Search results for: automatic classification

Authors: Ling Qi, Matloob Khushi, Josiah Poon

Abstract:

This paper introduces a pre-trained Masked Candlestick Model (MCM) for trading time-series data. The pre-trained model is based on three core designs. First, we convert trading price data at each data point as a set of normalized elements and produce embeddings of each element. Second, we generate a masked sequence of such embedded elements as inputs for self-supervised learning. Third, we use the encoder mechanism from the transformer to train the inputs. The masked model learns the contextual relations among the sequence of embedded elements, which can aid downstream classification tasks. To evaluate the performance of the pre-trained model, we fine-tune MCM for three different downstream classification tasks to predict future price trends. The fine-tuned models achieved better accuracy rates for all three tasks than the baseline models. To better analyze the effectiveness of MCM, we test the same architecture for three currency pairs, namely EUR/GBP, AUD/USD, and EUR/JPY. The experimentation results demonstrate MCM’s effectiveness on all three currency pairs and indicate the MCM’s capability for signal extraction from trading data.

Keywords: masked language model, transformer, time series prediction, trading prediction, embedding, transfer learning, self-supervised learning

Procedia PDF Downloads 128

Authors: G. C. Tikkiwal, Mukesh Upadhyay

Abstract:

During the surveillance operations at war or peace time, the Radar operator gets a scatter of targets over the screen. This may be a tracked vehicle like tank vis-à-vis T72, BMP etc, or it may be a wheeled vehicle like ALS, TATRA, 2.5Tonne, Shaktiman or moving army, moving convoys etc. The Radar operator selects one of the promising targets into Single Target Tracking (STT) mode. Once the target is locked, the operator gets a typical audible signal into his headphones. With reference to the gained experience and training over the time, the operator then identifies the random target. But this process is cumbersome and is solely dependent on the skills of the operator, thus may lead to misclassification of the object. In this paper we present a technique using mathematical and statistical methods like Fast Fourier Transformation (FFT) and Principal Component Analysis (PCA) to identify the random objects. The process of classification is based on transforming the audible signature of target into music octave-notes. The whole methodology is then automated by developing suitable software. This automation increases the efficiency of identification of the random target by reducing the chances of misclassification. This whole study is based on live data.

Keywords: radar target, fft, principal component analysis, eigenvector, octave-notes, dsp

Procedia PDF Downloads 346

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

Abstract:

In the precision agriculture area, one of the main tasks is the automated detection of diseases in crops. Machine Learning algorithms have been studied in recent decades for such tasks in view of their potential for improving economic outcomes that automated disease detection may attain over crop fields. The latest generation of deep learning convolution neural networks has presented significant results in the area of image classification. In this way, this work has tested the implementation of an architecture of deep learning convolution neural network for the detection of diseases in different types of crops. A data augmentation strategy was used to meet the requirements of the algorithm implemented with a deep learning framework. Two test scenarios were deployed. The first scenario implemented a neural network under images extracted from a controlled environment while the second one took images both from the field and the controlled environment. The results evaluated the generalisation capacity of the neural networks in relation to the two types of images presented. Results yielded a general classification accuracy of 59% in scenario 1 and 96% in scenario 2.

Keywords: convolutional neural networks, deep learning, disease detection, precision agriculture

Procedia PDF Downloads 259

Authors: David Pham, Yongfeng Zhang

Abstract:

Graphs are an important structure for data storage and computation. Recent years have seen the success of deep learning on graphs such as Graph Neural Networks (GNN) on various data mining and machine learning tasks. However, most of the deep learning models on graphs cannot easily explain their predictions and are thus often labelled as “black boxes.” For example, Graph Attention Network (GAT) is a frequently used GNN architecture, which adopts an attention mechanism to carefully select the neighborhood nodes for message passing and aggregation. However, it is difficult to explain why certain neighbors are selected while others are not and how the selected neighbors contribute to the final classification result. In this paper, we present a graph learning model called Explainable Graph Attention Network (XGAT), which integrates graph attention modeling and explainability. We use a single model to target both the accuracy and explainability of problem spaces and show that in the context of graph attention modeling, we can design a unified neighborhood selection strategy that selects appropriate neighbor nodes for both better accuracy and enhanced explainability. To justify this, we conduct extensive experiments to better understand the behavior of our model under different conditions and show an increase in both accuracy and explainability.

Keywords: explainable AI, graph attention network, graph neural network, node classification

Procedia PDF Downloads 199

Authors: Joseph Wolff, Jeffrey Eilbott

Abstract:

Autism Spectrum Disorders (ASD) are a spectrum of social disorders characterized by deficits in social communication, verbal ability, and interaction that can vary in severity. In recent years, researchers have used magnetic resonance imaging (MRI) to help detect how neural patterns in individuals with ASD differ from those of neurotypical (NT) controls for classification purposes. This study analyzed the classification of ASD within males and females using functional MRI data. Functional connectivity (FC) correlations among brain regions were used as feature inputs for machine learning algorithms. Analysis was performed on 558 cases from the Autism Brain Imaging Data Exchange (ABIDE) I dataset. When trained specifically on females, the algorithm underperformed in classifying the ASD subset of our testing population. Although the subject size was relatively smaller in the female group, the manual matching of both male and female training groups helps explain the algorithm’s bias, indicating the altered sex abnormalities in functional brain networks compared to typically developing peers. These results highlight the importance of taking sex into account when considering how generalizations of findings on males with ASD apply to females.

Keywords: autism spectrum disorder, machine learning, neuroimaging, sex differences

Procedia PDF Downloads 209

Authors: Waqqas-ur-Rehman Butt, Martin Servin, Marion Pause

Abstract:

In recent years, object detection has gained much attention and very encouraging research area in the field of computer vision. The robust object boundaries detection in an image is demanded in numerous applications of human computer interaction and automated surveillance systems. Many methods and approaches have been developed for automatic object detection in various fields, such as automotive, quality control management and environmental services. Inappropriately, to the best of our knowledge, object detection under illumination with shadow consideration has not been well solved yet. Furthermore, this problem is also one of the major hurdles to keeping an object detection method from the practical applications. This paper presents an approach to automatic object detection in images under non-standardized environmental conditions. A key challenge is how to detect the object, particularly under uneven illumination conditions. Image capturing conditions the algorithms need to consider a variety of possible environmental factors as the colour information, lightening and shadows varies from image to image. Existing methods mostly failed to produce the appropriate result due to variation in colour information, lightening effects, threshold specifications, histogram dependencies and colour ranges. To overcome these limitations we propose an object detection algorithm, with pre-processing methods, to reduce the interference caused by shadow and illumination effects without fixed parameters. We use the Y CrCb colour model without any specific colour ranges and predefined threshold values. The segmented object regions are further classified using morphological operations (Erosion and Dilation) and contours. Proposed approach applied on a large image data set acquired under various environmental conditions for wood stack detection. Experiments show the promising result of the proposed approach in comparison with existing methods.

Keywords: image processing, illumination equalization, shadow filtering, object detection

Procedia PDF Downloads 216

Authors: Zakari Mustapha, Clinton Aigbavboa, Wellington Didi Thwala

Abstract:

Majority of the incidents and accidents in complex high-risk systems that exist in the construction industry and other sectors have been attributed to unsafe acts of workers. The purpose of this paper was to asses Human Factors Analysis and Classification System (HFACS) in construction accident prevention. The study was conducted through the use of secondary data from journals, books and internet to achieve the objective of the study. The review of literature looked into details of different views from different scholars about HFACS framework in accidents investigations. It further highlighted on various sections or disciplines of accident occurrences in human performance within the construction. The findings from literature review showed that unsafe acts of a worker and unsafe working conditions are the two major causes of accident in the construction industry.Most significant factor in the cause of site accident in the construction industry is unsafe acts of a worker. The findings also show how the application of HFACS framework in the investigation of accident will lead to the identification of common trends. Further findings show that provision for the prevention of accident will be made based on past accident records to identify and prioritize where intervention is needed within the construction industry.

Keywords: accident, construction, HFACS, unsafe acts

Procedia PDF Downloads 321

Authors: Kishor Chandra Kandpal, Amit Kumar

Abstract:

The Indian Himalaya region harbours approximately 1748 plants of medicinal importance, and as per International Union for Conservation of Nature (IUCN), the 112 plant species among these are threatened and endangered. To ease the pressure on these plants, the government of India is encouraging its in-situ cultivation. The Saussurea costus, Valeriana jatamansi, and Picrorhiza kurroa have also been prioritized for large scale cultivation owing to their market demand, conservation value and medicinal properties. These species are found from 1000 m to 4000 m elevation ranges in the Indian Himalaya. Identification of these plants in the field requires taxonomic skills, which is one of the major bottleneck in the conservation and management of these plants. In recent years, Hyperspectral remote sensing techniques have been precisely used for the discrimination of plant species with the help of their unique spectral signatures. In this background, a spectral library of the above 03 medicinal plants was prepared by collecting the spectral data using a handheld spectroradiometer (325 to 1075 nm) from farmer’s fields of Himachal Pradesh and Uttarakhand states of Indian Himalaya. The Random forest (RF) model was implied on the spectral data for the classification of the medicinal plants. The 80:20 standard split ratio was followed for training and validation of the RF model, which resulted in training accuracy of 84.39 % (kappa coefficient = 0.72) and testing accuracy of 85.29 % (kappa coefficient = 0.77). This RF classifier has identified green (555 to 598 nm), red (605 nm), and near-infrared (725 to 840 nm) wavelength regions suitable for the discrimination of these species. The findings of this study have provided a technique for rapid and onsite identification of the above medicinal plants in the field. This will also be a key input for the classification of hyperspectral remote sensing images for mapping of these species in farmer’s field on a regional scale. This is a pioneer study in the Indian Himalaya region for medicinal plants in which the applicability of hyperspectral remote sensing has been explored.

Keywords: himalaya, hyperspectral remote sensing, machine learning; medicinal plants, random forests

Procedia PDF Downloads 203

Authors: Sadia Basar, Naila Habib, Awais Adnan

Abstract:

The paper presents the Technique for Image Segmentation Using K-Means Clustering Classification. The presented algorithms were specific, however, missed the neighboring information and required high-speed computerized machines to run the segmentation algorithms. Clustering is the process of partitioning a group of data points into a small number of clusters. The proposed method is content-aware and feature extraction method which is able to run on low-end computerized machines, simple algorithm, required low-quality streaming, efficient and used for security purpose. It has the capability to highlight the boundary and the object. At first, the user enters the data in the representation of the input. Then in the next step, the digital image is converted into groups clusters. Clusters are divided into many regions. The same categories with same features of clusters are assembled within a group and different clusters are placed in other groups. Finally, the clusters are combined with respect to similar features and then represented in the form of segments. The clustered image depicts the clear representation of the digital image in order to highlight the regions and boundaries of the image. At last, the final image is presented in the form of segments. All colors of the image are separated in clusters.

Keywords: clustering, image segmentation, K-means function, local and global minimum, region

Procedia PDF Downloads 376

Authors: Prabesh Karki, Shyam Thapa Chettri, Bajarang Prasad Sah, Manoj Bhattarai, Sudeep Mishra

Abstract:

Introduction: Frontal sinus is frequently described as the most difficult sinus to access surgically due to its proximity to the cribriform plate, orbit, and anterior ethmoid artery. Frontal sinus surgery requires a detailed understanding of the cellular structure and FSDP unique to each patient, making high-resolution CT scans an indispensable tool to assess the difficulty of planned sinus surgery. International Frontal Sinus Anatomy Classification (IFAC) was developed to provide a more precise nomenclature for cells in the frontal recess, classifying cells based on their anatomic origin. Objectives: To assess the proportion of frontal cell variants defined by IFAC, variation with respect to age and gender. Methods: 54 cases were enrolled after a detailed clinical history, thorough general and physical examinations, and CT a report ordered in a film. Assessment and tabulation of the presence of frontal cells according to the IFAC analyzed. The prevalence of each cell type was calculated, and data were entered in MS Excel and analyzed using Statistical Package for the Social Sciences (SPSS). Descriptive statistics and frequencies were defined for categorical and numerical variables. Frequency, percentage, the mean and standard deviation were calculated. Result: Among 54 patients, 30 (55.6%) were male and 24 (44.4%) were female. The patient enrolled ranged from 18 to 78 years. Majority33.3% (n=18) were in age group of >50 years.According to IFAC, Agger nasi cells (92.6%) were most common, whereas supraorbital ethmoidal cells were least common 16 (29.6%). Prevalence of other frontoethmoidal cells was SAC- 57.4%, SAFC- 38.9%, SBC- 74.1%, SBFC- 33.3%, FSC- 38.9% of 54 cases. Conclusion: IFAC is an international consensus document that describes an anatomically precise nomenclature for classifying frontoethmoidal cells' anatomy. This study has defined the prevalence, symmetry and reliability of frontoethmoidal cells as established by the IFAC system as in other parts of the world.

Keywords: frontal sinus, frontoethmoidal cells, international frontal sinus anatomy classification

Procedia PDF Downloads 100

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 80

Authors: Valentina Narvaez Gaitan, Laura Valentina Rodriguez Leguizamon, Ruben Dario Hernandez B.

Abstract:

This work describes a physiological signal emulation system that uses electromyography (EMG) signals obtained from muscle sensors in the first instance. These signals are used to extract their characteristics to model and emulate specific arm movements. The main objective of this effort is to develop a new biomedical software system capable of generating physiological signals through the use of embedded systems by establishing the characteristics of the acquired signals. The acquisition system used was Biosignals, which contains two EMG electrodes used to acquire signals from the forearm muscles placed on the extensor and flexor muscles. Processing algorithms were implemented to classify the signals generated by the arm muscles when performing specific movements such as wrist flexion extension, palmar grip, and wrist pronation-supination. Matlab software was used to condition and preprocess the signals for subsequent classification. Subsequently, the mathematical modeling of each signal is performed to be generated by the embedded system, with a validation of the accuracy of the obtained signal using the percentage of cross-correlation, obtaining a precision of 96%. The equations are then discretized to be emulated in the embedded system, obtaining a system capable of generating physiological signals according to the characteristics of medical analysis.

Keywords: classification, electromyography, embedded system, emulation, physiological signals

Procedia PDF Downloads 111

Authors: Chithra A. V., Somoshree Datta, Sandeep Nithyanandan

Abstract:

Sign Language Recognition (SLR) is the process of interpreting and translating sign language into spoken or written language using technological systems. It involves recognizing hand gestures, facial expressions, and body movements that makeup sign language communication. The primary goal of SLR is to facilitate communication between hearing- and speech-impaired communities and those who do not understand sign language. Due to the increased awareness and greater recognition of the rights and needs of the hearing- and speech-impaired community, sign language recognition has gained significant importance over the past 10 years. Technological advancements in the fields of Artificial Intelligence and Machine Learning have made it more practical and feasible to create accurate SLR systems. This paper presents a distinct approach to SLR by framing it as a video classification problem using Deep Learning (DL), whereby a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) has been used. This research targets the integration of sign language recognition into healthcare settings, aiming to improve communication between medical professionals and patients with hearing impairments. The spatial features from each video frame are extracted using a CNN, which captures essential elements such as hand shapes, movements, and facial expressions. These features are then fed into an RNN network that learns the temporal dependencies and patterns inherent in sign language sequences. The INCLUDE dataset has been enhanced with more videos from the healthcare domain and the model is evaluated on the same. Our model achieves 91% accuracy, representing state-of-the-art performance in this domain. The results highlight the effectiveness of treating SLR as a video classification task with the CNN-RNN architecture. This approach not only improves recognition accuracy but also offers a scalable solution for real-time SLR applications, significantly advancing the field of accessible communication technologies.

Keywords: sign language recognition, deep learning, convolution neural network, recurrent neural network

Procedia PDF Downloads 28

Authors: Rong-Yang Lai, Jia-Yu Wu, Chih-Han Chang, Yung-Chung Chen

Abstract:

The dental bridge is one of the clinical methods of the treatment for missing teeth. The dental bridge is generally designed for two layers, containing the inner layer of the framework(zirconia) and the outer layer of the porcelain-fused to framework restorations. The design of a conventional bridge is generally based on the antagonist tooth profile so that the framework evenly indented by an equal thickness from outer contour. All-ceramic dental bridge made of zirconia have well demonstrated remarkable potential to withstand a higher physiological occlusal load in posterior region, but it was found that there is still the risk of all-ceramic bridge failure in five years. Thus, how to reduce the incidence of failure is still a problem to be solved. Therefore, the objective of this study is to develop mechanical designs for all-ceramic dental bridges framework by reducing the stress and enhancing fracture resistance under given loading conditions by finite element method. In this study, dental design software is used to design dental bridge based on tooth CT images. After building model, Bi-directional Evolutionary Structural Optimization (BESO) Method algorithm implemented in finite element software was employed to analyze results of finite element software and determine the distribution of the materials in dental bridge; BESO searches the optimum distribution of two different materials, namely porcelain and zirconia. According to the previous calculation of the stress value of each element, when the element stress value is higher than the threshold value, the element would be replaced by the framework material; besides, the difference of maximum stress peak value is less than 0.1%, calculation is complete. After completing the design of dental bridge, the stress distribution of the whole structure is changed. BESO reduces the peak values of principle stress of 10% in outer-layer porcelain and avoids producing tensile stress failure.

Keywords: dental bridge, finite element analysis, framework, automatic program

Procedia PDF Downloads 282

Authors: Madushani Rodrigo, Banuka Athuraliya

Abstract:

In today's world of medical diagnosis and prediction, machine learning stands out as a strong tool, transforming old ways of caring for health. This study analyzes the use of machine learning in the specialized domain of sports medicine, with a focus on the timely and accurate detection of bone fractures in cricket athletes. Failure to identify bone fractures in real time can result in malunion or non-union conditions. To ensure proper treatment and enhance the bone healing process, accurately identifying fracture locations and types is necessary. When interpreting X-ray images, it relies on the expertise and experience of medical professionals in the identification process. Sometimes, radiographic images are of low quality, leading to potential issues. Therefore, it is necessary to have a proper approach to accurately localize and classify fractures in real time. The research has revealed that the optimal approach needs to address the stated problem and employ appropriate radiographic image processing techniques and object detection algorithms. These algorithms should effectively localize and accurately classify all types of fractures with high precision and in a timely manner. In order to overcome the challenges of misidentifying fractures, a distinct model for fracture localization and classification has been implemented. The research also incorporates radiographic image enhancement and preprocessing techniques to overcome the limitations posed by low-quality images. A classification ensemble model has been implemented using ResNet18 and VGG16. In parallel, a fracture segmentation model has been implemented using the enhanced U-Net architecture. Combining the results of these two implemented models, the FracXpert system can accurately localize exact fracture locations along with fracture types from the available 12 different types of fracture patterns, which include avulsion, comminuted, compressed, dislocation, greenstick, hairline, impacted, intraarticular, longitudinal, oblique, pathological, and spiral. This system will generate a confidence score level indicating the degree of confidence in the predicted result. Using ResNet18 and VGG16 architectures, the implemented fracture segmentation model, based on the U-Net architecture, achieved a high accuracy level of 99.94%, demonstrating its precision in identifying fracture locations. Simultaneously, the classification ensemble model achieved an accuracy of 81.0%, showcasing its ability to categorize various fracture patterns, which is instrumental in the fracture treatment process. In conclusion, FracXpert has become a promising ML application in sports medicine, demonstrating its potential to revolutionize fracture detection processes. By leveraging the power of ML algorithms, this study contributes to the advancement of diagnostic capabilities in cricket athlete healthcare, ensuring timely and accurate identification of bone fractures for the best treatment outcomes.

Keywords: multiclass classification, object detection, ResNet18, U-Net, VGG16

Procedia PDF Downloads 120

Authors: Insaf Ajili, Malik Mallem, Jean-Yves Didier

Abstract:

Human motion recognition has been extensively increased in recent years due to its importance in a wide range of applications, such as human-computer interaction, intelligent surveillance, augmented reality, content-based video compression and retrieval, etc. However, it is still regarded as a challenging task especially in realistic scenarios. It can be seen as a general machine learning problem which requires an effective human motion representation and an efficient learning method. In this work, we introduce a descriptor based on Laban Movement Analysis technique, a formal and universal language for human movement, to capture both quantitative and qualitative aspects of movement. We use Discrete Hidden Markov Model (DHMM) for training and classification motions. We improve the classification algorithm by proposing two DHMMs for each motion class to process the motion sequence in two different directions, forward and backward. Such modification allows avoiding the misclassification that can happen when recognizing similar motions. Two experiments are conducted. In the first one, we evaluate our method on a public dataset, the Microsoft Research Cambridge-12 Kinect gesture data set (MSRC-12) which is a widely used dataset for evaluating action/gesture recognition methods. In the second experiment, we build a dataset composed of 10 gestures(Introduce yourself, waving, Dance, move, turn left, turn right, stop, sit down, increase velocity, decrease velocity) performed by 20 persons. The evaluation of the system includes testing the efficiency of our descriptor vector based on LMA with basic DHMM method and comparing the recognition results of the modified DHMM with the original one. Experiment results demonstrate that our method outperforms most of existing methods that used the MSRC-12 dataset, and a near perfect classification rate in our dataset.

Keywords: human motion recognition, motion representation, Laban Movement Analysis, Discrete Hidden Markov Model

Procedia PDF Downloads 207

Authors: Hira Lal Gope, Hidekazu Fukai

Abstract:

The aim of this study is to develop a system which can identify and sort peaberries automatically at low cost for coffee producers in developing countries. In this paper, the focus is on the classification of peaberries and normal coffee beans using image processing and machine learning techniques. The peaberry is not bad and not a normal bean. The peaberry is born in an only single seed, relatively round seed from a coffee cherry instead of the usual flat-sided pair of beans. It has another value and flavor. To make the taste of the coffee better, it is necessary to separate the peaberry and normal bean before green coffee beans roasting. Otherwise, the taste of total beans will be mixed, and it will be bad. In roaster procedure time, all the beans shape, size, and weight must be unique; otherwise, the larger bean will take more time for roasting inside. The peaberry has a different size and different shape even though they have the same weight as normal beans. The peaberry roasts slower than other normal beans. Therefore, neither technique provides a good option to select the peaberries. Defect beans, e.g., sour, broken, black, and fade bean, are easy to check and pick up manually by hand. On the other hand, the peaberry pick up is very difficult even for trained specialists because the shape and color of the peaberry are similar to normal beans. In this study, we use image processing and machine learning techniques to discriminate the normal and peaberry bean as a part of the sorting system. As the first step, we applied Deep Convolutional Neural Networks (CNN) and Support Vector Machine (SVM) as machine learning techniques to discriminate the peaberry and normal bean. As a result, better performance was obtained with CNN than with SVM for the discrimination of the peaberry. The trained artificial neural network with high performance CPU and GPU in this work will be simply installed into the inexpensive and low in calculation Raspberry Pi system. We assume that this system will be used in under developed countries. The study evaluates and compares the feasibility of the methods in terms of accuracy of classification and processing speed.

Keywords: convolutional neural networks, coffee bean, peaberry, sorting, support vector machine

Procedia PDF Downloads 144

Authors: Gihan Thilakarathna, Fernando Ishara, Rathnayake Yasith, Bandara A. M. R. Y.

Abstract:

E-learning is a crucial component of intelligent education. Even in the midst of a pandemic, E-learning is becoming increasingly important in the educational system. Several e-learning programs are accessible for students. Here, we decided to create an e-learning framework for children. We've found a few issues that teachers are having with their online classes. When there are numerous students in an online classroom, how does a teacher recognize a student's focus on academics and below-the-surface behaviors? Some kids are not paying attention in class, and others are napping. The teacher is unable to keep track of each and every student. Key challenge in e-learning is online exams. Because students can cheat easily during online exams. Hence there is need of exam proctoring is occurred. In here we propose an automated online exam cheating detection method using a web camera. The purpose of this project is to present an E-learning platform for math education and include games for kids as an alternative teaching method for math students. The game will be accessible via a web browser. The imagery in the game is drawn in a cartoonish style. This will help students learn math through games. Everything in this day and age is moving towards automation. However, automatic answer evaluation is only available for MCQ-based questions. As a result, the checker has a difficult time evaluating the theory solution. The current system requires more manpower and takes a long time to evaluate responses. It's also possible to mark two identical responses differently and receive two different grades. As a result, this application employs machine learning techniques to provide an automatic evaluation of subjective responses based on the keyword provided to the computer as student input, resulting in a fair distribution of marks. In addition, it will save time and manpower. We used deep learning, machine learning, image processing and natural language technologies to develop these research components.

Keywords: math, education games, e-learning platform, artificial intelligence

Procedia PDF Downloads 156

Authors: Zuraidasahana Zulkarnain, Mohd Shafry Mohd Rahim, Nor Anita Fairos Ismail, Mohd Azhar M. Arsad

Abstract:

Handwritten signature is accepted widely as a biometric characteristic for personal authentication. The use of appropriate features plays an important role in determining accuracy of signature verification; therefore, this paper presents a feature based on the geometrical concept. To achieve the aim, triangle attributes are exploited to design a new feature since the triangle possesses orientation, angle and transformation that would improve accuracy. The proposed feature uses triangulation geometric set comprising of sides, angles and perimeter of a triangle which is derived from the center of gravity of a signature image. For classification purpose, Euclidean classifier along with Voting-based classifier is used to verify the tendency of forgery signature. This classification process is experimented using triangular geometric feature and selected global features. Based on an experiment that was validated using Grupo de Senales 960 (GPDS-960) signature database, the proposed triangular geometric feature achieves a lower Average Error Rates (AER) value with a percentage of 34% as compared to 43% of the selected global feature. As a conclusion, the proposed triangular geometric feature proves to be a more reliable feature for accurate signature verification.

Keywords: biometrics, euclidean classifier, features extraction, offline signature verification, voting-based classifier

Procedia PDF Downloads 379

Authors: Amaladhithyan Krishnamoorthy, Ruvaitha Banu

Abstract:

Vision is considered as the most important sense in humans, without which leading a normal can be often difficult. There are many existing smart canes for visually impaired with obstacle detection using ultrasonic transducer to help them navigate. Though the basic smart cane increases the safety of the users, it does not help in filling the void of visual loss. This paper introduces the concept of Digi-Buddy which is an evolved smart cane for visually impaired. The cane consists for several modules, apart from the basic obstacle detection features; the Digi-Buddy assists the user by capturing video/images and streams them to the server using a wide-angled camera, which then detects the objects using Deep Convolutional Neural Network. In addition to determining what the particular image/object is, the distance of the object is assessed by the ultrasonic transducer. The sound generation application, modelled with the help of Natural Language Processing is used to convert the processed images/object into audio. The object detected is signified by its name which is transmitted to the user with the help of Bluetooth hear phones. The object detection is extended to facial recognition which maps the faces of the person the user meets in the database of face images and alerts the user about the person. One of other crucial function consists of an automatic-intimation-alarm which is triggered when the user is in an emergency. If the user recovers within a set time, a button is provisioned in the cane to stop the alarm. Else an automatic intimation is sent to friends and family about the whereabouts of the user using GPS. In addition to safety and security by the existing smart canes, the proposed concept devices to be implemented as a prototype helping visually-impaired visualize their surroundings through audio more in an amicable way.

Keywords: artificial intelligence, facial recognition, natural language processing, internet of things

Procedia PDF Downloads 355

Authors: Mansoor Aslamzai, Delaqa Del, Sayed Azam Sajid

Abstract:

Introduction: Though moral disorders have a high burden, there is no separate topic regarding this problem in the International Classification of Diseases (ICD). Along with the modification of WHO ICD-11, spirituality can prevent the rapid progress of such derangement as well. Objective: This study evaluated the effects of bad moral characters on health, as well as carried out the role of spirituality in the improvement of immorality. Method: This narrative article review was accomplished in 2020-2021 and the articles were searched through the Web of Science, PubMed, BMC, and Google scholar. Results: Based on the current review, most experimental and observational studies revealed significant negative effects of unwell moral characters on the overall aspects of health and well-being. Nowadays, a lot of studies established the positive role of spirituality in the improvement of health and moral disorder. The studies concluded, facilities must be available within schools, universities, and communities for everyone to learn the knowledge of spirituality and improve their unwell moral character world. Conclusion: Considering the negative relationship between unwell moral characters and well-being, the current study proposes the addition of moral disorder as a separate topic in the WHO International Classification of Diseases. Based on this literature review, spirituality will improve moral disorder and establish excellent moral traits.

Keywords: bad moral characters, effect, health, spirituality and well-being

Procedia PDF Downloads 184

Authors: Rita Chattopadhyay, Vivek Anand Thoutam

Abstract:

Speech is the most acceptable means of communication where we can quickly exchange our feelings and thoughts. Quite often, people can communicate orally but cannot interact or work with computers or devices. It’s easy and quick to give speech commands than typing commands to computers. In the same way, it’s easy listening to audio played from a device than extract output from computers or devices. Especially with Robotics being an emerging market with applications in warehouses, the hospitality industry, consumer electronics, assistive technology, etc., speech-based human-machine interaction is emerging as a lucrative feature for robot manufacturers. Considering this factor, the objective of this paper is to design the “Audio-Visual Co-Data Processing Pipeline.” This pipeline is an integrated version of Automatic speech recognition, a Natural language model for text understanding, object detection, and text-to-speech modules. There are many Deep Learning models for each type of the modules mentioned above, but OpenVINO Model Zoo models are used because the OpenVINO toolkit covers both computer vision and non-computer vision workloads across Intel hardware and maximizes performance, and accelerates application development. A speech command is given as input that has information about target objects to be detected and start and end times to extract the required interval from the video. Speech is converted to text using the Automatic speech recognition QuartzNet model. The summary is extracted from text using a natural language model Generative Pre-Trained Transformer-3 (GPT-3). Based on the summary, essential frames from the video are extracted, and the You Only Look Once (YOLO) object detection model detects You Only Look Once (YOLO) objects on these extracted frames. Frame numbers that have target objects (specified objects in the speech command) are saved as text. Finally, this text (frame numbers) is converted to speech using text to speech model and will be played from the device. This project is developed for 80 You Only Look Once (YOLO) labels, and the user can extract frames based on only one or two target labels. This pipeline can be extended for more than two target labels easily by making appropriate changes in the object detection module. This project is developed for four different speech command formats by including sample examples in the prompt used by Generative Pre-Trained Transformer-3 (GPT-3) model. Based on user preference, one can come up with a new speech command format by including some examples of the respective format in the prompt used by the Generative Pre-Trained Transformer-3 (GPT-3) model. This pipeline can be used in many projects like human-machine interface, human-robot interaction, and surveillance through speech commands. All object detection projects can be upgraded using this pipeline so that one can give speech commands and output is played from the device.

Keywords: OpenVINO, automatic speech recognition, natural language processing, object detection, text to speech

Procedia PDF Downloads 80

Authors: Jacqueline Rose T. Alipo-on, Francesca Isabelle F. Escobar, Myles Joshua T. Tan, Hezerul Abdul Karim, Nouar Al Dahoul

Abstract:

Electrocardiogram (ECG) signal analysis and processing are crucial in the diagnosis of cardiovascular diseases, which are considered one of the leading causes of mortality worldwide. However, the traditional rule-based analysis of large volumes of ECG data is time-consuming, labor-intensive, and prone to human errors. With the advancement of the programming paradigm, algorithms such as machine learning have been increasingly used to perform an analysis of ECG signals. In this paper, various deep learning algorithms were adapted to classify five classes of heartbeat types. The dataset used in this work is the synthetic MIT-BIH Arrhythmia dataset produced from generative adversarial networks (GANs). Various deep learning models such as ResNet-50 convolutional neural network (CNN), 1-D CNN, and long short-term memory (LSTM) were evaluated and compared. ResNet-50 was found to outperform other models in terms of recall and F1 score using a five-fold average score of 98.88% and 98.87%, respectively. 1-D CNN, on the other hand, was found to have the highest average precision of 98.93%.

Keywords: heartbeat classification, convolutional neural network, electrocardiogram signals, generative adversarial networks, long short-term memory, ResNet-50

Procedia PDF Downloads 128

Authors: Nádia Pereira, Paula Ferreira, Sofia Francisco, Sofia Oliveira, Sidclay Souza, Paula Paulino, Ana Margarida Veiga Simão

Abstract:

Social media has progressed into a platform for hate speech among its users, and thus, there is an increasing need to develop automatic detection classifiers of offense and conflicts to help decrease the prevalence of such incidents. Online communication can be used to intentionally harm someone, which is why such classifiers could be essential in social networks. A possible application of these classifiers is the automatic detection of cyberbullying. Even though identifying the aggressive language used in online interactions could be important to build cyberbullying datasets, there are other criteria that must be considered. Being able to capture the language, which is indicative of the intent to harm others in a specific context of online interaction is fundamental. Offense and hate speech may be the foundation of online conflicts, which have become commonly used in social media and are an emergent research focus in machine learning and natural language processing. This study presents two Portuguese language offense-related datasets which serve as examples for future research and extend the study of the topic. The first is similar to other offense detection related datasets and is entitled Aggressiveness dataset. The second is a novelty because of the use of the history of the interaction between users and is entitled the Conflicts/Attacks dataset. Both datasets were developed in different phases. Firstly, we performed a content analysis of verbal aggression witnessed by adolescents in situations of cyberbullying. Secondly, we computed frequency analyses from the previous phase to gather lexical and linguistic cues used to identify potentially aggressive conflicts and attacks which were posted on Twitter. Thirdly, thorough annotation of real tweets was performed byindependent postgraduate educational psychologists with experience in cyberbullying research. Lastly, we benchmarked these datasets with other machine learning classifiers.

Keywords: aggression, classifiers, cyberbullying, datasets, hate speech, machine learning

Procedia PDF Downloads 228

Authors: Giovanni Menichini, Salvatore Giacomo Morano, Gloria Terenzi, Luca Salvatori, Maurizio Orlando

Abstract:

The “Guidelines for Risk Classification, Safety Assessment, and Structural Health Monitoring of Existing Bridges” were recently approved by the Italian Government to define technical standards for managing the national network of existing bridges. These guidelines provide a framework for risk mitigation and safety assessment of bridges, which are essential elements of the built environment and form the basis for the operation of transport systems. Within the guideline framework, a workflow based on three main points was proposed: (1) risk-based, i.e., based on typical parameters of hazard, vulnerability, and exposure; (2) multi-level, i.e., including six assessment levels of increasing complexity; and (3) multirisk, i.e., assessing structural/foundational, seismic, hydrological, and landslide risks. The paper focuses on applying the Italian Guidelines to specific case studies, aiming to identify the parameters that predominantly influence the determination of the “class of attention”. The significance of each parameter is determined via sensitivity analysis. Additionally, recommendations for enhancing the process of assigning the class of attention are proposed.

Keywords: bridge safety assessment, Italian guidelines implementation, risk classification, structural health monitoring

Procedia PDF Downloads 58

Authors: Taikchan Lildar, Ayesha Samad, Suraj Sookhu

Abstract:

Atrial fibrillation with rapid ventricular response results in the loss of atrial kick and shortened ventricular filling time, which often leads to decompensated heart failure. Pharmacologic rhythm control is the treatment of choice, and patients frequently benefit from the restoration of sinus rhythm. When pharmacologic treatment is unsuccessful or a patient declines hemodynamically, direct cardioversion is the treatment of choice. Torsades de pointes or “twisting of the points'' in French, is a rare but under-appreciated risk of cardioversion therapy and accounts for a significant number of sudden cardiac death each year. A 61-year-old female with no significant past medical history presented to the Emergency Department with worsening dyspnea. An electrocardiogram showed atrial fibrillation with rapid ventricular response, and a chest X-ray was significant for bilateral pulmonary vascular congestion. Full-dose anticoagulation and diuresis were initiated with moderate improvement in symptoms. A transthoracic echocardiogram revealed biventricular systolic dysfunction with a left ventricular ejection fraction of 30%. After consultation with an electrophysiologist, the consensus was to proceed with the restoration of sinus rhythm, which would likely improve the patient’s heart failure symptoms and possibly the ejection fraction. A transesophageal echocardiogram was negative for left atrial appendage thrombus; the patient was treated with a loading dose of amiodarone and underwent successful direct current cardioversion with 200 Joules. The patient was placed on telemetry monitoring for 24 hours and was noted to have frequent premature ventricular contractions with subsequent degeneration to torsades de pointes. The patient was found unresponsive and pulseless; cardiopulmonary resuscitation was initiated with cardioversion, and return of spontaneous circulation was achieved after four minutes to normal sinus rhythm. Post-cardiac arrest electrocardiogram showed sinus bradycardia with heart-rate corrected QT interval of 592 milliseconds. The patient continued to have frequent premature ventricular contractions and required two additional cardioversions to achieve a return of spontaneous circulation with intravenous magnesium and lidocaine. An automatic implantable cardioverter-defibrillator was subsequently implanted for secondary prevention of sudden cardiac death. The backup pacing rate of the automatic implantable cardioverter-defibrillator was set higher than usual in an attempt to prevent premature ventricular contractions-induced torsades de pointes. The patient did not have any further ventricular arrhythmias after implantation of the automatic implantable cardioverter-defibrillator. Overdrive pacing is a method utilized to treat premature ventricular contractions-induced torsades de pointes by preventing a patient’s susceptibility to R on T-wave-induced ventricular arrhythmias. Pacing at a rate of 90 beats per minute succeeded in controlling the arrhythmia without the need for traumatic cardiac defibrillation. In our patient, conversion of atrial fibrillation with rapid ventricular response to normal sinus rhythm resulted in a slower heart rate and an increased probability of premature ventricular contraction occurring on the T-wave and ensuing ventricular arrhythmia. This case highlights direct current cardioversion for atrial fibrillation with rapid ventricular response resulting in persistent ventricular arrhythmia requiring an automatic implantable cardioverter-defibrillator placement with overdrive pacing to prevent a recurrence.

Keywords: refractory atrial fibrillation, atrial fibrillation, overdrive pacing, torsades de pointes

Procedia PDF Downloads 147

Authors: Han-Jeong Hwang, Jae-Hyun Jo, Fatemeh Alimardani

Abstract:

An accurate diagnosis of psychiatric diseases is a challenging issue, in particular when distinct symptoms for different diseases are overlapped, such as delusions appeared in bipolar mood disorder (BMD) and schizophrenia (SCH). In the present study, we propose a useful way to discriminate BMD and SCH using electroencephalography (EEG). A total of thirty BMD and SCH patients (15 vs. 15) took part in our experiment. EEG signals were measured with nineteen electrodes attached on the scalp using the international 10-20 system, while they were exposed to a visual stimulus flickering at 16 Hz for 95 s. The flickering visual stimulus induces a certain brain signal, known as steady-state visual evoked potential (SSVEP), which is differently observed in patients with BMD and SCH, respectively, in terms of SSVEP amplitude because they process the same visual information in own unique way. For classifying BDM and SCH patients, machine learning technique was employed in which leave-one-out-cross validation was performed. The SSVEPs induced at the fundamental (16 Hz) and second harmonic (32 Hz) stimulation frequencies were extracted using fast Fourier transformation (FFT), and they were used as features. The most discriminative feature was selected using the Fisher score, and support vector machine (SVM) was used as a classifier. From the analysis, we could obtain a classification accuracy of 83.33 %, showing the feasibility of discriminating patients with BMD and SCH using EEG. We expect that our approach can be utilized for psychiatrists to more accurately diagnose the psychiatric disorders, BMD and SCH.

Keywords: bipolar mood disorder, electroencephalography, schizophrenia, machine learning

Procedia PDF Downloads 422

Authors: M. Bodner, M. Scampicchio

Abstract:

Fourier Transform Infrared (FT-IR) spectroscopy coupled with chemometrics was used to distinguish between butter samples and non-butter samples. Further, quantification of the content of margarine in adulterated butter samples was investigated. Fingerprinting region (1400-800 cm^–1) was used to develop unsupervised pattern recognition (Principal Component Analysis, PCA), supervised modeling (Soft Independent Modelling by Class Analogy, SIMCA), classification (Partial Least Squares Discriminant Analysis, PLS-DA) and regression (Partial Least Squares Regression, PLS-R) models. PCA of the fingerprinting region shows a clustering of the two sample types. All samples were classified in their rightful class by SIMCA approach; however, nine adulterated samples (between 1% and 30% w/w of margarine) were classified as belonging both at the butter class and at the non-butter one. In the two-class PLS-DA model’s (R² = 0.73, RMSEP, Root Mean Square Error of Prediction = 0.26% w/w) sensitivity was 71.4% and Positive Predictive Value (PPV) 100%. Its threshold was calculated at 7% w/w of margarine in adulterated butter samples. Finally, PLS-R model (R² = 0.84, RMSEP = 16.54%) was developed. PLS-DA was a suitable classification tool and PLS-R a proper quantification approach. Results demonstrate that FT-IR spectroscopy combined with PLS-R can be used as a rapid, simple and safe method to identify pure butter samples from adulterated ones and to determine the grade of adulteration of margarine in butter samples.

Keywords: adulterated butter, margarine, PCA, PLS-DA, PLS-R, SIMCA

Procedia PDF Downloads 143

Authors: Sahar Jahani, Meryem Ayse Yucel, David Boas, Seyed Kamaledin Setarehdan

Abstract:

Near-infrared spectroscopy allows monitoring of oxy- and deoxy-hemoglobin concentration changes associated with hemodynamic response function (HRF). HRF is usually affected by natural physiological hemodynamic (systemic interferences) which occur in all body tissues including brain tissue. This makes HRF extraction a very challenging task. In this study, we used Kalman filter based on a general linear model (GLM) of brain activity to define the proportion of systemic interference in the brain hemodynamic. The performance of the proposed algorithm is evaluated in terms of the peak to peak error (Ep), mean square error (MSE), and Pearson’s correlation coefficient (R2) criteria between the estimated and the simulated hemodynamic responses. This technique also has the ability of real time estimation of single trial functional activations as it was applied to classify finger tapping versus resting state. The average real-time classification accuracy of 74% over 11 subjects demonstrates the feasibility of developing an effective functional near infrared spectroscopy for brain computer interface purposes (fNIRS-BCI).

Keywords: hemodynamic response function, functional near-infrared spectroscopy, adaptive filter, Kalman filter

Procedia PDF Downloads 167

Authors: Mojtaba Heydarizad

Abstract:

Khorasan Razavi is the second most important province in north-east of Iran, which faces a water shortage crisis due to recent droughts and huge water consummation. Kardeh and Torogh dam reservoirs in this province provide a notable part of Mashhad metropolitan (with more than 4.5 million inhabitants) potable water needs. Hydrochemical analyses on these dam reservoirs samples demonstrate that MgHCO₃ in Kardeh and CaHCO₃ and to lower extent MgHCO₃ water types in Torogh dam reservoir are dominant. On the other hand, Gibbs binary diagram demonstrates that rock weathering is the main factor controlling water quality in dam reservoirs. Plotting dam reservoir samples on Mg²⁺/Na⁺ and HCO₃^-/Na⁺ vs. Ca²⁺/ Na⁺ diagrams demonstrate evaporative and carbonate mineral dissolution is the dominant rock weathering ion sources in these dam reservoirs. Cluster Analyses (CA) also demonstrate intense role of rock weathering mainly (carbonate and evaporative minerals dissolution) in water quality of these dam reservoirs. Studying water quality by the U.S. National Sanitation Foundation (NSF) WQI index NSF-WQI, Oregon Water Quality Index (OWQI) and Canadian Water Quality Index DWQI index show moderate and good quality.

Keywords: hydrochemistry, water quality classification, water quality indexes, Torogh and Kardeh dam reservoir

Procedia PDF Downloads 255