Search results for: Kazakh speech dataset

Authors: Onyedikachi Ulelu, Andrew P. Longstaff, Simon Fletcher, Simon Parkinson

Abstract:

The widespread interest in 'Industry 4.0' or 'digital manufacturing' has led to significant research requiring the acquisition of data from sensors, instruments, and machine signals. In-depth research then identifies methods of analysis of the massive amounts of data generated before and during manufacture to solve a particular problem. The ultimate goal is for industrial Internet of Things (IIoT) data to be processed automatically to assist with either visualisation or autonomous system decision-making. However, the collection and processing of data in an industrial environment come with a cost. Little research has been undertaken on how to specify optimally what data to capture, transmit, process, and store at various levels of an edge-cloud network. The first step in this specification is to categorise IIoT data for efficient and effective use. This paper proposes the required attributes and classification to take manufacturing digital data from various sources to determine the most suitable location for data processing on the edge-cloud network. The proposed classification framework will minimise overhead in terms of network bandwidth/cost and processing time of machine tool data via efficient decision making on which dataset should be processed at the ‘edge’ and what to send to a remote server (cloud). A fast-and-frugal heuristic method is implemented for this decision-making. The framework is tested using case studies from industrial machine tools for machine productivity and maintenance.

Keywords: data classification, decision making, edge computing, industrial IoT, industry 4.0

Procedia PDF Downloads 180

Authors: Youngjae Jin, Daeshik Kim

Abstract:

This paper describes a cycle accurate simulation results of weight values learned by an auto-encoder behavior model in terms of pre-route simulation. Given the results we visualized the first layer representations with natural images. Many common deep learning threads have focused on learning high-level abstraction of unlabeled raw data by unsupervised feature learning. However, in the process of handling such a huge amount of data, the learning method’s computation complexity and time limited advanced research. These limitations came from the fact these algorithms were computed by using only single core CPUs. For this reason, parallel-based hardware, FPGAs, was seen as a possible solution to overcome these limitations. We adopted and simulated the ready-made auto-encoder to design a behavior model in Verilog HDL before designing hardware. With the auto-encoder behavior model pre-route simulation, we obtained the cycle accurate results of the parameter of each hidden layer by using MODELSIM. The cycle accurate results are very important factor in designing a parallel-based digital hardware. Finally this paper shows an appropriate operation of behavior model based pre-route simulation. Moreover, we visualized learning latent representations of the first hidden layer with Kyoto natural image dataset.

Keywords: auto-encoder, behavior model simulation, digital hardware design, pre-route simulation, Unsupervised feature learning

Procedia PDF Downloads 446

Authors: Stelios A. Mitilineos, Nicolas-Alexander Tatlas, Georgia Korompili, Lampros Kokkalas, Stelios M. Potirakis

Abstract:

Obstructive Sleep Apnea Hypopnea Syndrome (OSAHS) is a widespread chronic disease that mostly remains undetected, mainly due to the fact that it is diagnosed via polysomnography which is a time and resource-intensive procedure. Screening the disease’s symptoms at home could be used as an alternative approach in order to alert individuals that potentially suffer from OSAHS without compromising their everyday routine. Since snoring is usually linked to OSAHS, developing a snore detector is appealing as an enabling technology for screening OSAHS at home using ubiquitous equipment like commodity microphones (included in, e.g., smartphones). In this context, this study developed a snore detection tool and herein present the approach and selection of specific sound features that discriminate snoring vs. environmental sounds, as well as the performance of the proposed tool. Furthermore, a Real-Time Snore Detector (RTSD) is built upon the snore detection tool and employed in whole-night sleep sound recordings resulting to a large dataset of snoring sound excerpts that are made freely available to the public. The RTSD may be used either as a stand-alone tool that offers insight to an individual’s sleep quality or as an independent component of OSAHS screening applications in future developments.

Keywords: obstructive sleep apnea hypopnea syndrome, apnea screening, snoring detection, machine learning, neural networks

Procedia PDF Downloads 207

Authors: Humara Bano, Nyla Anjum

Abstract:

Disability in any form has great impact not only for the person facing it but also for its family members too. This effect may be so severe that may lead to mal adjustment of any member of the family in society as well. This impact has also been multiplied due to negative attitudes of the society, unawareness about the needs of special needs and no legislation for the parents of children with special needs. As a result not only the separations among the parents have been reported but also the normal siblings in the home are also badly affected in their daily lives. The situation is more challenging when more than one child with disability is present in the family. The main objectives of this paper are to unfold the relationship of variety of disabilities (hearing, visual or physical impairment, mental retardation, speech impairment) in i) developing depression in home setting, ii) social exclusion, iii) anxiety and aggression and iv) development of insecure feelings among family members of the persons with disabilities, as well as, v) to identify coping strategies to manage the special needs by family members too. To reach on conclusion about fifty families (having any sort of disability in their homes) have been interviewed on basis of convenient sampling. Correlation, ANOVA and different analysis have been used to identify the relationship of disability in developing depression among family members in line of above mentioned problems. Results revealed that depression due to disability among families is a common phenomenon and adversely have affected their lives in daily routines as well as in following their life achievements. Coping with the situation and recommending various remedies by parents is the positive reflection of this study too that can help to families in managing their mental health.

Keywords: depression, anxiety and aggression, social exclusion, parents of children with special needs

Procedia PDF Downloads 475

Authors: Farshid Hajati, Federico Girosi, Shima Ghassempour

Abstract:

We present a Deep Belief Network (DBN) method for clustering health trajectories. Deep Belief Network (DBN) is a deep architecture that consists of a stack of Restricted Boltzmann Machines (RBM). In a deep architecture, each layer learns more complex features than the past layers. The proposed method depends on DBN in clustering without using back propagation learning algorithm. The proposed DBN has a better a performance compared to the deep neural network due the initialization of the connecting weights. We use Contrastive Divergence (CD) method for training the RBMs which increases the performance of the network. The performance of the proposed method is evaluated extensively on the Health and Retirement Study (HRS) database. The University of Michigan Health and Retirement Study (HRS) is a nationally representative longitudinal study that has surveyed more than 27,000 elderly and near-elderly Americans since its inception in 1992. Participants are interviewed every two years and they collect data on physical and mental health, insurance coverage, financial status, family support systems, labor market status, and retirement planning. The dataset is publicly available and we use the RAND HRS version L, which is easy to use and cleaned up version of the data. The size of sample data set is 268 and the length of the trajectories is equal to 10. The trajectories do not stop when the patient dies and represent 10 different interviews of live patients. Compared to the state-of-the-art benchmarks, the experimental results show the effectiveness and superiority of the proposed method in clustering health trajectories.

Keywords: health trajectory, clustering, deep learning, DBN

Procedia PDF Downloads 369

Authors: Dutica Luminita

Abstract:

For the music composer Myriam Marbe the musical time and memory represent 2 (complementary) phenomena with conclusive impact on the settlement of new musical ontologies. Summarizing the most important achievements of the contemporary techniques of composition, her vision on the microform presented in The Concert for Daniel Kientzy, saxophone and orchestra transcends the linear and unidirectional time in favour of a flexible, multi-vectorial speech with spiral developments, where the sound substance is auto(re)generated by analogy with the fundamental processes of the memory. The conceptual model is of an archetypal essence, the music composer being concerned with identifying the mechanisms of the creation process, especially of those specific to the collective creation (of oral tradition). Hence the spontaneity of expression, improvisation tint, free rhythm, micro-interval intonation, coloristic-timbral universe dominated by multiphonics and unique sound effects. Hence the atmosphere of ritual, however purged by the primary connotations and reprojected into a wonderful spectacular space. The Concert is a work of artistic maturity and enforces respect, among others, by the timbral diversity of the three species of saxophone required by the music composer (baritone, sopranino and alt), in Part III Daniel Kientzy shows the performance of playing two saxophones concomitantly. The score of the music composer Myriam Marbe contains a deeply spiritualized music, full or archetypal symbols, a music whose drama suggests a real cinematographic movement.

Keywords: archetype, chronogenesis, concert, multiphonics

Procedia PDF Downloads 543

Authors: Neha Ahirwar

Abstract:

In the contemporary digital era, the rise of credit card fraud poses a significant threat to both financial institutions and consumers. As fraudulent activities become more sophisticated, there is an escalating demand for robust and effective fraud detection mechanisms. Advanced machine learning algorithms have become crucial tools in addressing this challenge. This paper conducts a thorough examination of the design and evaluation of a credit card fraud detection system, utilizing four prominent machine learning algorithms: random forest, logistic regression, decision tree, and XGBoost. The surge in digital transactions has opened avenues for fraudsters to exploit vulnerabilities within payment systems. Consequently, there is an urgent need for proactive and adaptable fraud detection systems. This study addresses this imperative by exploring the efficacy of machine learning algorithms in identifying fraudulent credit card transactions. The selection of random forest, logistic regression, decision tree, and XGBoost for scrutiny in this study is based on their documented effectiveness in diverse domains, particularly in credit card fraud detection. These algorithms are renowned for their capability to model intricate patterns and provide accurate predictions. Each algorithm is implemented and evaluated for its performance in a controlled environment, utilizing a diverse dataset comprising both genuine and fraudulent credit card transactions.

Keywords: efficient credit card fraud detection, random forest, logistic regression, XGBoost, decision tree

Procedia PDF Downloads 66

Authors: Maria L. Swanson

Abstract:

Language is a system which constantly changes and reflects social and cultural transformations of a speech community. If it is phonetic system, morphological patterns and syntactic arrangements undergo little charge and are not easily transferable from one language to another, the lexicon has a high degree of flexibility. Borrowings in Arabic have always been an interesting and important subject of study to various fields of linguistics, history and culturology, and there is quite number of works devoted to this subject (al-Khalīl, Sībawīḥ, Jeffery, Belkin, al-Maghribii, Holes, Stetkevich, el-Mawlūdī, between many others). At the same time, the history of borrowing has never been described as a process starting from its originating and up to the present time. Most of the researches study lexical and morphological adaptation of borrowed words for specific or several historical periods or delineate this process on the whole. Meanwhile, we have described the whole history of borrowings in Arabic with the brief depicting of lexical and morphological specifics for each historical period using quantitative method through dividing Arabic borrowings into several groups, basing on the specific of their adaptation of new vocabulary which is tightly related to the global transformations in the Arabic history. We explain reasons for borrowings of specific lexical layers for each historical period together with the description of its morphological specifics. We also use qualitative approach through performing statistics about the share of loan vocabulary in Arabic during different periods and the percentage of borrowings from donor languages. The history of a character and amount of borrowings is a good resource for theoretical and practical lexicography and morphology studies. It is also beneficial for researchers in the field of global and specific national, political and social developments, and different types of contacts.

Keywords: anthropological linguistics, borrowings, historical linguistics, sociolinguistics

Procedia PDF Downloads 451

Authors: Sadeq Al Yaari, Ayman Al Yaari, Adham Al Yaari, Montaha Al Yaari, Aayah Al Yaari, Sajedah Al Yaari

Abstract:

Background & Objectives: Audio-visual aids and computer-assisted language instruction (CALI) effects are strong in teaching language components (sound system, grammatical structures and vocabulary) to students of special needs. To explore the effects of the audio-visual aids and CALI in teaching sound system to this class of students by speech language therapists (SLTs), an experiment has been undertaken to evaluate their performance during their study of the sound system course. Methods: Forty students (males and females) of special needs at al-Malādh school for teaching students of special needs in Dhamar (Yemen) range between 8 and 18 years old underwent this experimental study while they were studying language sound system course. Pre-and-posttests have been administered at the begging and end of the semester. Students' treatment was compared to a similar group (control group) of the same number under the same environment. Whereas the first group was taught using audio-visual aids and CALI, the second was not. Students' performances were linguistically and statistically evaluated. Results & conclusions: Compared with the control group, the treatment group showed significantly higher scores in the posttest (72.32% vs. 31%). Compared with females, males scored higher marks (1421 vs. 1472). Thus, we should take the audio-visual aids and CALI into consideration in teaching sound system to students of special needs.

Keywords: language components, sound system, audio-visual aids, CALI, students, special needs, SLTs

Procedia PDF Downloads 46

Authors: Jean-Francois Rajotte, Martin Sotir, Frank Gouineau

Abstract:

The installation and management of traffic monitoring devices can be costly from both a financial and resource point of view. It is therefore important to take advantage of in-place infrastructures to extract the most information. Here we show how low-quality urban road traffic images from cameras already available in many cities (such as Montreal, Vancouver, and Toronto) can be used to estimate traffic flow. To this end, we use a pre-trained neural network, developed for object detection, to count vehicles within images. We then compare the results with human annotations gathered through crowdsourcing campaigns. We use this comparison to assess performance and calibrate the neural network annotations. As a use case, we consider six months of continuous monitoring over hundreds of cameras installed in the city of Montreal. We compare the results with city-provided manual traffic counting performed in similar conditions at the same location. The good performance of our system allows us to consider applications which can monitor the traffic conditions in near real-time, making the counting usable for traffic-related services. Furthermore, the resulting annotations pave the way for building a historical vehicle counting dataset to be used for analysing the impact of road traffic on many city-related issues, such as urban planning, security, and pollution.

Keywords: traffic monitoring, deep learning, image annotation, vehicles, roads, artificial intelligence, real-time systems

Procedia PDF Downloads 200

Authors: S. Abera, T. Gidey, W. Terefe

Abstract:

Introduction: Testing for HIV is the key entry point to HIV prevention, treatment, and care and support services. Hence, predictive data mining techniques can greatly benefit to analyze and discover new patterns from huge datasets like that of EDHS 2011 data. Objectives: The objective of this study is to build a predictive modeling for HIV testing and identify determinants of HIV testing for adults with age above fourteen years using data mining techniques. Methods: Cross-Industry Standard Process for Data Mining (CRISP-DM) was used to predict the model for HIV testing and explore association rules between HIV testing and the selected attributes among adult Ethiopians. Decision tree, Naïve-Bayes, logistic regression and artificial neural networks of data mining techniques were used to build the predictive models. Results: The target dataset contained 30,625 study participants; of which 16, 515 (53.9%) were women. Nearly two-fifth; 17,719 (58%), have never been tested for HIV while the rest 12,906 (42%) had been tested. Ethiopians with higher wealth index, higher educational level, belonging 20 to 29 years old, having no stigmatizing attitude towards HIV positive person, urban residents, having HIV related knowledge, information about family planning on mass media and knowing a place where to get testing for HIV showed an increased patterns with respect to HIV testing. Conclusion and Recommendation: Public health interventions should consider the identified determinants to promote people to get testing for HIV.

Keywords: data mining, HIV, testing, ethiopia

Procedia PDF Downloads 496

Authors: Tannistha Dasgupta

Abstract:

This study explores the aspects of second language (L2) spoken fluency that are related to L2 linguistic knowledge and processing skill. It draws on Levelt’s ‘blueprint’ of the L2 speaker which discusses the cognitive issues underlying the act of speaking. However, L2 speaking assessments have largely neglected the underlying mechanism involved in language production; emphasis is given on the relationship between subjective ratings of L2 speech sample and objectively measured aspects of fluency. Hence, in this study, the relation between L2 linguistic knowledge and processing skill i.e. Cognitive Fluency (CF), and objectively measurable aspects of L2 spoken fluency i.e. Utterance Fluency (UF) is examined. The participants of the study are L2 learners of English, studying at high school level in Hyderabad, India. 50 participants with intermediate level of proficiency in English performed several lexical retrieval tasks and attention-shifting tasks to measure CF, and 8 oral tasks to measure UF. Each aspect of UF (speed, pause, and repair) were measured against the scores of CF to find out those aspects of UF which are reliable indicators of CF. Quantitative analysis of the data shows that among the three aspects of UF; speed is the best predictor of CF, and pause is weakly related to CF. The study suggests that including the speed aspect of UF could make L2 fluency assessment more reliable, valid, and objective. Thus, incorporating the assessment of psycholinguistic mechanisms into L2 spoken fluency testing, could result in fairer evaluation.

Keywords: attention-shifting, cognitive fluency, lexical retrieval, utterance fluency

Procedia PDF Downloads 711

Authors: Emily Purdom, Rachel Robinson

Abstract:

As the number of students worldwide requiring speech-language therapy, occupational therapy and mental health services during their school day increases, innovation is becoming progressively more important to meet the demand. Telepractice can be used to reach a greater number of students requiring specialized therapy while maintaining the highest quality of care. It can be provided in a way that is not only effective but ultimately more convenient for student, teacher and therapist without the added burden of travel. Teletherapy eradicates many hurdles to traditional on-site service delivery and helps to solve the pervasive shortage of certified professionals. Because location is no longer a barrier to specialized education plans for students with disabilities when teletherapy is conducted, there are many advantages that can be deployed. Increased frequency of engagement is possible along with students receiving specialized care from a clinician that may not be in their direct area. Educational teams, including parents, can work together more easily and engage in face-to-face, student-centered collaboration through videoconference. Practical strategies will be provided for connecting students with qualified therapists without the typical in-person dynamic. In most cases, better therapy outcomes are going to be achieved when treatment is most convenient for the student and educator. This workshop will promote discussion in the field of education to increase advocacy for remote service delivery. It will serve as a resource for those wanting to expand their knowledge of options for students with special needs afforded through innovation.

Keywords: education technology, innovation, student support services, telepractice

Procedia PDF Downloads 245

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 121

Authors: Chongya Song, Kang Yen, Alexander Pons, Jin Liu

Abstract:

In the field of machine learning, the ensemble has been employed as a common methodology to improve the performance upon multiple base classifiers. However, the true predictions are often canceled out by the false ones during consensus due to a phenomenon called “curse of correlation” which is represented as the strong interferences among the predictions produced by the base classifiers. In addition, the existing practices are still not able to effectively mitigate the problem of imbalanced classification. Based on the analysis on our experiment results, we conclude that the two problems are caused by some inherent deficiencies in the approach of consensus. Therefore, we create an enhanced ensemble algorithm which adopts a designed rank-based chain-mode consensus to overcome the two problems. In order to evaluate the proposed ensemble algorithm, we employ a well-known benchmark data set NSL-KDD (the improved version of dataset KDDCup99 produced by University of New Brunswick) to make comparisons between the proposed and 8 common ensemble algorithms. Particularly, each compared ensemble classifier uses the same 22 base classifiers, so that the differences in terms of the improvements toward the accuracy and reliability upon the base classifiers can be truly revealed. As a result, the proposed rank-based chain-mode consensus is proved to be a more effective ensemble solution than the traditional consensus approach, which outperforms the 8 ensemble algorithms by 20% on almost all compared metrices which include accuracy, precision, recall, F1-score and area under receiver operating characteristic curve.

Keywords: consensus, curse of correlation, imbalance classification, rank-based chain-mode ensemble

Procedia PDF Downloads 138

Authors: Lazhar Belkhiri, Ammar Tiri, Lotfi Mouni, Fatma Elhadj Lakouas

Abstract:

This study evaluates the surface water quality in the Kebir Rhumel Basin by analyzing hydrochemical parameters. To assess spatial and temporal variations in water quality, we applied the Water Quality Index (WQI), Mann-Kendall (MK) trend analysis, and hierarchical cluster analysis (HCA). Monthly measurements of eleven hydrochemical parameters were collected across eight stations from January 2016 to December 2020. Calcium and sulfate emerged as the dominant cation and anion, respectively. WQI analysis indicated a high incidence of poor water quality at stations Ain Smara (AS), Beni Haroune (BH), Grarem (GR), and Sidi Khalifa (SK), where 89.5%, 90.6%, 78.2%, and 62.7% of samples, respectively, fell into this category. The MK trend analysis revealed a significant upward trend in WQI at Oued Boumerzoug (ON) and SK stations, signaling temporal deterioration in these areas. HCA grouped the dataset into three clusters, covering approximately 22%, 30%, and 48% of the months, respectively. Within these clusters, specific stations exhibited elevated WQI values: GR and ON in the first cluster, OB and SK in the second, and AS, BH, El Milia (EM), and Hammam Grouz (HG) in the third. Furthermore, approximately 38%, 41%, and 38% of samples in clusters one, two, and three, respectively, were classified as having poor water quality. These findings provide essential insights for policymakers in formulating strategies to restore and manage surface water quality in the region.

Keywords: surface water quality, water quality index (WQI), Mann-Kendall Trend Analysis, hierarchical cluster analysis (HCA), spatial-temporal distribution, Kebir Rhumel Basin

Procedia PDF Downloads 16

Authors: Akankunda Veronicah Karuhanga

Abstract:

Dementia is an age mental disorder that makes victims lose normal functionality that needs delicate attention. It has been technically defined as a clinical syndrome that presents a number of difficulties in speech and other cognitive functions that change someone’s behaviors and can also cause impairments in activities of daily living, not forgetting a range of neurological disorders that bring memory loss and cognitive impairment. Family members are the primary healthcare givers and therefore, the way how they handle the situation in its early stages determines future deterioration syndromes like total memory loss. Unfortunately, most family members are ignorant about this condition and in most cases, the patients are brought to our facilities when their condition was already mismanaged by family members and we thus cannot do much. For example, incontinence can be managed at early stages through potty training or toilet scheduling before resorting to 24/7 diapers which are also not good. Professional Elderly care should be understood and practiced as an extension of homes, not a dumping place for people considered “abnormal” on account of ignorance. Immediate relatives should therefore be sensitized concerning the normalcy of dementia in the context of old age so that they can be understanding and supportive of dementia patients rather than discriminating against them as present-day lepers. There is a need to skill home-based caregivers on how to handle dementia in its early stages. Unless this is done, many of our elderly homes shall be filled with patients who should have been treated and supported from their homes. This skilling of home-based caregivers is a vital intervention because until elderly care is appreciated as a human moral obligation, many transactional rehabilitation centers will crop up and this shall be one of the worst moral decadences of our times.

Keywords: dementia, family, Alzheimers, relevancy

Procedia PDF Downloads 97

Authors: Larry Powell, Seth Polsley, Drew Casey, Tracy Hammond

Abstract:

Human activity recognition (HAR) systems have shown positive performance when recognizing repetitive activities like walking, running, and sleeping. Water-based activities are a reasonably new area for activity recognition. However, water-based activity recognition has largely focused on supporting the elite and competitive swimming population, which already has amazing coordination and proper form. Beginner swimmers are not perfect, and activity recognition needs to support the individual motions to help beginners. Activity recognition algorithms are traditionally built around short segments of timed sensor data. Using a time window input can cause performance issues in the machine learning model. The window’s size can be too small or large, requiring careful tuning and precise data segmentation. In this work, we present a method that uses a time window as the initial segmentation, then separates the data based on the change in the sensor value. Our system uses a multi-phase segmentation method that pulls all peaks and valleys for each axis of an accelerometer placed on the swimmer’s lower back. This results in high recognition performance using leave-one-subject-out validation on our study with 20 beginner swimmers, with our model optimized from our final dataset resulting in an F-Score of 0.95.

Keywords: time window, peak/valley segmentation, feature extraction, beginner swimming, activity recognition

Procedia PDF Downloads 123

Authors: Simone Leonardi, Luca Ardito

Abstract:

Micro-influencers are effective elements in the marketing strategies of companies and institutions because of their capability to create an hyper-engaged audience around a specific topic of interest. In recent years, many scientific approaches and commercial tools have handled the task of detecting this type of social media users. These strategies adopt solutions ranging from rule based machine learning models to deep neural networks and graph analysis on text, images, and account information. This work compares the existing solutions and proposes an ensemble method to generalize them with different input data and social media platforms. The deployed solution combines deep learning models on unstructured data with statistical machine learning models on structured data. We retrieve both social media accounts information and multimedia posts on Twitter and Instagram. These data are mapped into feature vectors for an eXtreme Gradient Boosting (XGBoost) classifier. Sixty different topics have been analyzed to build a rule based gold standard dataset and to compare the performances of our approach against baseline classifiers. We prove the effectiveness of our work by comparing the accuracy, precision, recall, and f1 score of our model with different configurations and architectures. We obtained an accuracy of 0.91 with our best performing model.

Keywords: deep learning, gradient boosting, image processing, micro-influencers, NLP, social media

Procedia PDF Downloads 183

Authors: Kishore Kumar R., Kaustav Sengupta, Shalini Sood Sehgal, Poornima Santhanam

Abstract:

Fashion is a human expression that is constantly changing. One of the prime factors that consistently influences fashion is the change in colour preferences. The role of colour in our everyday lives is very significant. It subconsciously explains a lot about one’s mindset and mood. Analyzing the colours by extracting them from the outfit images is a critical study to examine the individual’s/consumer behaviour. Several research works have been carried out on extracting colours from images, but to the best of our knowledge, there were no studies that extract colours to specific apparel and identify colour patterns geographically. This paper proposes a framework for accurately extracting colours from T-shirt images and predicting dominant colours geographically. The proposed method consists of two stages: first, a U-Net deep learning model is adopted to segment the T-shirts from the images. Second, the colours are extracted only from the T-shirt segments. The proposed method employs the iMaterialist (Fashion) 2019 dataset for the semantic segmentation task. The proposed framework also includes a mechanism for gathering data and analyzing India’s general colour preferences. From this research, it was observed that black and grey are the dominant colour in different regions of India. The proposed method can be adapted to study fashion’s evolving colour preferences.

Keywords: colour analysis in t-shirts, convolutional neural network, encoder-decoder, k-means clustering, semantic segmentation, U-Net model

Procedia PDF Downloads 111

Authors: Rishabh Ambavanekar

Abstract:

Expressive Aphasia (EA) is an oral disability, common among stroke victims, in which the Broca’s area of the brain is damaged, interfering with verbal communication abilities. EA currently has no technological solutions and its only current viable solutions are inefficient or only available to the affluent. This prompts the need for an affordable, innovative solution to facilitate recovery and assist in speech generation. This project proposes a novel concept: using a wearable low-cost electroencephalography (EEG) device-based brain-computer interface (BCI) to translate a user’s inner dialogue into words. A low-cost EEG device was developed and found to be 10 to 100 times less expensive than any current EEG device on the market. As part of the BCI, a machine learning (ML) model was developed and trained using the EEG data. Two stages of testing were conducted to analyze the effectiveness of the device: a proof-of-concept and a final solution test. The proof-of-concept test demonstrated an average accuracy of above 90% and the final solution test demonstrated an average accuracy of above 75%. These two successful tests were used as a basis to demonstrate the viability of BCI research in developing lower-cost verbal communication devices. Additionally, the device proved to not only enable users to verbally communicate but has the potential to also assist in accelerated recovery from the disorder.

Keywords: neurotechnology, brain-computer interface, neuroscience, human-machine interface, BCI, HMI, aphasia, verbal disability, stroke, low-cost, machine learning, ML, image recognition, EEG, signal analysis

Procedia PDF Downloads 119

Authors: Mais Nijim, Rama Devi Chennuboyina, Waseem Al Aqqad

Abstract:

Advances in spatial and spectral resolution of satellite images have led to tremendous growth in large image databases. The data we acquire through satellites, radars and sensors consists of important geographical information that can be used for remote sensing applications such as region planning, disaster management. Spatial data classification and object recognition are important tasks for many applications. However, classifying objects and identifying them manually from images is a difficult task. Object recognition is often considered as a classification problem, this task can be performed using machine-learning techniques. Despite of many machine-learning algorithms, the classification is done using supervised classifiers such as Support Vector Machines (SVM) as the area of interest is known. We proposed a classification method, which considers neighboring pixels in a region for feature extraction and it evaluates classifications precisely according to neighboring classes for semantic interpretation of region of interest (ROI). A dataset has been created for training and testing purpose; we generated the attributes by considering pixel intensity values and mean values of reflectance. We demonstrated the benefits of using knowledge discovery and data-mining techniques, which can be on image data for accurate information extraction and classification from high spatial resolution remote sensing imagery.

Keywords: remote sensing, object recognition, classification, data mining, waterbody identification, feature extraction

Procedia PDF Downloads 339

Authors: L. Yu, W. K. Li, S. K. Ong, A. Y. C. Nee

Abstract:

In this paper, a scalable augmented reality framework for handheld devices is presented. The presented framework is enabled by using a server-client data communication structure, in which the search for tracking targets among a database of images is performed on the server-side while pixel-wise 3D tracking is performed on the client-side, which, in this case, is a handheld mobile device. Image search on the server-side adopts a residual-enhanced image descriptors representation that gives the framework a scalability property. The tracking algorithm on the client-side is based on a gravity-aligned feature descriptor which takes the advantage of a sensor-equipped mobile device and an optimized intensity-based image alignment approach that ensures the accuracy of 3D tracking. Automatic content streaming is achieved by using a key-frame selection algorithm, client working phase monitoring and standardized rules for content communication between the server and client. The recognition accuracy test performed on a standard dataset shows that the method adopted in the presented framework outperforms the Bag-of-Words (BoW) method that has been used in some of the previous systems. Experimental test conducted on a set of video sequences indicated the real-time performance of the tracking system with a frame rate at 15-30 frames per second. The presented framework is exposed to be functional in practical situations with a demonstration application on a campus walk-around.

Keywords: augmented reality framework, server-client model, vision-based tracking, image search

Procedia PDF Downloads 275

Authors: Jack R. McKenzie, Peter A. Appleby, Thomas House, Neil Walton

Abstract:

Cold-start is a notoriously difficult problem which can occur in recommendation systems, and arises when there is insufficient information to draw inferences for users or items. To address this challenge, a contextual bandit algorithm – the Fast Approximate Bayesian Contextual Cold Start Learning algorithm (FAB-COST) – is proposed, which is designed to provide improved accuracy compared to the traditionally used Laplace approximation in the logistic contextual bandit, while controlling both algorithmic complexity and computational cost. To this end, FAB-COST uses a combination of two moment projection variational methods: Expectation Propagation (EP), which performs well at the cold start, but becomes slow as the amount of data increases; and Assumed Density Filtering (ADF), which has slower growth of computational cost with data size but requires more data to obtain an acceptable level of accuracy. By switching from EP to ADF when the dataset becomes large, it is able to exploit their complementary strengths. The empirical justification for FAB-COST is presented, and systematically compared to other approaches on simulated data. In a benchmark against the Laplace approximation on real data consisting of over 670, 000 impressions from autotrader.co.uk, FAB-COST demonstrates at one point increase of over 16% in user clicks. On the basis of these results, it is argued that FAB-COST is likely to be an attractive approach to cold-start recommendation systems in a variety of contexts.

Keywords: cold-start learning, expectation propagation, multi-armed bandits, Thompson Sampling, variational inference

Procedia PDF Downloads 108

Authors: Pattra Pukdeekiat, Siriluk Ruangrungrote

Abstract:

This work was originated to precisely determine direct solar radiation by using atmospheric physics models since the accurate prediction of solar radiation is necessary and useful for solar energy applications including atmospheric research. The possible models and techniques for a calculation of regional direct solar radiation were challenging and compulsory for the case of unavailable instrumental measurement. The investigation was mathematically governed by six astronomical parameters i.e. declination (δ), hour angle (ω), solar time, solar zenith angle (θz), extraterrestrial radiation (Iso) and eccentricity (E0) along with two atmospheric parameters i.e. air mass (mr) and dew point temperature at Bangna meteorological station (13.67° N, 100.61° E) in Bangkok, Thailand. Analyses of five models of solar radiation determination with the assumption of clear sky were applied accompanied by three statistical tests: Mean Bias Difference (MBD), Root Mean Square Difference (RMSD) and Coefficient of determination (R2) in order to validate the accuracy of obtainable results. The calculated direct solar radiation was in a range of 491-505 Watt/m2 with relative percentage error 8.41% for winter and 532-540 Watt/m2 with relative percentage error 4.89% for summer 2014. Additionally, dataset of seven continuous days, representing both seasons were considered with the MBD, RMSD and R2 of -0.08, 0.25, 0.86 and -0.14, 0.35, 3.29, respectively, which belong to Kumar model for winter and CSR model for summer. In summary, the determination of direct solar radiation based on atmospheric models and empirical equations could advantageously provide immediate and reliable values of the solar components for any site in the region without a constraint of actual measurement.

Keywords: atmospheric physics models, astronomical parameters, atmospheric parameters, clear sky condition

Procedia PDF Downloads 409

Authors: A. M. John-Otumu, M. M. Rahman, M. C. Onuoha, E. P. Ojonugwa

Abstract:

A Convolutional Neural Network (CNN) model for predicting Lassa fever was built using Python 3.8.0 programming language, alongside Keras 2.2.4 and TensorFlow 2.6.1 libraries as the development environment in order to reduce the current high risk of Lassa fever in West Africa, particularly in Nigeria. The study was prompted by some major flaws in existing conventional laboratory equipment for diagnosing Lassa fever (RT-PCR), as well as flaws in AI-based techniques that have been used for probing and prognosis of Lassa fever based on literature. There were 15,679 blood smear microscopic image datasets collected in total. The proposed model was trained on 70% of the dataset and tested on 30% of the microscopic images in avoid overfitting. A 3x3x3 convolution filter was also used in the proposed system to extract features from microscopic images. The proposed CNN-based model had a recall value of 96%, a precision value of 93%, an F1 score of 95%, and an accuracy of 94% in predicting and accurately classifying the images into clean or infected samples. Based on empirical evidence from the results of the literature consulted, the proposed model outperformed other existing AI-based techniques evaluated. If properly deployed, the model will assist physicians, medical laboratory scientists, and patients in making accurate diagnoses for Lassa fever cases, allowing the mortality rate due to the Lassa fever virus to be reduced through sound decision-making.

Keywords: artificial intelligence, ANN, blood smear, CNN, deep learning, Lassa fever

Procedia PDF Downloads 120

Authors: Benkouiten Imene, Chabli Ouerdia, Boutoutaou Hamid, Kadri Nesrine, Bouledroua Omar

Abstract:

Algeria is actively enhancing gas productivity by augmenting the supply flow. However, this effort has led to increased internal pressure, posing a potential risk to the pipeline's integrity, particularly in the presence of corrosion defects. Sonatrach relies on a vast network of pipelines spanning 24,000 kilometers for the transportation of gas and oil. The aging of these pipelines raises the likelihood of corrosion both internally and externally, heightening the risk of ruptures. To address this issue, a comprehensive inspection is imperative, utilizing specialized scraping tools. These advanced tools furnish a detailed assessment of all pipeline defects. It is essential to recalculate the pressure parameters to safeguard the corroded pipeline's integrity while ensuring the continuity of production. In this context, Sonatrach employs symbolic pressure limit calculations, such as ASME B31G (2009) and the modified ASME B31G (2012). The aim of this study is to perform a comparative analysis of various limit pressure calculation methods documented in the literature, namely DNV RP F-101, SHELL, P-CORRC, NETTO, and CSA Z662. This comparative assessment will be based on a dataset comprising 329 burst tests published in the literature. Ultimately, we intend to introduce a novel approach grounded in the finite element method, employing ANSYS software.

Keywords: pipeline burst pressure, burst test, corrosion defect, corroded pipeline, finite element method

Procedia PDF Downloads 58

Authors: Tae-Uk Yun, Pullip Chung, Kee-Young Kwahk, Hyunchul Ahn

Abstract:

Fake news is defined as the news articles that are intentionally and verifiably false, and could mislead readers. Spread of fake news may provoke anxiety, chaos, fear, or irrational decisions of the public. Thus, detecting fake news and preventing its spread has become very important issue in our society. However, due to the huge amount of fake news produced every day, it is almost impossible to identify it by a human. Under this context, researchers have tried to develop automated fake news detection using machine learning techniques over the past years. But, there have been no prior studies proposed an automated fake news detection method for Korean news to our best knowledge. In this study, we aim to detect Korean fake news using text mining and machine learning techniques. Our proposed method consists of two steps. In the first step, the news contents to be analyzed is convert to quantified values using various text mining techniques (topic modeling, TF-IDF, and so on). After that, in step 2, classifiers are trained using the values produced in step 1. As the classifiers, machine learning techniques such as logistic regression, backpropagation network, support vector machine, and deep neural network can be applied. To validate the effectiveness of the proposed method, we collected about 200 short Korean news from Seoul National University’s FactCheck. which provides with detailed analysis reports from 20 media outlets and links to source documents for each case. Using this dataset, we will identify which text features are important as well as which classifiers are effective in detecting Korean fake news.

Keywords: fake news detection, Korean news, machine learning, text mining

Procedia PDF Downloads 275

Authors: C. L. Huang, J. J. Sia

Abstract:

The interest-based social networks, also known as social bookmark sharing systems, are useful platforms for people to conveniently read and collect internet resources. These platforms also providing function of social networks, and users can share and explore internet resources from the social networks. Providing personalized internet resources to users is an important issue on these platforms. This study uses two types of relationship on the social networks—following and follower and proposes a collaborative recommender system, consisting of two main steps. First, this study calculates the relationship strength between the target user and the target user's followings and followers to find top-N similar neighbors. Second, from the top-N similar neighbors, the articles (internet resources) that may interest the target user are recommended to the target user. In this system, users can efficiently obtain recent, related and diverse internet resources (knowledge) from the interest-based social network. This study collected the experimental dataset from Diigo, which is a famous bookmark sharing system. The experimental results show that the proposed recommendation model is more accurate than two traditional baseline recommendation models but slightly lower than the cosine model in accuracy. However, in the metrics of the diversity and executing time, our proposed model outperforms the cosine model.

Keywords: recommender systems, social networks, tagging, bookmark sharing systems, collaborative recommender systems, knowledge management

Procedia PDF Downloads 172

Authors: Kolade Olawande Owoeye, George Weir

Abstract:

Terrorism and extremism activities on the internet are becoming the most significant threats to national security because of their potential dangers. In response to this challenge, law enforcement and security authorities are actively implementing comprehensive measures by countering the use of the internet for terrorism. To achieve the measures, there is need for intelligence gathering via the internet. This includes real-time monitoring of potential websites that are used for recruitment and information dissemination among other operations by extremist groups. However, with billions of active webpages, real-time monitoring of all webpages become almost impossible. To narrow down the search domain, there is a need for efficient webpage classification techniques. This research proposed a new approach tagged: SentiPosit-based method. SentiPosit-based method combines features of the Posit-based method and the Sentistrenght-based method for classification of terrorism and extremism webpages. The experiment was carried out on 7500 webpages obtained through TENE-webcrawler by International Cyber Crime Research Centre (ICCRC). The webpages were manually grouped into three classes which include the ‘pro-extremist’, ‘anti-extremist’ and ‘neutral’ with 2500 webpages in each category. A supervised learning algorithm is then applied on the classified dataset in order to build the model. Results obtained was compared with existing classification method using the prediction accuracy and runtime. It was observed that our proposed hybrid approach produced a better classification accuracy compared to existing approaches within a reasonable runtime.

Keywords: sentiposit, classification, extremism, terrorism

Procedia PDF Downloads 278