Search results for: short-term recall

Authors: Kaine Gulozer

Abstract:

Listening comprehension in a foreign language context has been a constant challenge for Turkish speakers of English. Syntactic priming (SP) of relative clauses might affect the perception of subsequent sentences of identical structure and this could have an impact on the listening comprehension of second or foreign language learners. There has been little attempt to investigate the syntactic priming of English subject relative clauses and object relative clauses in relation to perception for the learners of English in Turkish context. This study investigates SP effects on low-proficiency EFL learners’ production of English relative clauses. Both qualitative and quantitative method along with a pre-test and post-test tasks were adopted, recruiting 62 EFL learners to receive a six-week listening instruction on relative clauses. Testing instruments for language production included the two tasks: (1) the visual- cued presentation and recall and (2) the auditory-cued presentation and recall. Students’ listening comprehension in task 1 and 2 were recorded and transcribed. Fifteen of the participants were also interviewed. The results of the dependent samples t-test analyses revealed that SP had a significant effect on the overall perception of relative clauses.

Keywords: listening comprehension, relative clauses, structural priming, syntactic persistance, syntactic priming

Procedia PDF Downloads 171

Authors: Radhika Ranjan Roy

Abstract:

Deployment of machine learning (ML)/deep learning (DL) algorithms for cyberattack detection in operational communications networks (wireless and/or wire-line) is being delayed because of low-performance parameters (e.g., recall, precision, and f₁-score). If datasets become imbalanced, which is the usual case for communications networks, the performance tends to become worse. Complexities in handling reducing dimensions of the feature sets for increasing performance are also a huge problem. Mahalanobis algorithms have been widely applied in scientific research because Mahalanobis distance metric learning is a successful framework. In this paper, we have investigated the Mahalanobis binary classifier algorithm for increasing cyberattack detection performance over communications networks as a proof of concept. We have also found that high-dimensional information in intermediate features that are not utilized as much for classification tasks in ML/DL algorithms are the main contributor to the state-of-the-art of improved performance of the Mahalanobis method, even for imbalanced and sparse datasets. With no feature reduction, MD offers uniform results for precision, recall, and f₁-score for unbalanced and sparse NSL-KDD datasets.

Keywords: Mahalanobis distance, machine learning, deep learning, NS-KDD, local intrinsic dimensionality, chi-square, positive semi-definite, area under the curve

Procedia PDF Downloads 78

Authors: Musatafa Abbas Abbood Albadr, Masri Ayob, Sabrina Tiun, Fahad Taha Al-Dhief, Mohammad Kamrul Hasan

Abstract:

Breast Cancer (BC) is considered one of the most frequent reasons of cancer death in women between 40 to 55 ages. The BC is diagnosed by using digital images of the FNA (Fine Needle Aspirate) for both benign and malignant tumors of the breast mass. Therefore, this work proposes the Online Sequential Extreme Learning Machine (OSELM) algorithm for diagnosing BC by using the tumor features of the breast mass. The current work has used the Wisconsin Diagnosis Breast Cancer (WDBC) dataset, which contains 569 samples (i.e., 357 samples for benign class and 212 samples for malignant class). Further, numerous measurements of assessment were used in order to evaluate the proposed OSELM algorithm, such as specificity, precision, F-measure, accuracy, G-mean, MCC, and recall. According to the outcomes of the experiment, the highest performance of the proposed OSELM was accomplished with 97.66% accuracy, 98.39% recall, 95.31% precision, 97.25% specificity, 96.83% F-measure, 95.00% MCC, and 96.84% G-Mean. The proposed OSELM algorithm demonstrates promising results in diagnosing BC. Besides, the performance of the proposed OSELM algorithm was superior to all its comparatives with respect to the rate of classification.

Keywords: breast cancer, machine learning, online sequential extreme learning machine, artificial intelligence

Procedia PDF Downloads 111

Authors: Shital Patil, Surendra Bhosale

Abstract:

Cardiac diseases are the leading causes of mortality and morbidity in the world, from recent few decades accounting for a large number of deaths have emerged as the most life-threatening disorder globally. Machine learning and Artificial intelligence have been playing key role in predicting the heart diseases. A relevant set of feature can be very helpful in predicting the disease accurately. In this study, we proposed a comparative analysis of 4 different features selection methods and evaluated their performance with both raw (Unbalanced dataset) and sampled (Balanced) dataset. The publicly available Z-Alizadeh Sani dataset have been used for this study. Four feature selection methods: Data Analysis, minimum Redundancy maximum Relevance (mRMR), Recursive Feature Elimination (RFE), Chi-squared are used in this study. These methods are tested with 8 different classification models to get the best accuracy possible. Using balanced and unbalanced dataset, the study shows promising results in terms of various performance metrics in accurately predicting heart disease. Experimental results obtained by the proposed method with the raw data obtains maximum AUC of 100%, maximum F1 score of 94%, maximum Recall of 98%, maximum Precision of 93%. While with the balanced dataset obtained results are, maximum AUC of 100%, F1-score 95%, maximum Recall of 95%, maximum Precision of 97%.

Keywords: cardio vascular diseases, machine learning, feature selection, SMOTE

Procedia PDF Downloads 118

Authors: Zahra Alipour, Amirreza Moheb Afzali

Abstract:

In the field of human-computer interaction (HCI), hand gestures play a crucial role in facilitating communication by expressing emotions and intentions. The precise tracking of the index finger and the estimation of joint positions are essential for developing effective gesture recognition systems. However, various challenges, such as anatomical variations, occlusions, and environmental influences, hinder optimal functionality. This study investigates the performance of the YOLOv8m model for hand detection using the EgoHands dataset, which comprises diverse hand gesture images captured in various environments. Over three training processes, the model demonstrated significant improvements in precision (from 88.8% to 96.1%) and recall (from 83.5% to 93.5%), achieving a mean average precision (mAP) of 97.3% at an IoU threshold of 0.7. We also compared YOLOv8m with MediaPipe and an integrated YOLOv8 + MediaPipe approach. The combined method outperformed the individual models, achieving an accuracy of 99% and a recall of 99%. These findings underscore the benefits of model integration in enhancing gesture recognition accuracy and localization for real-time applications. The results suggest promising avenues for future research in HCI, particularly in augmented reality and assistive technologies, where improved gesture recognition can significantly enhance user experience.

Keywords: YOLOv8, mediapipe, finger tracking, joint estimation, human-computer interaction (HCI)

Procedia PDF Downloads 5

Authors: John Paul Q. Tomas, Mark Wilson L. de los Reyes, Kirsten Joyce P. Vasquez

Abstract:

The most frequent type of fracture is a wrist fracture, which often makes it difficult for medical professionals to find and locate. In this study, fractures in wrist x-ray pictures were located and identified using deep learning and computer vision. The researchers used image filtering, masking, morphological operations, and data augmentation for the image preprocessing and trained the RetinaNet and Faster R-CNN models with ResNet50 backbones and Adam optimizers separately for each image filtering technique and projection. The RetinaNet model with Anisotropic Diffusion Smoothing filter trained with 50 epochs has obtained the greatest accuracy of 99.14%, precision of 100%, sensitivity/recall of 98.41%, specificity of 100%, and an IoU score of 56.44% for the Posteroanterior projection utilizing augmented data. For the Lateral projection using augmented data, the RetinaNet model with an Anisotropic Diffusion filter trained with 50 epochs has produced the highest accuracy of 98.40%, precision of 98.36%, sensitivity/recall of 98.36%, specificity of 98.43%, and an IoU score of 58.69%. When comparing the test results of the different individual projections, models, and image filtering techniques, the Anisotropic Diffusion filter trained with 50 epochs has produced the best classification and regression scores for both projections.

Keywords: Artificial Intelligence, Computer Vision, Wrist Fracture, Deep Learning

Procedia PDF Downloads 73

Authors: Rajvir Kaur, Jeewani Anupama Ginige

Abstract:

With recent trends in Big Data and advancements in Information and Communication Technologies, the healthcare industry is at the stage of its transition from clinician oriented to technology oriented. Many people around the world die of cancer because the diagnosis of disease was not done at an early stage. Nowadays, the computational methods in the form of Machine Learning (ML) are used to develop automated decision support systems that can diagnose cancer with high confidence in a timely manner. This paper aims to carry out the comparative evaluation of a selected set of ML classifiers on two existing datasets: breast cancer and cervical cancer. The ML classifiers compared in this study are Decision Tree (DT), Support Vector Machine (SVM), k-Nearest Neighbor (k-NN), Logistic Regression, Ensemble (Bagged Tree) and Artificial Neural Networks (ANN). The evaluation is carried out based on standard evaluation metrics Precision (P), Recall (R), F1-score and Accuracy. The experimental results based on the evaluation metrics show that ANN showed the highest-level accuracy (99.4%) when tested with breast cancer dataset. On the other hand, when these ML classifiers are tested with the cervical cancer dataset, Ensemble (Bagged Tree) technique gave better accuracy (93.1%) in comparison to other classifiers.

Keywords: artificial neural networks, breast cancer, classifiers, cervical cancer, f-score, machine learning, precision, recall

Procedia PDF Downloads 277

Authors: Rahimah Akbar, Abdullah Al-Hashemi, Hanan Taqi, Taiba Sadeq

Abstract:

As technology continues to develop, teaching curriculums in both schools and universities have begun adopting a more computer/digital based approach to the transmission of knowledge and information, as opposed to the more old-fashioned use of textbooks. This gives rise to the question: Are there any differences in learning from a digital source over learning from a printed source, as in from a textbook? More specifically, which medium of information results in better long-term retention? A review of the confounding factors implicated in understanding the relationship between learning from the two different mediums was done. Alongside this, a 4-week cohort study involving 76 1st year English Language female students was performed, whereby the participants were divided into 2 groups. Group A studied material from a paper source (referred to as the Print Medium), and Group B studied material from a digital source (Digital Medium). The dependent variables were grading of memory recall indexed by a 4 point grading system, and total frequency of item repetition. The study was facilitated by advanced computer software called Super Memo. Results showed that, contrary to prevailing evidence, the Digital Medium group showed no statistically significant differences in terms of the shift from Remember (Episodic) to Know (Semantic) when all confounding factors were accounted for. The shift from Random Guess and Familiar to Remember occurred faster in the Digital Medium than it did in the Print Medium.

Keywords: digital medium, print medium, long-term memory recall, episodic memory, semantic memory, super memo, forgetting index, frequency of repetitions, total time spent

Procedia PDF Downloads 289

Authors: Dandeswar Bisoyi, Preeti Yadav, Utpal Barua

Abstract:

This study address particular way that verbal information can affect the processing of positive and interesting qualities which help in making the brand attractive to the consumer. Also, it address the development of a communication strategy which is a very important part of the marketing plan we have to take into account many factors. Out of all the product strengths, the strategy has to outline one marked differential which will drive our brand. This is the fundamental base on which the entire creative strategy will be big idea-based.

Keywords: copy writing, advertisement, marketing, branding, recall

Procedia PDF Downloads 582

Authors: Sevilay Çankaya

Abstract:

The detection of deception in children’s interviews is essential for statement veracity. The widely used method for deception detection is building cognitive load, which is the logic of the cognitive interview (CI), and its effectiveness for adults is approved. This meta-analysis delves into the effectiveness of inducing cognitive load as a means of enhancing veracity detection during interviews with children. Additionally, the effectiveness of cognitive load on children's total number of events recalled is assessed as a second part of the analysis. The current meta-analysis includes ten effect sizes from search using databases. For the effect size calculation, Hedge’s g was used with a random effect model by using CMA version 2. Heterogeneity analysis was conducted to detect potential moderators. The overall result indicated that cognitive load had no significant effect on veracity outcomes (g =0.052, 95% CI [-.006,1.25]). However, a high level of heterogeneity was found (I² = 92%). Age, participants’ characteristics, interview setting, and characteristics of the interviewer were coded as possible moderators to explain variance. Age was significant moderator (β = .021; p = .03, R2 = 75%) but the analysis did not reveal statistically significant effects for other potential moderators: participants’ characteristics (Q = 0.106, df = 1, p = .744), interview setting (Q = 2.04, df = 1, p = .154), and characteristics of interviewer (Q = 2.96, df = 1, p = .086). For the second outcome, the total number of events recalled, the overall effect was significant (g =4.121, 95% CI [2.256,5.985]). The cognitive load was effective in total recalled events when interviewing with children. All in all, while age plays a crucial role in determining the impact of cognitive load on veracity, the surrounding context, interviewer attributes, and inherent participant traits may not significantly alter the relationship. These findings throw light on the need for more focused, age-specific methods when using cognitive load measures. It may be possible to improve the precision and dependability of deceit detection in children's interviews with the help of more studies in this field.

Keywords: deceit detection, cognitive load, memory recall, children interviews, meta-analysis

Procedia PDF Downloads 55

Authors: Kehabtimer Shiferaw Kotiso, Getachew Hailemariam, Abiy Seifu Estifanos

Abstract:

Introduction: Despite the highest share of low birth weight (LBW) for neonatal mortality and morbidity, predicting births with LBW for better intervention preparation is challenging. This study aims to predict LBW using a dataset encompassing 53,637 birth cohorts collected from 36 primary hospitals across seven regions in Ethiopia from February 2022 to June 2024. Methods: We identified ten explanatory variables related to maternal and neonatal characteristics, including maternal education, age, residence, history of miscarriage or abortion, history of preterm birth, type of pregnancy, number of livebirths, number of stillbirths, antenatal care frequency, and sex of the fetus to predict LBW. Using WEKA 3.8.2, we developed and compared seven machine learning algorithms. Data preprocessing included handling missing values, outlier detection, and ensuring data integrity in birth weight records. Model performance was evaluated through metrics such as accuracy, precision, recall, F1-score, and area under the Receiver Operating Characteristic curve (ROC AUC) using 10-fold cross-validation. Results: The results demonstrated that the decision tree, J48, logistic regression, and gradient boosted trees model achieved the highest accuracy (94.5% to 94.6%) with a precision of 93.1% to 93.3%, F1-score of 92.7% to 93.1%, and ROC AUC of 71.8% to 76.6%. Conclusion: This study demonstrates the effectiveness of machine learning models in predicting LBW. The high accuracy and recall rates achieved indicate that these models can serve as valuable tools for healthcare policymakers and providers in identifying at-risk newborns and implementing timely interventions to achieve the sustainable developmental goal (SDG) related to neonatal mortality.

Keywords: low birth weight, machine learning, classification, neonatal mortality, Ethiopia

Procedia PDF Downloads 21

Authors: Ivana Hrebickova, Maria Sevcikova, Romana Slamberova

Abstract:

The present study was aimed at evaluation of cognitive changes following scheduled neonatal methamphetamine exposure in combination with long-term exposure in adulthood of female Wistar rats. Pregnant mothers were divided into two groups: group with indirect exposure (methamphetamine in dose 5 mg/ml/kg, saline in dose 1 ml/kg) during early lactation period (postnatal day 1–11) - progeny of these mothers were exposed to the effects of methamphetamine or saline indirectly via the breast milk; and the second group with direct exposure – all mothers were left intact for the entire lactation period, while progeny was treated with methamphetamine (5 mg/ml/kg) by injection or the control group, which was received needle pick (shame, not saline) at the same time each day of period of application (postnatal day 1–11). Learning ability and memory consolidation were tested in the Morris Water Maze, which consisted of three types of tests: ‘Place Navigation Test ‘; ‘Probe Test ‘; and ‘Memory Recall Test ‘. Adult female progeny were injected daily, after completion last trial with saline or methamphetamine (1 mg/ml/kg). We compared the effects of indirect/direct neonatal methamphetamine exposure and adult methamphetamine treatment on cognitive function of female rats. Statistical analyses showed that neonatal methamphetamine exposure worsened spatial learning and ability to remember the position of the platform. The present study demonstrated that direct methamphetamine exposure has more significant impact on process of learning and memory than indirect exposure. Analyses of search strategies (thigmotaxis, scanning) used by females during the Place Navigation Test and Memory Recall Test confirm all these results.

Keywords: methamphetamine, Morris water maze, neonatal exposure, strategies, Wistar rats

Procedia PDF Downloads 266

Authors: Mohammad Hassanzadeh

Abstract:

As far as incidental vocabulary learning is concerned, the basic contention of the Involvement Load Hypothesis (ILH) is that retention of unfamiliar words is, generally, conditional upon the degree of involvement in processing them. This study examined input modality and incidental vocabulary uptake in a task-induced setting whereby three variously loaded task types (marginal glosses, fill-in-task, and sentence-writing) were alternately assigned to one group of students at Allameh Tabataba’i University (n=2l) during six classroom sessions. While one round of exposure was comprised of the audiovisual medium (TV talk shows), the second round consisted of textual materials with approximately similar subject matter (reading texts). In both conditions, however, the tasks were equivalent to one another. Taken together, the study pursued the dual objectives of establishing a litmus test for the ILH and its proposed values of ‘need’, ‘search’ and ‘evaluation’ in the first place. Secondly, it sought to bring to light the superiority issue of exposure to audiovisual input versus the written input as far as the incorporation of tasks is concerned. At the end of each treatment session, a vocabulary active recall test was administered to measure their incidental gains. Running a one-way analysis of variance revealed that the audiovisual intervention yielded higher gains than the written version even when differing tasks were included. Meanwhile, task 'three' (sentence-writing) turned out the most efficient in tapping learners' active recall of the target vocabulary items. In addition to shedding light on the superiority of audiovisual input over the written input when circumstances are relatively held constant, this study for the most part, did support the underlying tenets of ILH.

Keywords: Keywords— Evaluation, incidental vocabulary learning, input mode, Involvement Load Hypothesis, need, search.

Procedia PDF Downloads 279

Authors: Mohammad Abu-Shaira, Weishi Shi

Abstract:

Adaptive learning, a commonly employed solution to drift, involves updating predictive models online during their operation to react to concept drifts, thereby serving as a critical component and natural extension for online learning systems that learn incrementally from each example. This paper introduces LSTM-SCCM “Long Short-Term Memory Stream Cruise Control Method”, a drift adaptation-as-a-service framework for online learning. LSTM-SCCM automates drift adaptation through prompt detection, drift magnitude quantification, dynamic hyperparameter tuning, performing shortterm optimization and model recalibration for immediate adjustments, and, when necessary, conducting long-term model recalibration to ensure deeper enhancements in model performance. LSTM-SCCM is incorporated into a suite of cutting-edge online regression models, assessing their performance across various types of concept drift using diverse datasets with varying characteristics. The findings demonstrate that LSTM-SCCM represents a notable advancement in both model performance and efficacy in handling concept drift occurrences. LSTM-SCCM stands out as the sole framework adept at effectively tackling concept drifts within regression scenarios. Its proactive approach to drift adaptation distinguishes it from conventional reactive methods, which typically rely on retraining after significant degradation to model performance caused by drifts. Additionally, LSTM-SCCM employs an in-memory approach combined with the Self-Adjusting Memory (SAM) architecture to enhance real-time processing and adaptability. The framework incorporates variable thresholding techniques and does not assume any particular data distribution, making it an ideal choice for managing high-dimensional datasets and efficiently handling large-scale data. Our experiments, which include abrupt, incremental, and gradual drifts across both low- and high-dimensional datasets with varying noise levels, and applied to four state-of-the-art online regression models, demonstrate that LSTM-SCCM is versatile and effective, rendering it a valuable solution for online regression models to address concept drift.

Keywords: automated drift detection and adaptation, concept drift, hyperparameters optimization, online and adaptive learning, regression

Procedia PDF Downloads 11

Authors: Puja Mahesh

Abstract:

Purpose: A good slogan captures the essence of your brand's promised consumer benefit in one short phrase. A good slogan conjures up positive imagery about your business or your product. A good slogan has the element of immediacy. Immediacy does not necessarily mean that the slogan will inspire consumers to run right out and buy your product. It does mean, however, that your slogan has an immediate cognitive impact. It forces your audience to "stop-and-think" after exposure as a necessary first step toward remembering your slogan promise. A good slogan is memorable and durability. When your slogan promise is occupying prime real estate in the consumer's subconscious, it aids in recall and activates preference for your brand when you want it -when consumers are ready to buy. The objective of current study is to understand the consumer perception of slogans/taglines of higher education sector in India. Design/Methodology/Approach: Survey of 500 consumers (largely comprising of youth) will be done using questionnaire. Universities and institutes will be chosen on the basis of various streams and Credible Rankings. The perception will be taken from the respondents on the basis of scale. Findings: Catchy phrases, rhymes, music, jingles, avatars (visual representations) and unique imagery are just a few of the mnemonic clutter-busting tactics commonly used in slogans to stand apart from the competition and to aid in memory recall. The study will reveal whether it is true that catchy phrases, rhymes, music, jingles, avatars (visual representations) and unique imagery across disciplines and universities help in building stronger brands. It will also be found whether consumers pay more attention to reputation of University/ College or brand identity. Originality/Value: Researcher has not come across any study of Consumer Perception of Slogans/Taglines of Higher Education Brands in India. Also, it would be interesting to understand Consumer Perception of various colleges/streams particularly Management colleges who invest a lot of time in branding exercise.

Keywords: consumer perception, higher education, slogans, taglines

Procedia PDF Downloads 424

Authors: Jarmila Štěpánová, Martin Kudláček, Lukáš Jakubec

Abstract:

The people with spinal cord injury are one of the least sport active members of our society. Their hypoactivity is determined by primary injury, i.e., the loss of motor function, the injured part of the body is connected with health complications and social handicap. Study performs one part of the standardization process of semi-structured interview PARA-SCI.CZ (Czech version of the Physical Activity Recall Assessment for People with Spinal Cord Injury), which measures the type, frequency, duration, and intensity of physical activity of people with spinal cord injury. The study focused on persons with paraplegia who use a wheelchair as their primary mode of mobility. The aim of this study was to perform a process to determine the criterion validity of PARA-SCI.CZ. The actual physical activity of wheelchair users was monitored during three days by using accelerometers Actigraph GT3X fixed on the non-dominant wrist, and semi-structured interview PARA-SCI.CZ. During the PARA-SCI.CZ interview, participants were asked to recall activities they had done over the past 3 days, starting with the previous day. PARA-SCI.CZ captured frequency, duration, and intensity (low, moderate, and heavy) of two categories of physical activity (leisure time physical activity and activities of a usual day). Accelerometer Actigraph GT3X captured duration and intensity (low and moderate + heavy) of physical activity during three days and nights. The study presented three potential recalculations of measured data. Standardization process of PARA-SCI.CZ is essential to critically approach issues of health and active lifestyle of persons with spinal cord injury in the Czech Republic. Standardized PARA-SCI.CZ can be used in practice by physiotherapists and sports pedagogues from the field of adapted physical activities.

Keywords: physical activity, lifestyle, paraplegia, semi-structure interview, accelerometer

Procedia PDF Downloads 325

Authors: Emiel Caron

Abstract:

Patent databases contain patent related data, organized in a relational data model, and are used to produce various patent statistics. These databases store raw data about scientific references cited by patents. For example, Patstat holds references to tens of millions of scientific journal publications and conference proceedings. These references might be used to connect patent databases with bibliographic databases, e.g. to study to the relation between science, technology, and innovation in various domains. Problematic in such studies is the low data quality of the references, i.e. they are often ambiguous, unstructured, and incomplete. Moreover, a complete bibliographic reference is stored in only one attribute. Therefore, a computerized cleaning and disambiguation method for large patent databases is developed in this work. The method uses rule-based scoring and clustering. The rules are based on bibliographic metadata, retrieved from the raw data by regular expressions, and are transparent and adaptable. The rules in combination with string similarity measures are used to detect pairs of records that are potential duplicates. Due to the scoring, different rules can be combined, to join scientific references, i.e. the rules reinforce each other. The scores are based on expert knowledge and initial method evaluation. After the scoring, pairs of scientific references that are above a certain threshold, are clustered by means of single-linkage clustering algorithm to form connected components. The method is designed to disambiguate all the scientific references in the Patstat database. The performance evaluation of the clustering method, on a large golden set with highly cited papers, shows on average a 99% precision and a 95% recall. The method is therefore accurate but careful, i.e. it weighs precision over recall. Consequently, separate clusters of high precision are sometimes formed, when there is not enough evidence for connecting scientific references, e.g. in the case of missing year and journal information for a reference. The clusters produced by the method can be used to directly link the Patstat database with bibliographic databases as the Web of Science or Scopus.

Keywords: clustering, data cleaning, data disambiguation, data mining, patent analysis, scientometrics

Procedia PDF Downloads 194

Authors: Saeid Asghari

Abstract:

The growing interest in sustainability and healthy lifestyles has stimulated the development of solutions that promote mindful consumption and healthier choices. One such solution is the use of transparent graded lanes in product packaging, which enables consumers to visually track their product consumption and encourages portion control. However, the extent to which this packaging affects consumer behavior, trust, and loyalty towards a product or brand, as well as the effectiveness of messaging on the graded lanes, remains unclear. The research aims to examine the impact of transparent graded lanes on consumer behavior, trust, and loyalty towards products or brands in the context of the Janbo chain supermarket in Tehran, Iran, focusing on Ketchup and edible oils containers. A representative sample of 720 respondents is selected using quota sampling based on sex, age, and financial status. The study assesses the effect of messaging on the graded lanes in enhancing consumer recall and recognition of the product at the time of purchase, increasing repeat purchases, and fostering long-term relationships with customers. Furthermore, the potential outcomes of using transparent graded lanes, including the promotion of healthy consumption habits and the reduction of food waste, are also considered. The findings and results can inform the development of effective messaging strategies for graded lanes and suggest ways to enhance consumer engagement with product packaging. Moreover, the study's outcomes can contribute to the broader discourse on sustainable consumption and healthy lifestyles, highlighting the potential role of packaging innovations in promoting these values. We used four theories (social cognitive theory, self-perception theory, nudge theory, and marketing and consumer behavior) to examine the effect of these transparent graded lanes on consumer behavior. The conceptual model integrates the use of transparent graded lanes, consumer behavior, trust and loyalty, messaging, and promotion of healthy consumption habits. The study aims to provide insights into how transparent graded lanes can promote mindful consumption, increase consumer recognition and recall of the product, and foster long-term relationships with customers. Findings suggest that the use of transparent graded lanes on Ketchup and edible oils containers can have a positive impact on consumer behavior, trust, and loyalty towards a product or brand, as well as promote mindful consumption and healthier choices. The messaging on the graded lanes is also found to be effective in promoting recall and recognition of the product at the time of purchase and encouraging repeat purchases. However, the impact of transparent graded lanes may be limited by factors such as cultural norms, personal values, and financial status. Broadly speaking, the investigation provides valuable insights into the potential benefits and challenges of using transparent graded lanes in product packaging, as well as effective strategies for promoting healthy consumption habits and building long-term relationships with customers.

Keywords: packaging customer behavior, purchase, brand loyalty, healthy consumption

Procedia PDF Downloads 252

Authors: AnjalI A. Prasad

Abstract:

Nowadays, social media played an important role in spreading misinformation or fake news. This study analyzes the fake news related to the COVID-19 pandemic spread in social media. This paper aims at evaluating and comparing different approaches that are used to mitigate this issue, including popular deep learning approaches, such as CNN, RNN, LSTM, and BERT algorithm for classification. To evaluate models’ performance, we used accuracy, precision, recall, and F1-score as the evaluation metrics. And finally, compare which algorithm shows better result among the four algorithms.

Keywords: BERT, CNN, LSTM, RNN

Procedia PDF Downloads 205

Authors: Bahareh Ansari

Abstract:

Background: The Open Government Data (OGD) movement in the last decade has encouraged many government organizations around the world to make their data publicly available to advance democratic processes. But current open data platforms have not yet reached to their full potential in supporting all interested parties. To make the data useful and understandable for everyone, scholars suggested that opening the data should be supplemented by visualization. However, different visualizations of the same information can dramatically change an individual’s cognitive and emotional experience in working with the data. This study reviews the data visualization literature to create a list of the methods empirically tested to enhance users’ performance and experience in working with a visualization tool. This list can be used in evaluating the OGD visualization practices and informing the future open data initiatives. Methods: Previous reviews of visualization literature categorized the visualization outcomes into four categories including recall/memorability, insight/comprehension, engagement, and enjoyment. To identify the papers, a search for these outcomes was conducted in the abstract of the publications of top-tier visualization venues including IEEE Transactions for Visualization and Computer Graphics, Computer Graphics, and proceedings of the CHI Conference on Human Factors in Computing Systems. The search results are complemented with a search in the references of the identified articles, and a search for 'open data visualization,' and 'visualization evaluation' keywords in the IEEE explore and ACM digital libraries. Articles are included if they provide empirical evidence through conducting controlled user experiments, or provide a review of these empirical studies. The qualitative synthesis of the studies focuses on identification and classifying the methods, and the conditions under which they are examined to positively affect the visualization outcomes. Findings: The keyword search yields 760 studies, of which 30 are included after the title/abstract review. The classification of the included articles shows five distinct methods: interactive design, aesthetic (artistic) style, storytelling, decorative elements that do not provide extra information including text, image, and embellishment on the graphs), and animation. Studies on decorative elements show consistency on the positive effects of these elements on user engagement and recall but are less consistent in their examination of the user performance. This inconsistency could be attributable to the particular data type or specific design method used in each study. The interactive design studies are consistent in their findings of the positive effect on the outcomes. Storytelling studies show some inconsistencies regarding the design effect on user engagement, enjoyment, recall, and performance, which could be indicative of the specific conditions required for the use of this method. Last two methods, aesthetics and animation, have been less frequent in the included articles, and provide consistent positive results on some of the outcomes. Implications for e-government: Review of the visualization best-practice methods show that each of these methods is beneficial under specific conditions. By using these methods in a potentially beneficial condition, OGD practices can promote a wide range of individuals to involve and work with the government data and ultimately engage in government policy-making procedures.

Keywords: best practices, data visualization, literature review, open government data

Procedia PDF Downloads 105

Authors: Maryam Bahreini, Mostafa Talebi Garekani, Fatemeh Rasooli, Atefeh Abdollahi

Abstract:

Introduction: Procedural sedation and analgesia have been desirable to handle painful procedures. The trend to find the agent with more efficacy and less complications is still controversial; thus, many sedative regimens have been studied. This study tried to assess the effectiveness and adverse effects of thiopental sodium-fentanyl with the known medication, ketamine-propofol for procedural sedation in the emergency department. Methods: Consenting patients were enrolled in this randomized double-blind trial to receive either 1:1 ketamine-propofol (KP) or thiopental-fentanyl (TF) 1:1 mg: Mg proportion on a weight-based dosing basis to reach the sedation level of American Society of Anesthesiologist class III/IV. The respiratory and hemodynamic complications, nausea and vomiting, recovery agitation, patient recall and satisfaction, provider satisfaction and recovery time were compared. The study was registered in Iranian randomized Control Trial Registry (Code: IRCT2015111325025N1). Results: 96 adult patients were included and randomized, 47 in the KP group and 49 in the TF group. 2.1% in the KP group and 8.1 % in the TF group experienced transient hypoxia leading to performing 4.2 % versus 8.1 % airway maneuvers for 2 groups, respectively; however, no statistically significant difference was observed between 2 combinations, and there was no report of endotracheal placement or further admission. Patient and physician satisfaction were significantly higher in the KP group. There was no difference in respiratory, gastrointestinal, cardiovascular and psychiatric adverse events, recovery time and patient recall of the procedure between groups. The efficacy and complications were not related to the type of procedure or patients’ smoking or addiction trends. Conclusion: Ketamine-propofol and thiopental-fentanyl combinations were effectively comparable although KP resulted in higher patient and provider satisfaction. It is estimated that thiopental fentanyl combination can be as potent and efficacious as ketofol with relatively similar incidence of adverse events in procedural sedation.

Keywords: adverse effects, conscious sedation, fentanyl, propofol, ketamine, safety, thiopental

Procedia PDF Downloads 218

Authors: Erin Lynne Plettenberg, Jeremy Vickery

Abstract:

In an access-control situation, the role of a user determines whether a data request is appropriate. This paper combines vetted web mining and logic modeling to build a lightweight system for determining the role of a health care provider based only on their prior authorized requests. The model identifies provider roles with 100% recall from very little data. This shows the value of vetted web mining in AI systems, and suggests the impact of the ICD classification on medical practice.

Keywords: electronic medical records, information extraction, logic modeling, ontology, vetted web mining

Procedia PDF Downloads 172

Authors: E. C. Swart, E. Kunneke

Abstract:

Background: Disparities in food security exist between communities and households across the country, reflecting continuing social and economic inequalities. The purpose of this study was to investigate the presence of food insecurity amongst UWC students. Method: Cross-sectional study recruited 200 students via email and cellphone from an ICS generated list of randomly selected students aged 18-25. Data collection took place during the first two weeks of term 3. Individual appointments were made with consenting participants and conducted in English by trained BSc Dietetics students. Data was analysed using SPSS. The hunger scale used by Stats SA (October 2010) was used. Dietary intake was assessed using a single 24hr recall. Results: Sixty-three percent of the students reported that they do experience some food insecurity whilst 14.5% reported to go hungry due to inadequate access to food. Coping mechanisms during periods of food insecurity include: Asking a friend, neighbour, family member (40%); Borrow (15%); Steal (none); Casual jobs (12%). Anthropometric status of students did not differ statistically significantly by food security status. A statistically significantly greater proportion of Xhosa speaking students reported inadequate money for food. Students residing in residences off campus appear to be least food secure in terms of money available and limiting food intake, whilst those residing at home are less food insecure. Similar proportions of students who receive bursaries or whose parents are paying reported going hungry whilst those who supports themselves never goes hungry. Mean nutrient intake during the previous 24 hours of students who reported inadequate resources to buy food, who eat less due to inadequate resources and who goes hungry only differed statistically significantly for Vitamin B (go hungry) and for fibre (money shortage). In general the nutrient intake is lower for those who reported to eat less and go hungry except for added sugar, vitamin A and folate (go hungry), and energy, fibre, iron, riboflavin and folate (eat less). For students who reported to have inadequate money to buy food, the mean nutrient intake was higher except for calcium and thiamin. The mean body mass index of this group of students was also higher even though the difference was not statistically significant. Conclusion: Hunger is present on campus however a single 24hr recall did not confirm statistically significant lower nutrient intakes for students who reported different levels of food insecurity.

Keywords: anthropometry, dietary intake, nutritional status, students

Procedia PDF Downloads 374

Authors: Jemima C. A. Sumboh

Abstract:

Given the urgency and consensus for countries to move towards Universal Health Coverage (UHC), health financing systems need to be accurately and consistently monitored to provide valuable data to inform policy and practice. Most of the indicators for monitoring UHC, particularly catastrophe and impoverishment, are established based on the impact of out-of-pocket health payments (OOPHP) on households’ living standards, collected through varied household surveys. These surveys, however, vary substantially in survey methods such as the length of the recall period or the number of items included in the survey questionnaire or the farming of questions, potentially influencing the level of OOPHP. Using different survey instruments can provide inaccurate, inconsistent, erroneous and misleading estimates of UHC, subsequently influencing wrong policy decisions. Using data from a household budget survey conducted by the Navrongo Health Research Center in Ghana from May 2017 to December 2018, this study intends to explore the potential implications of using surveys with varied levels of disaggregation of OOPHP data on estimates of financial risk protection. The household budget survey, structured around food and non-food expenditure, compared three OOPHP measuring instruments: Version I (existing questions used to measure OOPHP in household budget surveys), Version II (new questions developed through benchmarking the existing Classification of the Individual Consumption by Purpose (COICOP) OOPHP questions in household surveys) and Version III (existing questions used to measure OOPHP in health surveys integrated into household budget surveys- for this, the demographic and health surveillance (DHS) health survey was used). Version I, II and III contained 11, 44, and 56 health items, respectively. However, the choice of recall periods was held constant across versions. The sample size for Version I, II and III were 930, 1032 and 1068 households, respectively. Financial risk protection will be measured based on the catastrophic and impoverishment methodologies using STATA 15 and Adept Software for each version. It is expected that findings from this study will present valuable contributions to the repository of knowledge on standardizing survey instruments to obtain estimates of financial risk protection that are valid and consistent.

Keywords: Ghana, household budget surveys, measuring financial risk protection, out-of-pocket health payments, survey instruments, universal health coverage

Procedia PDF Downloads 137

Authors: Mira Trebar

Abstract:

Logistics processes of perishable food in the supply chain include the distribution activities and the real time temperature monitoring to fulfil the cold chain requirements. The paper presents the use of RFID (Radio Frequency Identification) technology as an identification tool of receiving and shipping activities in the cold store. At the same time, the use of RFID data loggers with temperature sensors is presented to observe and store the temperatures for the purpose of analyzing the processes and having the history data available for traceability purposes and efficient recall management.

Keywords: logistics, warehouse, RFID device, cold chain

Procedia PDF Downloads 631

Authors: Elcin Timur Cakmak, Ayse Oguzlar

Abstract:

This study presents the results of the tweets sent by Twitter users on social media about the Russia-Ukraine war by bigram and trigram methods. On February 24, 2022, Russian President Vladimir Putin declared a military operation against Ukraine, and all eyes were turned to this war. Many people living in Russia and Ukraine reacted to this war and protested and also expressed their deep concern about this war as they felt the safety of their families and their futures were at stake. Most people, especially those living in Russia and Ukraine, express their views on the war in different ways. The most popular way to do this is through social media. Many people prefer to convey their feelings using Twitter, one of the most frequently used social media tools. Since the beginning of the war, it is seen that there have been thousands of tweets about the war from many countries of the world on Twitter. These tweets accumulated in data sources are extracted using various codes for analysis through Twitter API and analysed by Python programming language. The aim of the study is to find the word sequences in these tweets by the n-gram method, which is known for its widespread use in computational linguistics and natural language processing. The tweet language used in the study is English. The data set consists of the data obtained from Twitter between February 24, 2022, and April 24, 2022. The tweets obtained from Twitter using the #ukraine, #russia, #war, #putin, #zelensky hashtags together were captured as raw data, and the remaining tweets were included in the analysis stage after they were cleaned through the preprocessing stage. In the data analysis part, the sentiments are found to present what people send as a message about the war on Twitter. Regarding this, negative messages make up the majority of all the tweets as a ratio of %63,6. Furthermore, the most frequently used bigram and trigram word groups are found. Regarding the results, the most frequently used word groups are “he, is”, “I, do”, “I, am” for bigrams. Also, the most frequently used word groups are “I, do, not”, “I, am, not”, “I, can, not” for trigrams. In the machine learning phase, the accuracy of classifications is measured by Classification and Regression Trees (CART) and Naïve Bayes (NB) algorithms. The algorithms are used separately for bigrams and trigrams. We gained the highest accuracy and F-measure values by the NB algorithm and the highest precision and recall values by the CART algorithm for bigrams. On the other hand, the highest values for accuracy, precision, and F-measure values are achieved by the CART algorithm, and the highest value for the recall is gained by NB for trigrams.

Keywords: classification algorithms, machine learning, sentiment analysis, Twitter

Procedia PDF Downloads 73

Authors: Shahbaz Ahmed

Abstract:

This study is conducted to demonstrate the knowledge of intentional learning and incidental learning. Hypothesis of this experiment is intentional learning is better than incidental learning, participants were demonstrated and were asked to learn the 10 nonsense syllables in a specific sequence from the colored cards in the end they were asked to recall the background color of each card instead of nonsense syllables. Independent variables of the experiment are the colored cards containing nonsense syllables which are to be memorized by the participants, dependent variables are the number of correct responses made by the participant. The findings of the experiment concluded that intentional learning is better than incidental learning, hence hypothesis is proved.

Keywords: intentional learning, incidental learning, non-sense syllable cards, score sheets

Procedia PDF Downloads 534

Authors: Tet H. Yeap

Abstract:

An analog restricted Hopfield Network is presented in this paper. It consists of two layers of nodes, visible and hidden nodes, connected by directional weighted paths forming a bipartite graph with no intralayer connection. An energy or Lyapunov function was derived to show that the proposed network will converge to stable states. By introducing hidden nodes, the proposed network can be trained to store patterns and has increased memory capacity. Training to be an associative memory, simulation results show that the associative memory performs better than a classical Hopfield network by being able to perform better memory recall when the input is noisy.

Keywords: restricted Hopfield network, Lyapunov function, simultaneous perturbation stochastic approximation

Procedia PDF Downloads 133

Authors: Simone B. K. Aires, Cinthia O. de A. Freitas, Luiz E. S. Oliveira

Abstract:

This paper contributes to the CBIR systems applied to trademark retrieval. The proposed model includes aspects from visual perception of the shapes, by means of feature extractor associated to a non-symmetrical perceptual zoning mechanism based on the Principles of Gestalt. Thus, the feature set were performed using Scale Invariant Feature Transform (SIFT). We carried out experiments using four different zonings strategies (Z = 4, 5H, 5V, 7) for matching and retrieval tasks. Our proposal method achieved the normalized recall (Rn) equal to 0.84. Experiments show that the non-symmetrical zoning could be considered as a tool to build more reliable trademark retrieval systems.

Keywords: CBIR, Gestalt, matching, non-symmetrical zoning, SIFT

Procedia PDF Downloads 313

Authors: Preeti Yadav, Dandeswar Bisoyi, Debkumar Chakrabati

Abstract:

For many years organization have been exercising a creative technique of applying brand mascots, which results in making a visual ‘ambassador’ of a brand. The goal of mascot’s is just not confined to strengthening the brand identity, improving customer perception, but also acting as a vehicle of anthropomorphic translation towards the consumer. Such that it helps in embracing the power of recognition and processing the experiences happening in our daily lives. The study examines the relationship between the specific mascot features and brand attitude. It eliminates that mascot trust is an important mediator of the mascot features on brand attitude. Anthropomorphic characters turn out to be the key players despite the application of brand mascots in today’s marketing.

Keywords: advertising, mascot, branding, recall

Procedia PDF Downloads 334