Search results for: neural signal recording

Authors: G. Vinitha, A. Ramalingam

Abstract:

In view of a possible application in optical data storage devices, diffraction grating efficiency of an organic dye, Acid Fuchsin doped in PMMA matrix was studied under excitation with CW diode pumped Nd: YAG laser at 532 nm. The open aperture Z-scan of dye doped polymer displayed saturable absorption and the closed aperture Z-scan of the samples exhibited negative nonlinearity. The diffraction efficiency of the grating is the ratio of the intensity of the first order diffracted power to the incident read beam power. The dye doped polymer films were found to be good media for recording. It is observed that the formation of gratings strongly depend on the concentration of dye in the polymer film, the intensity ratios of the writing beams and the angle between the writing beams. It has been found that efficient writing can be made at an angle of 20° and when the intensity ratio of the writing beams is unity.

Keywords: diffraction efficiency, nonlinear optical material, saturable absorption, surface-relief-gratings

Procedia PDF Downloads 289

Authors: Gabriel Sitler, Yousef Sardahi, Asad Salem

Abstract:

This paper presents an optimal and robust sliding mode controller (SMC) to regulate the position of the knee joint angle for patients suffering from knee injuries. The controller imitates the role of active orthoses that produce the joint torques required to overcome gravity and loading forces and regain natural human movements. To this end, a mathematical model of the shank, the lower part of the leg, is derived first and then used for the control system design and computer simulations. The design of the controller is carried out in optimal and multi-objective settings. Four objectives are considered: minimization of the control effort and tracking error; and maximization of the control signal smoothness and closed-loop system’s speed of response. Optimal solutions in terms of the Pareto set and its image, the Pareto front, are obtained. The results show that there are trade-offs among the design objectives and many optimal solutions from which the decision-maker can choose to implement. Also, computer simulations conducted at different points from the Pareto set and assuming knee squat movement demonstrate competing relationships among the design goals. In addition, the proposed control algorithm shows robustness in tracking a standard gait signal when accounting for uncertainty in the shank’s parameters.

Keywords: optimal control, multi-objective optimization, sliding mode control, wearable knee exoskeletons

Procedia PDF Downloads 69

Authors: M. Ahmadi, M. Kafil, H. Ebrahimi

Abstract:

Nowadays, induction motors have a significant role in industries. Condition monitoring (CM) of this equipment has gained a remarkable importance during recent years due to huge production losses, substantial imposed costs and increases in vulnerability, risk, and uncertainty levels. Motor current signature analysis (MCSA) is one of the most important techniques in CM. This method can be used for rotor broken bars detection. Signal processing methods such as Fast Fourier transformation (FFT), Wavelet transformation and Empirical Mode Decomposition (EMD) are used for analyzing MCSA output data. In this study, these signal processing methods are used for broken bar problem detection of Mobarakeh steel company induction motors. Based on wavelet transformation method, an index for fault detection, CF, is introduced which is the variation of maximum to the mean of wavelet transformation coefficients. We find that, in the broken bar condition, the amount of CF factor is greater than the healthy condition. Based on EMD method, the energy of intrinsic mode functions (IMF) is calculated and finds that when motor bars become broken the energy of IMFs increases.

Keywords: broken bar, condition monitoring, diagnostics, empirical mode decomposition, fourier transform, wavelet transform

Procedia PDF Downloads 139

Authors: Budhvin T. Withana, Sulochana Rupasinghe

Abstract:

The educational system faces a significant concern with regards to Dyslexia and Dysgraphia, which are learning disabilities impacting reading and writing abilities. This is particularly challenging for children who speak the Sinhala language due to its complexity and uniqueness. Commonly used methods to detect the risk of Dyslexia and Dysgraphia rely on subjective assessments, leading to limited coverage and time-consuming processes. Consequently, delays in diagnoses and missed opportunities for early intervention can occur. To address this issue, the project developed a hybrid model that incorporates various deep learning techniques to detect the risk of Dyslexia and Dysgraphia. Specifically, Resnet50, VGG16, and YOLOv8 models were integrated to identify handwriting issues. The outputs of these models were then combined with other input data and fed into an MLP model. Hyperparameters of the MLP model were fine-tuned using Grid Search CV, enabling the identification of optimal values for the model. This approach proved to be highly effective in accurately predicting the risk of Dyslexia and Dysgraphia, providing a valuable tool for early detection and intervention. The Resnet50 model exhibited a training accuracy of 0.9804 and a validation accuracy of 0.9653. The VGG16 model achieved a training accuracy of 0.9991 and a validation accuracy of 0.9891. The MLP model demonstrated impressive results with a training accuracy of 0.99918, a testing accuracy of 0.99223, and a loss of 0.01371. These outcomes showcase the high accuracy achieved by the proposed hybrid model in predicting the risk of Dyslexia and Dysgraphia.

Keywords: neural networks, risk detection system, dyslexia, dysgraphia, deep learning, learning disabilities, data science

Procedia PDF Downloads 49

Authors: Sandeep Santosh, O. P. Sahu

Abstract:

In this paper, performance comparison of wideband covariance matrix sparse representation (W-CMSR) method with other existing wideband Direction of Arrival (DOA) estimation methods has been made.W-CMSR relies less on a priori information of the incident signal number than the ordinary subspace based methods.Consider the perturbation free covariance matrix of the wideband array output. The diagonal covariance elements are contaminated by unknown noise variance. The covariance matrix of array output is conjugate symmetric i.e its upper right triangular elements can be represented by lower left triangular ones.As the main diagonal elements are contaminated by unknown noise variance,slide over them and align the lower left triangular elements column by column to obtain a measurement vector.Simulation results for W-CMSR are compared with simulation results of other wideband DOA estimation methods like Coherent signal subspace method (CSSM), Capon, l1-SVD, and JLZA-DOA. W-CMSR separate two signals very clearly and CSSM, Capon, L1-SVD and JLZA-DOA fail to separate two signals clearly and an amount of pseudo peaks exist in the spectrum of L1-SVD.

Keywords: W-CMSR, wideband direction of arrival (DOA), covariance matrix, electrical and computer engineering

Procedia PDF Downloads 456

Authors: Keshav Prasad Kandel, Balaram Khadka, Karan Bhatta, Basu Dev Ghimire

Abstract:

Earthquakes still exist as a threating disaster. Being able to predict earthquakes will certainly help prevent substantial loss of life and property. Perhaps, Very Low Frequency/Low Frequency (VLF/LF) signal band (3-30 kHz), which is effectively reflected from D-layer of ionosphere, can be established as a tool to predict earthquake. On May 20 and May 29, 2012, earthquakes of magnitude 6.1 and 5.8 respectively struck Emilia-Romagna of Italy. A year back, on August 24, 2016, an earthquake of magnitude 6.2 struck Central Italy (42.7060 N and 13.2230 E) at 1:36 UT. We present the results obtained from the US Navy VLF Transmitter’s NSY signal of 45.9 kHz transmitted from Niscemi, in the province of Sicily, Italy and received at the Kiel Longwave Monitor, Germany for 2012 and 2016. We analyzed the terminator times, their individual differences and nighttime fluctuation counts. We also analyzed trends, dispersion and nighttime fluctuation which gave us a possible precursors to these earthquakes. Since perturbations in VLF amplitude could also be due to various other factors like lightning, geomagnetic activities (storms, auroras etc.) and solar activities (flares, UV flux, etc.), we filtered the possible perturbations due to these agents to guarantee that the perturbations seen in VLF/LF amplitudes were as a precursor to Earthquakes. As our TRGCP path is North-south, the sunrise and sunset time in transmitter and receiver places matches making pathway for VLF/LF smoother and therefore hoping to obtain more natural data. To our surprise, we found many clear anomalies (as precursors) in terminator times 5 days to 16 days before the earthquakes. Moreover, using night time fluctuation method, we found clear anomalies 5 days to 13 days prior to main earthquakes. This exactly correlates with the findings of previous authors that ionospheric perturbations are seen few days to one month before the seismic activity. In addition to this, we were amazed to observe unexpected decrease of dispersion on certain anomalies where it was supposed to increase, thereby not supporting our finding to some extent. To resolve this problem, we devised a new parameter called dispersion nighttime (dispersion). On analyzing, this parameter decreases significantly on days of nighttime anomalies thereby supporting our precursors to much extent.

Keywords: D-layer, TRGCP (Transmitter Receiver Great Circle Path), terminator times, VLF/LF

Procedia PDF Downloads 173

Authors: Nuraddeen Usman, Khiruddin Abdullah, Mohd Nawawi, Amin Khalil Ismail

Abstract:

A magnetic survey is carried out in order to locate the remains of construction items, specifically concrete pillars. The conventional Euler deconvolution technique can perform the task but it requires the use of fixed structural index (SI) and the construction items are made of materials with different shapes which require different SI (unknown). A Euler deconvolution technique that estimate background, horizontal coordinate (xo and yo), depth and structural index (SI) simultaneously is prepared and used for this task. The synthetic model study carried indicated the new methodology can give a good estimate of location and does not depend on magnetic latitude. For field data, both the total magnetic field and gradiometer reading had been collected simultaneously. The computed vertical derivatives and gradiometer readings are compared and they have shown good correlation signifying the effectiveness of the method. The filtering is carried out using automated procedure, analytic signal and other traditional techniques. The clustered depth solutions coincided with the high amplitude/values of analytic signal and these are the possible target positions of the concrete pillars being sought. The targets under investigation are interpreted to be located at the depth between 2.8 to 9.4 meters. More follow up survey is recommended as this mark the preliminary stage of the work.

Keywords: concrete pillar, magnetic survey, geotechnical investigation, Euler Deconvolution

Procedia PDF Downloads 247

Authors: Budhvin T. Withana, Sulochana Rupasinghe

Abstract:

The problem of Dyslexia and Dysgraphia, two learning disabilities that affect reading and writing abilities, respectively, is a major concern for the educational system. Due to the complexity and uniqueness of the Sinhala language, these conditions are especially difficult for children who speak it. The traditional risk detection methods for Dyslexia and Dysgraphia frequently rely on subjective assessments, making it difficult to cover a wide range of risk detection and time-consuming. As a result, diagnoses may be delayed and opportunities for early intervention may be lost. The project was approached by developing a hybrid model that utilized various deep learning techniques for detecting risk of Dyslexia and Dysgraphia. Specifically, Resnet50, VGG16 and YOLOv8 were integrated to detect the handwriting issues, and their outputs were fed into an MLP model along with several other input data. The hyperparameters of the MLP model were fine-tuned using Grid Search CV, which allowed for the optimal values to be identified for the model. This approach proved to be effective in accurately predicting the risk of Dyslexia and Dysgraphia, providing a valuable tool for early detection and intervention of these conditions. The Resnet50 model achieved an accuracy of 0.9804 on the training data and 0.9653 on the validation data. The VGG16 model achieved an accuracy of 0.9991 on the training data and 0.9891 on the validation data. The MLP model achieved an impressive training accuracy of 0.99918 and a testing accuracy of 0.99223, with a loss of 0.01371. These results demonstrate that the proposed hybrid model achieved a high level of accuracy in predicting the risk of Dyslexia and Dysgraphia.

Keywords: neural networks, risk detection system, Dyslexia, Dysgraphia, deep learning, learning disabilities, data science

Procedia PDF Downloads 83

Authors: Rachel Y. Zhang, Christopher K. Anderson

Abstract:

A critical aspect of revenue management is a firm’s ability to predict demand as a function of price. Historically hotels have used simple time series models (regression and/or pick-up based models) owing to the complexities of trying to build casual models of demands. Machine learning approaches are slowly attracting attention owing to their flexibility in modeling relationships. This study provides an overview of approaches to forecasting hospitality demand – focusing on the opportunities created by machine learning approaches, including K-Nearest-Neighbors, Support vector machine, Regression Tree, and Artificial Neural Network algorithms. The out-of-sample performances of above approaches to forecasting hotel demand are illustrated by using a proprietary sample of the market level (24 properties) transactional data for Las Vegas NV. Causal predictive models can be built and evaluated owing to the availability of market level (versus firm level) data. This research also compares and contrast model accuracy of firm-level models (i.e. predictive models for hotel A only using hotel A’s data) to models using market level data (prices, review scores, location, chain scale, etc… for all hotels within the market). The prospected models will be valuable for hotel revenue prediction given the basic characters of a hotel property or can be applied in performance evaluation for an existed hotel. The findings will unveil the features that play key roles in a hotel’s revenue performance, which would have considerable potential usefulness in both revenue prediction and evaluation.

Keywords: hotel revenue, k-nearest-neighbors, machine learning, neural network, prediction model, regression tree, support vector machine

Procedia PDF Downloads 117

Authors: Agampodi Promoda Perera, Yong Shin, Mi Kyoung Park

Abstract:

The successful detection of pathogenic bacteria in blood provides important information for early detection, diagnosis and the prevention and treatment of infectious diseases. Silicon microring resonators are refractive-index-based optical biosensors that provide highly sensitive, label-free, real-time multiplexed detection of biomolecules. We demonstrate the technique of using GO (graphene oxide) to enhance the signal output of the silicon microring optical sensor. The activated carboxylic groups in GO molecules bind directly to single stranded DNA with an amino modified 5’ end. This conjugation amplifies the shift in resonant wavelength in a real-time manner. We designed a capture probe for strain Staphylococcus aureus of 21 bp and a longer complementary target sequence of 70 bp. The mismatched target sequence we used was of Streptococcus agalactiae of 70 bp. GO is added after the complementary binding of the probe and target. GO conjugates to the unbound single stranded segment of the target and increase the wavelength shift on the silicon microring resonator. Furthermore, our results show that GO could successfully differentiate between the mismatched DNA sequences from the complementary DNA sequence. Therefore, the proposed concept could effectively enhance sensitivity of pathogen detection sensors.

Keywords: label free biosensor, pathogenic bacteria, graphene oxide, diagnosis

Procedia PDF Downloads 448

Authors: Juliana A. Knocikova

Abstract:

Methods of nonlinear signal analysis are based on finding that random behavior can arise in deterministic nonlinear systems with a few degrees of freedom. Considering the dynamical systems, entropy is usually understood as a rate of information production. Changes in temporal dynamics of physiological data are indicating evolving of system in time, thus a level of new signal pattern generation. During last decades, many algorithms were introduced to assess some patterns of physiological responses to external stimulus. However, the reflex responses are usually characterized by short periods of time. This characteristic represents a great limitation for usual methods of nonlinear analysis. To solve the problems of short recordings, parameter of approximate entropy has been introduced as a measure of system complexity. Low value of this parameter is reflecting regularity and predictability in analyzed time series. On the other side, increasing of this parameter means unpredictability and a random behavior, hence a higher system complexity. Reduced neurophysiological data complexity has been observed repeatedly when analyzing electroneurogram and electromyogram activities during defence reflex responses. Quantitative phrenic neurogram changes are also obvious during severe hypoxia, as well as during airway reflex episodes. Concluding, the approximate entropy parameter serves as a convenient tool for analysis of reflex behavior characterized by short lasting time series.

Keywords: approximate entropy, neurophysiological data, nonlinear dynamics, reflex

Procedia PDF Downloads 289

Authors: A. Das, L. Hitihamillage, S. Moridpour

Abstract:

Natural disasters are inevitable to the biodiversity. Disasters such as flood, tsunami and tornadoes could be brutal, harsh and devastating. In Australia, flooding is a major issue experienced by different parts of the country. In such crisis, delays in evacuation could decide the life and death of the people living in those regions. Congestion management could become a mammoth task if there are no steps taken before such situations. In the past to manage congestion in such circumstances, many strategies were utilised such as converting the road shoulders to extra lanes or changing the road geometry by adding more lanes. However, expansion of road to resolving congestion problems is not considered a viable option nowadays. The authorities avoid this option due to many reasons, such as lack of financial support and land space. They tend to focus their attention on optimising the current resources they possess and use traffic signals to overcome congestion problems. Traffic Signal Management strategy was considered a viable option, to alleviate congestion problems in the City of Geelong, Victoria. Arterial road with signalised intersections considered in this paper and the traffic data required for modelling collected from VicRoads. Traffic signalling software SIDRA used to model the roads, and the information gathered from VicRoads. In this paper, various signal parameters utilised to assess and improve the corridor performance to achieve the best possible Level of Services (LOS) for the arterial road.

Keywords: congestion, constraints, management, LOS

Procedia PDF Downloads 380

Authors: Liudmyla Vesper

Abstract:

The problems of modern education are large-scale and diverse. The aspirations of parents, teachers, and experts converge - everyone interested in growing up a generation of whole, well-educated persons. Both the family and society are expected in the future generation to be self-sufficient, desirable in the labor market, and capable of lifelong learning. Today's children have a powerful potential that is difficult to realize in the conditions of traditional school approaches. Focusing on STEM education in practice often ends with the simple use of computers and gadgets during class. "Science", "technology", "engineering" and "mathematics" are difficult to combine within school and university curricula, which have not changed much during the last 10 years. Solving the problems of modern education largely depends on teachers - innovators, teachers - practitioners who develop and implement effective educational methods and programs. Teachers who propose innovative pedagogical practices that allow students to master large-scale knowledge and apply it to the practical plane. Effective education considers the creation of stable neural structures during the learning process, which allow to preserve and increase knowledge throughout life. The author proposed a method of integrated lessons – cases based on the maths patterns for forming a holistic perception of the world. This method and program are scientifically substantiated and have more than 15 years of practical application experience in school and student classrooms. The first results of the practical application of the author's methodology and curriculum were announced at the International Conference "Teaching and Learning Strategies to Promote Elementary School Success", 2006, April 22-23, Yerevan, Armenia, IREX-administered 2004-2006 Multiple Component Education Project. This program is based on the concept of interdisciplinary connections and its implementation in the process of continuous learning. This allows students to save and increase knowledge throughout life according to a single pattern. The pattern principle stores information on different subjects according to one scheme (pattern), using long-term memory. This is how neural structures are created. The author also admits that a similar method can be successfully applied to the training of artificial intelligence neural networks. However, this assumption requires further research and verification. The educational method and program proposed by the author meet the modern requirements for education, which involves mastering various areas of knowledge, starting from an early age. This approach makes it possible to involve the child's cognitive potential as much as possible and direct it to the preservation and development of individual talents. According to the methodology, at the early stages of learning students understand the connection between school subjects (so-called "sciences" and "humanities") and in real life, apply the knowledge gained in practice. This approach allows students to realize their natural creative abilities and talents, which makes it easier to navigate professional choices and find their place in life.

Keywords: science education, maths education, AI, neuroplasticity, innovative education problem, creativity development, modern education problem

Procedia PDF Downloads 44

Authors: Jangje Park, So Young Kim

Abstract:

The market demand for audio quality in mobile devices continues to increase, and audible buzz noise generated in time division communication is a chronic problem that goes against the market demand. In the case of time division type communication, the RF Power Amplifier (RF PA) is driven at the audio frequency cycle, and it makes various influences on the audio signal. In this paper, we measured the ground bounce noise generated by the peak current flowing through the ground network in the RF PA with the audio frequency; it was confirmed that the noise is the cause of the audible buzz noise during a call. In addition, a grounding method of the microphone device that can improve the buzzing noise was proposed. Considering that the level of the audio signal generated by the microphone device is -38dBV based on 94dB Sound Pressure Level (SPL), even ground bounce noise of several hundred uV will fall within the range of audible noise if it is induced by the audio amplifier. Through the grounding method of the microphone device proposed in this paper, it was confirmed that the audible buzz noise power density at the RF PA driving frequency was improved by more than 5dB under the conditions of the Printed Circuit Board (PCB) used in the experiment. A fundamental improvement method was presented regarding the buzzing noise during a mobile phone call.

Keywords: audio frequency, buzz noise, ground bounce, microphone grounding

Procedia PDF Downloads 127

Authors: Bo Wan, Xiu Wen, Lingling An, Xiaoling Ding

Abstract:

The paper describes a Chinese shadow play animation system based on Kinect. Users, without any professional training, can personally manipulate the shadow characters to finish a shadow play performance by their body actions and get a shadow play video through giving the record command to our system if they want. In our system, Kinect is responsible for capturing human movement and voice commands data. Gesture recognition module is used to control the change of the shadow play scenes. After packaging the data from Kinect and the recognition result from gesture recognition module, VRPN transmits them to the server-side. At last, the server-side uses the information to control the motion of shadow characters and video recording. This system not only achieves human-computer interaction, but also realizes the interaction between people. It brings an entertaining experience to users and easy to operate for all ages. Even more important is that the application background of Chinese shadow play embodies the protection of the art of shadow play animation.

Keywords: hadow play animation, Kinect, gesture recognition, VRPN, HCI

Procedia PDF Downloads 386

Authors: Varun Agarwal

Abstract:

Introduction: With the advent of personalized medicine, histopathological review of whole slide images (WSIs) for cancer diagnosis presents an exceedingly time-consuming, complex task. Specifically, detecting metastatic regions in WSIs of sentinel lymph node biopsies necessitates a full-scanned, holistic evaluation of the image. Thus, digital pathology, low-level image manipulation algorithms, and machine learning provide significant advancements in improving the efficiency and accuracy of WSI analysis. Using Camelyon16 data, this paper proposes a deep learning pipeline to automate and ameliorate breast cancer metastasis localization and WSI classification. Methodology: The model broadly follows five stages -region of interest detection, WSI partitioning into image tiles, convolutional neural network (CNN) image-segment classifications, probabilistic mapping of tumor localizations, and further processing for whole WSI classification. Transfer learning is applied to the task, with the implementation of Inception-ResNetV2 - an effective CNN classifier that uses residual connections to enhance feature representation, adding convolved outputs in the inception unit to the proceeding input data. Moreover, in order to augment the performance of the transfer learning CNN, a stack of convolutional denoising autoencoders (CDAE) is applied to produce embeddings that enrich image representation. Through a saliency-detection algorithm, visual training segments are generated, which are then processed through a denoising autoencoder -primarily consisting of convolutional, leaky rectified linear unit, and batch normalization layers- and subsequently a contrast-normalization function. A spatial pyramid pooling algorithm extracts the key features from the processed image, creating a viable feature map for the CNN that minimizes spatial resolution and noise. Results and Conclusion: The simplified and effective architecture of the fine-tuned transfer learning Inception-ResNetV2 network enhanced with the CDAE stack yields state of the art performance in WSI classification and tumor localization, achieving AUC scores of 0.947 and 0.753, respectively. The convolutional feature retention and compilation with the residual connections to inception units synergized with the input denoising algorithm enable the pipeline to serve as an effective, efficient tool in the histopathological review of WSIs.

Keywords: breast cancer, convolutional neural networks, metastasis mapping, whole slide images

Procedia PDF Downloads 117

Authors: Maryam Zarabian, Hector Guzman, Pedro Pereira-Almao, Abraham Fapojuwo

Abstract:

Dry reforming of methane (DRM) has sparked significant industrial and scientific interest not only as a viable alternative for addressing the environmental concerns of two main contributors of the greenhouse effect, i.e., carbon dioxide (CO₂) and methane (CH₄), but also produces syngas, i.e., a mixture of hydrogen (H₂) and carbon monoxide (CO) utilized by a wide range of downstream processes as a feedstock for other chemical productions. In this study, we develop an AI-enable syngas production model to tackle the problem of achieving an equivalent H₂/CO ratio [1:1] with respect to the most efficient conversion. Firstly, the unsupervised density-based spatial clustering of applications with noise (DBSAN) algorithm removes outlier data points from the original experimental dataset. Then, random forest (RF) and deep neural network (DNN) models employ the error-free dataset to predict the DRM results. DNN models inherently would not be able to obtain accurate predictions without a huge dataset. To cope with this limitation, we employ reusing pre-trained layers’ approaches such as transfer learning and greedy layer-wise pretraining. Compared to the other deep models (i.e., pure deep model and transferred deep model), the greedy layer-wise pre-trained deep model provides the most accurate prediction as well as similar accuracy to the RF model with R² values 1.00, 0.999, 0.999, 0.999, 0.999, and 0.999 for the total outlet flow, H₂/CO ratio, H₂ yield, CO yield, CH₄ conversion, and CO₂ conversion outputs, respectively.

Keywords: artificial intelligence, dry reforming of methane, artificial neural network, deep learning, machine learning, transfer learning, greedy layer-wise pretraining

Procedia PDF Downloads 70

Authors: Pius Marthin, Nihal Ata Tutkun

Abstract:

Survival analysis has become one of the paramount procedures in the modeling of time-to-event data. When we encounter complex survival problems, the traditional approach remains limited in accounting for the complex correlational structure between the covariates and the outcome due to the strong assumptions that limit the inference and prediction ability of the resulting models. Several studies exist on the deep learning approach to survival modeling; moreover, the application for the case of complex survival problems still needs to be improved. In addition, the existing models need to address the data structure's complexity fully and are subject to noise and redundant information. In this study, we design a deep learning technique (CmpXRnnSurv_AE) that obliterates the limitations imposed by traditional approaches and addresses the above issues to jointly predict the risk-specific probabilities and survival function for recurrent events with competing risks. We introduce the component termed Risks Information Weights (RIW) as an attention mechanism to compute the weighted cumulative incidence function (WCIF) and an external auto-encoder (ExternalAE) as a feature selector to extract complex characteristics among the set of covariates responsible for the cause-specific events. We train our model using synthetic and real data sets and employ the appropriate metrics for complex survival models for evaluation. As benchmarks, we selected both traditional and machine learning models and our model demonstrates better performance across all datasets.

Keywords: cumulative incidence function (CIF), risk information weight (RIW), autoencoders (AE), survival analysis, recurrent events with competing risks, recurrent neural networks (RNN), long short-term memory (LSTM), self-attention, multilayers perceptrons (MLPs)

Procedia PDF Downloads 73

Authors: Avi Harel

Abstract:

Most accidents are commonly attributed in hindsight to human errors, yet most methodologies for safety focus on technical issues. According to the Black Swan theory, this paradox is due to insufficient data about the ways systems fail. The article presents a study of the sources of errors, and proposes a methodology for utility-oriented design, comprising methods for coping with each of the sources identified. Accident analysis indicates that errors typically result from difficulties of operating in exceptional conditions. Therefore, following STAMP, the focus should be on preventing exceptions. Exception analysis indicates that typically they involve an improper account of the operational scenario, due to deficiencies in the system integration. The methodology proposes a model, which is a formal definition of the system operation, as well as principles and guidelines for safety-oriented system integration. The article calls to develop and integrate tools for recording and analysis of the system activity during the operation, required to implement validate the model.

Keywords: accidents, complexity, errors, exceptions, interaction, modeling, resilience, risks

Procedia PDF Downloads 187

Authors: E. Kharaishvili, M. Chavleishvili, M. Natsvaladze

Abstract:

The article presents the trends in Georgian wine market development and evaluates the competitive advantages of Georgia to enter the wine market based on its customs, traditions and historical practices combined with modern technologies. In order to analyze the supply of wine, dynamics of vineyard land area and grape varieties are discussed, trends in wine production are presented, trends in export and import are evaluated, local wine market, its micro and macro environments are studied and analyzed based on the interviews with experts and analysis of initial recording materials. For strengthening its position on the international market, the level of competitiveness of Georgian wine is defined, which is evaluated by “ex-ante” and “ex-post” methods, as well as by four basic and two additional factors of the Porter’s diamond method; potential advantages and disadvantages of Georgian wine are revealed. Conclusions are made by identifying the factors that hinder the development of Georgian wine market. Based on the conclusions, relevant recommendations are developed.

Keywords: Georgian wine market, competitive advantage, bio wine, export-import, Porter's diamond model

Procedia PDF Downloads 374

Authors: Pawel Albrycht, Monika Ksiezopolska-Gocalska, Robert Holyst

Abstract:

Surface Enhanced Raman Spectroscopy (SERS) is a technique of growing importance not only in purely scientific research related to analytical chemistry. It finds more and more applications in broadly understood testing - medical, forensic, pharmaceutical, food - and everywhere works perfectly, on one condition that SERS substrates used for testing give adequate enhancement, repeatability, and homogeneity of SERS signal. This is a problem that has existed since the invention of this technique. Some laboratories use as SERS amplifiers colloids with silver or gold nanoparticles, others form rough silver or gold surfaces, but results are generally either weak or unrepeatable. Furthermore, these structures are very often highly specific - they amplify the signal only of a small group of compounds. It means that they work with some kinds of analytes but only with those which were used at a developer’s laboratory. When it comes to research on different compounds, completely new SERS 'substrates' are required. That underlay our decision to develop universal substrates for the SERS spectroscopy. Generally, each compound has different affinity for both silver and gold, which have the best SERS properties, and that's what depends on what signal we get in the SERS spectrum. Our task was to create the platform that gives a characteristic 'fingerprint' of the largest number of compounds with very high repeatability - even at the expense of the intensity of the enhancement factor (EF) (possibility to repeat research results is of the uttermost importance). As specified above SERS substrates are offered by SERSitive company. Applied method is based on cyclic potentiodynamic electrodeposition of silver or silver-gold nanoparticles on the conductive surface of ITO-coated glass at controlled temperature of the reaction solution. Silver nanoparticles are supplied in the form of silver nitrate (AgNO₃, 10 mM), gold nanoparticles are derived from tetrachloroauric acid (10 mM) while sodium sulfite (Na₂O₃, 5 mM) is used as a reductor. To limit and standardize the size of the SERS surface on which nanoparticles are deposited, photolithography is used. We secure the desired ITO-coated glass surface, and then etch the unprotected ITO layer which prevents nanoparticles from settling at these sites. On the prepared surface, we carry out the process described above, obtaining SERS surface with nanoparticles of sizes 50-400 nm. The SERSitive platforms present highly sensitivity (EF = 10⁵-10⁶), homogeneity and repeatability (70-80%).

Keywords: electrodeposition, nanoparticles, Raman spectroscopy, SERS, SERSitive, SERS platforms, SERS substrates

Procedia PDF Downloads 146

Authors: Imen Soltani, Takoua Soltani, Taoufik Aguili

Abstract:

Metamaterials crossover classic physical boundaries and gives rise to new phenomena and applications in the domain of beam steering and shaping. Where electromagnetic near and far field manipulations were achieved in an accurate manner. In this sense, 3D imaging is one of the beneficiaries and in particular Denis Gabor’s invention: holography. But, the major difficulty here is the lack of a suitable recording medium. So some enhancements were essential, where the 2D version of bulk metamaterials have been introduced the so-called metasurface. This new class of interfaces simplifies the problem of recording medium with the capability of tuning the phase, amplitude, and polarization at a given frequency. In order to achieve an intelligible wavefront control, the electromagnetic properties of the metasurface should be optimized by means of solving Maxwell’s equations. In this context, integral methods are emerging as an important method to study electromagnetic from microwave to optical frequencies. The method of moment presents an accurate solution to reduce the problem of dimensions by writing its boundary conditions in the form of integral equations. But solving this kind of equations tends to be more complicated and time-consuming as the structural complexity increases. Here, the use of equivalent circuit’s method exhibits the most scalable experience to develop an integral method formulation. In fact, for allaying the resolution of Maxwell’s equations, the method of Generalised Equivalent Circuit was proposed to convey the resolution from the domain of integral equations to the domain of equivalent circuits. In point of fact, this technique consists in creating an electric image of the studied structure using discontinuity plan paradigm and taken into account its environment. So that, the electromagnetic state of the discontinuity plan is described by generalised test functions which are modelled by virtual sources not storing energy. The environmental effects are included by the use of an impedance or admittance operator. Here, we propose a tunable metasurface composed of graphene-based elements which combine the advantages of reflectarrays concept and graphene as a pillar constituent element at Terahertz frequencies. The metasurface’s building block consists of a thin gold film, a dielectric spacer SiO₂ and graphene patch antenna. Our electromagnetic analysis is based on the method of moment combined with generalised equivalent circuit (MoM-GEC). We begin by restricting our attention to study the effects of varying graphene’s chemical potential on the unit cell input impedance. So, it was found that the variation of complex conductivity of graphene allows controlling the phase and amplitude of the reflection coefficient at each element of the array. From the results obtained here, we were able to determine that the phase modulation is realized by adjusting graphene’s complex conductivity. This modulation is a viable solution compared to tunning the phase by varying the antenna length because it offers a full 2π reflection phase control.

Keywords: graphene, method of moment combined with generalised equivalent circuit, reconfigurable metasurface, reflectarray, terahertz domain

Procedia PDF Downloads 168

Authors: F. Ghazalnaz Sharifonnasabi, Iman Makhdoom

Abstract:

Breast cancer is a serious health concern that affects many people around the world. According to a study published in the Breast journal, the global burden of breast cancer is expected to increase significantly over the next few decades. The number of deaths from breast cancer has been increasing over the years, but the age-standardized mortality rate has decreased in some countries. It’s important to be aware of the risk factors for breast cancer and to get regular check- ups to catch it early if it does occur. Machin learning techniques have been used to aid in the early detection and diagnosis of breast cancer. These techniques, that have been shown to be effective in predicting and diagnosing the disease, have become a research hotspot. In this study, we consider two deep learning approaches including: Multi-Layer Perceptron (MLP), and Convolutional Neural Network (CNN). We also considered the five-machine learning algorithm titled: Decision Tree (C4.5), Naïve Bayesian (NB), Support Vector Machine (SVM), K-Nearest Neighbors (KNN) Algorithm and XGBoost (eXtreme Gradient Boosting) on the Breast Cancer Wisconsin Diagnostic dataset. We have carried out the process of evaluating and comparing classifiers involving selecting appropriate metrics to evaluate classifier performance and selecting an appropriate tool to quantify this performance. The main purpose of the study is predicting and diagnosis breast cancer, applying the mentioned algorithms and also discovering of the most effective with respect to confusion matrix, accuracy and precision. It is realized that CNN outperformed all other classifiers and achieved the highest accuracy (0.982456). The work is implemented in the Anaconda environment based on Python programing language.

Keywords: breast cancer, multi-layer perceptron, Naïve Bayesian, SVM, decision tree, convolutional neural network, XGBoost, KNN

Procedia PDF Downloads 58

Authors: Moez ul Hassan, Bushra Noman, Sarmad Hameed, Shahab Mehmood, Asma Bashir

Abstract:

The importance of Noble prize winning “Patch Clamp Technique” is well documented. However, Patch Clamp Technique is very expensive and hence hinders research in developing countries. In this paper, detection, processing and recording of ultra low current from induced cells by using transimpedence amplifier is described. The sensitivity of the proposed amplifier is in the range of femto amperes (fA). Capacitive-feedback is used with active load to obtain a 20MΩ transimpedance gain. The challenging task in designing includes achieving adequate performance in gain, noise immunity and stability. The circuit designed by the authors was able to measure current in the rangeof 300fA to 100pA. Adequate performance shown by the amplifier with different input current and outcome result was found to be within the acceptable error range. Results were recorded using LabVIEW 8.5®for further research.

Keywords: drug discovery, ionic current, operational amplifier, patch clamp

Procedia PDF Downloads 504

Authors: Jinan Fiaidhi, Sabah Mohammed, Petros Zezos

Abstract:

Capsule endoscopy (CE) is an established noninvasive diagnostic modality in investigating small bowel disease. CE has a pivotal role in assessing patients with suspected bleeding or identifying evidence of active Crohn's disease in the small bowel. However, CE produces lengthy videos with at least eighty thousand frames, with a frequency rate of 2 frames per second. Gastroenterologists cannot dedicate 8 to 15 hours to reading the CE video frames to arrive at a diagnosis. This is why the issue of analyzing CE videos based on modern artificial intelligence techniques becomes a necessity. However, machine learning, including deep learning, has failed to report robust results because of the lack of large samples to train its neural nets. In this paper, we are describing a thick data approach that learns from a few anchor images. We are using sound datasets like KVASIR and CrohnIPI to filter candidate frames that include interesting anomalies in any CE video. We are identifying candidate frames based on feature extraction to provide representative measures of the anomaly, like the size of the anomaly and the color contrast compared to the image background, and later feed these features to a decision tree that can classify the candidate frames as having a condition like the Crohn's Disease. Our thick data approach reported accuracy of detecting Crohn's Disease based on the availability of ulcer areas at the candidate frames for KVASIR was 89.9% and for the CrohnIPI was 83.3%. We are continuing our research to fine-tune our approach by adding more thick data methods for enhancing diagnosis accuracy.

Keywords: thick data analytics, capsule endoscopy, Crohn’s disease, siamese neural network, decision tree

Procedia PDF Downloads 131

Authors: Nassima Noufail, Sara Bouhali

Abstract:

In this work, we develop a semi-supervised solution for the purpose of action detection in videos and propose an efficient algorithm for video segmentation. The approach is divided into video segmentation, feature extraction, and classification. In the first part, a video is segmented into clips, and we used the K-means algorithm for this segmentation; our goal is to find groups based on similarity in the video. The application of k-means clustering into all the frames is time-consuming; therefore, we started by the identification of transition frames where the scene in the video changes significantly, and then we applied K-means clustering into these transition frames. We used two image filters, the gaussian filter and the Laplacian of Gaussian. Each filter extracts a set of features from the frames. The Gaussian filter blurs the image and omits the higher frequencies, and the Laplacian of gaussian detects regions of rapid intensity changes; we then used this vector of filter responses as an input to our k-means algorithm. The output is a set of cluster centers. Each video frame pixel is then mapped to the nearest cluster center and painted with a corresponding color to form a visual map. The resulting visual map had similar pixels grouped. We then computed a cluster score indicating how clusters are near each other and plotted a signal representing frame number vs. clustering score. Our hypothesis was that the evolution of the signal would not change if semantically related events were happening in the scene. We marked the breakpoints at which the root mean square level of the signal changes significantly, and each breakpoint is an indication of the beginning of a new video segment. In the second part, for each segment from part 1, we randomly selected a 16-frame clip, then we extracted spatiotemporal features using convolutional 3D network C3D for every 16 frames using a pre-trained model. The C3D final output is a 512-feature vector dimension; hence we used principal component analysis (PCA) for dimensionality reduction. The final part is the classification. The C3D feature vectors are used as input to a multi-class linear support vector machine (SVM) for the training model, and we used a multi-classifier to detect the action. We evaluated our experiment on the UCF101 dataset, which consists of 101 human action categories, and we achieved an accuracy that outperforms the state of art by 1.2%.

Keywords: video segmentation, action detection, classification, Kmeans, C3D

Procedia PDF Downloads 61

Authors: Abeer A. Aljohani

Abstract:

COVID-19 virus spread has been one of the extreme pandemics across the globe. It is also referred to as coronavirus, which is a contagious disease that continuously mutates into numerous variants. Currently, the B.1.1.529 variant labeled as omicron is detected in South Africa. The huge spread of COVID-19 disease has affected several lives and has surged exceptional pressure on the healthcare systems worldwide. Also, everyday life and the global economy have been at stake. This research aims to predict COVID-19 disease in its initial stage to reduce the death count. Machine learning (ML) is nowadays used in almost every area. Numerous COVID-19 cases have produced a huge burden on the hospitals as well as health workers. To reduce this burden, this paper predicts COVID-19 disease is based on the symptoms and medical history of the patient. This research presents a unique architecture for COVID-19 detection using ML techniques integrated with feature dimensionality reduction. This paper uses a standard UCI dataset for predicting COVID-19 disease. This dataset comprises symptoms of 5434 patients. This paper also compares several supervised ML techniques to the presented architecture. The architecture has also utilized 10-fold cross validation process for generalization and the principal component analysis (PCA) technique for feature reduction. Standard parameters are used to evaluate the proposed architecture including F1-Score, precision, accuracy, recall, receiver operating characteristic (ROC), and area under curve (AUC). The results depict that decision tree, random forest, and neural networks outperform all other state-of-the-art ML techniques. This achieved result can help effectively in identifying COVID-19 infection cases.

Keywords: supervised machine learning, COVID-19 prediction, healthcare analytics, random forest, neural network

Procedia PDF Downloads 79

Authors: Syed Asif Hassan, Syed Atif Hassan

Abstract:

Multidrug-resistant Tuberculosis (MDR-TB) is an infection caused by the resistant strains of Mycobacterium tuberculosis that do not respond either to isoniazid or rifampicin, which are the most important anti-TB drugs. The increase in the occurrence of a drug-resistance strain of MTB calls for an intensive search of novel target-based therapeutics. In this context LprG (Rv1411c) a lipoprotein from MTB plays a pivotal role in the immune evasion of Mtb leading to survival and propagation of the bacterium within the host cell. Therefore, a machine learning method will be developed for generating a computational model that could predict for a potential anti LprG activity of the novel antituberculosis compound. The present study will utilize dataset from PubChem database maintained by National Center for Biotechnology Information (NCBI). The dataset involves compounds screened against MTB were categorized as active and inactive based upon PubChem activity score. PowerMV, a molecular descriptor generator, and visualization tool will be used to generate the 2D molecular descriptors for the actives and inactive compounds present in the dataset. The 2D molecular descriptors generated from PowerMV will be used as features. We feed these features into three different classifiers, namely, random forest, a deep neural network, and a recurring neural network, to build separate predictive models and choosing the best performing model based on the accuracy of predicting novel antituberculosis compound with an anti LprG activity. Additionally, the efficacy of predicted active compounds will be screened using SMARTS filter to choose molecule with drug-like features.

Keywords: antituberculosis drug, classifier, machine learning, molecular descriptors, prediction

Procedia PDF Downloads 376

Authors: Goutam Kumar Ghorai, Sandip Sadhukhan, Arpita Sarkar, Debprasad Sinha, G. Sarkar, Ashis K. Dhara

Abstract:

Diabetes mellitus is one of the most common chronic diseases in all countries and continues to increase in numbers significantly. Diabetic retinopathy (DR) is damage to the retina that occurs with long-term diabetes. DR is a major cause of blindness in the Indian population. Therefore, its early diagnosis is of utmost importance towards preventing progression towards imminent irreversible loss of vision, particularly in the huge population across rural India. The barriers to eye examination of all diabetic patients are socioeconomic factors, lack of referrals, poor access to the healthcare system, lack of knowledge, insufficient number of ophthalmologists, and lack of networking between physicians, diabetologists and ophthalmologists. A few diabetic patients often visit a healthcare facility for their general checkup, but their eye condition remains largely undetected until the patient is symptomatic. This work aims to focus on the design and development of a fully automated intelligent decision system for screening retinal fundus images towards detection of the pathophysiology caused by microaneurysm in the early stage of the diseases. Automated detection of microaneurysm is a challenging problem due to the variation in color and the variation introduced by the field of view, inhomogeneous illumination, and pathological abnormalities. We have developed aconvolutional neural network for efficient detection of microaneurysm. A loss function is also developed to handle severe class imbalance due to very small size of microaneurysms compared to background. The network is able to locate the salient region containing microaneurysms in case of noisy images captured by non-mydriatic cameras. The ground truth of microaneurysms is created by expert ophthalmologists for MESSIDOR database as well as private database, collected from Indian patients. The network is trained from scratch using the fundus images of MESSIDOR database. The proposed method is evaluated on DIARETDB1 and the private database. The method is successful in detection of microaneurysms for dilated and non-dilated types of fundus images acquired from different medical centres. The proposed algorithm could be used for development of AI based affordable and accessible system, to provide service at grass root-level primary healthcare units spread across the country to cater to the need of the rural people unaware of the severe impact of DR.

Keywords: retinal fundus image, deep convolutional neural network, early detection of microaneurysms, screening of diabetic retinopathy

Procedia PDF Downloads 126

Authors: Marek Gancarz, Agnieszka Nawrocka, Robert Rusinek, Marcin Tadla

Abstract:

Volatile organic compounds (VOCs) are the fungi metabolites in the gaseous form produced during improper storage of agricultural commodities (e.g. grain, food). The spoilt commodities produce a wide range of VOCs including alcohols, esters, aldehydes, ketones, alkanes, alkenes, furans, phenols etc. The characteristic VOCs and odours can be determined by using electronic nose (e-Nose) which contains a matrix of different kinds of sensors e.g. resistive sensors. The aim of the present studies was to determine relationship between response of the resistive sensors on the chosen volatiles and their concentration. According to the literature, it was chosen volatiles characteristic for the cereals: ethanol, 3-methyl-1-butanol and hexanal. Analysis of the sensor signals shows that a signal shape is different for the different substances. Moreover, each VOC signal gives information about a maximum of the normalized sensor response (R/Rmax), an impregnation time (tIM) and a cleaning time at half maximum of R/Rmax (tCL). These three parameters can be regarded as a ‘VOC fingerprint’. Seven resistive sensors (TGS2600-B00, TGS2602-B00, TGS2610-C00, TGS2611-C00, TGS2611-E00, TGS2612-D00, TGS2620-C00) produced by Figaro USA Inc., and one (AS-MLV-P2) produced by AMS AG, Austria were used. Two out of seven sensors (TGS2611-E00, TGS2612-D00) did not react to the chosen VOCs. The most responsive sensor was AS-MLV-P2. The research was supported by the National Centre for Research and Development (NCBR), Grant No. PBS2/A8/22/2013.

Keywords: agricultural commodities, organic compounds, resistive sensors, volatile

Procedia PDF Downloads 356