Search results for: recall

Authors: Shruti Jain

Abstract:

During its independence struggle in the early 20th century, India witnessed trends of politicisation of various spiritual paths, one of them being that of Shaktism. Interestingly, Nietzsche’s teachings were being interpreted as being essentially the worship of Shakti. The present paper aims at investigating this claim and hence undertakes an intercultural archaeological excavation in the realm of the Goddess archetypes that Nietzsche’s work invokes. Ariadne is placed next to Radha, Baubo to Lajja Gauri, Medusa to Chhinnamasta, Hecate to Kali and Dhumavati and Athena to Sarawati. Indeed, the Eternal Feminine plays a vital role in Nietzsche’s writings. One might recall that Nietzsche even declared himself to be the first Psychologist of the Eternal Feminine. The present paper aims to illustrate how, the matter of the Eternal Feminine, like all other matters, is subjected to Nietzsche’s basic creative principle of transvaluation of values and new meaning making. In order to achieve this, Nietzsche applies what Heidegger calls a 'cross-wise striking-through' technique in his analysis of what can be termed as his engagement with Shaktism. Hence, not only is the mystical ascent and descent of the creative energy (Kundalini Shakti) dealt with under erasure in Thus Spake Zarathustra, but coincidentally also the Three Metamorphoses emerge as an instance of such an erasure, making the Devi invisible and yet not so invisible for an Indian reader.

Keywords: eternal feminine, Nietzsche and India, Shaktism, transvaluation of values

Procedia PDF Downloads 128

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

Abstract:

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

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

Procedia PDF Downloads 78

Authors: Shu-Ching Chiu, Shu-Fang Chang

Abstract:

The World Health Organization (WHO) has been actively developing intervention programs to deal with geriatric frailty. In its White Paper on Healthcare Policy 2020, the Department of Health, Bureau of Health Promotion proposed that active aging and the prevention of disability are essential for elderly people to maintain good health. The paper recommended five main policies relevant to this objective, one of which is the prevention of frailty and disability. Scholars have proposed a number of different criteria to diagnose and assess frailty; no consistent or normative standard of measurement is currently available. In addition, many methods of assessment are recursive, which can easily result in recall bias. Due to the relationship between frailty and physical fitness with regard to co-morbidity, it is important that academics optimize the criteria used to assess frailty by objectively evaluating the physical fitness of senior citizens. This study used a review of the literature to identify fitness indicators suitable for measuring frailty in the elderly. This study recommends that measurement criteria be integrated to produce an optimized predictive value for frailty score. Healthcare professionals could use this data to detect frailty at an early stage and provide appropriate care to prevent further debilitation and increase longevity.

Keywords: frailty, aging, physical fitness, optimized criteria, healthcare

Procedia PDF Downloads 323

Authors: Setareh Shayanfar

Abstract:

Given the increasing importance of peer relationships during adolescence, the present study aimed to examine peer interactions that facilitate or hinder adolescents’ regulation of negative emotions. Using the Enhanced Critical Incident Technique, 1-hour semi-structured interviews were conducted with 16 junior high school adolescents. Participants were asked to recall situations when they experienced strong negative emotions during the past school year, indicate the peer interactions that helped or hindered their emotion regulation, and identify prospective interactions with the potential to help regulate their emotions. Data analysis extracted 182 critical incidents, including 109 helping incidents, 45 hindering incidents, and 28 wish list items, which generated 10 categories nested within four overarching themes: Positive Personal Support included (a) supportive presence, (b) expressing concern, (c) empathizing, and (d) encouraging and cheering up; while Strategy Transmission included (e) sharing perspective, and (f) giving advice; Activated Support included (g) taking action, and (h) distracting; while Negative Personal Interactions included (i) withdrawing and (j) punishing. Implications for mental health and service providers, as well as recommendations for future research, are presented.

Keywords: adolescence, emotion regulation, enhanced critical incident technique, peers

Procedia PDF Downloads 108

Authors: A. Elsehemy, M. Abdeen , T. Nazmy

Abstract:

Since the appearance of the Semantic web, many semantic search techniques and models were proposed to exploit the information in ontology to enhance the traditional keyword-based search. Many advances were made in languages such as English, German, French and Spanish. However, other languages such as Arabic are not fully supported yet. In this paper we present a framework for ontology based information retrieval for Arabic language. Our system consists of four main modules, namely query parser, indexer, search and a ranking module. Our approach includes building a semantic index by linking ontology concepts to documents, including an annotation weight for each link, to be used in ranking the results. We also augmented the framework with an automatic document categorizer, which enhances the overall document ranking. We have built three Arabic domain ontologies: Sports, Economic and Politics as example for the Arabic language. We built a knowledge base that consists of 79 classes and more than 1456 instances. The system is evaluated using the precision and recall metrics. We have done many retrieval operations on a sample of 40,316 documents with a size 320 MB of pure text. The results show that the semantic search enhanced with text classification gives better performance results than the system without classification.

Keywords: Arabic text classification, ontology based retrieval, Arabic semantic web, information retrieval, Arabic ontology

Procedia PDF Downloads 496

Authors: Asiri Wijesinghe, N. D. Kodikara, Damitha Sandaruwan

Abstract:

The Diabetic Retinopathy (DR) is a rapidly growing interrogation around the world which can be annotated by abortive metabolism of glucose that causes long-term infection in human retina. This is one of the preliminary reason of visual impairment and blindness of adults. Information on retinal pathological mutation can be recognized using ocular fundus images. In this research, we are mainly focused on resurrecting an automated diagnosis system to detect DR anomalies such as severity level classification of DR patient (Non-proliferative Diabetic Retinopathy approach) and vessel tortuosity measurement of untwisted vessels to assessment of vessel anomalies (Proliferative Diabetic Retinopathy approach). Severity classification method is obtained better results according to the precision, recall, F-measure and accuracy (exceeds 94%) in all formats of cross validation. In ROC (Receiver Operating Characteristic) curves also visualized the higher AUC (Area Under Curve) percentage (exceeds 95%). User level evaluation of severity capturing is obtained higher accuracy (85%) result and fairly better values for each evaluation measurements. Untwisted vessel detection for tortuosity measurement also carried out the good results with respect to the sensitivity (85%), specificity (89%) and accuracy (87%).

Keywords: fundus image, exudates, microaneurisms, hemorrhages, tortuosity, diabetic retinopathy, optic disc, fovea

Procedia PDF Downloads 294

Authors: Mahtab Davari, Charles Edward Okon, Somayeh Aghanavesi

Abstract:

Every institute of learning is usually interested in the performance of enrolled students. The level of these performances determines the approach an institute of study may adopt in rendering academic services. The focus of this paper is to evaluate students' academic performance in given courses of study using machine learning methods. This study evaluated various supervised machine learning classification algorithms such as Logistic Regression (LR), Support Vector Machine, Random Forest, Decision Tree, K-Nearest Neighbors, Linear Discriminant Analysis, and Quadratic Discriminant Analysis, using selected features to predict study performance. The accuracy, precision, recall, and F1 score obtained from a 5-Fold Cross-Validation were used to determine the best classification algorithm to predict students’ performances. SVM (using a linear kernel), LDA, and LR were identified as the best-performing machine learning methods. Also, using the LR model, this study identified students' educational habits such as reading and paying attention in class as strong determinants for a student to have an above-average performance. Other important features include the academic history of the student and work. Demographic factors such as age, gender, high school graduation, etc., had no significant effect on a student's performance.

Keywords: student performance, supervised machine learning, classification, cross-validation, prediction

Procedia PDF Downloads 85

Authors: Sheena Christabel Pravin, M. Palanivelan

Abstract:

Speech disfluencies are common in spontaneous speech. The primary purpose of this study was to distinguish linguistic disfluencies from stuttering disfluencies in bilingual Tamil–English (TE) speaking children. The secondary purpose was to determine whether their disfluencies are mediated by native language dominance and/or on an early onset of developmental stuttering at childhood. A detailed study was carried out to identify the prosodic and acoustic features that uniquely represent the disfluent regions of speech. This paper focuses on statistical modeling of repetitions, prolongations, pauses and interjections in the speech corpus encompassing bilingual spontaneous utterances from school going children – English and Tamil. Two classifiers including Hidden Markov Models (HMM) and the Multilayer Perceptron (MLP), which is a class of feed-forward artificial neural network, were compared in the classification of disfluencies. The results of the classifiers document the patterns of disfluency in spontaneous speech samples of school-aged children to distinguish between Children Who Stutter (CWS) and Children with Language Impairment CLI). The ability of the models in classifying the disfluencies was measured in terms of F-measure, Recall, and Precision.

Keywords: bi-lingual, children who stutter, children with language impairment, hidden markov models, multi-layer perceptron, linguistic disfluencies, stuttering disfluencies

Procedia PDF Downloads 183

Authors: Lauren Dixon, David Galvani

Abstract:

Objective: Sharing devastating news with patients is often considered the most difficult task of doctors. This study aimed to explore patients’ perceptions of receiving bad news including which features improve the experience and which areas need refining. Methods: A questionnaire was written based on the steps of the SPIKES model for breaking bad news. 20 patients receiving treatment for a haematological malignancy completed the questionnaire. Results: Overall, the results are promising as most patients praised their consultation. ‘Poor’ was more commonly rated by women and participants aged 45-64. The main differences between the ‘excellent’ and ‘poor’ consultations include the doctor’s sensitivity and checking the patients’ understanding. Only 35% of patients were asked their existing knowledge and 85% of consultations failed to discuss the impact of the diagnosis on daily life. Conclusion: This study agreed with the consensus of existing literature. The commended aspects include consultation set-up and information given. Areas patients felt needed improvement include doctors determining the patient’s existing knowledge and exploring how the diagnosis will affect the patient’s life. With a poorer prognosis, doctors should work on conveying appropriate hope. The study was limited by a small sample size and potential recall bias.

Keywords: cancer, diagnosis, haematology, patients

Procedia PDF Downloads 278

Authors: Rita Garcia

Abstract:

Intelligent Programming Tutors, IPTs, are supplemental educational devices that assist in teaching software development. These systems provide customized learning allowing the user to select the presentation pace, pedagogical strategy, and to recall previous and additional teaching materials reinforcing learning objectives. In addition, IPTs automatically records individual’s progress, providing feedback to the instructor and student. These tutoring systems have an advantage over Tutoring Systems because Intelligent Programming Tutors are not limited to one teaching strategy and can adjust when it detects the user struggling with a concept. The Intelligent Programming Tutor is a category of Intelligent Tutoring Systems, ITS. ITS are available for many fields in education, supporting different learning objectives and integrate into other learning tools, improving the student's learning experience. This study provides a comparison of the IPTs currently adopted by the educational community and will focus on the different teaching methodologies and programming languages. The study also includes the ability to integrate the IPT into other educational technologies, such as massive open online courses, MOOCs. The intention of this evaluation is to determine one system that would best serve in a larger ongoing research project and provide findings for other institutions looking to adopt an Intelligent Programming Tutor.

Keywords: computer education tools, integrated software development assistance, intelligent programming tutors, tutoring systems

Procedia PDF Downloads 284

Authors: Pimploi Tirastittam, Phutthiwat Waiyawuththanapoom, Manop Tirastittam

Abstract:

Traceability system is one of the tools which can ensure the product’s confident of the consumer as it can trace the product back to its origin and can reduce the operation cost of recall. Nowadays, there are so many technologies which can be applied to the traceability system and also able to increase the efficiency of the system such as QR Code, barcode, GS1 and GTIN. As the result, this research is aimed to study and design the information technology pattern that suits for the traceability of Thailand’s orchid because Thailand’s orchid is the popular export product for Japan, USA, China, Netherlands and Italy. This study will enhance the value of Thailand’s orchid and able to prevent the unexpected event of the defects or damaged product. The traceability pattern was received IOC test from 12 experts from 4 fields of study which are traceability field, information technology field, information communication technology field and orchid export field. The result of the in-depth interview and questionnaire showed that the technology which most compatibility with the traceability system is the QR code. The mean of the score was 4.25 and the standard deviation was 0.5 as the QR code is the new technology and user-friendly. The traceability system should start from the farm to the consumer in the consuming country as the traceability system will enhance the quality level of the product and increase the value of its as well. The other outcome from this research is the supply chain model of Thailand’s Orchid along with the system architecture and working system diagram.

Keywords: exporting, information technology pattern, orchid, traceability

Procedia PDF Downloads 185

Authors: Olivia Kurucz

Abstract:

Gamification is one of the outstanding new methodological possibilities of urban public participation processes to make the most informed decision possible for the future steps of urban development. This paper examines four Hungarian experimental projects in which gamified tools were applied during the public participation progresses by the Urban Future Laboratory (UFLab) research workshop of Budapest University of Technology and Economics (BUTE). The recently implemented future planning projects (in the cities of Pécel, Kistarcsa, Budapest, and Salgótarján) were initiated by various motives, but the multi-stakeholder dialogues were facilitated through physical gamified tools in all cases. Based on the urban gamification hypothesis, the use of gamified tools supported certain steps of participatory processes in several aspects: it helped to increase the attractiveness of public events, to create a more informal atmosphere, to ensure equal conditions for actors, to recall a design mindset, to bridge contrasting social or cultural differences, to fix opinions and to assist dialogue between city actors, designers, and residents. This statement is confirmed by assessing the applied tools, analyzing the case studies, and comparing them to perceive their effects and interrelations.

Keywords: experimental projects, future planning, gamification, gamified tools, Hungary, public participation, UFLab, urban gamification

Procedia PDF Downloads 108

Authors: Niranjana Devi N.

Abstract:

Test case selection is to select the subset of only the fit test cases and remove the unfit, ambiguous, redundant, unnecessary test cases which in turn improve the quality and reduce the cost of software testing. Test cases optimization is the problem of finding the best subset of test cases from a pool of the test cases to be audited. It will meet all the objectives of testing concurrently. But most of the research have evaluated the fitness of test cases only on single parameter fault detecting capability and optimize the test cases using a single objective. In the proposed approach, nine parameters are considered for test case selection and the best subset of parameters for test case selection is obtained using Interval Type-2 Fuzzy Rough Set. Test case selection is done in two stages. The first stage is the fuzzy entropy-based filtration technique, used for estimating and reducing the ambiguity in test case fitness evaluation and selection. The second stage is the ant colony optimization-based wrapper technique with a forward search strategy, employed to select test cases from the reduced test suite of the first stage. The results are evaluated using the Coverage parameters, Precision, Recall, F-Measure, APSC, APDC, and SSR. The experimental evaluation demonstrates that by this approach considerable computational effort can be avoided.

Keywords: ant colony optimization, fuzzy entropy, interval type-2 fuzzy rough set, test case selection

Procedia PDF Downloads 624

Authors: Yavuz Unal, Kemal Polat, H. Erdinc Kocer

Abstract:

In this study, a decision support system comprising three stages has been proposed to detect the disc abnormalities of the lumbar region. In the first stage named the feature extraction, T2-weighted sagittal and axial Magnetic Resonance Images (MRI) were taken from 55 people and then 27 appearance and shape features were acquired from both sagittal and transverse images. In the second stage named the feature weighting process, k-means clustering based feature weighting (KMCBFW) proposed by Gunes et al. Finally, in the third stage named the classification process, the classifier algorithms including multi-layer perceptron (MLP- neural network), support vector machine (SVM), Naïve Bayes, and decision tree have been used to classify whether the subject has lumbar disc or not. In order to test the performance of the proposed method, the classification accuracy (%), sensitivity, specificity, precision, recall, f-measure, kappa value, and computation times have been used. The best hybrid model is the combination of k-means clustering based feature weighting and decision tree in the detecting of lumbar disc disease based on both sagittal and axial MR images.

Keywords: lumbar disc abnormality, lumbar MRI, lumbar spine, hybrid models, hybrid features, k-means clustering based feature weighting

Procedia PDF Downloads 495

Authors: Iulia Crisan

Abstract:

Objective: The present study investigates the cross-cultural validity of three North-American performance validity indicators (PVTs) by comparing base rates of failure (BRF) in Romanian and Canadian disability applicants. Methods: Three PVTs (Test of Memory Malingering Trial 1 [TOMM-1], Rey Fifteen Item Test free recall [Rey-15 FR], and Rey FR+Recognition [Rey COMB]) were administered to a heterogeneous Romanian clinical sample (N Ro =54) and a similar Canadian sample (N Can = 52). Patients were referred for assessment to determine the severity of their cognitive deficits. Results: We compared the BRF in both samples at various cutoffs. BRF on TOMM-1 at ≤ 43 was similar (Ro = 33.3% vs. Can = 40.4%); at ≤40, Ro = 22.2% vs. Can = 25.0%. Likewise, comparable BRF were observed on Rey-15 FR at ≤ 8 (Ro = 7.4% vs. Can = 11.5%) and ≤ 11 (Ro = 27.8% vs. Can = 23.1%). However, the Romanian sample produced significantly higher failure rates on the Rey COMB at variable cutoffs (p <.05), possibly because Romanian patients were significantly older than the Canadian sample. Conclusion: Our findings offer proof of concept for the cross-cultural validity of the TOMM and Rey-15 FR. At the same time, they serve as a reminder that the generalizability of PVT cutoffs to different populations should not be assumed but verified empirically. Employing the TOMM as a criterion measure for newly developed PVTs is discussed.

Keywords: performance validity indicators, cross-cultural validity, failure base rates, clinical samples, cognitive dysfunction, TOMM-1, Rey-15, Rey COMB

Procedia PDF Downloads 41

Authors: Inayatullah Khan, Afzal Khan, Hamzullah Khan, Afzal Khan

Abstract:

Objectives: The objective of this study was to compare different statistical variables for vaccinated and unvaccinated children in measles cases. Material and Methods: This cross sectional comparative study was conducted at Isolation ward, Department of Paediatrics, Lady Reading Hospital (LRH), Peshawar, from April 2012 to March 2013. A total of 566 admitted cases of measles were enrolled. Data regarding age, sex, address, vaccination status, measles contact, hospital stay and outcome was collected and recorded on a proforma. History of measles vaccination was ascertained either by checking the vaccination cards or on parental recall. Result: In 566 cases of measles, 211(39%) were vaccinated and 345 (61%) were unvaccinated. Three hundred and ten (54.80%) patients were males and 256 (45.20%) were females with a male to female ratio of 1.2:1.The age range was from 1 year to 14 years with mean age with SD of 3.2 +2 years. Majority (371, 65.5%) of the patients were 1-3 years old. Mean hospital stay was 3.08 days with a range of 1-10 days and a standard deviation of ± 1.15. History of measles contact was present in 393 (69.4%) cases. Fourty eight patients were expired with a mortality rate of 8.5%. Conclusion: Majority of the children in Khyber Pukhtunkhwa are unvaccinated and unprotected against measles. Among vaccinated children, 39% of children attracted measles which indicate measles vaccine failure. This figure is clearly higher than that accepted for measles vaccine (2-10%).

Keywords: measles, vaccination, immunity, population

Procedia PDF Downloads 410

Authors: C. -L. Huang, J. -H. Ho

Abstract:

Social media has become more and more important in our life. Many enterprises promote their services and products to fans via the social media. The positive or negative sentiment of feedbacks from fans is very important for enterprises to improve their products, services, and promotion activities. The purpose of this paper is to understand the sentiment of the fan’s responses by analyzing the responses posted by fans on Facebook. The entity and aspect of fan’s responses were analyzed based on a predefined ontology. The ontology for cell phone sentiment analysis consists of aspect categories on the top level as follows: overall, shape, hardware, brand, price, and service. Each category consists of several sub-categories. All aspects for a fan’s response were found based on the ontology, and their corresponding sentimental terms were found using lexicon-based approach. The sentimental scores for aspects of fan responses were obtained by summarizing the sentimental terms in responses. The frequency of 'like' was also weighted in the sentimental score calculation. Three famous cell phone fan pages on Facebook were selected as demonstration cases to evaluate performances of the proposed methodology. Human judgment by several domain experts was also built for performance comparison. The performances of proposed approach were as good as those of human judgment on precision, recall and F1-measure.

Keywords: opinion mining, ontology, sentiment analysis, text mining

Procedia PDF Downloads 208

Authors: Ranjana Dani

Abstract:

Brand communication narratives in India has evolved today to reflect the vibrant and intriguing tone of voice inspired by a rich cultural heritage while addressing the culturally alert attitude of the contemporary global Indian. Brands are strongly associated with the organization's values, vision, and mission and portray this through specific ‘look and feel’ and ‘tone of voice’. It is within the brand’s visual language that COLOUR has evolved to become a most powerful weapon in the designer’s arsenal. Color is big business in Brand Design! A brand is a ‘collection of perceptions’, meaningful brand connect is about striving to occupy head and heart space in consumers. The persona of the young Indian reflects a deep attachment to cultural roots as seen through the characteristic of ‘Indie Pride,’ blended with the ambitious, aspirational traits of a modern ‘global citizen’.Studies on ‘Color Perceptions’ indicate a trend that amplifies this, and hence brands reflect a GLOCAL palette, a Global and Local Blend. This paper establishes this through case studies that expand the inspirations, selection processes, and use of innovative color palettes crafted by some dynamic brand designers. This throws light on the role of color as it generates visual impact and recall for successful brands.

Keywords: colour palettes, brand design and business, cultural context, colour perceptions, glocal, contemporaneity

Procedia PDF Downloads 51

Authors: Regina Chua

Abstract:

To reduce the costs of re-fielding a large survey, a Random Forest classifier was applied to measure the accuracy of classifying individuals into their assigned segments with the fewest possible questions. Given a long survey, one needed to determine the most predictive ten or fewer questions that would accurately assign new individuals to custom segments. Furthermore, the solution needed to be quick in its classification and usable in non-Python environments. In this paper, a supervised Random Forest classifier was modeled on a dataset with 7,000 individuals, 60 questions, and 254 features. The Random Forest consisted of an iterative collection of individual decision trees that result in a predicted segment with robust precision and recall scores compared to a single tree. A random 70-30 stratified sampling for training the algorithm was used, and accuracy trade-offs at different depths for each segment were identified. Ultimately, the Random Forest classifier performed at 87% accuracy at a depth of 10 with 20 instead of 254 features and 10 instead of 60 questions. With an acceptable accuracy in prioritizing feature selection, new tools were developed for non-Python environments: a worksheet with a formulaic version of the algorithm and an embedded function to predict the segment of an individual in real-time. Random Forest was determined to be an optimal classification model by its feature selection, performance, processing speed, and flexible application in other environments.

Keywords: machine learning, supervised learning, data science, random forest, classification, prediction, predictive modeling

Procedia PDF Downloads 67

Authors: Yingkun Huang, Li Guo, Zekang Lan, Kai Tian

Abstract:

Hard disk drives (HDD) failure of the exascale supercomputing system may lead to service interruption and invalidate previous calculations, and it will cause permanent data loss. Therefore, initiating corrective actions before hard drive failures materialize is critical to the continued operation of jobs. In this paper, a highly accurate analysis model based on CNN-LSTM and oversampling technique was proposed, which can correctly predict the necessity of a disk replacement even ten days in advance. Generally, the learning-based method performs poorly on a training dataset with long-tail distribution, especially fault prediction is a very classic situation as the scarcity of failure data. To overcome the puzzle, a new oversampling was employed to augment the data, and then, an improved CNN-LSTM with the shortcut was built to learn more effective features. The shortcut transmits the results of the previous layer of CNN and is used as the input of the LSTM model after weighted fusion with the output of the next layer. Finally, a detailed, empirical comparison of 6 prediction methods is presented and discussed on a public dataset for evaluation. The experiments indicate that the proposed method predicts disk failure with 0.91 Precision, 0.91 Recall, 0.91 F-measure, and 0.90 MCC for 10 days prediction horizon. Thus, the proposed algorithm is an efficient algorithm for predicting HDD failure in supercomputing.

Keywords: HDD replacement, failure, CNN-LSTM, oversampling, prediction

Procedia PDF Downloads 45

Authors: Benniche Omar

Abstract:

We are concerned with abstract fully nonlinear differential equations having the form y’(t)=Ay(t)+f(t,y(t)) where A is an m—dissipative operator (possibly multi—valued) defined on a subset D(A) of a Banach space X with values in X and f is a given function defined on I×X with values in X. We consider a graph K in I×X. We recall that K is said to be viable with respect to the above abstract differential equation if for each initial data in K there exists at least one trajectory starting from that initial data and remaining in K at least for a short time. The viability problem has been studied by many authors by using various techniques and frames. If K is closed, it is shown that a tangency condition, which is mainly linked to the dynamic, is crucial for viability. In the case when X is infinite dimensional, compactness and convexity assumptions are needed. In this paper, we are concerned with the notion of near viability for a given graph K with respect to y’(t)=Ay(t)+f(t,y(t)). Roughly speaking, the graph K is said to be near viable with respect to y’(t)=Ay(t)+f(t,y(t)), if for each initial data in K there exists at least one trajectory remaining arbitrary close to K at least for short time. It is interesting to note that the near viability is equivalent to an appropriate tangency condition under mild assumptions on the dynamic. Adding natural convexity and compactness assumptions on the dynamic, we may recover the (exact) viability. Here we investigate near viability for a graph K in I×X with respect to y’(t)=Ay(t)+f(t,y(t)) where A and f are as above. We emphasis that the t—dependence on the perturbation f leads us to introduce a new tangency concept. In the base of a tangency conditions expressed in terms of that tangency concept, we formulate criteria for K to be near viable with respect to y’(t)=Ay(t)+f(t,y(t)). As application, an abstract null—controllability theorem is given.

Keywords: abstract differential equation, graph, tangency condition, viability

Procedia PDF Downloads 115

Authors: Chia-Min Lai, Wan-Ching Lin, Hahn-Ming Lee, Ching-Hao Mao

Abstract:

As world wild internet has non-stop developments, making profit by lending registered domain names emerges as a new business in recent years. Unfortunately, the larger the market scale of domain lending service becomes, the riskier that there exist malicious behaviors or malwares hiding behind parked domains will be. Also, previous work for differentiating parked domain suffers two main defects: 1) too much data-collecting effort and CPU latency needed for features engineering and 2) ineffectiveness when detecting parked domains containing external links that are usually abused by hackers, e.g., drive-by download attack. Aiming for alleviating above defects without sacrificing practical usability, this paper proposes ParkedGuard as an efficient and accurate parked domain detector. Several scripting behavioral features were analyzed, while those with special statistical significance are adopted in ParkedGuard to make feature engineering much more cost-efficient. On the other hand, finding memberships between external links and parked domains was modeled as a graph mining problem, and a coarse-to-fine strategy was elaborately designed by leverage the graphical locality such that ParkedGuard outperforms the state-of-the-art in terms of both recall and precision rates.

Keywords: coarse-to-fine strategy, domain parking service, graphical locality analysis, parked domain

Procedia PDF Downloads 384

Authors: Sandesh Achar

Abstract:

Personalized advertising holds greater potential for higher conversion rates compared to generic advertisements. However, its widespread application in the retail industry faces challenges due to complex implementation processes. These complexities impede the swift adoption of personalized advertisement on a large scale. Personalized advertisement, being a data-driven approach, necessitates consumer-related data, adding to its complexity. This paper introduces an innovative data-driven decision-making framework, D3Advert, which personalizes advertisements by analyzing personalities using a BiLSTM network. The framework utilizes the Myers–Briggs Type Indicator (MBTI) dataset for development. The employed BiLSTM network, specifically designed and optimized for D3Advert, classifies user personalities into one of the sixteen MBTI categories based on their social media posts. The classification accuracy is 86.42%, with precision, recall, and F1-Score values of 85.11%, 84.14%, and 83.89%, respectively. The D3Advert framework personalizes advertisements based on these personality classifications. Experimental implementation and performance analysis of D3Advert demonstrate a 40% improvement in impressions. D3Advert’s innovative and straightforward approach has the potential to transform personalized advertising and foster widespread personalized advertisement adoption in marketing.

Keywords: personalized advertisement, deep Learning, MBTI dataset, BiLSTM network, NLP.

Procedia PDF Downloads 12

Authors: Dewi Juliah Ratnaningsih, Imas Sukaesih Sitanggang

Abstract:

Classification is one of data mining techniques that aims to discover a model from training data that distinguishes records into the appropriate category or class. Data mining classification methods can be applied in education, for example, to determine the classification of non-active students in Indonesia Open University. This paper presents a comparison of three methods of classification: Naïve Bayes, Bagging, and C.45. The criteria used to evaluate the performance of three methods of classification are stratified cross-validation, confusion matrix, the value of the area under the ROC Curve (AUC), Recall, Precision, and F-measure. The data used for this paper are from the non-active Indonesia Open University students in registration period of 2004.1 to 2012.2. Target analysis requires that non-active students were divided into 3 groups: C1, C2, and C3. Data analyzed are as many as 4173 students. Results of the study show: (1) Bagging method gave a high degree of classification accuracy than Naïve Bayes and C.45, (2) the Bagging classification accuracy rate is 82.99 %, while the Naïve Bayes and C.45 are 80.04 % and 82.74 % respectively, (3) the result of Bagging classification tree method has a large number of nodes, so it is quite difficult in decision making, (4) classification of non-active Indonesia Open University student characteristics uses algorithms C.45, (5) based on the algorithm C.45, there are 5 interesting rules which can describe the characteristics of non-active Indonesia Open University students.

Keywords: comparative analysis, data mining, clasiffication, Bagging, Naïve Bayes, C.45, non-active students, Indonesia Open University

Procedia PDF Downloads 283

Authors: Xinghang Lv, Tao Peng, Jia Chen, Junping Liu, Xinrong Hu, Ruhan He, Minghua Jiang, Wenli Cao

Abstract:

As one of the most dangerous vulnerabilities, effective detection of buffer overflow vulnerabilities is extremely necessary. Traditional detection methods are not accurate enough and consume more resources to meet complex and enormous code environment at present. In order to resolve the above problems, we propose the method for Buffer overflow detection based on Abstract syntax tree, Control flow graph, and Data dependency graph (BodeACD) in C/C++ programs with source code. Firstly, BodeACD constructs the function samples of buffer overflow that are available on Github, then represents them as code representation sequences, which fuse control flow, data dependency, and syntax structure of source code to reduce information loss during code representation. Finally, BodeACD learns vulnerability patterns for vulnerability detection through deep learning. The results of the experiments show that BodeACD has increased the precision and recall by 6.3% and 8.5% respectively compared with the latest methods, which can effectively improve vulnerability detection and reduce False-positive rate and False-negative rate.

Keywords: vulnerability detection, abstract syntax tree, control flow graph, data dependency graph, code representation, deep learning

Procedia PDF Downloads 135

Authors: Anastasia Sorokina

Abstract:

Graduate language loss or attrition has been well documented in individuals who migrate and become emersed in a different language environment. This phenomenon of first language (L1) attrition is an example of non-pathological (not due to trauma) and can manifest itself in frequent pauses, search for words, or grammatical errors. While the widely experienced loss of one’s first language might seem harmless, there is convincing evidence from the disciplines of Developmental Psychology, Bilingual Studies, and even Psychotherapy that language plays a crucial role in the memory of self. In fact, we remember, store, and share personal memories with the help of language. Dual-Coding Theory suggests that language memory code deterioration could lead to forgetting. Yet, no one has investigated a possible connection between language loss and memory. The present study aims to address this research gap by examining a corpus of 1,495 memories of Russian-English bilinguals who are on a continuum of L1 (first language) attrition. Since phenomenological properties capture how well a memory is remembered, the following descriptors were selected - vividness, ease of recall, emotional valence, personal significance, and confidence in the event. A series of linear regression statistical analyses were run to examine the possible negative effects of L1 attrition on autobiographical memory. The results revealed that L1 attrition might compromise perceived vividness and confidence in the event, which is indicative of memory deterioration. These findings suggest the importance of heritage language maintenance in immigrant communities who might be forced to assimilate as language loss might negatively affect the memory of self.

Keywords: L1 attrition, autobiographical memory, language loss, memory phenomenology, dual coding

Procedia PDF Downloads 75

Authors: Muhammad Ali

Abstract:

Cyber-attacks and anomaly detection on the Internet of Things (IoT) infrastructure is emerging concern in the domain of data-driven intrusion. Rapidly increasing IoT risk is now making headlines around the world. denial of service, malicious control, data type probing, malicious operation, DDos, scan, spying, and wrong setup are attacks and anomalies that can affect an IoT system failure. Everyone talks about cyber security, connectivity, smart devices, and real-time data extraction. IoT devices expose a wide variety of new cyber security attack vectors in network traffic. For further than IoT development, and mainly for smart and IoT applications, there is a necessity for intelligent processing and analysis of data. So, our approach is too secure. We train several machine learning models that have been compared to accurately predicting attacks and anomalies on IoT systems, considering IoT applications, with ANOVA-based feature selection with fewer prediction models to evaluate network traffic to help prevent IoT devices. The machine learning (ML) algorithms that have been used here are KNN, SVM, NB, D.T., and R.F., with the most satisfactory test accuracy with fast detection. The evaluation of ML metrics includes precision, recall, F1 score, FPR, NPV, G.M., MCC, and AUC & ROC. The Random Forest algorithm achieved the best results with less prediction time, with an accuracy of 99.98%.

Keywords: machine learning, analysis of variance, Internet of Thing, network security, intrusion detection

Procedia PDF Downloads 90

Authors: Siti Rahmah Fitrianti, Mela Milani

Abstract:

Inadequate of water intake has negative effects on the health of the body, which can cause kidney failure and death. One of the factors that can affect someone intake of water is level of knowledge about the importance of water intake itself. A good knowledge of the daily water intake can increase the awareness of daily needed of water intake. Therefore, researchers initiated a study on the relationship of water intake to the level of knowledge related with water intake in food workers, at “Puspa” Hospital. Type of this research is quantitative research with cross-sectional approach. The research data was collected by measuring the independent and dependent variable at a time. This study took place in the food production unit of Nutrition Installation in "Puspa" Hospital, Jakarta in October 2016. The population target in this study were workers in food production unit aged 30-64 years. The instrument was a questionnaire question regarding water intake and 24 hours food recall. The result is 78.6% of respondents have less knowledge about the importance of water intake. Meanwhile, as many as 85.7% of respondents have adequate water intake. Tested by Chi-Square test, showed that no significant relationship between water intake with the level of knowledge related to water intake in workers of food production unit. Adequate intake of water in food workers commonly may be not caused by the level of knowledge related to water intake, but it may be cause of work environment factor which has a high temperature.

Keywords: food production unit, food workers, level of knowledge, water intake

Procedia PDF Downloads 321

Authors: Mst Shapna Akter, Hossain Shahriar

Abstract:

Neural network approaches are machine learning methods used in many domains, such as healthcare and cyber security. Neural networks are mostly known for dealing with image datasets. While training with the images, several fundamental mathematical operations are carried out in the Neural Network. The operation includes a number of algebraic and mathematical functions, including derivative, convolution, and matrix inversion and transposition. Such operations require higher processing power than is typically needed for computer usage. Central Processing Unit (CPU) is not appropriate for a large image size of the dataset as it is built with serial processing. While Graphics Processing Unit (GPU) has parallel processing capabilities and, therefore, has higher speed. This paper uses advanced Neural Network techniques such as VGG16, Resnet50, Densenet, Inceptionv3, Xception, Mobilenet, XGBOOST-VGG16, and our proposed models to compare CPU and GPU resources. A system for classifying autism disease using face images of an autistic and non-autistic child was used to compare performance during testing. We used evaluation matrices such as Accuracy, F1 score, Precision, Recall, and Execution time. It has been observed that GPU runs faster than the CPU in all tests performed. Moreover, the performance of the Neural Network models in terms of accuracy increases on GPU compared to CPU.

Keywords: autism disease, neural network, CPU, GPU, transfer learning

Procedia PDF Downloads 79

Authors: X. Laurent, M. A. Estevez, P. Mari-Beffa

Abstract:

A focus of recent research is to understand the role of our own response goals in the selection of information that will be encoded in episodic memory. For example, if we respond to a target in the presence of distractors, an important aspect under study is whether the distractor and the target share a common response (compatible) or not (incompatible). Some studies have found that compatible objects tend to be groups together and stored in episodic memory, whereas others found that targets in the presence of incompatible distractors are remembered better. Our current research seems to support both views. We used a Tulving-based definition of episodic memory to differentiate memory from episodic and non-episodic traces. In this task, participants first had to classify a blue object as human or animal (target) which appeared in the presence of a green one (distractor) that could belong to the same category of the target (compatible), to the opposite (incompatible) or to an irrelevant one (neutral). Later they had to report the identity (What), location (Where) and time (When) of both target objects (which had been previously responded to) and distractors (which had been ignored). Episodic memory was inferred when the three scene properties (identity, location and time) were correct. The measure of non-episodic memory consisted of those trials in which the identity was correctly remembered, but not the location or time. Our results showed that episodic memory for compatible stimuli is significantly superior to incompatible ones. In sharp contrast, non-episodic measures found superior memory for targets in the presence of incompatible distractors. Our results demonstrate that response compatibility affects the encoding of episodic and non-episodic memory traces in different ways.

Keywords: episodic memory, action systems, compatible response, what-where-when task

Procedia PDF Downloads 138