Search results for: multimodal fusion classifier

Authors: Rohit Gupta, Ravinder Agarwal

Abstract:

Surface electromyographic (sEMG) signal has the potential to identify the human activities and intention. This potential is further exploited to control the artificial limbs using the sEMG signal from residual limbs of amputees. The paper deals with the development of multichannel cost efficient sEMG signal interface for research application, along with evaluation of proposed class dependent statistical approach of the feature selection method. The sEMG signal acquisition interface was developed using ADS1298 of Texas Instruments, which is a front-end interface integrated circuit for ECG application. Further, the sEMG signal is recorded from two lower limb muscles for three locomotions namely: Plane Walk (PW), Stair Ascending (SA), Stair Descending (SD). A class dependent statistical approach is proposed for feature selection and also its performance is compared with 12 preexisting feature vectors. To make the study more extensive, performance of five different types of classifiers are compared. The outcome of the current piece of work proves the suitability of the proposed feature selection algorithm for locomotion recognition, as compared to other existing feature vectors. The SVM Classifier is found as the outperformed classifier among compared classifiers with an average recognition accuracy of 97.40%. Feature vector selection emerges as the most dominant factor affecting the classification performance as it holds 51.51% of the total variance in classification accuracy. The results demonstrate the potentials of the developed sEMG signal acquisition interface along with the proposed feature selection algorithm.

Keywords: classifiers, feature selection, locomotion, sEMG

Procedia PDF Downloads 269

Authors: Azita Ramezani, Ghazal Mashhadiagha, Bahareh Sanabakhsh

Abstract:

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

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

Procedia PDF Downloads 10

Authors: Harshit Agrawal, Salman Muhammad

Abstract:

Degradation to reinforced concrete (RC), primarily due to corrosion of embedded reinforcement, has been a major cause of concern worldwide. Among several ways to control corrosion, the use of coated reinforcement has gained significant interest in field applications. However, the choice of proper coating material and the effect of damage over coating are yet to be addressed for effective application of coated reinforcements. The present study aims to investigate and compare the performance of three different types of coated reinforcements —Fusion-Bonded Epoxy Coating (FBEC), Cement Polymer Composite Coating (CPCC), and Dual Zinc-Epoxy Coating (DZEC) —in concrete structures. The aim is to assess their corrosion resistance, durability, and overall effectiveness as coated reinforcement materials both in undamaged and simulated damaged conditions. Through accelerated corrosion tests, electrochemical analysis, and exposure to aggressive marine environments, the study evaluates the long-term performance of each coating system. This research serves as a crucial guide for engineers and construction professionals in selecting the most suitable corrosion protection for reinforced concrete, thereby enhancing the durability and sustainability of infrastructure.

Keywords: corrosion, reinforced concrete, coated reinforcement, seawater exposure, electrochemical analysis, service life, corrosion prevention

Procedia PDF Downloads 51

Authors: Gayathri Devi V, Aravamudan Kannan, Amit Sircar

Abstract:

In the inner fuel cycle system of a nuclear fusion reactor, the Hydrogen Isotopes Removal System (HIRS) plays a pivoted role. It enables the effective extraction of the hydrogen isotopes from the breeder purge gas which helps to maintain the tritium breeding ratio and sustain the fusion reaction. One of the components of HIRS, Cryogenic Molecular Sieve Bed (CMSB) columns with zeolites adsorbents are considered for the physisorption of hydrogen isotopes at 1 bar and 77 K. Even though zeolites have good thermal stability and reduced activation properties making them ideal for use in nuclear reactor applications, their modest capacity for hydrogen isotopes adsorption is a cause of concern. In order to enhance the adsorbent capacity in an informed manner, it is helpful to understand the adsorption phenomena at the quantum electronic structure level. Physicochemical modifications of the adsorbent material enhances the adsorption capacity through the incorporation of active sites. This may be accomplished through the incorporation of suitable metal ions in the zeolite framework. In this work, molecular hydrogen isotopes adsorption on the active sites of functionalized zeolites are investigated in detail using Density Functional Theory (DFT) study. This involves the utilization of hybrid Generalized Gradient Approximation (GGA) with dispersion correction to account for the exchange and correlation functional of DFT. The electronic energies, adsorption enthalpy, adsorption free energy, Highest Occupied Molecular Orbital (HOMO), Lowest Unoccupied Molecular Orbital (LUMO) energies are computed on the stable 8T zeolite clusters as well as the periodic structure functionalized with different active sites. The characteristics of the dihydrogen bond with the active metal sites and the isotopic effects are also studied in detail. Validation studies with DFT will also be presented for adsorption of hydrogen on metal ion functionalized zeolites. The ab-inito screening analysis gave insights regarding the mechanism of hydrogen interaction with the zeolites under study and also the effect of the metal ion on adsorption. This detailed study provides guidelines for selection of the appropriate metal ions that may be incorporated in the zeolites framework for effective adsorption of hydrogen isotopes in the HIRS.

Keywords: adsorption enthalpy, functionalized zeolites, hydrogen isotopes, nuclear fusion, physisorption

Procedia PDF Downloads 157

Authors: Sahila Chopra, Hemdeep, Arshdeep Kaur, Raj K. Gupta

Abstract:

In recent times, we noticed an interesting and important role of non-coplanar degree-of-freedom (Φ = 00) in heavy ion reactions. Using the dynamical cluster-decay model (DCM) with Φ degree-of-freedom included, we have studied three compound systems 246Bk∗, 164Yb∗ and 105Ag∗. Here, within the DCM with pocket formula for nuclear proximity potential, we look for the effects of including compact, non-coplanar configurations (Φc = 00) on the non-compound nucleus (nCN) contribution in total fusion cross section σfus. For 246Bk∗, formed in 11B+235U and 14N+232Th reaction channels, the DCM with coplanar nuclei (Φc = 00) shows an nCN contribution for 11B+235U channel, but none for 14N+232Th channel, which on including Φ gives both reaction channels as pure compound nucleus decays. In the case of 164Yb∗, formed in 64Ni+100Mo, the small nCN effects for Φ=00 are reduced to almost zero for Φ = 00. Interestingly, however, 105Ag∗ for Φ = 00 shows a small nCN contribution, which gets strongly enhanced for Φ = 00, such that the characteristic property of PCN presents a change of behaviour, like that of a strongly fissioning superheavy element to a weakly fissioning nucleus; note that 105Ag∗ is a weakly fissioning nucleus and Psurv behaves like one for a weakly fissioning nucleus for both Φ = 00 and Φ = 00. Apparently, Φ is presenting itself like a good degree-of-freedom in the DCM.

Keywords: dynamical cluster-decay model, fusion cross sections, non-compound nucleus effects, non-coplanarity

Procedia PDF Downloads 278

Authors: Hiba Naccache, Rima Hleiss

Abstract:

Additive manufacturing AM or 3D printing is one of the pillars of Industry 4.0. Compared to traditional manufacturing, AM provides a prototype before production in order to optimize the design and avoid the stock market and uses strictly necessary material which can be recyclable, for the benefit of leaning towards local production, saving money, time and resources. Different types of AM exist and it has a broad range of applications across several industries like aerospace, automotive, medicine, education and else. The Laser Powder Bed Fusion (LPBF) is a metal AM technique that uses a laser to liquefy metal powder, layer by layer, to build a three-dimensional (3D) object. In industry 4.0 and aligned with the numbers 9 (Industry, Innovation and Infrastructure) and 12 (Responsible Production and Consumption) of the Sustainable Development Goals of the UNESCO 2030 Agenda, the AM’s manufacturers committed to minimizing the environmental impact by being sustainable in every production. The LPBF has several environmental advantages, like reduced waste production, lower energy consumption, and greater flexibility in creating components with lightweight and complex geometries. However, LPBF also have environmental drawbacks, like energy consumption, gas consumption and emissions. It is critical to recognize the environmental impacts of LPBF in order to mitigate them. To increase awareness and promote sustainable practices regarding LPBF, the researchers use the Elaboration Likelihood Model (ELM) theory where people from multiple universities in France and Qatar process information in two ways: peripherally and centrally. The peripheral campaigns use superficial cues to get attention, and the central campaigns provide clear and concise information. The authors created a seminar including a video showing LPBF production and a website with educational resources. The data is collected using questionnaire to test attitude about the public awareness before and after the seminar. The results reflected a great shift on the awareness toward LPBF and its impact on the environment. With no presence of similar research, to our best knowledge, this study will add to the literature on the sustainability of the LPBF production technique.

Keywords: additive manufacturing, laser powder bed fusion, elaboration likelihood model theory, sustainable development goals, education-awareness, France, Qatar, specific energy consumption, environmental impact, lightweight components

Procedia PDF Downloads 51

Authors: Karim Kheloufi, El Hachemi Amara

Abstract:

In the present study, a three-dimensional transient numerical model was developed to study the temperature field and cutting kerf shape during laser fusion cutting. The finite volume model has been constructed, based on the Navier–Stokes equations and energy conservation equation for the description of momentum and heat transport phenomena, and the Volume of Fluid (VOF) method for free surface tracking. The Fresnel absorption model is used to handle the absorption of the incident wave by the surface of the liquid metal and the enthalpy-porosity technique is employed to account for the latent heat during melting and solidification of the material. To model the physical phenomena occurring at the liquid film/gas interface, including momentum/heat transfer, a new approach is proposed which consists of treating friction force, pressure force applied by the gas jet and the heat absorbed by the cutting front surface as source terms incorporated into the governing equations. All these physics are coupled and solved simultaneously in Fluent CFD®. The main objective of using a transient phase change model in the current case is to simulate the dynamics and geometry of a growing laser-cutting generated kerf until it becomes fully developed. The model is used to investigate the effect of some process parameters on temperature fields and the formed kerf geometry.

Keywords: laser cutting, numerical simulation, heat transfer, fluid flow

Procedia PDF Downloads 305

Authors: Huawei Bai, Jianguo Yao, Fellow, IEEE

Abstract:

Atrial fibrillation (AF) is the most common form of heart arrhythmia and is closely associated with mortality and morbidity in heart failure, stroke, and coronary artery disease. The development of single spot optical sensors enables widespread photoplethysmography (PPG) screening, especially for AF, since it represents a more convenient and noninvasive approach. To our knowledge, most existing studies based on public and unbalanced datasets can barely handle the multiple noises sources in the real world and, also, lack interpretability. In this paper, we construct a large- scale PPG dataset using measurements collected from PPG wrist- watch devices worn by volunteers and propose an attention-based two-stream heterogeneous neural network (TSHNN). The first stream is a hybrid neural network consisting of a three-layer one-dimensional convolutional neural network (1D-CNN) and two-layer attention- based bidirectional long short-term memory (Bi-LSTM) network to learn representations from temporally sampled signals. The second stream extracts latent representations from the PPG time-frequency spectrogram using a five-layer CNN. The outputs from both streams are fed into a fusion layer for the outcome. Visualization of the attention weights learned demonstrates the effectiveness of the attention mechanism against noise. The experimental results show that the TSHNN outperforms all the competitive baseline approaches and with 98.09% accuracy, achieves state-of-the-art performance.

Keywords: PPG wearables, atrial fibrillation, feature fusion, attention mechanism, hyber network

Procedia PDF Downloads 87

Authors: Saliha Gachi, Mouloud Aissani, Fouad Boubenider

Abstract:

Friction Stir Welding (FSW) is a solid-state welding technique that can join material without melting the plates to be welded. In this work, we are interested to demonstrate the potentiality of FSW for joining the heat-treatable aluminum alloy 2024-T3 which is reputed as difficult to be welded by fusion techniques. Thereafter, the FSW joint is compared with another one obtained from a conventional fusion process Tungsten Inert Gas (TIG). FSW welds are made up using an FSW tool mounted on a milling machine. Single pass welding was applied to fabricated TIG joint. The comparison between the two processes has been made on the temperature evolution, mechanical and microstructure behavior. The microstructural examination revealed that FSW weld is composed of four zones: Base metal (BM), Heat affected zone (HAZ), Thermo-mechanical affected zone (THAZ) and the nugget zone (NZ). The NZ exhibits a recrystallized equiaxed refined grains that induce better mechanical properties and good ductility compared to TIG joint where the grains have a larger size in the welded region compared with the BM due to the elevated heat input. The microhardness results show that, in FSW weld, the THAZ contains the lowest microhardness values and increase in the NZ; however, in TIG process, the lowest values are localized on the NZ.

Keywords: friction stir welding, tungsten inert gaz, aluminum, microstructure

Procedia PDF Downloads 254

Authors: M. Kharrat, G. Moreau, Z. Aboura

Abstract:

The latest advances in the weaving industry, combined with increasingly sophisticated means of materials processing, have made it possible to produce complex 3D composite structures. Mainly used in aeronautics, composite materials with 3D architecture offer better mechanical properties than 2D reinforced composites. Nevertheless, these materials require a good understanding of their behavior. Because of the complexity of such materials, the damage mechanisms are multiple, and the scenario of their appearance and evolution depends on the nature of the exerted solicitations. The AE technique is a well-established tool for discriminating between the damage mechanisms. Suitable sensors are used during the mechanical test to monitor the structural health of the material. Relevant AE-features are then extracted from the recorded signals, followed by a data analysis using pattern recognition techniques. In order to better understand the damage scenarios of interlock composite materials, a multi-instrumentation was set-up in this work for tracking damage initiation and development, especially in the vicinity of the first significant damage, called macro-damage. The deployed instrumentation includes video-microscopy, Digital Image Correlation, Acoustic Emission (AE) and micro-tomography. In this study, a multi-variable AE data analysis approach was developed for the discrimination between the different signal classes representing the different emission sources during testing. An unsupervised classification technique was adopted to perform AE data clustering without a priori knowledge. The multi-instrumentation and the clustered data served to label the different signal families and to build a learning database. This latter is useful to construct a supervised classifier that can be used for automatic recognition of the AE signals. Several materials with different ingredients were tested under various solicitations in order to feed and enrich the learning database. The methodology presented in this work was useful to refine the damage threshold for the new generation materials. The damage mechanisms around this threshold were highlighted. The obtained signal classes were assigned to the different mechanisms. The isolation of a 'noise' class makes it possible to discriminate between the signals emitted by damages without resorting to spatial filtering or increasing the AE detection threshold. The approach was validated on different material configurations. For the same material and the same type of solicitation, the identified classes are reproducible and little disturbed. The supervised classifier constructed based on the learning database was able to predict the labels of the classified signals.

Keywords: acoustic emission, classifier, damage mechanisms, first damage threshold, interlock composite materials, pattern recognition

Procedia PDF Downloads 135

Authors: Areej Salaymeh, Loren Schwiebert, Stephen Remias, Jonathan Waddell

Abstract:

Extracting information from new data sources has emerged as a crucial task in many traffic planning processes, such as identifying traffic patterns, route planning, traffic forecasting, and locating infrastructure improvements. Given the advanced technologies used to collect Global Positioning System (GPS) data from dedicated GPS devices, GPS equipped phones, and navigation tools, intelligent data analysis methodologies are necessary to mine this raw data. In this research, an automatic detection framework is proposed to help identify and classify the locations of stopped GPS waypoints into two main categories: signalized intersections or highway congestion. The Delaunay triangulation is used to perform this assessment in the clustering phase. While most of the existing clustering algorithms need assumptions about the data distribution, the effectiveness of the Delaunay triangulation relies on triangulating geographical data points without such assumptions. Our proposed method starts by cleaning noise from the data and normalizing it. Next, the framework will identify stoppage points by calculating the traveled distance. The last step is to use clustering to form groups of waypoints for signalized traffic and highway congestion. Next, a binary classifier was applied to find distinguish highway congestion from signalized stop points. The binary classifier uses the length of the cluster to find congestion. The proposed framework shows high accuracy for identifying the stop positions and congestion points in around 99.2% of trials. We show that it is possible, using limited GPS data, to distinguish with high accuracy.

Keywords: Delaunay triangulation, clustering, intelligent transportation systems, GPS data

Procedia PDF Downloads 252

Authors: Gustavo Menezes De Souza Melo, Arnaud Heitz, Johannes Henrich Schleifenbaum

Abstract:

Additive manufacturing is a growing market that is taking over in many industries as it offers numerous advantages like new design possibilities, weight-saving solutions, ease of manufacture, and simplification of assemblies. These are all unquestionable technical or financial assets. As to the environmental aspect, additive manufacturing is often discussed whether it is the best solution to decarbonize our industries or if conventional manufacturing remains cleaner. This work presents a life cycle assessment (LCA) comparison based on the technological case of a motorbike swing-arm. We compare the original equipment manufacturer part made with conventional manufacturing (CM) methods to an additive manufacturing (AM) version printed using the laser powder bed fusion process. The AM version has been modified and optimized to achieve better dynamic performance without any regard to weight saving. Lightweight not being a priority in the creation of the 3D printed part brings us a unique perspective in this study. To achieve the LCA, we are using the open-source life cycle, and sustainability software OpenLCA combined with the ReCiPe 2016 at midpoint and endpoint level method. This allows the calculation and the presentation of the results through indicators such as global warming, water use, resource scarcity, etc. The results are then showing the relative impact of the AM version compared to the CM one and give us a key to understand and answer questions about the environmental sustainability of additive manufacturing.

Keywords: additive manufacturing, environmental impact, life cycle assessment, laser powder bed fusion

Procedia PDF Downloads 232

Authors: A: Annis Fathima, V. Vaidehi, S. Ajitha

Abstract:

Face recognition system finds many applications in surveillance and human computer interaction systems. As the applications using face recognition systems are of much importance and demand more accuracy, more robustness in the face recognition system is expected with less computation time. In this paper, a hybrid approach for face recognition combining Gabor Wavelet and Linear Discriminant Analysis (HGWLDA) is proposed. The normalized input grayscale image is approximated and reduced in dimension to lower the processing overhead for Gabor filters. This image is convolved with bank of Gabor filters with varying scales and orientations. LDA, a subspace analysis techniques are used to reduce the intra-class space and maximize the inter-class space. The techniques used are 2-dimensional Linear Discriminant Analysis (2D-LDA), 2-dimensional bidirectional LDA ((2D)2LDA), Weighted 2-dimensional bidirectional Linear Discriminant Analysis (Wt (2D)2 LDA). LDA reduces the feature dimension by extracting the features with greater variance. k-Nearest Neighbour (k-NN) classifier is used to classify and recognize the test image by comparing its feature with each of the training set features. The HGWLDA approach is robust against illumination conditions as the Gabor features are illumination invariant. This approach also aims at a better recognition rate using less number of features for varying expressions. The performance of the proposed HGWLDA approaches is evaluated using AT&T database, MIT-India face database and faces94 database. It is found that the proposed HGWLDA approach provides better results than the existing Gabor approach.

Keywords: face recognition, Gabor wavelet, LDA, k-NN classifier

Procedia PDF Downloads 449

Authors: Shalini Rankawat, Mansi Rankawat, Rahul Dubey, Mazad Zaveri

Abstract:

Physiological signals such as electrocardiogram (ECG) and arterial blood pressure (ABP) in the intensive care unit (ICU) are often seriously corrupted by noise, artifacts, and missing data, which lead to errors in the estimation of heart rate (HR) and incidences of false alarm from ICU monitors. Clinical support in ICU requires most reliable heart rate estimation. Cardiac activity, because of its relatively high electrical energy, may introduce artifacts in Electroencephalogram (EEG), Electrooculogram (EOG), and Electromyogram (EMG) recordings. This paper presents a robust heart rate estimation method by detection of R-peaks of ECG artifacts in EEG, EMG & EOG signals, using energy-based function and a novel Signal Quality Index (SQI) assessment technique. SQIs of physiological signals (EEG, EMG, & EOG) were obtained by correlation of nonlinear energy operator (teager energy) of these signals with either ECG or ABP signal. HR is estimated from ECG, ABP, EEG, EMG, and EOG signals from separate Kalman filter based upon individual SQIs. Data fusion of each HR estimate was then performed by weighing each estimate by the Kalman filters’ SQI modified innovations. The fused signal HR estimate is more accurate and robust than any of the individual HR estimate. This method was evaluated on MIMIC II data base of PhysioNet from bedside monitors of ICU patients. The method provides an accurate HR estimate even in the presence of noise and artifacts.

Keywords: ECG, ABP, EEG, EMG, EOG, ECG artifacts, Teager-Kaiser energy, heart rate, signal quality index, Kalman filter, data fusion

Procedia PDF Downloads 673

Authors: B. Elshafei, X. Mao

Abstract:

The demand for renewable energy is significantly increasing, major investments are being supplied to the wind power generation industry as a leading source of clean energy. The wind energy sector is entirely dependable and driven by the prediction of wind speed, which by the nature of wind is very stochastic and widely random. This s0tudy employs deep multi-fidelity Gaussian process regression, used to predict wind speeds for medium term time horizons. Data of the RUNE experiment in the west coast of Denmark were provided by the Technical University of Denmark, which represent the wind speed across the study area from the period between December 2015 and March 2016. The study aims to investigate the effect of pre-processing the data by denoising the signal using empirical wavelet transform (EWT) and engaging the vector components of wind speed to increase the number of input data layers for data fusion using deep multi-fidelity Gaussian process regression (GPR). The outcomes were compared using root mean square error (RMSE) and the results demonstrated a significant increase in the accuracy of predictions which demonstrated that using vector components of the wind speed as additional predictors exhibits more accurate predictions than strategies that ignore them, reflecting the importance of the inclusion of all sub data and pre-processing signals for wind speed forecasting models.

Keywords: data fusion, Gaussian process regression, signal denoise, temporal extrapolation

Procedia PDF Downloads 114

Authors: Bliss Singhal

Abstract:

Machine learning (ML) is a branch of Artificial Intelligence (AI) where computers analyze data and find patterns in the data. The study focuses on the detection of metastatic cancer using ML. Metastatic cancer is the stage where cancer has spread to other parts of the body and is the cause of approximately 90% of cancer-related deaths. Normally, pathologists spend hours each day to manually classifying whether tumors are benign or malignant. This tedious task contributes to mislabeling metastasis being over 60% of the time and emphasizes the importance of being aware of human error and other inefficiencies. ML is a good candidate to improve the correct identification of metastatic cancer, saving thousands of lives and can also improve the speed and efficiency of the process, thereby taking fewer resources and time. So far, the deep learning methodology of AI has been used in research to detect cancer. This study is a novel approach to determining the potential of using preprocessing algorithms combined with classification algorithms in detecting metastatic cancer. The study used two preprocessing algorithms: principal component analysis (PCA) and the genetic algorithm, to reduce the dimensionality of the dataset and then used three classification algorithms: logistic regression, decision tree classifier, and k-nearest neighbors to detect metastatic cancer in the pathology scans. The highest accuracy of 71.14% was produced by the ML pipeline comprising of PCA, the genetic algorithm, and the k-nearest neighbor algorithm, suggesting that preprocessing and classification algorithms have great potential for detecting metastatic cancer.

Keywords: breast cancer, principal component analysis, genetic algorithm, k-nearest neighbors, decision tree classifier, logistic regression

Procedia PDF Downloads 57

Authors: Preecha Yupapin And Somnath

Abstract:

From the emptiness, the vibration induces the fractal, and the strings are formed. From which the first elementary particle groups, known as quarks, were established. The neutrino and electron are created by them. More elementary particles and life are formed by organic and inorganic substances. The universe is constructed, from which the multi-universe has formed in the same way. universe assumes that the intense energy has escaped from the singularity cone from the multi-universes. Initially, the single mass energy is confined, from which it is disturbed by the space-time distortion. It splits into the entangled pair, where the circular motion is established. It will consider one side of the entangled pair, where the fusion energy of the strong coupling force has formed. The growth of the fusion energy has the quantum physic phenomena, where the moving of the particle along the circumference with a speed faster than light. It introduces the wave-particle duality aspect, which will be saturated at the stopping point. It will be re-run again and again without limitation, which can say that the universe has been created and expanded. The Bose-Einstein condensate (BEC) is released through the singularity by the wormhole, which will be condensed to become a mass associated with the Sun's size. It will circulate(orbit) along the Sun. the consideration of the uncertainty principle is applied, from which the breath control is followed by the uncertainty condition ∆p∆x=∆E∆t~ℏ. The flowing in-out air into a body via a nose has applied momentum and energy control respecting the movement and time, in which the target is that the distortion of space-time will have vanished. Finally, the body is clean which can go to the next procedure, where the mind can escape from the body by the speed of light. However, the borderline between contemplation to being an Arahant is a vacuum, which will be explained.

Keywords: space-time, relativity, enlightenment, emptiness

Procedia PDF Downloads 41

Authors: Asma Omri, Noureddine Benothman, Sofiane Sayahi, Fethi Tlili, Hichem Besbes

Abstract:

Cycling, a popular mode of transportation, can also be perilous due to cyclists' vulnerability to collisions with vehicles and obstacles. This paper presents an innovative cyclist safety system based on radar technology designed to offer real-time collision risk warnings to cyclists. The system incorporates a low-power radar sensor affixed to the bicycle and connected to a microcontroller. It leverages radar point cloud detections, a clustering algorithm, and a supervised classifier. These algorithms are optimized for efficiency to run on the TI’s AWR 1843 BOOST radar, utilizing a coarse classification approach distinguishing between cars, trucks, two-wheeled vehicles, and other objects. To enhance the performance of clustering techniques, we propose a 2-Level clustering approach. This approach builds on the state-of-the-art Density-based spatial clustering of applications with noise (DBSCAN). The objective is to first cluster objects based on their velocity, then refine the analysis by clustering based on position. The initial level identifies groups of objects with similar velocities and movement patterns. The subsequent level refines the analysis by considering the spatial distribution of these objects. The clusters obtained from the first level serve as input for the second level of clustering. Our proposed technique surpasses the classical DBSCAN algorithm in terms of geometrical metrics, including homogeneity, completeness, and V-score. Relevant cluster features are extracted and utilized to classify objects using an SVM classifier. Potential obstacles are identified based on their velocity and proximity to the cyclist. To optimize the system, we used the View of Delft dataset for hyperparameter selection and SVM classifier training. The system's performance was assessed using our collected dataset of radar point clouds synchronized with a camera on an Nvidia Jetson Nano board. The radar-based cyclist safety system is a practical solution that can be easily installed on any bicycle and connected to smartphones or other devices, offering real-time feedback and navigation assistance to cyclists. We conducted experiments to validate the system's feasibility, achieving an impressive 85% accuracy in the classification task. This system has the potential to significantly reduce the number of accidents involving cyclists and enhance their safety on the road.

Keywords: 2-level clustering, coarse classification, cyclist safety, warning system based on radar technology

Procedia PDF Downloads 55

Authors: Jinge Liu, Shuyuan Min, Bingchuan Liu, Bangzhao Yin, Bo Peng, Peng Wen, Yun Tian

Abstract:

WE43 magnesium alloy can be additively manufactured via laser powder bed fusion (LPBF) for biodegradable applications, but the as-built WE43 exhibits an excessively rapid corrosion rate. High-temperature oxidation (HTO) was performed on the as-built WE43 to improve its biodegradation behavior. A sandwich structure including an oxide layer at the surface, a transition layer in the middle, and the matrix was generated influenced by the oxidation reaction and diffusion of RE atoms when heated at 525 ℃for 8 hours. The oxide layer consisted of Y₂O₃ and Nd₂O₃ oxides with a thickness of 2-3 μm. The transition layer is composed of α-Mg and Y₂O₃ with a thickness of 60-70 μm, while Mg24RE5 could be observed except α-Mg and Y₂O₃. The oxide layer and transition layer appeared to have an effective passivation effect. The as-built WE43 lost 40% weight after the in vitro immersion test for three days and finally broke into debris after seven days of immersion. The high-temperature oxidation samples kept the structural integrity and lost only 6.88 % weight after 28-day immersion. The corrosion rate of HTO samples was significantly controlled, which improved the biocompatibility of the as-built WE43 at the same time. The samples after HTO had better osteogenic capability according to ALP activity. Moreover, as built WE43 performed unqualified in cell adhesion and hemolytic test due to its excessively rapid corrosion rate. While as for HTO samples, cells adhered well, and the hemolysis ratio was only 1.59%.

Keywords: laser powder bed fusion, biodegradable metal, high temperature oxidation, biodegradation behavior, WE43

Procedia PDF Downloads 78

Authors: Flavio Cannavo

Abstract:

Continuous evaluation of the status of potentially hazardous volcanos plays a key role for civil protection purposes. The importance of monitoring volcanic activity, especially for energetic paroxysms that usually come with tephra emissions, is crucial not only for exposures to the local population but also for airline traffic. Presently, real-time surveillance of most volcanoes worldwide is essentially delegated to one or more human experts in volcanology, who interpret data coming from different kind of monitoring networks. Unfavorably, the high nonlinearity of the complex and coupled volcanic dynamics leads to a large variety of different volcanic behaviors. Moreover, continuously measured parameters (e.g. seismic, deformation, infrasonic and geochemical signals) are often not able to fully explain the ongoing phenomenon, thus making the fast volcano state assessment a very puzzling task for the personnel on duty at the control rooms. With the aim of aiding the personnel on duty in volcano surveillance, here we introduce a system based on an ensemble of data-driven classifiers to infer automatically the ongoing volcano status from all the available different kind of measurements. The system consists of a heterogeneous set of independent classifiers, each one built with its own data and algorithm. Each classifier gives an output about the volcanic status. The ensemble technique allows weighting the single classifier output to combine all the classifications into a single status that maximizes the performance. We tested the model on the Mt. Etna (Italy) case study by considering a long record of multivariate data from 2011 to 2015 and cross-validated it. Results indicate that the proposed model is effective and of great power for decision-making purposes.

Keywords: Bayesian networks, expert system, mount Etna, volcano monitoring

Procedia PDF Downloads 221

Authors: Roza Dzierzak, Waldemar Wojcik, Piotr Kacejko

Abstract:

Analysis of the texture of medical images consists of determining the parameters and characteristics of the examined tissue. The main goal is to assign the analyzed area to one of two basic groups: as a healthy tissue or a tissue with pathological changes. The CT images of the thoracic lumbar spine from 15 healthy patients and 15 with confirmed osteoporosis were used for the analysis. As a result, 120 samples with dimensions of 50x50 pixels were obtained. The set of features has been obtained based on the histogram, gradient, run-length matrix, co-occurrence matrix, autoregressive model, and Haar wavelet. As a result of the image analysis, 290 descriptors of textural features were obtained. The dimension of the space of features was reduced by the use of three selection methods: Fisher coefficient (FC), mutual information (MI), minimization of the classification error probability and average correlation coefficients between the chosen features minimization of classification error probability (POE) and average correlation coefficients (ACC). Each of them returned ten features occupying the initial place in the ranking devised according to its own coefficient. As a result of the Fisher coefficient and mutual information selections, the same features arranged in a different order were obtained. In both rankings, the 50% percentile (Perc.50%) was found in the first place. The next selected features come from the co-occurrence matrix. The sets of features selected in the selection process were evaluated using six classification tree methods. These were: decision stump (DS), Hoeffding tree (HT), logistic model trees (LMT), random forest (RF), random tree (RT) and reduced error pruning tree (REPT). In order to assess the accuracy of classifiers, the following parameters were used: overall classification accuracy (ACC), true positive rate (TPR, classification sensitivity), true negative rate (TNR, classification specificity), positive predictive value (PPV) and negative predictive value (NPV). Taking into account the classification results, it should be stated that the best results were obtained for the Hoeffding tree and logistic model trees classifiers, using the set of features selected by the POE + ACC method. In the case of the Hoeffding tree classifier, the highest values of three parameters were obtained: ACC = 90%, TPR = 93.3% and PPV = 93.3%. Additionally, the values of the other two parameters, i.e., TNR = 86.7% and NPV = 86.6% were close to the maximum values obtained for the LMT classifier. In the case of logistic model trees classifier, the same ACC value was obtained ACC=90% and the highest values for TNR=88.3% and NPV= 88.3%. The values of the other two parameters remained at a level close to the highest TPR = 91.7% and PPV = 91.6%. The results obtained in the experiment show that the use of classification trees is an effective method of classification of texture features. This allows identifying the conditions of the spongy tissue for healthy cases and those with the porosis.

Keywords: classification, feature selection, texture analysis, tree algorithms

Procedia PDF Downloads 147

Authors: Ping Li, Bing Feng, Junpu Zhao, Xudong Xie, Dangpeng Xu, Kuixing Zheng, Qihua Zhu, Xiaofeng Wei

Abstract:

In laser driven inertial confinement fusion (ICF), the control of the temporal shape of the laser pulse is a key point to ensure an optimal interaction of laser-target. One of the main difficulties in controlling the temporal shape is the foot part control accuracy of high contrast pulse. Based on the analysis of pulse perturbation in the process of amplification and frequency conversion in high power lasers, an approach of beam spatio-temporal multiplexing is proposed to improve the control precision of high contrast pulse. In the approach, the foot and peak part of high contrast pulse are controlled independently, which propagate separately in the near field, and combine together in the far field to form the required pulse shape. For high contrast pulse, the beam area ratio of the two parts is optimized, and then beam fluence and intensity of the foot part are increased, which brings great convenience to the control of pulse. Meanwhile, the near field distribution of the two parts is also carefully designed to make sure their F-numbers are the same, which is another important parameter for laser-target interaction. The integrated calculation results show that for a pulse with a contrast of up to 500, the deviation of foot part can be improved from 20% to 5% by using beam spatio-temporal multiplexing approach with beam area ratio of 1/20, which is almost the same as that of peak part. The research results are expected to bring a breakthrough in power balance of high power laser facility.

Keywords: inertial confinement fusion, laser pulse control, beam spatio-temporal multiplexing, power balance

Procedia PDF Downloads 131

Authors: Gertraud Koch, Teresa Stumpf, Alejandra Tijerina García

Abstract:

Discourse analysis research approaches belong to the central research strategies applied throughout the humanities; they focus on the countless forms and ways digital texts and images shape present-day notions of the world. Despite the constantly growing number of relevant digital, multimodal discourse resources, digital humanities (DH) methods are thus far not systematically developed and accessible for discourse analysis approaches. Specifically, the significance of multimodality and meaning plurality modelling are yet to be sufficiently addressed. In order to address this research gap, the D-WISE project aims to develop a prototypical working environment as digital support for the sociology of knowledge approach to discourse analysis and new IT-analysis approaches for the use of context-oriented embedding representations. Playing an essential role throughout our research endeavor is the constant optimization of hermeneutical methodology in the use of (semi)automated processes and their corresponding epistemological reflection. Among the discourse analyses, the sociology of knowledge approach to discourse analysis is characterised by the reconstructive and accompanying research into the formation of knowledge systems in social negotiation processes. The approach analyses how dominant understandings of a phenomenon develop, i.e., the way they are expressed and consolidated by various actors in specific arenas of discourse until a specific understanding of the phenomenon and its socially accepted structure are established. This article presents insights and initial findings from D-WISE, a joint research project running since 2021 between the Institute of Anthropological Studies in Culture and History and the Language Technology Group of the Department of Informatics at the University of Hamburg. As an interdisciplinary team, we develop central innovations with regard to the availability of relevant DH applications by building up a uniform working environment, which supports the procedure of the sociology of knowledge approach to discourse analysis within open corpora and heterogeneous, multimodal data sources for researchers in the humanities. We are hereby expanding the existing range of DH methods by developing contextualized embeddings for improved modelling of the plurality of meaning and the integrated processing of multimodal data. The alignment of this methodological and technical innovation is based on the epistemological working methods according to grounded theory as a hermeneutic methodology. In order to systematically relate, compare, and reflect the approaches of structural-IT and hermeneutic-interpretative analysis, the discourse analysis is carried out both manually and digitally. Using the example of current discourses on digitization in the healthcare sector and the associated issues regarding data protection, we have manually built an initial data corpus of which the relevant actors and discourse positions are analysed in conventional qualitative discourse analysis. At the same time, we are building an extensive digital corpus on the same topic based on the use and further development of entity-centered research tools such as topic crawlers and automated newsreaders. In addition to the text material, this consists of multimodal sources such as images, video sequences, and apps. In a blended reading process, the data material is filtered, annotated, and finally coded with the help of NLP tools such as dependency parsing, named entity recognition, co-reference resolution, entity linking, sentiment analysis, and other project-specific tools that are being adapted and developed. The coding process is carried out (semi-)automated by programs that propose coding paradigms based on the calculated entities and their relationships. Simultaneously, these can be specifically trained by manual coding in a closed reading process and specified according to the content issues. Overall, this approach enables purely qualitative, fully automated, and semi-automated analyses to be compared and reflected upon.

Keywords: entanglement of structural IT and hermeneutic-interpretative analysis, multimodality, plurality of meaning, sociology of knowledge approach to discourse analysis

Procedia PDF Downloads 205

Authors: Qiaosi Li, Frankie Kwan Kit Wong, Tung Fung

Abstract:

Lightweight unmanned aerial vehicle (UAV) loading with novel sensors offers a low cost approach for data acquisition in complex environment. This study established a framework for applying UAV system in complex environment quick mapping and assessed the performance of UAV-based hyperspectral image and digital surface model (DSM) derived from photogrammetric point clouds for 13 species classification in wetland area Mai Po Inner Deep Bay Ramsar Site, Hong Kong. The study area was part of shallow bay with flat terrain and the major species including reedbed and four mangroves: Kandelia obovata, Aegiceras corniculatum, Acrostichum auerum and Acanthus ilicifolius. Other species involved in various graminaceous plants, tarbor, shrub and invasive species Mikania micrantha. In particular, invasive species climbed up to the mangrove canopy caused damage and morphology change which might increase species distinguishing difficulty. Hyperspectral images were acquired by Headwall Nano sensor with spectral range from 400nm to 1000nm and 0.06m spatial resolution image. A sequence of multi-view RGB images was captured with 0.02m spatial resolution and 75% overlap. Hyperspectral image was corrected for radiative and geometric distortion while high resolution RGB images were matched to generate maximum dense point clouds. Furtherly, a 5 cm grid digital surface model (DSM) was derived from dense point clouds. Multiple feature reduction methods were compared to identify the efficient method and to explore the significant spectral bands in distinguishing different species. Examined methods including stepwise discriminant analysis (DA), support vector machine (SVM) and minimum noise fraction (MNF) transformation. Subsequently, spectral subsets composed of the first 20 most importance bands extracted by SVM, DA and MNF, and multi-source subsets adding extra DSM to 20 spectrum bands were served as input in maximum likelihood classifier (MLC) and SVM classifier to compare the classification result. Classification results showed that feature reduction methods from best to worst are MNF transformation, DA and SVM. MNF transformation accuracy was even higher than all bands input result. Selected bands frequently laid along the green peak, red edge and near infrared. Additionally, DA found that chlorophyll absorption red band and yellow band were also important for species classification. In terms of 3D data, DSM enhanced the discriminant capacity among low plants, arbor and mangrove. Meanwhile, DSM largely reduced misclassification due to the shadow effect and morphological variation of inter-species. In respect to classifier, nonparametric SVM outperformed than MLC for high dimension and multi-source data in this study. SVM classifier tended to produce higher overall accuracy and reduce scattered patches although it costs more time than MLC. The best result was obtained by combining MNF components and DSM in SVM classifier. This study offered a precision species distribution survey solution for inaccessible wetland area with low cost of time and labour. In addition, findings relevant to the positive effect of DSM as well as spectral feature identification indicated that the utility of UAV-borne hyperspectral and photogrammetry deriving 3D data is promising in further research on wetland species such as bio-parameters modelling and biological invasion monitoring.

Keywords: digital surface model (DSM), feature reduction, hyperspectral, photogrammetric point cloud, species mapping, unmanned aerial vehicle (UAV)

Procedia PDF Downloads 232

Authors: Fernanda M. Assef, Maria Teresinha A. Steiner

Abstract:

The aim of this paper is to compare and discuss better classifier algorithm options for credit risk assessment by applying different Machine Learning techniques. Using records from a Brazilian financial institution, this study uses a database of 5,432 companies that are clients of the bank, where 2,600 clients are classified as non-defaulters, 1,551 are classified as defaulters and 1,281 are temporarily defaulters, meaning that the clients are overdue on their payments for up 180 days. For each case, a total of 15 attributes was considered for a one-against-all assessment using four different techniques: Artificial Neural Networks Multilayer Perceptron (ANN-MLP), Artificial Neural Networks Radial Basis Functions (ANN-RBF), Logistic Regression (LR) and finally Support Vector Machines (SVM). For each method, different parameters were analyzed in order to obtain different results when the best of each technique was compared. Initially the data were coded in thermometer code (numerical attributes) or dummy coding (for nominal attributes). The methods were then evaluated for each parameter and the best result of each technique was compared in terms of accuracy, false positives, false negatives, true positives and true negatives. This comparison showed that the best method, in terms of accuracy, was ANN-RBF (79.20% for non-defaulter classification, 97.74% for defaulters and 75.37% for the temporarily defaulter classification). However, the best accuracy does not always represent the best technique. For instance, on the classification of temporarily defaulters, this technique, in terms of false positives, was surpassed by SVM, which had the lowest rate (0.07%) of false positive classifications. All these intrinsic details are discussed considering the results found, and an overview of what was presented is shown in the conclusion of this study.

Keywords: artificial neural networks (ANNs), classifier algorithms, credit risk assessment, logistic regression, machine Learning, support vector machines

Procedia PDF Downloads 79

Authors: Samhita Bharadwaj

Abstract:

This is an empirical study of classifiers in Assamese and Bodo, two genetically unrelated languages of India. The objective of the paper is to address the language contact between Assamese and Bodo as reflected in classifiers. The data has been collected through fieldwork in Bodo recording narratives and folk tales and eliciting specific data from the speakers. The data for Assamese is self-produced as native speaker of the language. Assamese is the easternmost New-Indo-Aryan (henceforth NIA) language mainly spoken in the Brahmaputra valley of Assam and some other north-eastern states of India. It is the lingua franca of Assam and is creolised in the neighbouring state of Nagaland. Bodo, on the other hand, is a Tibeto-Burman (henceforth TB) language of the Bodo-Garo group. It has the highest number of speakers among the TB languages of Assam. However, compared to Assamese, it is still a lesser documented language and due to the prestige of Assamese, all the Bodo speakers are fluent bi-lingual in Assamese, though the opposite isn’t the case. With this context, classifiers, a characteristic phenomenon of TB languages, but not so much of NIA languages, presents an interesting case study on language contact caused by bilingualism. Assamese, as a result of its language contact with the TB languages which are rich in classifiers; has developed the richest classifier system among the IA languages in India. Yet, as a part of rampant borrowing of Assamese words and patterns into Bodo; Bodo is seen to borrow even Assamese classifiers into its system. This paper analyses the borrowed classifiers of Bodo and finds the route of this borrowing phenomenon in the number system of the languages. As the Bodo speakers start replacing the higher numbers from five with Assamese ones, they also choose the Assamese classifiers to attach to these numbers. Thus, the partial loss of number in Bodo as a result of language contact and bilingualism in Assamese is found to be the reason behind the borrowing of classifiers in Bodo. The significance of the study lies in exploring an interesting aspect of language contact in Assam. It is hoped that this will attract further research on bilingualism and classifiers in Assam.

Keywords: Assamese, bi-lingual, Bodo, borrowing, classifier, language contact

Procedia PDF Downloads 195

Authors: Aynur Aker, Hasan Kaya

Abstract:

In recent years, the use of the aluminum based alloys in the industry and technology are increasing. Alloying elements in aluminum have further been improving the strength and stiffness properties that provide superior compared to other metals. In this study, investigation of physical properties (microstructure, microhardness, tensile strength, electrical conductivity and thermal properties) in the Al-12.6wt.%Si-%2wt.Ni ternary alloy were investigated. Al-Si-Ni alloy was prepared in a graphite crucible under vacuum atmosphere. The samples were directionally solidified upwards with different growth rate (V) at constant temperature gradient G (7.73 K/mm). The microstructures (flake spacings, λ), microhardness (HV), ultimate tensile strength, electrical resistivity and thermal properties enthalpy of fusion and specific heat and melting temperature) of the samples were measured. Influence of the growth rate and flake spacings on microhardness, ultimate tensile strength and electrical resistivity were investigated and relationships between them were experimentally obtained by using regression analysis. According to results, λ values decrease with increasing V, but microhardness, ultimate tensile strength, electrical resistivity values increase with increasing V. Variations of electrical resistivity for cast samples with the temperature in the range of 300-1200 K were also measured by using a standard dc four-point probe technique. The enthalpy of fusion and specific heat for the same alloy was also determined by means of differential scanning calorimeter (DSC) from heating trace during the transformation from liquid to solid. The results obtained in this work were compared with the previous similar experimental results obtained for binary and ternary alloys.

Keywords: electrical resistivity, enthalpy, microhardness, solidification, tensile stress

Procedia PDF Downloads 353

Authors: Eric Yi-Hsiu Huang, Meng-Chun Kao, Wen-Chuan Kuo

Abstract:

For every laparoscopic surgery, a safe pneumoperitoneumcreation (gaining access to the peritoneal cavity) is the first and essential step. However, closed pneumoperitoneum is usually obtained by blind insertion of a Veress needle into the peritoneal cavity, which may carry potential risks suchas bowel and vascular injury.Until now, there remains no definite measure to visually confirm the position of the needle tip inside the peritoneal cavity. Therefore, this study established an image-guided Veress needle method by combining a fiber probe with optical coherence tomography (OCT). An algorithm was also proposed for determining the exact location of the needle tip through the acquisition of OCT images. Our method not only generates a series of “live” two-dimensional (2D) images during the needle puncture toward the peritoneal cavity but also can eliminate operator variation in image judgment, thus improving peritoneal access safety. This study was approved by the Ethics Committee of Taipei Veterans General Hospital (Taipei VGH IACUC 2020-144). A total of 2400 in vivo OCT images, independent of each other, were acquired from experiments of forty peritoneal punctures on two piglets. Characteristic OCT image patterns could be observed during the puncturing process. The ROC curve demonstrates the discrimination capability of these quantitative image features of the classifier, showing the accuracy of the classifier for determining the inside vs. outside of the peritoneal was 98% (AUC=0.98). In summary, the present study demonstrates the ability of the combination of our proposed automatic identification method and OCT imaging for automatically and objectively identifying the location of the needle tip. OCT images translate the blind closed technique of peritoneal access into a visualized procedure, thus improving peritoneal access safety.

Keywords: pneumoperitoneum, optical coherence tomography, automatic identification, veress needle

Procedia PDF Downloads 104

Authors: Bushra Zafar, Usman Qamar

Abstract:

Large data sample size and dimensions render the effectiveness of conventional data mining methodologies. A data mining technique are important tools for collection of knowledgeable information from variety of databases and provides supervised learning in the form of classification to design models to describe vital data classes while structure of the classifier is based on class attribute. Classification efficiency and accuracy are often influenced to great extent by noisy and undesirable features in real application data sets. The inherent natures of data set greatly masks its quality analysis and leave us with quite few practical approaches to use. To our knowledge first time, we present a new approach for investigation of structure and quality of datasets by providing a targeted analysis of localization of noisy and irrelevant features of data sets. Machine learning is based primarily on feature selection as pre-processing step which offers us to select few features from number of features as a subset by reducing the space according to certain evaluation criterion. The primary objective of this study is to trim down the scope of the given data sample by searching a small set of important features which may results into good classification performance. For this purpose, a heuristic for wrapper-based feature selection using genetic algorithm and for discriminative feature selection an external classifier are used. Selection of feature based on its number of occurrence in the chosen chromosomes. Sample dataset has been used to demonstrate proposed idea effectively. A proposed method has improved average accuracy of different datasets is about 95%. Experimental results illustrate that proposed algorithm increases the accuracy of prediction of different diseases.

Keywords: data mining, generic algorithm, KNN algorithms, wrapper based feature selection

Procedia PDF Downloads 298

Authors: Shrabani Ghosh

Abstract:

Automatic offensive language detection in social media has become a stirring task in today's NLP. Manual Offensive language detection is tedious and laborious work where automatic methods based on machine learning are only alternatives. Previous works have done sentiment analysis over social media in different ways such as supervised, semi-supervised, and unsupervised manner. Domain adaptation in a semi-supervised way has also been explored in NLP, where the source domain and the target domain are different. In domain adaptation, the source domain usually has a large amount of labeled data, while only a limited amount of labeled data is available in the target domain. Pretrained transformers like BERT, RoBERTa models are fine-tuned to perform text classification in an unsupervised manner to perform further pre-train masked language modeling (MLM) tasks. In previous work, hate speech detection has been explored in Gab.ai, which is a free speech platform described as a platform of extremist in varying degrees in online social media. In domain adaptation process, Twitter data is used as the source domain, and Gab data is used as the target domain. The performance of domain adaptation also depends on the cross-domain similarity. Different distance measure methods such as L2 distance, cosine distance, Maximum Mean Discrepancy (MMD), Fisher Linear Discriminant (FLD), and CORAL have been used to estimate domain similarity. Certainly, in-domain distances are small, and between-domain distances are expected to be large. The previous work finding shows that pretrain masked language model (MLM) fine-tuned with a mixture of posts of source and target domain gives higher accuracy. However, in-domain performance of the hate classifier on Twitter data accuracy is 71.78%, and out-of-domain performance of the hate classifier on Gab data goes down to 56.53%. Recently self-supervised learning got a lot of attention as it is more applicable when labeled data are scarce. Few works have already been explored to apply self-supervised learning on NLP tasks such as sentiment classification. Self-supervised language representation model ALBERTA focuses on modeling inter-sentence coherence and helps downstream tasks with multi-sentence inputs. Self-supervised attention learning approach shows better performance as it exploits extracted context word in the training process. In this work, a self-supervised attention mechanism has been proposed to detect hate speech on Gab.ai. This framework initially classifies the Gab dataset in an attention-based self-supervised manner. On the next step, a semi-supervised classifier trained on the combination of labeled data from the first step and unlabeled data. The performance of the proposed framework will be compared with the results described earlier and also with optimized outcomes obtained from different optimization techniques.

Keywords: attention learning, language model, offensive language detection, self-supervised learning

Procedia PDF Downloads 84