Search results for: classifiers accuracy

Authors: James Rigor Camacho, Wansu Lim

Abstract:

Over the last few years, the development of new wearable and processing technologies has accelerated in order to harness physiological data such as electroencephalograms (EEGs) for EEG-based applications. EEG has been demonstrated to be a source of emotion recognition signals with the highest classification accuracy among physiological signals. However, when emotion recognition systems are used for real-time classification, the training unit is frequently left to run offline or in the cloud rather than working locally on the edge. That strategy has hampered research, and the full potential of using an edge AI device has yet to be realized. Edge AI devices are computers with high performance that can process complex algorithms. It is capable of collecting, processing, and storing data on its own. It can also analyze and apply complicated algorithms like localization, detection, and recognition on a real-time application, making it a powerful embedded device. The NVIDIA Jetson series, specifically the Jetson Nano device, was used in the implementation. The cEEGrid, which is integrated to the open-source brain computer-interface platform (OpenBCI), is used to collect EEG signals. An EEG-based real-time emotion recognition system on Edge AI is proposed in this paper. To perform graphical spectrogram categorization of EEG signals and to predict emotional states based on input data properties, machine learning-based classifiers were used. Until the emotional state was identified, the EEG signals were analyzed using the K-Nearest Neighbor (KNN) technique, which is a supervised learning system. In EEG signal processing, after each EEG signal has been received in real-time and translated from time to frequency domain, the Fast Fourier Transform (FFT) technique is utilized to observe the frequency bands in each EEG signal. To appropriately show the variance of each EEG frequency band, power density, standard deviation, and mean are calculated and employed. The next stage is to identify the features that have been chosen to predict emotion in EEG data using the K-Nearest Neighbors (KNN) technique. Arousal and valence datasets are used to train the parameters defined by the KNN technique.Because classification and recognition of specific classes, as well as emotion prediction, are conducted both online and locally on the edge, the KNN technique increased the performance of the emotion recognition system on the NVIDIA Jetson Nano. Finally, this implementation aims to bridge the research gap on cost-effective and efficient real-time emotion recognition using a resource constrained hardware device, like the NVIDIA Jetson Nano. On the cutting edge of AI, EEG-based emotion identification can be employed in applications that can rapidly expand the research and implementation industry's use.

Keywords: edge AI device, EEG, emotion recognition system, supervised learning algorithm, sensors

Procedia PDF Downloads 84

Authors: Regis Pochon, Nicolas Stefaniak, Veronique Baltazart, Pamela Gobin

Abstract:

Anxiety is known to have an impact on working memory. In reasoning or memory tasks, individuals with anxiety tend to show longer response times and poorer performance. Furthermore, there is a memory bias for negative information in anxiety. Given the crucial role of working memory in lexical learning, anxious students may encounter more difficulties in learning to read and spell. Anxiety could even affect an earlier learning, that is the activation of phonological representations, which are decisive for the learning of reading and writing. The aim of this study is to compare the access to phonological representations of beginning readers and writers according to their level of anxiety, using an auditory lexical decision task. Eighty students of 6- to 9-years-old completed the French version of the Revised Children's Manifest Anxiety Scale and were then divided into four anxiety groups according to their total score (Low, Median-Low, Median-High and High). Two set of eighty-one stimuli (words and non-words) have been auditory presented to these students by means of a laptop computer. Stimuli words were selected according to their emotional valence (positive, negative, neutral). Students had to decide as quickly and accurately as possible whether the presented stimulus was a real word or not (lexical decision). Response times and accuracy were recorded automatically on each trial. It was anticipated a) longer response times for the Median-High and High anxiety groups in comparison with the two others groups, b) faster response times for negative-valence words in comparison with positive and neutral-valence words only for the Median-High and High anxiety groups, c) lower response accuracy for Median-High and High anxiety groups in comparison with the two others groups, d) better response accuracy for negative-valence words in comparison with positive and neutral-valence words only for the Median-High and High anxiety groups. Concerning the response times, our results showed no difference between the four groups. Furthermore, inside each group, the average response times was very close regardless the emotional valence. Otherwise, group differences appear when considering the error rates. Median-High and High anxiety groups made significantly more errors in lexical decision than Median-Low and Low groups. Better response accuracy, however, is not found for negative-valence words in comparison with positive and neutral-valence words in the Median-High and High anxiety groups. Thus, these results showed a lower response accuracy for above-median anxiety groups than below-median groups but without specificity for the negative-valence words. This study suggests that anxiety can negatively impact the lexical processing in young students. Although the lexical processing speed seems preserved, the accuracy of this processing may be altered in students with moderate or high level of anxiety. This finding has important implication for the prevention of reading and spelling difficulties. Indeed, during these learnings, if anxiety affects the access to phonological representations, anxious students could be disturbed when they have to match phonological representations with new orthographic representations, because of less efficient lexical representations. This study should be continued in order to precise the impact of anxiety on basic school learning.

Keywords: anxiety, emotional valence, childhood, lexical access

Procedia PDF Downloads 270

Authors: R. Christopher, C. Brandt, N. Damons

Abstract:

Background: The sequence of prevention model states that by constant assessment of injury, injury mechanisms and risk factors are identified, highlighting that collecting and recording of data is a core approach for preventing injuries. Several screening tools are available for use in the clinical setting. These screening techniques only recently received research attention, hence there is a dearth of inconsistent and controversial data regarding their applicability, validity, and reliability. Several systematic reviews related to common soccer injuries have been conducted; however, none of them addressed the screening tools for common soccer injuries. Objectives: The purpose of this study was to conduct a review of screening tools and their accuracy for common injuries in soccer. Methods: A systematic scoping review was performed based on the Joanna Briggs Institute procedure for conducting systematic reviews. Databases such as SPORT Discus, Cinahl, Medline, Science Direct, PubMed, and grey literature were used to access suitable studies. Some of the key search terms included: injury screening, screening, screening tool accuracy, injury prevalence, injury prediction, accuracy, validity, specificity, reliability, sensitivity. All types of English studies dating back to the year 2000 were included. Two blind independent reviewers selected and appraised articles on a 9-point scale for inclusion as well as for the risk of bias with the ACROBAT-NRSI tool. Data were extracted and summarized in tables. Plot data analysis was done, and sensitivity and specificity were analyzed with their respective 95% confidence intervals. I² statistic was used to determine the proportion of variation across studies. Results: The initial search yielded 95 studies, of which 21 were duplicates, and 54 excluded. A total of 10 observational studies were included for the analysis: 3 studies were analysed quantitatively while the remaining 7 were analysed qualitatively. Seven studies were graded low and three studies high risk of bias. Only high methodological studies (score > 9) were included for analysis. The pooled studies investigated tools such as the Functional Movement Screening (FMS™), the Landing Error Scoring System (LESS), the Tuck Jump Assessment, the Soccer Injury Movement Screening (SIMS), and the conventional hamstrings to quadriceps ratio. The accuracy of screening tools was of high reliability, sensitivity and specificity (calculated as ICC 0.68, 95% CI: 52-0.84; and 0.64, 95% CI: 0.61-0.66 respectively; I² = 13.2%, P=0.316). Conclusion: Based on the pooled results from the included studies, the FMS™ has a good inter-rater and intra-rater reliability. FMS™ is a screening tool capable of screening for common soccer injuries, and individual FMS™ scores are a better determinant of performance in comparison with the overall FMS™ score. Although meta-analysis could not be done for all the included screening tools, qualitative analysis also indicated good sensitivity and specificity of the individual tools. Higher levels of evidence are, however, needed for implication in evidence-based practice.

Keywords: accuracy, screening tools, sensitivity, soccer injuries, specificity

Procedia PDF Downloads 155

Authors: S. H. J. Liu

Abstract:

This paper aims to explore the role of peer Corrective Feedback (CF) in improving written productions by English-as-a- foreign-language (EFL) learners who work together via Wikispaces. It attempted to determine the effect of peer CF on form accuracy in English, such as grammar and lexis. Thirty-four EFL learners at the tertiary level were randomly assigned into the experimental (with peer feedback) or the control (without peer feedback) group; each group was subdivided into small groups of two or three. This resulted in six and seven small groups in the experimental and control groups, respectively. In the experimental group, each learner played a role as an assessor (providing feedback to others), as well as an assessee (receiving feedback from others). Each participant was asked to compose his/her written work and revise it based on the feedback. In the control group, on the other hand, learners neither provided nor received feedback but composed and revised their written work on their own. Data collected from learners’ compositions and post-task interviews were analyzed and reported in this study. Following the completeness of three writing tasks, 10 participants were selected and interviewed individually regarding their perception of collaborative learning in the Computer-Mediated Communication (CMC) environment. Language aspects to be analyzed included lexis (e.g., appropriate use of words), verb tenses (e.g., present and past simple), prepositions (e.g., in, on, and between), nouns, and articles (e.g., a/an). Feedback types consisted of CF, affective, suggestive, and didactic. Frequencies of feedback types and the accuracy of the language aspects were calculated. The results first suggested that accurate items were found more in the experimental group than in the control group. Such results entail that those who worked collaboratively outperformed those who worked non-collaboratively on the accuracy of linguistic aspects. Furthermore, the first type of CF (e.g., corrections directly related to linguistic errors) was found to be the most frequently employed type, whereas affective and didactic were the least used by the experimental group. The results further indicated that most participants perceived that peer CF was helpful in improving the language accuracy, and they demonstrated a favorable attitude toward working with others in the CMC environment. Moreover, some participants stated that when they provided feedback to their peers, they tended to pay attention to linguistic errors in their peers’ work but overlook their own errors (e.g., past simple tense) when writing. Finally, L2 or FL teachers or practitioners are encouraged to employ CMC technologies to train their students to give each other feedback in writing to improve the accuracy of the language and to motivate them to attend to the language system.

Keywords: peer corrective feedback, computer-mediated communication (CMC), second or foreign language (L2 or FL) learning, Wikispaces

Procedia PDF Downloads 227

Authors: Ariangelo Hauer Dias Filho, Gustavo Antoniácomi de Carvalho, Benjamim de Melo Carvalho

Abstract:

The work´s purpose was to evaluate the possibility of manufacturing casting tools utilizing Fused Filament Fabrication, a 3D printing technique, without any post-processing on the printed part. Taguchi Orthogonal array was used to evaluate the influence of extrusion temperature, bed temperature, layer height, and infill on the dimensional accuracy of a 3D-Printed Polymer Model. A Zeiss T-SCAN CS 3D Scanner was used for dimensional evaluation of the printed parts within the limit of ±0,2 mm. The mold capabilities were tested with the printed model to check how it would interact with the green sand. With little adjustments in the 3D model, it was possible to produce rapid tools without the need for post-processing for iron casting. The results are important for reducing time and cost in the development of such tools.

Keywords: additive manufacturing, Taguchi method, rapid tooling, fused filament fabrication, casting mold

Procedia PDF Downloads 120

Authors: Carla Van De Sande, Jana Vandenberg

Abstract:

Just like physical skills, cognitive skills grow rusty over time unless they are regularly used and practiced, so academic breaks can have negative consequences on student learning and success. The Keeping in School Shape (KiSS) program is an engaging, accessible, and cost-effective intervention that harnesses the benefits of retrieval practice by using technology to help students maintain proficiency over breaks from school by delivering a daily review problem via text message or email. A growth mindset is promoted through feedback messages encouraging students to try again if they get a problem wrong and to take on a challenging problem if they get a problem correct. This paper reports on the relationship between confidence, accuracy, and decision-making during the implementation of the KiSS Program at a large university during winter break for students enrolled in an engineering introductory Calculus course sequence.

Keywords: growth mindset, learning loss, on-the-go learning, retrieval practice

Procedia PDF Downloads 187

Authors: Nirmal Sugathan, Santosh Maruthy

Abstract:

Background: A considerable number of studies have evidenced that phonological encoding (PE) and working memory (WM) skills operate differently in adults who stutter (AWS). In order to tap these skills, several paradigms have been employed such as phonological priming, phoneme monitoring, and nonword repetition tasks. This study, however, utilizes a word jumble paradigm to assess both PE and WM using different modalities and this may give a better understanding of phonological processing deficits in AWS. Aim: The present study investigated PE and WM abilities in conjunction with lexical access in AWS using jumbled words. The study also aimed at investigating the effect of increase in cognitive load on phonological processing in AWS by comparing the speech reaction time (SRT) and accuracy scores across various syllable lengths. Method: Participants were 11 AWS (Age range=19-26) and 11 adults who do not stutter (AWNS) (Age range=19-26) matched for age, gender and handedness. Stimuli: Ninety 3-, 4-, and 5-syllable jumbled words (JWs) (n=30 per syllable length category) constructed from Kannada words served as stimuli for jumbled word paradigm. In order to generate jumbled words (JWs), the syllables in the real words were randomly transpositioned. Procedures: To assess PE, the JWs were presently visually using DMDX software and for WM task, JWs were presented through auditory mode through headphones. The participants were asked to silently manipulate the jumbled words to form a Kannada real word and verbally respond once. The responses for both tasks were audio recorded using record function in DMDX software and the recorded responses were analyzed using PRAAT software to calculate the SRT. Results: SRT: Mann-Whitney test results demonstrated that AWS performed significantly slower on both tasks (p < 0.001) as indicated by increased SRT. Also, AWS presented with increased SRT on both the tasks in all syllable length conditions (p < 0.001). Effect of syllable length: Wilcoxon signed rank test was carried out revealed that, on task assessing PE, the SRT of 4syllable JWs were significantly higher in both AWS (Z= -2.93, p=.003) and AWNS (Z= -2.41, p=.003) when compared to 3-syllable words. However, the findings for 4- and 5-syllable words were not significant. Task Accuracy: The accuracy scores were calculated for three syllable length conditions for both PE and PM tasks and were compared across the groups using Mann-Whitney test. The results indicated that the accuracy scores of AWS were significantly below that of AWNS in all the three syllable conditions for both the tasks (p < 0.001). Conclusion: The above findings suggest that PE and WM skills are compromised in AWS as indicated by increased SRT. Also, AWS were progressively less accurate in descrambling JWs of increasing syllable length and this may be interpreted as, rather than existing as a uniform deficiency, PE and WM deficits emerge when the cognitive load is increased. AWNS exhibited increased SRT and increased accuracy for JWs of longer syllable length whereas AWS was not benefited from increasing the reaction time, thus AWS had to compromise for both SRT and accuracy while solving JWs of longer syllable length.

Keywords: adults who stutter, phonological ability, working memory, encoding, jumbled words

Procedia PDF Downloads 215

Authors: Amien Rahardjo, Faiz Husnayain, Iwa Garniwa

Abstract:

PLN used the kWh meter to determine the amount of energy consumed by the household customers. High precision of kWh meter is needed in order to give accuracy results as the accuracy can be decreased due to the presence of harmonic. In this study, an estimation of active power consumed was developed. Based on the first year study results, the largest deviation due to harmonics can reach up to 9.8% in 2200VA and 12.29% in 3500VA with kWh meter analog. In the second year of study, deviation of digital customer meter reaches 2.01% and analog meter up to 9.45% for 3500VA household customers. The aim of this research is to produce an estimation system to calculate the total energy consumed by household customer using analog meter so the losses due to irregularities PLN recording of energy consumption based on the measurement used Analog kWh-meter installed is avoided.

Keywords: harmonics estimation, harmonic distortion, kWh meters analog and digital, THD, household customers

Procedia PDF Downloads 465

Authors: Sanjin Kršćanski, Josip Brnić

Abstract:

Virtual Crack Closure Technique (VCCT) is a method used for calculating stress intensity factor (SIF) of a cracked body that is easily implemented on top of basic finite element (FE) codes and as such can be applied on the various component geometries. It is a relatively simple method that does not require any special finite elements to be used and is usually used for calculating stress intensity factors at the crack tip for components made of brittle materials. This paper studies applicability and accuracy of VCCT applied on standard metal specimens containing trough thickness crack, subjected to an in-plane bending load. Finite element analyses were performed using regular 4-node, regular 8-node and a modified quarter-point 8-node 2D elements. Stress intensity factor was calculated from the FE model results for a given crack length, using data available from FE analysis and a custom programmed algorithm based on virtual crack closure technique. Influence of the finite element size on the accuracy of calculated SIF was also studied. The final part of this paper includes a comparison of calculated stress intensity factors with results obtained from analytical expressions found in available literature and in ASTM standard. Results calculated by this algorithm based on VCCT were found to be in good correlation with results obtained with mentioned analytical expressions.

Keywords: VCCT, stress intensity factor, finite element analysis, 2D finite elements, bending

Procedia PDF Downloads 278

Authors: Chi Wu, Dean Wu, Wen-Te Liu, Cheng-Yu Tsai, Shin-Mei Hsu, Yin-Tzu Lin, Ru-Yin Yang

Abstract:

Background: The results of previous studies compared the benefits and risks of receiving insomnia medication. However, the effects between hypnotic drugs used and enhancement of sleep quality were still unclear. Objective: The aim of this study is to establish a prediction model for hypnotic drugs' dosage used for insomnia subjects and associated the relationship between sleep stage ratio change and drug types. Methodologies: According to American Academy of Sleep Medicine (AASM) guideline, sleep stages were classified and transformed to hypnogram via the polysomnography (PSG) in a hospital in New Taipei City (Taiwan). The subjects with diagnosis for insomnia without receiving hypnotic drugs treatment were be set as the comparison group. Conversely, hypnotic drugs dosage within the past three months was obtained from the clinical registration for each subject. Furthermore, the collecting subjects were divided into two groups for training and testing. After training convolution neuron network (CNN) to predict types of hypnotics used and dosages are taken, the test group was used to evaluate the accuracy of classification. Results: We recruited 76 subjects in this study, who had been done PSG for transforming hypnogram from their sleep stages. The accuracy of dosages obtained from confusion matrix on the test group by CNN is 81.94%, and accuracy of hypnotic drug types used is 74.22%. Moreover, the subjects with high ratio of wake stage were correctly classified as requiring medical treatment. Conclusion: CNN with hypnogram was potentially used for adjusting the dosage of hypnotic drugs and providing subjects to pre-screening the types of hypnotic drugs taken.

Keywords: convolution neuron network, hypnotic drugs, insomnia, polysomnography

Procedia PDF Downloads 168

Authors: Sahar Khedr, Dina Sayed, Ayman Hanafy

Abstract:

Arabic is one of the most ancient and critical languages in the world. It has over than 250 million Arabic native speakers and more than twenty countries having Arabic as one of its official languages. In the past decade, we have witnessed a rapid evolution in smart devices, social network and technology sector which led to the need to provide tools and libraries that properly tackle the Arabic language in different domains. Stemming is one of the most crucial linguistic fundamentals. It is used in many applications especially in information extraction and text mining fields. The motivation behind this work is to enhance the Arabic light stemmer to serve the data mining industry and leverage it in an open source community. The presented implementation works on enhancing the Arabic light stemmer by utilizing and enhancing an algorithm that provides an extension for a new set of rules and patterns accompanied by adjusted procedure. This study has proven a significant enhancement for better search accuracy with an average 10% improvement in comparison with previous works.

Keywords: Arabic data mining, Arabic Information extraction, Arabic Light stemmer, Arabic stemmer

Procedia PDF Downloads 285

Authors: Sylvain Devie, Pierre-Philippe Robet, Yannick Aoustin, Maxime Gautier

Abstract:

The aim of this paper is to show that the observation of the external effort and the sensor-less control of a system is limited by the mechanical system. First, the model of a one-joint robot with a prismatic joint is presented. Based on this model, two different procedures were performed in order to identify the mechanical parameters of the system and observe the external effort applied on it. Experiments have proven that the accuracy of the force observer, based on the DC motor current, is limited by the mechanics of the robot. The sensor-less control will be limited by the accuracy in estimation of the mechanical parameters and by the maximum static friction force, that is the minimum force which can be observed in this case. The consequence of this limitation is that industrial robots without specific design are not well adapted to perform sensor-less precision tasks. Finally, an efficient control law is presented for high effort applications.

Keywords: control, identification, robot, co-manipulation, sensor-less

Procedia PDF Downloads 141

Authors: ChunYi Peng, Wei Hsuan CHeng, Shyh Kuang Ueng

Abstract:

This study focuses on the application of self-organizing maps (SOM) technology in analyzing credit card transaction data, aiming to enhance the accuracy and efficiency of fraud detection. Som, as an artificial neural network, is particularly suited for pattern recognition and data classification, making it highly effective for the complex and variable nature of credit card transaction data. By analyzing transaction characteristics with SOM, the research identifies abnormal transaction patterns that could indicate potentially fraudulent activities. Moreover, this study has developed a specialized visualization tool to intuitively present the relationships between SOM analysis outcomes and transaction data, aiding financial institution personnel in quickly identifying and responding to potential fraud, thereby reducing financial losses. Additionally, the research explores the integration of SOM technology with composite intelligent system technologies (including finite state machines, fuzzy logic, and decision trees) to further improve fraud detection accuracy. This multimodal approach provides a comprehensive perspective for identifying and understanding various types of fraud within credit card transactions. In summary, by integrating SOM technology with visualization tools and composite intelligent system technologies, this research offers a more effective method of fraud detection for the financial industry, not only enhancing detection accuracy but also deepening the overall understanding of fraudulent activities.

Keywords: self-organizing map technology, fraud detection, information visualization, data analysis, composite intelligent system technologies, decision support technologies

Procedia PDF Downloads 30

Authors: Peng, Chun-Yi, Chen, Wei-Hsuan, Ueng, Shyh-Kuang

Abstract:

This study focuses on the application of self-organizing maps (SOM) technology in analyzing credit card transaction data, aiming to enhance the accuracy and efficiency of fraud detection. Som, as an artificial neural network, is particularly suited for pattern recognition and data classification, making it highly effective for the complex and variable nature of credit card transaction data. By analyzing transaction characteristics with SOM, the research identifies abnormal transaction patterns that could indicate potentially fraudulent activities. Moreover, this study has developed a specialized visualization tool to intuitively present the relationships between SOM analysis outcomes and transaction data, aiding financial institution personnel in quickly identifying and responding to potential fraud, thereby reducing financial losses. Additionally, the research explores the integration of SOM technology with composite intelligent system technologies (including finite state machines, fuzzy logic, and decision trees) to further improve fraud detection accuracy. This multimodal approach provides a comprehensive perspective for identifying and understanding various types of fraud within credit card transactions. In summary, by integrating SOM technology with visualization tools and composite intelligent system technologies, this research offers a more effective method of fraud detection for the financial industry, not only enhancing detection accuracy but also deepening the overall understanding of fraudulent activities.

Keywords: self-organizing map technology, fraud detection, information visualization, data analysis, composite intelligent system technologies, decision support technologies

Procedia PDF Downloads 35

Authors: S. Athiralakshmi, B.E. Bhojaraja, U. Pruthviraj

Abstract:

In agriculture, remote sensing is applied for monitoring of plant development, evaluating of physiological processes and growth conditions. Especially valuable are the spatio-temporal aspects of the remotely sensed data in detecting crop state differences and stress situations. In this study, hyperion imagery is used for classifying arecanut crops based on their age so that these maps can be used in yield estimation of crops, irrigation purposes, applying fertilizers etc. Traditional hard classifiers assigns the mixed pixels to the dominant classes. The proposed method uses a sub pixel level classifier called linear spectral unmixing available in ENVI software. It provides the relative abundance of surface materials and the context within a pixel that may be a potential solution to effectively identifying the land-cover distribution. Validation is done referring to field spectra collected using spectroradiometer and the ground control points obtained from GPS.

Keywords: FLAASH, Hyperspectral remote sensing, Linear Spectral Unmixing, Spectral Angle Mapper Classifier.

Procedia PDF Downloads 495

Authors: Eyob Seife, Molla Alemayaehu, Tesfalem Teshome, Bereket Seyoum, Behailu Getachew

Abstract:

Globally, immunization averts between 2 and 3 million deaths yearly, but Vaccine-Preventable Diseases still account for more in Sub-Saharan African countries and takes the majority of under-five deaths yearly, which indicates the need for consistent and on-time information to have evidence-based decision so as to save lives of these vulnerable groups. However, ensuring data of sufficient quality and promoting an information-use culture at the point of collection remains critical and challenging, especially in remote areas where the Ararso district is selected based on a hypothesis of there is a difference in reported and recounted immunization data consistency. Data quality is dependent on different factors where organizational, behavioral, technical and contextual factors are the mentioned ones. A cross-sectional quantitative study was conducted on September 2022 in the Ararso district. The study used the world health organization (WHO) recommended data quality self-assessment (DQS) tools. Immunization tally sheets, registers and reporting documents were reviewed at 4 health facilities (1 health center and 3 health posts) of primary health care units for one fiscal year (12 months) to determine the accuracy ratio, availability and timeliness of reports. The data was collected by trained DQS assessors to explore the quality of monitoring systems at health posts, health centers, and at the district health office. A quality index (QI), availability and timeliness of reports were assessed. Accuracy ratios formulated were: the first and third doses of pentavalent vaccines, fully immunized (FI), TT2+ and the first dose of measles-containing vaccines (MCV). In this study, facility-level results showed poor timeliness at all levels and both over-reporting and under-reporting were observed at all levels when computing the accuracy ratio of registration to health post reports found at health centers for almost all antigens verified. A quality index (QI) of all facilities also showed poor results. Most of the verified immunization data accuracy ratios were found to be relatively better than that of quality index and timeliness of reports. So attention should be given to improving the capacity of staff, timeliness of reports and quality of monitoring system components, namely recording, reporting, archiving, data analysis and using information for decisions at all levels, especially in remote and areas.

Keywords: accuracy ratio, ararso district, quality of monitoring system, regular immunization program, timeliness of reports, Somali region-Ethiopia

Procedia PDF Downloads 46

Authors: Aurore Cauquis, Philippe Heinrich, Mario Ricchiuto, Audrey Gailler

Abstract:

In this talk, we look for an accurate time scheme to model the propagation of waves. Several numerical schemes have been developed to solve the extended weakly nonlinear weakly dispersive Boussinesq Equations. The temporal schemes used are two Lax-Wendroff schemes, second or third order accurate, two Runge-Kutta schemes of second and third order and a simplified third order accurate Lax-Wendroff scheme. Spatial derivatives are evaluated with fourth order accuracy. The numerical model is applied to two monodimensional benchmarks on a flat bottom. It is also applied to the simulation of the Algerian tsunami generated by a Mw=6 seism on the 18th March 2021. The tsunami propagation was highly dispersive and propagated across the Mediterranean Sea. We study here the effects of the order of temporal discretization on the accuracy of the results and on the time of computation.

Keywords: numerical analysis, tsunami propagation, water wave, boussinesq equations

Procedia PDF Downloads 211

Authors: Revoti Prasad Bora, Saurabh Yadav, Nikita Katyal

Abstract:

In the context of educational data mining, the use case of extracting information from images containing both text and diagrams is of high importance. Hence, document analysis requires the extraction of diagrams from such images and processes the text and diagrams separately. To the author’s best knowledge, none among plenty of approaches for extracting tables, figures, etc., suffice the need for real-time processing with high accuracy as needed in multiple applications. In the education domain, diagrams can be of varied characteristics viz. line-based i.e. geometric diagrams, chemical bonds, mathematical formulas, etc. There are two broad categories of approaches that try to solve similar problems viz. traditional computer vision based approaches and deep learning approaches. The traditional computer vision based approaches mainly leverage connected components and distance transform based processing and hence perform well in very limited scenarios. The existing deep learning approaches either leverage YOLO or faster-RCNN architectures. These approaches suffer from a performance-accuracy tradeoff. This paper proposes a U-Net based architecture that formulates the diagram extraction as a segmentation problem. The proposed method provides similar accuracy with a much faster extraction time as compared to the mentioned state-of-the-art approaches. Further, the segmentation mask in this approach allows the extraction of diagrams of irregular shapes.

Keywords: computer vision, deep-learning, educational data mining, faster-RCNN, figure extraction, image segmentation, real-time document analysis, text extraction, U-Net, YOLO

Procedia PDF Downloads 109

Authors: Linyu Wang, Jiahui Ma, Jianhong Xiang, Hanyu Jiang

Abstract:

the traditional greedy compressed sensing algorithm needs to know the signal sparsity when recovering the signal, but the signal sparsity in the practical application can not be obtained as a priori information, and the recovery accuracy is low, which does not meet the needs of practical application. To solve this problem, this paper puts forward Piecewise adaptive backtracking orthogonal least squares algorithm. The algorithm is divided into two stages. In the first stage, the sparsity pre-estimation strategy is adopted, which can quickly approach the real sparsity and reduce time consumption. In the second stage iteration, the correction strategy and adaptive step size are used to accurately estimate the sparsity, and the backtracking idea is introduced to improve the accuracy of signal recovery. Through experimental simulation, the algorithm can accurately recover the estimated signal with fewer iterations when the sparsity is unknown.

Keywords: compressed sensing, greedy algorithm, least square method, adaptive reconstruction

Procedia PDF Downloads 122

Authors: Filip Buruiana, Alexander Hall, Reimar Hofmann, Thomas Hofmann, Silviu Ganceanu, Alexandru Tudorica

Abstract:

In-memory column-stores make interactive analysis feasible for many big data scenarios. PowerDrill is a system used internally at Google for exploration in logs data. Even though it is a highly parallelized column-store and uses in memory caching, interactive response times cannot be achieved for all datasets (note that it is common to analyze data with 50 billion records in PowerDrill). In this paper, we investigate two orthogonal approaches to optimize performance at the expense of an acceptable loss of accuracy. Both approaches can be implemented as outer wrappers around existing database engines and so they should be easily applicable to other systems. For the first optimization we show that memory is the limiting factor in executing queries at speed and therefore explore possibilities to improve memory efficiency. We adapt some of the theory behind data sketches to reduce the size of particularly expensive fields in our largest tables by a factor of 4.5 when compared to a standard compression algorithm. This saves 37% of the overall memory in PowerDrill and introduces a 0.4% relative error in the 90th percentile for results of queries with the expensive fields. We additionally evaluate the effects of using sampling on accuracy and propose a simple heuristic for annotating individual result-values as accurate (or not). Based on measurements of user behavior in our real production system, we show that these estimates are essential for interpreting intermediate results before final results are available. For a large set of queries this effectively brings down the 95th latency percentile from 30 to 4 seconds.

Keywords: big data, in-memory column-store, high-performance SQL queries, approximate SQL queries

Procedia PDF Downloads 242

Authors: Cristina Vatamanu, Doina Cosovan, Dragos Gavrilut, Henri Luchian

Abstract:

In the past few years, the amount of malicious software increased exponentially and, therefore, machine learning algorithms became instrumental in identifying clean and malware files through semi-automated classification. When working with very large datasets, the major challenge is to reach both a very high malware detection rate and a very low false positive rate. Another challenge is to minimize the time needed for the machine learning algorithm to do so. This paper presents a comparative study between different machine learning techniques such as linear classifiers, ensembles, decision trees or various hybrids thereof. The training dataset consists of approximately 2 million clean files and 200.000 infected files, which is a realistic quantitative mixture. The paper investigates the above mentioned methods with respect to both their performance (detection rate and false positive rate) and their practicability.

Keywords: ensembles, false positives, feature selection, one side class algorithm

Procedia PDF Downloads 269

Authors: Elison Eduardo Jardim Bierhals, Claudineia Brazil, Deivid Pires, Rafael Haag, Elton Gimenez Rossini

Abstract:

This study evaluated the uncertainties involved in the solar radiation projections generated by the Brazilian Earth System Model (BESM) of the Weather and Climate Prediction Center (CPTEC) belonging to Coupled Model Intercomparison Phase 5 (CMIP5), with the aim of identifying efficiency in the projections for solar radiation of said model and in this way establish the viability of its use. Two different scenarios elaborated by Intergovernmental Panel on Climate Change (IPCC) were evaluated: RCP 4.5 (with more optimistic contour conditions) and 8.5 (with more pessimistic initial conditions). The method used to verify the accuracy of the present model was the Nash coefficient and the Statistical bias, as it better represents these atmospheric patterns. The BESM showed a tendency to overestimate the data ​​of solar radiation projections in most regions of the state of Rio Grande do Sul and through the validation methods adopted by this study, BESM did not present a satisfactory accuracy.

Keywords: climate changes, projections, solar radiation, uncertainty

Procedia PDF Downloads 226

Authors: Mohamed Ramdani, Hassen Abdellaoui, Abdenour Boudrassen

Abstract:

Mobile platform’s attitude estimation approaches mainly based on combined positioning techniques and developed algorithms; which aim to reach a fast and accurate solution. In this work, we describe the design and the implementation of an attitude determination (AD) process, using only measurements from GPS sensors. The major issue is based on smoothed GPS code data using Hatch filter and raw carrier-phase measurements integrated into attitude algorithm based on vectors measurement using least squares (LSQ) estimation method. GPS dataset from a static experiment is used to investigate the effectiveness of the presented approach and consequently to check the accuracy of the attitude estimation algorithm. Attitude results from GPS multi-antenna over short baselines are introduced and analyzed. The 3D accuracy of estimated attitude parameters using smoothed measurements is over 0.27°.

Keywords: attitude determination, GPS code data smoothing, hatch filter, carrier-phase measurements, least-squares attitude estimation

Procedia PDF Downloads 138

Authors: Mohammad Arabi

Abstract:

The development of advanced technologies in the field of signal processing and vibration analysis has enabled more accurate analysis and fault detection in electrical systems. This research investigates the application of temporal and frequency features in detecting faults in electric motor bearings, aiming to enhance fault detection accuracy and prevent unexpected failures. The use of methods such as deep learning algorithms and neural networks in this process can yield better results. The main objective of this research is to evaluate the efficiency and accuracy of methods based on temporal and frequency features in identifying faults in electric motor bearings to prevent sudden breakdowns and operational issues. Additionally, the feasibility of using techniques such as machine learning and optimization algorithms to improve the fault detection process is also considered. This research employed an experimental method and random sampling. Vibration signals were collected from electric motors under normal and faulty conditions. After standardizing the data, temporal and frequency features were extracted. These features were then analyzed using statistical methods such as analysis of variance (ANOVA) and t-tests, as well as machine learning algorithms like artificial neural networks and support vector machines (SVM). The results showed that using temporal and frequency features significantly improves the accuracy of fault detection in electric motor bearings. ANOVA indicated significant differences between normal and faulty signals. Additionally, t-tests confirmed statistically significant differences between the features extracted from normal and faulty signals. Machine learning algorithms such as neural networks and SVM also significantly increased detection accuracy, demonstrating high effectiveness in timely and accurate fault detection. This study demonstrates that using temporal and frequency features combined with machine learning algorithms can serve as an effective tool for detecting faults in electric motor bearings. This approach not only enhances fault detection accuracy but also simplifies and streamlines the detection process. However, challenges such as data standardization and the cost of implementing advanced monitoring systems must also be considered. Utilizing temporal and frequency features in fault detection of electric motor bearings, along with advanced machine learning methods, offers an effective solution for preventing failures and ensuring the operational health of electric motors. Given the promising results of this research, it is recommended that this technology be more widely adopted in industrial maintenance processes.

Keywords: electric motor, fault detection, frequency features, temporal features

Procedia PDF Downloads 18

Authors: Shahin Mirshekari, Mohammadreza Moradi, Hossein Jafari, Mehdi Jafari, Mohammad Ensaf

Abstract:

This research employs Gaussian Process Regression (GPR) with an ensemble kernel, integrating Exponential Squared, Revised Matern, and Rational Quadratic kernels to analyze pharmaceutical sales data. Bayesian optimization was used to identify optimal kernel weights: 0.76 for Exponential Squared, 0.21 for Revised Matern, and 0.13 for Rational Quadratic. The ensemble kernel demonstrated superior performance in predictive accuracy, achieving an R² score near 1.0, and significantly lower values in MSE, MAE, and RMSE. These findings highlight the efficacy of ensemble kernels in GPR for predictive analytics in complex pharmaceutical sales datasets.

Keywords: Gaussian process regression, ensemble kernels, bayesian optimization, pharmaceutical sales analysis, time series forecasting, data analysis

Procedia PDF Downloads 51

Authors: Samina Khalid, Shamila Nasreen

Abstract:

Dimensionality reduction as a preprocessing step to machine learning is effective in removing irrelevant and redundant data, increasing learning accuracy, and improving result comprehensibility. However, the recent increase of dimensionality of data poses a severe challenge to many existing feature selection and feature extraction methods with respect to efficiency and effectiveness. In the field of machine learning and pattern recognition, dimensionality reduction is important area, where many approaches have been proposed. In this paper, some widely used feature selection and feature extraction techniques have analyzed with the purpose of how effectively these techniques can be used to achieve high performance of learning algorithms that ultimately improves predictive accuracy of classifier. An endeavor to analyze dimensionality reduction techniques briefly with the purpose to investigate strengths and weaknesses of some widely used dimensionality reduction methods is presented.

Keywords: age related macular degeneration, feature selection feature subset selection feature extraction/transformation, FSA’s, relief, correlation based method, PCA, ICA

Procedia PDF Downloads 468

Authors: Rosa Figueroa, Christopher Flores

Abstract:

Text categorization is the problem of assigning a new document to a set of predetermined categories, on the basis of a training set of free-text data that contains documents whose category membership is known. To train a classification model, it is necessary to extract characteristics in the form of tokens that facilitate the learning and classification process. In text categorization, the feature extraction process involves the use of word sequences also known as N-grams. In general, it is expected that documents belonging to the same category share similar features. The Smith-Waterman (SW) algorithm is a dynamic programming algorithm that performs a local sequence alignment in order to determine similar regions between two strings or protein sequences. This work explores the use of SW algorithm as an alternative to feature extraction in text categorization. The dataset used for this purpose, contains 2,610 annotated documents with the classes Obese/Non-Obese. This dataset was represented in a matrix form using the Bag of Word approach. The score selected to represent the occurrence of the tokens in each document was the term frequency-inverse document frequency (TF-IDF). In order to extract features for classification, four experiments were conducted: the first experiment used SW to extract features, the second one used unigrams (single word), the third one used bigrams (two word sequence) and the last experiment used a combination of unigrams and bigrams to extract features for classification. To test the effectiveness of the extracted feature set for the four experiments, a Support Vector Machine (SVM) classifier was tuned using 20% of the dataset. The remaining 80% of the dataset together with 5-Fold Cross Validation were used to evaluate and compare the performance of the four experiments of feature extraction. Results from the tuning process suggest that SW performs better than the N-gram based feature extraction. These results were confirmed by using the remaining 80% of the dataset, where SW performed the best (accuracy = 97.10%, weighted average F-measure = 97.07%). The second best was obtained by the combination of unigrams-bigrams (accuracy = 96.04, weighted average F-measure = 95.97) closely followed by the bigrams (accuracy = 94.56%, weighted average F-measure = 94.46%) and finally unigrams (accuracy = 92.96%, weighted average F-measure = 92.90%).

Keywords: comorbidities, machine learning, obesity, Smith-Waterman algorithm

Procedia PDF Downloads 276

Authors: Saad Alkentar, Abdulkareem Assalem

Abstract:

Recognizing small targets has always posed a significant challenge in image analysis. Over long distances, the image signal-to-noise ratio tends to be low, limiting the amount of useful information available to detection systems. Consequently, visual target recognition becomes an intricate task to tackle. In this study, we introduce a Track Before Detect (TBD) approach that leverages target trajectory information (coordinates) to effectively distinguish between noise and potential targets. By reframing the problem as a multivariate time series classification, we have achieved remarkable results. Specifically, our TBD method achieves an impressive 97% accuracy in separating target signals from noise within a mere half-second time span (consisting of 10 data points). Furthermore, when classifying the identified targets into our predefined categories—airplane, drone, and bird—we achieve an outstanding classification accuracy of 96% over a more extended period of 1.5 seconds (comprising 30 data points).

Keywords: small targets, drones, trajectory information, TBD, multivariate time series

Procedia PDF Downloads 24

Authors: Luca Vascelli, Silvia Iacomini, Giada Gueli, Francesca Cavallini, Carlo Cavallini, Federica Berardo

Abstract:

The study was conducted to evaluate the effect of training on Big 6 + 6 motor skills to promote daily living skills. Precision teaching (PT) suggests that improved speed of the component behaviors can lead to better performance of composite skills. This study assessed the effects of the repeated timed practice of component motor skills on speed and accuracy of composite skills related to daily living skills. An 18 years old adolescent with intellectual disability participated. A pre post probe single-subject design was used. The results suggest that the participant was able to perform the component skills at his individual aims (endurance was assessed). The speed and accuracy of composite skills were increased; stability and retention were also measured for the composite skill after the training.

Keywords: big 6+6, daily living skills, intellectual disability, precision teaching

Procedia PDF Downloads 130

Authors: Christian Kapuku, Seung-Young Kho

Abstract:

An accurate representation of the transportation system serving the region is one of the important aspects of transportation modeling. Such representation often requires developing an abstract model of the system elements, which also requires important amount of data, surveys and time. However, in some cases such as in developing countries, data deficiencies, time and budget constraints do not always allow such accurate representation, leaving opportunities to assumptions that may negatively affect the quality of the analysis. With the emergence of Internet open source data especially in the mapping technologies as well as the advances in Geography Information System, opportunities to tackle these issues have raised. Therefore, the objective of this paper is to demonstrate such application through a practical case of the development of the transportation network for the city of Kinshasa. The GIS geo-referencing was used to construct the digitized map of Transportation Analysis Zones using available scanned images. Centroids were then dynamically placed at the center of activities using an activities density map. Next, the road network with its characteristics was built using OpenStreet data and other official road inventory data by intersecting their layers and cleaning up unnecessary links such as residential streets. The accuracy of the final network was then checked, comparing it with satellite images from Google and Bing. For the validation, the final network was exported into Emme3 to check for potential network coding issues. Results show a high accuracy between the built network and satellite images, which can mostly be attributed to the use of open source data.

Keywords: geographic information system (GIS), network construction, transportation database, open source data

Procedia PDF Downloads 150