the real course and speed of the target through a predictor filter. At last, the classification algorithm is based on the DEMON method, i.e., the extraction of the acoustic signature of single vessels. The following results were obtained; the detection algorithm succeeded in evaluating the bearing angle with respect to each buoy and the position of the target, with an uncertainty of 2 degrees and a maximum range of 2.5 km. The tracking algorithm succeeded in reconstructing the real vessel courses and estimating the speed with an accuracy of 20% respect to the Automatic Identification System (AIS) signals. The classification algorithm succeeded in isolating the acoustic signature of single vessels, demonstrating its temporal stability and the consistency of both buoys results. As reference, the results were compared with the Hilbert transform of single channel signals. The algorithm for tracking multiple targets is ready to be developed, thanks to the modularity of the single ship algorithm: the classification module will enumerate and identify all targets present in the study area; for each of them, the detection module and the tracking module will be applied to monitor their course.

Keywords: acoustic-noise, bottlenose-dolphin, hydrophone, motorboat

Procedia PDF Downloads 162

Authors: Magdalena Igras, Joanna Grzybowska, Mariusz Ziółko

Abstract:

The study of emotions expressed in emergency phone call is presented, covering both statistical analysis of emotions configurations and an attempt to automatically classify emotions. An emergency call is a situation usually accompanied by intense, authentic emotions. They influence (and may inhibit) the communication between caller and responder. In order to support responders in their responsible and psychically exhaustive work, we studied when and in which combinations emotions appeared in calls. A corpus of 45 hours of conversations (about 3300 calls) from emergency call center was collected. Each recording was manually tagged with labels of emotions valence (positive, negative or neutral), type (sadness, tiredness, anxiety, surprise, stress, anger, fury, calm, relief, compassion, satisfaction, amusement, joy) and arousal (weak, typical, varying, high) on the basis of perceptual judgment of two annotators. As we concluded, basic emotions tend to appear in specific configurations depending on the overall situational context and attitude of speaker. After performing statistical analysis we distinguished four main types of emotional behavior of callers: worry/helplessness (sadness, tiredness, compassion), alarm (anxiety, intense stress), mistake or neutral request for information (calm, surprise, sometimes with amusement) and pretension/insisting (anger, fury). The frequency of profiles was respectively: 51%, 21%, 18% and 8% of recordings. A model of presenting the complex emotional profiles on the two-dimensional (tension-insecurity) plane was introduced. In the stage of acoustic analysis, a set of prosodic parameters, as well as Mel-Frequency Cepstral Coefficients (MFCC) were used. Using these parameters, complex emotional states were modeled with machine learning techniques including Gaussian mixture models, decision trees and discriminant analysis. Results of classification with several methods will be presented and compared with the state of the art results obtained for classification of basic emotions. Future work will include optimization of the algorithm to perform in real time in order to track changes of emotions during a conversation.

Keywords: acoustic analysis, complex emotions, emotion recognition, machine learning

Procedia PDF Downloads 388

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

Abstract:

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

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

Procedia PDF Downloads 316

Authors: Alsaidi M. Altaher, Mohd Tahir Ismail

Abstract:

Wavelet thresholding has been a power tool in curve estimation and data analysis. In the presence of outliers this non parametric estimator can not suppress the outliers involved. This study proposes a new two-stage combined method based on the use of the median filter as primary step before applying wavelet thresholding. After suppressing the outliers in a signal through the median filter, the classical wavelet thresholding is then applied for removing the remaining noise. We use automatic boundary corrections; using a low order polynomial model or local polynomial model as a more realistic rule to correct the bias at the boundary region; instead of using the classical assumptions such periodic or symmetric. A simulation experiment has been conducted to evaluate the numerical performance of the proposed method. Results show strong evidences that the proposed method is extremely effective in terms of correcting the boundary bias and eliminating outlier’s sensitivity.

Keywords: boundary correction, median filter, simulation, wavelet thresholding

Procedia PDF Downloads 422

Authors: Sheikha Ali Salim Al-Breiki

Abstract:

The purpose of this study was to explore the types of the spelling errors students of grade ten make and to find out whether there were any significant differences between males and females with respect to the types of the spelling errors made. The sample of the study included 90 grade ten students from four different schools in North Batinah. The researcher manipulated the use of a test that consisted of two questions: an oral dictation test of 70 words with a contextualizing sentence and a free writing task. The misspellings were classified into nine different types. The findings revealed that the most common spelling errors among Omani grade ten students were vowel substitution, then came vowel omission in the second place and consonant substitution in the third place. Male students omitted more vowels than female students while females made more true word errors than their male counterparts. In light of the findings, the study presents some recommendations and suggestions for further studies.

Keywords: types of spelling errors, errors, ESL/EFL, error analysis

Procedia PDF Downloads 367

Authors: B. Sabayan, A. Alidadi, S. Ebrahimi, N. M. Bakhshani

Abstract:

Neuropsychological problems are more common in hemodialysis (HD) patients than in healthy individuals. The aim of this study was to investigate the effect of long term HD on memory types of HD patients. To assess the different type of memory, we used memory parts of the Persian Papers and Pencil Cognitive assessment package (PCAP) and Addenbrooke's Cognitive Examination (ACE-R). Our study included 80 HD patients of whom 39 had less than six months of HD and 41 patients and another group which had a history of HD more than six months. The population had a mean age of 51.60 years old and 27.5% of them were female. The scores of patients who have been hemodialyzed for a long time (median time of HD was up to 4 years) had lower score in anterograde, explicit, visual, recall and recognition memory (5.44±1.07, 9.49±3.472, 22.805±6.6913, 5.59±10.435, 11.02±3.190 score) than the HD patients who underwent HD for a shorter term, where the median time was 3 to 5 months (P<0.01). The regression result shows that, by increasing the HD duration, all memory types are reduced (R2=0.600, P<0.01). The present study demonstrated that HD patients who were under HD for a long time had significantly lower scores in the different types of memory. However, additional researches are needed in this area.

Keywords: hemodialysis patients, duration of hemodialysis, memory types, Zahedan

Procedia PDF Downloads 166

Authors: Dimitrie Marinceu, Alan Murchison

Abstract:

The Canadian Used Fuel Container (UFC) is a mid-size hemispherical headed copper coated steel container measuring 2.5 meters in length and 0.5 meters in diameter containing 48 used fuel bundles. The contained used fuel produces significant gamma radiation requiring automated assembly processes to complete the assembly. The design throughput of 2,500 UFCs per year places constraints on equipment and hot cell design for repeatability, speed of processing, robustness and recovery from upset conditions. After UFC assembly, the UFC is inserted into a Buffer Box (BB). The BB is made from adequately pre-shaped blocks (lower and upper block) and Highly Compacted Bentonite (HCB) material. The blocks are practically ‘sandwiching’ the UFC between them after assembly. This paper identifies one possible approach for the BB automatic assembly cell and processes. Automation of the BB assembly will have a significant positive impact on nuclear safety, quality, productivity, and reliability.

Keywords: used fuel packing plant, automatic assembly cell, used fuel container, buffer box, deep geological repository

Procedia PDF Downloads 265

Authors: Aileen F. Wang

Abstract:

Mammography has been one of the most reliable methods for early detection and diagnosis of breast cancer. However, mammography misses about 17% and up to 30% of breast cancers due to the subtle and unstable appearances of breast cancer in their early stages. Recent computer-aided diagnosis (CADx) technology using Zernike moments has improved detection accuracy. However, it has several drawbacks: it uses manual segmentation, Zernike moments are not robust, and it still has a relatively high false negative rate (FNR)–17.6%. This project will focus on the development of a novel breast cancer detection algorithm to automatically segment the breast mass and further reduce FNR. The algorithm consists of automatic segmentation of a single breast mass using Point Region Growing Segmentation, reconstruction of the segmented breast mass using Pseudo-Zernike moments, and classification of the breast mass using the root mean square (RMS). A comparative study among the various algorithms on the segmentation and reconstruction of breast masses was performed on randomly selected mammographic images. The results demonstrated that the newly developed algorithm is the best in terms of accuracy and cost effectiveness. More importantly, the new classifier RMS has the lowest FNR–6%.

Keywords: computer aided diagnosis, mammography, point region growing segmentation, pseudo-zernike moments, root mean square

Procedia PDF Downloads 443

Authors: Bernhard Bauer, Thomas Meixner, Amir Dini, Detlef Heck

Abstract:

The inner city building stock is characterized by different types of buildings of different decades and centuries and different types of historical constructions. Depending on the natural growth of a city, those types are often located in downtown areas and the surrounding suburbs. Since the population is becoming older and the variation of the different social requirements spread with the so-called 'Silver Society', city quarters have to be seen alternatively. If an area is very attractive for young students to live there because of the busy nightlife, it might not be suitable for the older society. To identify 'Location Types A, B, C' for different user groups, qualitative interviews with 24 citizens of the city of Graz (Austria) have been carried out, in order to identify the most important values for making a location or city quarter 'A', 'B', or 'C'. Furthermore these acknowledgements have been put into a softwaretool for predicting locations that are the most suitable for certain user groups. On the other hands side, investors or owners of buildings can use the tool for determining the most suitable user group for the location of their building or construction project in order to adapt the project or building stock to the requirements of the users.

Keywords: building stock, location parameters, inner city population, built environment

Procedia PDF Downloads 307

Authors: Wataru Nakamura, Tomoaki Hashimoto, Liang-Kuang Chen

Abstract:

This paper provides a state estimation method for automatic control systems of nonlinear vehicle dynamics. A nonlinear tire model is employed to represent the realistic behavior of a vehicle. In general, all the state variables of control systems are not precisedly known, because those variables are observed through output sensors and limited parts of them might be only measurable. Hence, automatic control systems must incorporate some type of state estimation. It is needed to establish a state estimation method for nonlinear vehicle dynamics with restricted measurable state variables. For this purpose, unscented Kalman filter method is applied in this study for estimating the state variables of nonlinear vehicle dynamics. The objective of this paper is to propose a state estimation method using unscented Kalman filter for nonlinear vehicle dynamics. The effectiveness of the proposed method is verified by numerical simulations.

Keywords: state estimation, control systems, observer systems, nonlinear systems

Procedia PDF Downloads 127