A Tabletop Interface Using Fingernail Images and Real Object Recognition

Many researches and developments of table-top interface have been proposed in the last decade. In a table-top system, the difference of operations between the digital media and the physical media like a paper gives us unsatisfactory experience and disturbs a comfortable simultaneous using of them. It is required for user satisfaction that the user can operate the digital and physical media seamlessly. In this paper, we propose a table-top interface system that allows users to operate digital media intuitively by using gesture recognition. The proposed table can capture an image of the object on the table by press gesture recognition from users' nail images based on SVM, and can acquire a digital content from a digital paper reader by shake gesture of the device. The evaluation experiments show that the proposed system recognizes users' finger state with higher accuracy and the users can intuitively operate the table without awareness of the data transmission.

Cultural tourism is one category that attracts local and foreign tourists. Various previous studies have shown that digital marketing communication media plays an essential role in influencing tourist interest in visiting tourist destinations. This study aims to analyze the implementation of digital marketing communication strategies in marketing cultural tourism with a case study of cultural tourism destinations in Yogyakarta. This study uses a case study method with indepth interviews and field observations as data collection methods. The collected data were analyzed using thematic analysis and SWOT analysis. The results showed that managers of cultural tourism destinations optimize social media such as Facebook and Instagram for promotion. Whatsapp and email are also used for more personal communication with customers. The company's systematic digital marketing communications planning system supports solid work teams and produces original content. In addition, the extensive national and international marketing network and stable institutional position, because it is a stateowned company, are the advantages of this company. The increasing public interest at home and abroad for travel, the reduced Covid-19 pandemic, and the availability of various digital promotional media are opportunities for this company. However, the technical competence of staff in managing digital marketing media still needs to be improved. In addition, the digital content production and distribution scheduling system has not been implemented strictly and consistently. The quantity and quality of digital media content are also still limited. In addition, this cultural tourism object has several external challenges, such as the emergence of various new tourist objects in Yogyakarta, which are more aggressively promoted through digital media, and the possibility of a re-emergence of the Covid-19 pandemic or other natural disasters. This paper contributes to the literature on digital marketing communications by focusing on its implementation in the context of cultural tourism.

During the past decade there has been a significant increase in children’s access to the internet and digital devices, such as computers and touch-screen devices. Literature concerning the digital media usage of Dual Language Learners (DLLs) and their English language development is limited, but the number of DLLs in the U.S. is increasing rapidly. The purpose of this study is to examine DLLs’ digital media (frequency & content) usage and its impact on their receptive and expressive English language development in kindergarten. It also examines how factors, such as family digital media rules and DLLs’ pre-K care arrangements may moderate their digital media’s effect on English language development. This study used a sample of 7,432 Dual Language Learners in kindergartens across the U.S. This sample was extracted from a secondary dataset, the Early Childhood Longitudinal Study, Kindergarten Class of 2010-11 (ECLS-K:2011). The study employed descriptive statistics, mean differences analyses, correlations, and regression analyses (using coefficients) to examine the study questions and hypotheses. Results showed that DLLs’ expressive and receptive language development varied based on their computer use frequency. DLLs’ expressive and receptive English language development increased as their TV viewing frequency decreased. However, it did not vary based on the digital media content they consumed. Family digital media rules had no moderating effect on DLLs’ language development, but their pre-K care arrangements did moderate the impact of TV viewing frequency on their receptive and expressive language development. Pre-K care arrangements also moderated the impact of DLLs’ recreational digital media use on their receptive language development, but not on their expressive language development. These findings contribute to the limited literature on DLLs’ digital media use in relation to their language development. Results can be used by pediatricians to recommend the best use of digital media. Parents may also find this information helpful in deciding how often and how their children should use digital media. Early childhood educators and policymakers can also use these findings to advocate for the importance of preschool attendance and its impact on young DLLs’ language development.

In the context of current animation design and production, computer artwork and the creation of digital entertainment technology may demonstrate a natural affinity between 3D art material and cartoon design and production; as a result, digital media technology is offered as an innovative design idea and technique, maximizing the production efficiency of basic needs. pictures from modern multimedia technology. The Times' progress requires cartoon design and production reform and innovation. Digital media in animated design and production promotes industry growth. Animation seeks light and shadow. Based on an examination of digital media properties, the system architecture and module functions are built. Animation design system framework is built on the scalability and effectiveness of digital media platforms. Digital content technology is ingeniously employed, and 3D animation style and modeling environment technology are merged to boost animation's intellectual information and level. The system's test shows that it runs properly and steadily. Digital modern media technology is integrated into cartoon creation and production to encourage digital development.

A Stanford University research group explores how design alternatives for tabletop interfaces can impact group dynamics to promote effective teamwork. They built and evaluated a series of novel prototypes that explore Multi-User Coordination Policies and cooperative gesturing, encouraging equitable participation in educational tasks and supporting social skills development for special-needs populations.

Co-located collaborative Web browsing is a relatively common task and yet is poorly supported by conventional tools. Prior research in this area has focused on adapting conventional browsing interfaces to add collaboration support. We propose an alternative approach, drawing on ideas from tabletop interfaces. We present WebSurface, a novel tabletop interface for collaborative Web browsing. WebSurface explores two design challenges of this approach: providing sufficient resolution for legible text; and navigating through information. We report our early experiences with an exploratory user study, in which pairs of collaborators gathered information using WebSurface. The findings suggest that a tabletop approach for collaborative Web browsing can help address limitations of conventional tools, and presents beneficial affordances for information layout.

The last decade has witnessed the development and uprising of social media web services. The use of these shared online media as a source of huge amount of data for research purposes is still a challenging problem. In this paper, a novel framework is proposed to collect training samples from online media data to model the visual appearance of social events automatically. The visual training samples are collected through the analysis of the spatial and temporal context of media data and events. While collecting positive samples can be achieved easily thanks to dedicated event machine-tags, finding the most representative negative samples from the vast amount of irrelevant multimedia documents is a more challenging task. Here, we argue and demonstrate that the most common negative samples, originating from the same location as the event to be modeled, are best suited for the task. A novel ranking approach is devised to automatically select a set of negative samples. Finally the automatically collected samples are used to learn visual event models using Support Vector Machine (SVM). The resulting event models are effective to filter out irrelevant photos and perform with a high accuracy as demonstrated on various social events originating for various categories of events.

Gesture recognition is a topic in computer science and language technology that aims to interpret human gestures with computer programs and many different algorithms. It can be seen as the way computers can understand human body language. Today, the main interaction tools between computers and humans are still the keyboard and mouse. Gesture recognition can be used as a tool for communication with the machine and interaction without any mechanical device such as a keyboard or mouse. In this paper, we present the results of a comparison of eight different machine learning (ML) classifiers in the task of human hand gesture recognition and classification to explore how to efficiently implement one or more tested ML algorithms on an 8-bit AVR microcontroller for on-line human gesture recognition with the intention to gesturally control the mobile robot. The 8-bit AVR microcontrollers are still widely used in the industry, but due to their lack of computational power and limited memory, it is a challenging task to efficiently implement ML algorithms on them for on-line classification. Gestures were recorded by using inertial sensors, gyroscopes, and accelerometers placed at the wrist and index finger. One thousand and eight hundred (1800) hand gestures were recorded and labelled. Six important features were defined for the identification of nine different hand gestures using eight different machine learning classifiers: Decision Tree (DT), Random Forests (RF), Logistic Regression (LR), Linear Discriminant Analysis (LDA), Support Vector Machine (SVM) with linear kernel, Naïve Bayes classifier (NB), K-Nearest Neighbours (KNN), and Stochastic Gradient Descent (SGD). All tested algorithms were ranged according to Precision, Recall, and F1-score (abb.: P-R-F1). The best algorithms were SVM (P-R-F1: 0.9865, 0.9861, and 0.0863), and RF (P-R-F1: 0.9863, 0.9861, and 0.0862), but their main disadvantage is their unusability for on-line implementations in 8-bit AVR microcontrollers, as proven in the paper. The next best algorithms have had only slightly poorer performance than SVM and RF: KNN (P-R-F1: 0.9835, 0.9833, and 0.9834) and LR (P-R-F1: 0.9810, 0.9810, and 0.9810). Regarding the implementation on 8-bit microcontrollers, KNN has proven to be inadequate, like SVM and RF. However, the analysis for LR has proved that this classifier could be efficiently implemented on targeted microcontrollers. Having in mind its high F1-score (comparable to SVM, RF, and KNN), this leads to the conclusion that the LR is the most suitable classifier among tested for on-line applications in resource-constrained environments, such as embedded devices based on 8-bit AVR microcontrollers, due to its lower computational complexity in comparison with other tested algorithms.

Social media is an online media that users use to interact with each other by expressing themselves by giving comments, and one example is Instagram. All the collected comments will form a public opinion. This opinion can be used with sentiment analysis to become information. The method commonly used to carry out sentiment analysis is classification using machine learning. One of the machine learning that is often used is the Support Vector Machine (SVM). However, on non-linear problems such as sentiment analysis, SVM requires the kernel to map vectors into high-dimensional spaces to solve non-linear problems. The problem faced in using the kernel is to choose the optimal parameters for the classification model to produce a good classification model. This study proposes a new approach to obtain optimal parameters for SVM using Genetic Algorithm (GA). This study designed an SVM-GA classification model from the data collection, processing, classification, and evaluation stages. The results showed that the best accuracy produced with parameters optimized with the genetic algorithm was 81.6%, or an increase of 2.4% from the SVM sentiment analysis method without GA optimization.

The development of technology in modern times makes it easier for people to obtain information, especially online media, one of which is Y ouTube. Y ouTube has attracted many users all over the world. With several features such as like, subscribe and comment. By analyzing the comments given by the public to videos on Y ouTube, it is hoped that the results of the analysis of these comments can become reference material for Y outubers when making videos to be uploaded on Y ouTube. To find out the nature of every comment that the public gives to videos on Y ouTube, analysis is needed to assess the nature of these comments, positive or negative. To analyze these comments, the authors classify comments using the Support Vector Machine (SVM) algorithm. While the method, the gain ratio is used by the author for the feature selection process stage to help the performance of the Support Vector Machine (SVM) algorithm where the features used are from 100% features to 5% features so that they get different Accuracy, Precision, Recall values. From the results of research conducted by the author, the best precision results are at 50% features, while for accuracy and recall are at 5% features.

The amount of unuseful contents, such as hoaxes or false news, and non-educational content bring negative impact to the society, especially to the students. People who were influenced by hoaxes and non-educational digital content from the news and various digital contents, responded by writing negative comments on digital media. By utilizing digital literacy, it will contribute positive conduct in responding various digital content, for example being educated with positive content and contributing to the society by creating qualify digital content. Because of this reason, a digital content model contains social science education is needed as a media literacy to educate students and to digital society in general. High quality of digital content has certain standards so that it will bring positive influence when it is distributed in digital media. Digital contents are not just the process of digitizing traditional content into digital media. Furthe more, various parameters of digital content, such as: Search Engine Optimization, writing mechanism, knowledge, social studies competency, digital media and digital copyright are part of the fundamental elements of qualify digital content models, which is built using transdisciplinary knowledge.

Hand gesture recognition is a relevant study topic for a reason that sometimes we may not be in position to communicate verbally. There is need to design Hand gesture recognition systems in order to help people adopt to nonverbal communication mainly sign language. However, there is no clue to understand the meaning of gesture through the computers directly. So this calls for definitions that generalize models in a computer. That is why the machine-learning approaches are implemented in recognition systems. There are generally two types of hand gestures recognition systems which researches have concentrated on. These include static and dynamic Hand gesture recognition systems. However, in building Hand gesture recognition systems, various machine learning approaches have been used. For implementing the proposed system, MS Kinect depth sensor was used as a hardware. The Kinect depth sensor is composed of an infrared camera. This is an advantage to the systems that are designed basing on the depth sensing because factors like color, clothing and background have less effect on the performance. So Kinect based depth sensor systems have a high accuracy and performance making them relevant and applicable in our daily lives. In this paper, we propose a static hand gesture recognition system in real time using two machine learning methods namely Support Vector Machine and Artificial Neural Networks. We use of the newly launched Microsoft Kinect sensor for image extraction. The sensor helps us to extract the hand images. We implement the system on a Matlab platform for reasons that Matlab is widely used by researchers in different fields and that can handle complex computations. In the training of the model, we collect a hundred depth-based Histogram of Oriented Gradient features per alphabet from the hand gesture images which we trained, tested and validated using Artificial Neural Networks (ANN) and Support Vector Machine (SVM). From this dataset, we can generate the generalized gesture model for each alphabet image. For the proposed system, the classification with ANN proves a higher performance then SVM.

Bond rating is regarded as an important event for measuring financial risk of companies and for determining the investment returns of investors. As a result, it has been a popular research topic for researchers to predict companies' credit ratings by applying statistical and machine learning techniques. The statistical techniques, including multiple regression, multiple discriminant analysis (MDA), logistic models (LOGIT), and probit analysis, have been traditionally used in bond rating. However, one major drawback is that it should be based on strict assumptions. Such strict assumptions include linearity, normality, independence among predictor variables and pre-existing functional forms relating the criterion variablesand the predictor variables. Those strict assumptions of traditional statistics have limited their application to the real world. Machine learning techniques also used in bond rating prediction models include decision trees (DT), neural networks (NN), and Support Vector Machine (SVM). Especially, SVM is recognized as a new and promising classification and regression analysis method. SVM learns a separating hyperplane that can maximize the margin between two categories. SVM is simple enough to be analyzed mathematical, and leads to high performance in practical applications. SVM implements the structuralrisk minimization principle and searches to minimize an upper bound of the generalization error. In addition, the solution of SVM may be a global optimum and thus, overfitting is unlikely to occur with SVM. In addition, SVM does not require too many data sample for training since it builds prediction models by only using some representative sample near the boundaries called support vectors. A number of experimental researches have indicated that SVM has been successfully applied in a variety of pattern recognition fields. However, there are three major drawbacks that can be potential causes for degrading SVM's performance. First, SVM is originally proposed for solving binary-class classification problems. Methods for combining SVMs for multi-class classification such as One-Against-One, One-Against-All have been proposed, but they do not improve the performance in multi-class classification problem as much as SVM for binary-class classification. Second, approximation algorithms (e.g. decomposition methods, sequential minimal optimization algorithm) could be used for effective multi-class computation to reduce computation time, but it could deteriorate classification performance. Third, the difficulty in multi-class prediction problems is in data imbalance problem that can occur when the number of instances in one class greatly outnumbers the number of instances in the other class. Such data sets often cause a default classifier to be built due to skewed boundary and thus the reduction in the classification accuracy of such a classifier. SVM ensemble learning is one of machine learning methods to cope with the above drawbacks. Ensemble learning is a method for improving the performance of classification and prediction algorithms. AdaBoost is one of the widely used ensemble learning techniques. It constructs a composite classifier by sequentially training classifiers while increasing weight on the misclassified observations through iterations. The observations that are incorrectly predicted by previous classifiers are chosen more often than examples that are correctly predicted. Thus Boosting attempts to produce new classifiers that are better able to predict examples for which the current ensemble's performance is poor. In this way, it can reinforce the training of the misclassified observations of the minority class. This paper proposes a multiclass Geometric Mean-based Boosting (MGM-Boost) to resolve multiclass prediction problem. Since MGM-Boost introduces the notion of geometric mean into AdaBoost, it can perform learning process considering the geometric mean-based accuracy and errors of multiclass. This study applies MGM-Boost to the real-world bond rating case for Korean companies to examine the feasibility of MGM-Boost. 10-fold cross validations for threetimes with different random seeds are performed in order to ensure that the comparison among three different classifiers does not happen by chance. For each of 10-fold cross validation, the entire data set is first partitioned into tenequal-sized sets, and then each set is in turn used as the test set while the classifier trains on the other nine sets. That is, cross-validated folds have been tested independently of each algorithm. Through these steps, we have obtained the results for classifiers on each of the 30 experiments. In the comparison of arithmetic mean-based prediction accuracy between individual classifiers, MGM-Boost (52.95%) shows higher prediction accuracy than both AdaBoost (51.69%) and SVM (49.47%). MGM-Boost (28.12%) also shows the higher prediction accuracy than AdaBoost (24.65%) and SVM (15.42%)in terms of geometric mean-based prediction accuracy. T-test is used to examine whether the performance of each classifiers for 30 folds is significantly different. The results indicate that performance of MGM-Boost is significantly different from AdaBoost and SVM classifiers at 1% level. These results mean that MGM-Boost can provide robust and stable solutions to multi-classproblems such as bond rating.

BackgroundMonitoring linguistic cues from adolescents’ digital media use (DMU; ie, digital content transmitted on the web, such as through text messages or social media) that could denote suicidal risk offers a unique opportunity to protect adolescents vulnerable to suicide, the second leading cause of death among youth. Adolescents communicate through digital media in high volumes and frequently express emotionality. In fact, web-based disclosures of suicidality are more common than in-person disclosures. The use of automated methods of digital media monitoring triggered by a natural language processing algorithm offers the potential to detect suicidal risk from subtle linguistic units (eg, negatively valanced words, phrases, or emoticons known to be associated with suicidality) present within adolescents’ digital media content and to use this information to respond to alerts of suicidal risk. Critical to the implementation of such an approach is the consideration of its acceptability in the clinical care of adolescents at high risk of suicide.ObjectiveThrough data collection among recently suicidal adolescents, parents, and clinicians, this study examines the current context of digital media monitoring for suicidal adolescents seeking clinical care to inform the need for automated monitoring and the factors that influence the acceptance of automated monitoring of suicidal adolescents’ DMU within clinical care.MethodsA total of 15 recently suicidal adolescents (aged 13-17 years), 12 parents, and 10 clinicians participated in focus groups, qualitative interviews, and a group discussion, respectively. Data were recorded, transcribed, and analyzed using thematic analysis.ResultsParticipants described important challenges to the current strategies for monitoring the DMU of suicidal youth. They felt that automated monitoring would have advantages over current monitoring approaches, namely, by protecting web-based environments and aiding adolescent disclosure and support seeking about web-based suicidal risk communication, which may otherwise go unnoticed. However, they identified barriers that could impede implementation within clinical care, namely, adolescents’ and parents’ concerns about unintended consequences of automated monitoring, that is, the potential for loss of privacy or false alerts, and clinicians’ concerns about liability to respond to alerts of suicidal risk. On the basis of the needs and preferences of adolescents, parents, and clinicians, a model for automated digital media monitoring is presented that aims to optimize acceptability within clinical care for suicidal youth.ConclusionsAutomated digital media monitoring offers a promising means to augment detection and response to suicidal risk within the clinical care of suicidal youth when strategies that address the preferences of adolescents, parents, and clinicians are in place.

Menarche in teenage girls may increase their risk of anemia relative to boys in the same age category. This research was carried out to explore how educational media affects adolescent girls' perceptions and motivation concerning the use of iron-supplement tablets. The study used a quasi-experimental design, implementing a one-group pretest and post-test method without a control group. Sample selection was conducted via purposive sampling, and data collection utilized questionnaires aimed at evaluating adolescent girls' perceptions and motivations. After the preliminary pretest, an intervention was implemented that featured printed standing banners and digital content, such as videos and digital scrapbooks. Data analysis included employing the paired t-test to detect any variations in perception and motivation prior to and following the media intervention. The outcomes of the statistical analyses showed a notable shift in perception and motivation after exposure to printed standing banner media (p < 0.05). Nevertheless, no notable changes were detected following the interventions of digital video and digital scrapbook media (p ≥ 0.05). The research finds that printed media significantly influences adolescent girls' views and motivation to take iron-supplement tablets more than digital media does.