Search results for: STS benchmark dataset

Authors: Prajamitra Bhuyan

Abstract:

Transport operators have a range of intervention options available to improve or enhance their networks. But often such interventions are made in the absence of sound evidence on what outcomes may result. Cycling superhighways were promoted as a sustainable and healthy travel mode which aims to cut traffic congestion. The estimation of the impacts of the cycle superhighways on congestion is complicated due to the non-random assignment of such intervention over the transport network. In this paper, we analyse the causal effect of cycle superhighways utilising pre-innervation and post-intervention information on traffic and road characteristics along with socio-economic factors. We propose a modeling framework based on the propensity score and outcome regression model. The method is also extended to doubly robust set-up. Simulation results show the superiority of the performance of the proposed method over existing competitors. The method is applied to analyse a real dataset on the London transport network, and the result would help effective decision making to improve network performance.

Keywords: average treatment effect, confounder, difference-in-difference, intelligent transportation system, potential outcome

Procedia PDF Downloads 242

Authors: Angely Sim Jia Wun, Sasa Arsovski

Abstract:

Numerous studies have been conducted on the segmentation of medical images. Segmenting the lungs is one of the common research topics in those studies. Our research stemmed from the lack of solutions for automatic bone, airway, and vessel segmentation, despite the existence of multiple lung segmentation techniques. Consequently, currently, available software tools used for medical image segmentation do not provide automatic lung, bone, airway, and vessel segmentation. This paper presents segmentation techniques along with an interactive software tool architecture for segmenting bone, lung, airway, and vessel tissues. Additionally, we propose a method for creating binary masks from automatically generated segments. The key contribution of our approach is the technique for automatic image thresholding using adjustable Hounsfield values and binary mask extraction. Generated binary masks can be successfully used as a training dataset for deep-learning solutions in medical image segmentation. In this paper, we also examine the current software tools used for medical image segmentation, discuss our approach, and identify its advantages.

Keywords: lung segmentation, binary masks, U-Net, medical software tools

Procedia PDF Downloads 98

Authors: Abe D. Desta

Abstract:

This study suggests a deep learning-based method for identifying and following moving objects in surveillance video. The proposed method uses a fast regional convolution neural network (F-RCNN) trained on a substantial dataset of vehicle images to first detect vehicles. A Kalman filter and a data association technique based on a Hungarian algorithm are then used to monitor the observed vehicles throughout time. However, in general, F-RCNN algorithms have been shown to be effective in achieving high detection accuracy and robustness in this research study. For example, in one study The study has shown that the vehicle detection and tracking, the system was able to achieve an accuracy of 97.4%. In this study, the F-RCNN algorithm was compared to other popular object detection algorithms and was found to outperform them in terms of both detection accuracy and speed. The presented system, which has application potential in actual surveillance systems, shows the usefulness of deep learning approaches in vehicle detection and tracking.

Keywords: artificial intelligence, computer vision, deep learning, fast-regional convolutional neural networks, feature extraction, vehicle tracking

Procedia PDF Downloads 129

Authors: Umair Rashid

Abstract:

Normally softmax loss is used as the supervision signal in face recognition (FR) system, and it boosts the separability of features. In the last two years, a number of techniques have been proposed by reformulating the original softmax loss to enhance the discriminating power of Deep Convolutional Neural Networks (DCNNs) for FR system. To learn angularly discriminative features Cosine-Margin based softmax has been adjusted as monotonically decreasing angular function, that is the main challenge for angular based softmax. On that issue, we propose monotonically decreasing element for Cosine-Margin based softmax and also, we discussed the effect of different monotonically decreasing parameters on angular Margin softmax for FR system. We train the model on publicly available dataset CASIA- WebFace via our proposed monotonically decreasing parameters for cosine function and the tests on YouTube Faces (YTF, Labeled Face in the Wild (LFW), VGGFace1 and VGGFace2 attain the state-of-the-art performance.

Keywords: deep convolutional neural networks, cosine margin face recognition, softmax loss, monotonically decreasing parameter

Procedia PDF Downloads 102

Authors: Bin Ji, Kai Xu, Shunyu Yao, Jingjing Liu, Ye Pan

Abstract:

Human pose estimation is a popular research area in computer vision for its important application in human-machine interface. In recent years, 2D human pose estimation based on convolution neural network has got great progress and development. However, in more and more practical applications, people often need to deal with tasks based on video. It’s not far-fetched for us to consider how to combine the spatial and temporal information together to achieve a balance between computing cost and accuracy. To address this issue, this study proposes a new spatiotemporal model, namely Spatiotemporal Net (STNet) to combine both temporal and spatial information more rationally. As a result, the predicted keypoints heatmap is potentially more accurate and spatially more precise. Under the condition of ensuring the recognition accuracy, the algorithm deal with spatiotemporal series in a decoupled way, which greatly reduces the computation of the model, thus reducing the resource consumption. This study demonstrate the effectiveness of our network over the Penn Action Dataset, and the results indicate superior performance of our network over the existing methods.

Keywords: convolutional long short-term memory, deep learning, human pose estimation, spatiotemporal series

Procedia PDF Downloads 150

Authors: Laurie Dempsey

Abstract:

Relationships are considered to be beneficial for emotional wellbeing, happiness and physical health. However, they are also complicated: individuals engage in a multitude of complex and volatile relationships during their lifetime, where the change to or ending of these dynamics can be deeply disruptive. As the internet is further integrated into everyday life and relationships are increasingly mediated, Media Studies’ and Sociology’s research interests intersect and converge. This study longitudinally explores how relationship change over time corresponds with the developing UK technological landscape between 2005-2018. Since the early 2000s, the use of computer-mediated communication (CMC) in the UK has dramatically reshaped interaction. Its use has compelled individuals to renegotiate how they consider their relationships: some argue it has allowed for vast networks to be accumulated and strengthened; others contend that it has eradicated the core values and norms associated with communication, damaging relationships. This research collaborated with UK media regulator Ofcom, utilising the longitudinal dataset from their Adult Media Lives study to explore how relationships and CMC use developed over time. This is a unique qualitative dataset covering 2005-2018, where the same 18 participants partook in annual in-home filmed depth interviews. The interviews’ raw video footage was examined year-on-year to consider how the same people changed their reported behaviour and outlooks towards their relationships, and how this coincided with CMC featuring more prominently in their everyday lives. Each interview was transcribed, thematically analysed and coded using NVivo 11 software. This study allowed for a comprehensive exploration into these individuals’ changing relationships over time, as participants grew older, experienced marriages or divorces, conceived and raised children, or lost loved ones. It found that as technology developed between 2005-2018, everyday CMC use was increasingly normalised and incorporated into relationship maintenance. It played a crucial role in altering relationship dynamics, even factoring in the breakdown of several ties. Three key relationships were identified as being shaped by CMC use: parent-child; extended family; and friendships. Over the years there were substantial instances of relationship conflict: for parents renegotiating their dynamic with their child as they tried to both restrict and encourage their child’s technology use; for estranged family members ‘forced’ together in the online sphere; and for friendships compelled to publicly display their relationship on social media, for fear of social exclusion. However, it was also evident that CMC acted as a crucial lifeline for these participants, providing opportunities to strengthen and maintain their bonds via previously unachievable means, both over time and distance. A longitudinal study of this length and nature utilising the same participants does not currently exist, thus provides crucial insight into how and why relationship dynamics alter over time. This unique and topical piece of research draws together Sociology and Media Studies, illustrating how the UK’s changing technological landscape can reshape one of the most basic human compulsions. This collaboration with Ofcom allows for insight that can be utilised in both academia and policymaking alike, making this research relevant and impactful across a range of academic fields and industries.

Keywords: computer mediated communication, longitudinal research, personal relationships, qualitative data

Procedia PDF Downloads 123

Authors: Shweta Pinjarkar, Shrutika Yawale, Mayuri Patil, Reshma Adagale

Abstract:

Face recognition is the technique which can be applied to the wide variety of problems like image and film processing, human computer interaction, criminal identification etc. This has motivated researchers to develop computational models to identify the faces, which are easy and simple to implement. In this, demonstrates the face recognition system in android device using eigenface. The system can be used as the base for the development of the recognition of human identity. Test images and training images are taken directly with the camera in android device.The test results showed that the system produces high accuracy. The goal is to implement model for particular face and distinguish it with large number of stored faces. face recognition system detects the faces in picture taken by web camera or digital camera and these images then checked with training images dataset based on descriptive features. Further this algorithm can be extended to recognize the facial expressions of a person.recognition could be carried out under widely varying conditions like frontal view,scaled frontal view subjects with spectacles. The algorithm models the real time varying lightning conditions. The implemented system is able to perform real-time face detection, face recognition and can give feedback giving a window with the subject's info from database and sending an e-mail notification to interested institutions using android application. Face recognition is the technique which can be applied to the wide variety of problems like image and film processing, human computer interaction, criminal identification etc. This has motivated researchers to develop computational models to identify the faces, which are easy and simple to implement. In this , demonstrates the face recognition system in android device using eigenface. The system can be used as the base for the development of the recognition of human identity. Test images and training images are taken directly with the camera in android device.The test results showed that the system produces high accuracy. The goal is to implement model for particular face and distinguish it with large number of stored faces. face recognition system detects the faces in picture taken by web camera or digital camera and these images then checked with training images dataset based on descriptive features. Further this algorithm can be extended to recognize the facial expressions of a person.recognition could be carried out under widely varying conditions like frontal view,scaled frontal view subjects with spectacles. The algorithm models the real time varying lightning conditions. The implemented system is able to perform real-time face detection, face recognition and can give feedback giving a window with the subject's info from database and sending an e-mail notification to interested institutions using android application.

Keywords: face detection, face recognition, eigen faces, algorithm

Procedia PDF Downloads 361

Authors: Sajjad Ahmed, Knut Hinkelmann, Flavio Corradini

Abstract:

Fake news detection research is still in the early stage as this is a relatively new phenomenon in the interest raised by society. Machine learning helps to solve complex problems and to build AI systems nowadays and especially in those cases where we have tacit knowledge or the knowledge that is not known. We used machine learning algorithms and for identification of fake news; we applied three classifiers; Passive Aggressive, Naïve Bayes, and Support Vector Machine. Simple classification is not completely correct in fake news detection because classification methods are not specialized for fake news. With the integration of machine learning and text-based processing, we can detect fake news and build classifiers that can classify the news data. Text classification mainly focuses on extracting various features of text and after that incorporating those features into classification. The big challenge in this area is the lack of an efficient way to differentiate between fake and non-fake due to the unavailability of corpora. We applied three different machine learning classifiers on two publicly available datasets. Experimental analysis based on the existing dataset indicates a very encouraging and improved performance.

Keywords: fake news detection, natural language processing, machine learning, classification techniques.

Procedia PDF Downloads 168

Authors: Monica Racha, Siva Chandrasekaran, Alex Stojcevski

Abstract:

The engineering programs focus on promoting students' personal and professional development by ensuring that students acquire technical and professional competencies during four-year studies. The traditional engineering laboratory provides an opportunity for students to "practice by doing," and laboratory facilities aid them in obtaining insight and understanding of their discipline. Due to rapid technological advancements and the current COVID-19 outbreak, the traditional labs were transforming into virtual learning environments. Aim: To better understand the limitations of the physical laboratory, this research study aims to use a Machine Learning (ML) algorithm that interfaces with the Augmented Reality HoloLens and predicts the image behavior to classify and detect the electronic components. The automated electronic components error classification and detection automatically detect and classify the position of all components on a breadboard by using the ML algorithm. This research will assist first-year undergraduate engineering students in conducting laboratory practices without any supervision. With the help of HoloLens, and ML algorithm, students will reduce component placement error on a breadboard and increase the efficiency of simple laboratory practices virtually. Method: The images of breadboards, resistors, capacitors, transistors, and other electrical components will be collected using HoloLens 2 and stored in a database. The collected image dataset will then be used for training a machine learning model. The raw images will be cleaned, processed, and labeled to facilitate further analysis of components error classification and detection. For instance, when students conduct laboratory experiments, the HoloLens captures images of students placing different components on a breadboard. The images are forwarded to the server for detection in the background. A hybrid Convolutional Neural Networks (CNNs) and Support Vector Machines (SVMs) algorithm will be used to train the dataset for object recognition and classification. The convolution layer extracts image features, which are then classified using Support Vector Machine (SVM). By adequately labeling the training data and classifying, the model will predict, categorize, and assess students in placing components correctly. As a result, the data acquired through HoloLens includes images of students assembling electronic components. It constantly checks to see if students appropriately position components in the breadboard and connect the components to function. When students misplace any components, the HoloLens predicts the error before the user places the components in the incorrect proportion and fosters students to correct their mistakes. This hybrid Convolutional Neural Networks (CNNs) and Support Vector Machines (SVMs) algorithm automating electronic component error classification and detection approach eliminates component connection problems and minimizes the risk of component damage. Conclusion: These augmented reality smart glasses powered by machine learning provide a wide range of benefits to supervisors, professionals, and students. It helps customize the learning experience, which is particularly beneficial in large classes with limited time. It determines the accuracy with which machine learning algorithms can forecast whether students are making the correct decisions and completing their laboratory tasks.

Keywords: augmented reality, machine learning, object recognition, virtual laboratories

Procedia PDF Downloads 137

Authors: Tzong-Ying Hao, Mohammad T. Rahmani

Abstract:

The Torre Central building is a 9-story shear wall structure located in Santiago, Chile, and has been instrumented since 2009. Events of different intensity (ambient vibrations, weak and strong earthquake motions) have been recorded, and thus the building can serve as a full-scale benchmark to evaluate the structural health monitoring method developed. The first part of this article presents an analysis of inter-story drifts, and of changes in the first system frequencies (estimated from the relative displacement response of the 8th-floor with respect to the basement from recorded data) as baseline indicators of the occurrence of damage. During 2010 Chile earthquake the system frequencies were detected decreasing approximately 24% in the EW and 27% in NS motions. Near the end of shaking, an increase of about 17% in the EW motion was detected. The structural health monitoring (SHM) method based on changes in wave traveling time (wave method) within a layered shear beam model of structure is presented in the second part of this article. If structural damage occurs the velocity of wave propagated through the structure changes. The wave method measures the velocities of shear wave propagation from the impulse responses generated by recorded data at various locations inside the building. Our analysis and results show that the detected changes in wave velocities are consistent with the observed damages. On this basis, the wave method is proven for actual implementation in structural health monitoring systems.

Keywords: Chile earthquake, damage detection, earthquake response, impulse response, layered shear beam, structural health monitoring, Torre Central building, wave method, wave travel time

Procedia PDF Downloads 364

Authors: Xinyuan Liu, Xiaojun Jing, Yuan He, Junsheng Mu

Abstract:

Aspect-based Sentiment Analysis (ABSA) has attracted much attention due to its capacity to determine the sentiment polarity of the certain aspect in a sentence. In previous works, great significance of the interaction between aspect and sentence has been exhibited in ABSA. In consequence, a Multi-Level Attentional Networks (MLAN) is proposed. MLAN consists of four parts: Embedding Layer, Encoding Layer, Multi-Level Attentional (MLA) Layers and Final Prediction Layer. Among these parts, MLA Layers including Aspect Level Attentional (ALA) Layer and Interactive Attentional (ILA) Layer is the innovation of MLAN, whose function is to focus on the important information and obtain multiple levels’ attentional weighted representation of aspect and sentence. In the experiments, MLAN is compared with classical TD-LSTM, MemNet, RAM, ATAE-LSTM, IAN, AOA, LCR-Rot and AEN-GloVe on SemEval 2014 Dataset. The experimental results show that MLAN outperforms those state-of-the-art models greatly. And in case study, the works of ALA Layer and ILA Layer have been proven to be effective and interpretable.

Keywords: deep learning, aspect-based sentiment analysis, attention, natural language processing

Procedia PDF Downloads 139

Authors: Sarthak Deshpande, Akshay Patil, Pradip Pandhare, Nikhil Wankhede, Rushali Deshmukh

Abstract:

Among the highly significant duties for any language most effective is the sentiment analysis, which is also a key area of NLP, that recently made impressive strides. There are several models and datasets available for those tasks in popular and commonly used languages like English, Russian, and Spanish. While sentiment analysis research is performed extensively, however it is lagging behind for the regional languages having few resources such as Hindi, Marathi. Marathi is one of the languages that included in the Indian Constitution’s 8th schedule and is the third most widely spoken language in the country and primarily spoken in the Deccan region, which encompasses Maharashtra and Goa. There isn’t sufficient study on sentiment analysis methods based on Marathi text due to lack of available resources, information. Therefore, this project proposes the use of different ML/NLP models for the analysis of Marathi data from the comments below YouTube content, tweets or Instagram posts. We aim to achieve a short and precise analysis and summary of the related data using our dataset (Dates, names, root words) and lexicons to locate exact information.

Keywords: multilingual sentiment analysis, Marathi, natural language processing, text summarization, lexicon-based approaches

Procedia PDF Downloads 76

Authors: Yassine Bouzouita, Oumaima Belghith, Cyrine Zitoun, Charles Bonneau

Abstract:

Performance measurement framework (PMF) is an essential tool in any organization to assess the performance of its processes. It guides businesses to stay on track with their objectives and benchmark themselves from the market. With the growing trend of the digital transformation of business processes, led by innovations in artificial intelligence (AI) & Big Data applications, developing a mature system capable of capturing the impact of digital solutions across different industries became a necessity. Based on the conducted research, no such system has been developed in academia nor the industry. In this context, this paper covers a variety of methodologies on performance measurement, overviews the major AI and big data applications in the banking sector, and covers an exhaustive list of relevant metrics. Consequently, this paper is of interest to both researchers and practitioners. From an academic perspective, it offers a comparative analysis of the reviewed performance measurement frameworks. From an industry perspective, it offers exhaustive research, from market leaders, of the major applications of AI and Big Data technologies, across the different departments of an organization. Moreover, it suggests a standardized classification model with a well-defined structure of intelligent digital solutions. The aforementioned classification is mapped to a centralized library that contains an indexed collection of potential metrics for each application. This library is arranged in a manner that facilitates the rapid search and retrieval of relevant metrics. This proposed framework is meant to guide professionals in identifying the most appropriate AI and big data applications that should be adopted. Furthermore, it will help them meet their business objectives through understanding the potential impact of such solutions on the entire organization.

Keywords: AI and Big Data applications, impact assessment, metrics, performance measurement

Procedia PDF Downloads 198

Authors: Mst. Tuhin Akter, Sharun Akter Khushbu, S. M. Shaqib

Abstract:

A real-time system architecture is highly effective for monitoring and detecting various damaged products or fruits that may deteriorate over time or become infected with diseases. Deep learning models have proven to be effective in building such architectures. However, building a deep learning model from scratch is a time-consuming and costly process. A more efficient solution is to utilize deep neural network (DNN) based transfer learning models in the real-time monitoring architecture. This study focuses on using a novel strawberry dataset to develop effective transfer learning models for the proposed real-time monitoring system architecture, specifically for evaluating and detecting strawberry freshness. Several state-of-the-art transfer learning models were employed, and the best performing model was found to be Xception, demonstrating higher performance across evaluation metrics such as accuracy, recall, precision, and F1-score.

Keywords: strawberry freshness evaluation, deep neural network, transfer learning, image augmentation

Procedia PDF Downloads 91

Authors: Arif Sikander, Imran Saeed

Abstract:

The behavioral pattern and performance of airline pilots are influenced by the level of stress, their ethical decision-making ability and above all their leadership style as part of the Crew Management process. Cultural differences of pilots, especially while working in ex-country airlines, could influence the stress perception. Culture also influences ethical decision making. Leadership style is also a variable dimension, and pilots need to adapt to the cultural settings while flying with the local pilots as part of their team. Studies have found that age, education, gender, and management experience are statistically significant factors in ethical maturity. However, in the decades to come, more studies are required to validate the results over and over again; thereby, providing support for the validity of the Moral Development Theory. Leadership style plays a vital role in ethical decision making. This study is grounded in the Moral Development theory and seeks to analyze the styles of leadership of airline pilots related to ethical decision making and also the influence of the culture on their stress perception. The sample for the study included commercial pilots from a National Airline. It is expected that these results should provide useful input to the literature in the context of developing appropriate Talent Management strategies. The authors intend to extend this study (carried out in one country) to major national carriers (many countries) to be able to develop a ultimate framework on Talent Management which should serve as a benchmark for any international airline as most of them (e.g., Emirates, Etihad, Cathay Pacific, China Southern, etc.) are dependent on the supply of this scarce resource from outside countries.

Keywords: ethics, leadership, pilot, stress

Procedia PDF Downloads 145

Authors: Abhijith Asok

Abstract:

This paper presents a generalized approach for the simple linear data transformation, Y=bX, through an integration of multidimensional coordinate geometry, vector space theory and polygonal geometry. The scaling is performed by adding an additional ’Dummy Dimension’ to the n-dimensional data, which helps plot two dimensional component-wise straight lines on pairs of dimensions. The end result is a set of scaled extensions of observations in any of the 2n spatial divisions, where n is the total number of applicable dimensions/dataset variables, created by shifting the n-dimensional plane along the ’Dummy Axis’. The derived scaling factor was found to be dependent on the coordinates of the common point of origin for diverging straight lines and the plane of extension, chosen on and perpendicular to the ’Dummy Axis’, respectively. This result indicates the geometrical interpretation of a linear data transformation and hence, opportunities for a more informed choice of the factor ’b’, based on a better choice of these coordinate values. The paper follows on to identify the effect of this transformation on certain popular distance metrics, wherein for many, the distance metric retained the same scaling factor as that of the features.

Keywords: data transformation, dummy dimension, linear transformation, scaling

Procedia PDF Downloads 299

Authors: Kemal Polat

Abstract:

In this paper, three feature weighting methods have been used to improve the classification performance of diabetic retinopathy (DR). To classify the diabetic retinopathy, features extracted from the output of several retinal image processing algorithms, such as image-level, lesion-specific and anatomical components, have been used and fed them into the classifier algorithms. The dataset used in this study has been taken from University of California, Irvine (UCI) machine learning repository. Feature weighting methods including the fuzzy c-means clustering based feature weighting, subtractive clustering based feature weighting, and Gaussian mixture clustering based feature weighting, have been used and compered with each other in the classification of DR. After feature weighting, five different classifier algorithms comprising multi-layer perceptron (MLP), k- nearest neighbor (k-NN), decision tree, support vector machine (SVM), and Naïve Bayes have been used. The hybrid method based on combination of subtractive clustering based feature weighting and decision tree classifier has been obtained the classification accuracy of 100% in the screening of DR. These results have demonstrated that the proposed hybrid scheme is very promising in the medical data set classification.

Keywords: machine learning, data weighting, classification, data mining

Procedia PDF Downloads 327

Authors: Yishu Gong, Liangliang Yang, Jianyu Zhang, Zhengyu Chen, Sihong He, Xusheng Zhang, Wei Zhang

Abstract:

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder that affects millions of people worldwide and is characterized by cognitive decline and behavioral changes. People living with Alzheimer’s disease often find it hard to complete routine tasks. However, there are limited objective assessments that aim to quantify the difficulty of certain tasks for AD patients compared to non-AD people. In this study, we propose to use speech emotion recognition (SER), especially the frustration level, as a potential biomarker for quantifying the difficulty patients experience when describing a picture. We build an SER model using data from the IEMOCAP dataset and apply the model to the DementiaBank data to detect the AD/non-AD group difference and perform longitudinal analysis to track the AD disease progression. Our results show that the frustration level detected from the SER model can possibly be used as a cost-effective tool for objective tracking of AD progression in addition to the Mini-Mental State Examination (MMSE) score.

Keywords: Alzheimer’s disease, speech emotion recognition, longitudinal biomarker, machine learning

Procedia PDF Downloads 114

Authors: Shanhua Hu

Abstract:

Social media as a critical propagandizing form of film, video games, and digital products has received substantial research attention, but there exists several critical barriers such as: (1) few studies exploring the internal and external connections of a product as part of the multimodal context that gives rise to readability and commercial return; (2) the lack of study of multimodal analysis in product’s official account of game publishers and its impact on users’ behaviors including purchase intention, social media engagement, and playing time; (3) no standardized ecologically-valid, game type-varying data can be used to study the complexity of official account’s postings within a time period. This proposed research helps to tackle these limitations in order to develop a model of readability study that is more ecologically valid, robust, and thorough. To accomplish this objective, this paper provides a more diverse dataset comprising different visual elements and messages collected from the official Twitter accounts of the Top 20 best-selling games of 2021. Video game companies target potential users through social media, a popular approach is to set up an official account to maintain exposure. Typically, major game publishers would create an official account on Twitter months before the game's release date to update on the game's development, announce collaborations, and reveal spoilers. Analyses of tweets from those official Twitter accounts would assist publishers and marketers in identifying how to efficiently and precisely deploy advertising to increase game sales. The purpose of this research is to determine how official game accounts use Twitter to attract new customers, specifically which types of messages are most effective at increasing sales. The dataset includes the number of days until the actual release date on Twitter posts, the readability of the post (Flesch Reading Ease Score, FRES), the number of emojis used, the number of hashtags, the number of followers of the mentioned users, the categorization of the posts (i.e., spoilers, collaborations, promotions), and the number of video views. The timeline of Twitter postings from official accounts will be compared to the history of pre-orders and sales figures to determine the potential impact of social media posts. This study aims to determine how the above-mentioned characteristics of official accounts' Twitter postings influence the sales of the game and to examine the possible causes of this influence. The outcome will provide researchers with a list of potential aspects that could influence people's judgments in limited-word posts. With the increased average online time, users would adapt more quickly than before in online information exchange and readings, such as the word to use sentence length, and the use of emojis or hashtags. The study on the promotion of official game accounts will not only enable publishers to create more effective promotion techniques in the future but also provide ideas for future research on the influence of social media posts with a limited number of words on consumers' purchasing decisions. Future research can focus on more specific linguistic aspects, such as precise word choice in advertising.

Keywords: engagement, official account, promotion, twitter, video game

Procedia PDF Downloads 78

Authors: Ashlesha Khanapure, Harsh Kashyap, Abhinav Anand, Sanjana Habib, Anupama Bidargaddi

Abstract:

Technologies that are developing quickly are being developed daily in a variety of disciplines, particularly the medical field. For the purpose of detecting bone fractures in X-ray pictures of different body segments, our work compares the ResNet-50 and MobileNetV3 architectures. It evaluates accuracy and computing efficiency with X-rays of the elbow, hand, and shoulder from the MURA dataset. Through training and validation, the models are evaluated on normal and fractured images. While ResNet-50 showcases superior accuracy in fracture identification, MobileNetV3 showcases superior speed and resource optimization. Despite ResNet-50’s accuracy, MobileNetV3’s swifter inference makes it a viable choice for real-time clinical applications, emphasizing the importance of balancing computational efficiency and accuracy in medical imaging. We created a graphical user interface (GUI) for MobileNet V3 model bone fracture detection. This research underscores MobileNetV3’s potential to streamline bone fracture diagnoses, potentially revolutionizing orthopedic medical procedures and enhancing patient care.

Keywords: CNN, MobileNet V3, ResNet-50, healthcare, MURA, X-ray, fracture detection

Procedia PDF Downloads 69

Authors: Francesco Paolone

Abstract:

This paper investigates the role of Operating Cash Flow (OCF) and accruals in firm valuation analyzing financial statement information from the largest European companies and evaluating their relation to firm market value. Using a dataset of 500 largest European companies in 2018, the study investigates the relative value-relevance of equity, net income and operating cash flow (OCF). Findings show that the cash flow measure has the same explanatory power and intensity as equity and earnings to explain the market value. This study contributes to the debate on the value relevance of OCF incremental to book value and earnings. It also extends the literature, showing that OCF has information content (value relevance) superior to earnings and book value in the main European markets (Bepari et al., 2013). Finally, the study provides a support that accounting method choice may confuse investors, who have reduced confidence in accounting earnings and book value; in other words, nowadays European investors rely more on cash flows instead of accruals numbers.

Keywords: Cash Flow Statement, Value Relevance, Accounting, Financial Statement Analysis

Procedia PDF Downloads 132

Authors: Vani Singhal, Jitendra Parmar, Satyendra Singh Chouhan

Abstract:

Unseen class discovery has now become an important part of a machine-learning algorithm to judge new classes. Unseen classes are the classes on which the machine learning model is not trained on. With the advancement in technology and AI replacing humans, the amount of data has increased to the next level. So while implementing a model on real-world examples, we come across unseen new classes. Our aim is to find the number of unseen classes by using a hierarchical-based active learning algorithm. The algorithm is based on hierarchical clustering as well as active sampling. The number of clusters that we will get in the end will give the number of unseen classes. The total clusters will also contain some clusters that have unseen classes. Instead of first discovering unseen classes and then finding their number, we directly calculated the number by applying the algorithm. The dataset used is for intent classification. The target data is the intent of the corresponding query. We conclude that when the machine learning model will encounter real-world data, it will automatically find the number of unseen classes. In the future, our next work would be to label these unseen classes correctly.

Keywords: active sampling, hierarchical clustering, open world learning, unseen class discovery

Procedia PDF Downloads 173

Authors: Hui-Ling Huang, Tamara Vasylenko, Phasit Charoenkwan, Shih-Hsiang Chiu, Shinn-Ying Ho

Abstract:

The knowledge of the human transporters is still limited due to technically demanding procedure of crystallization for the structural characterization of transporters by spectroscopic methods. It is desirable to develop bioinformatics tools for effective analysis of available sequences in order to identify human transmembrane transporter proteins (HMTPs). This study proposes a scoring card method (SCM) based method for predicting HMTPs. We estimated a set of propensity scores of dipeptides to be HMTPs using SCM from the training dataset (HTS732) consisting of 366 HMTPs and 366 non-HMTPs. SCM using the estimated propensity scores of 20 amino acids and 400 dipeptides -as HMTPs, has a training accuracy of 87.63% and a test accuracy of 66.46%. The five top-ranked dipeptides include LD, NV, LI, KY, and MN with scores 996, 992, 989, 987, and 985, respectively. Five amino acids with the highest propensity scores are Ile, Phe, Met, Gly, and Leu, that hydrophobic residues are mostly highly-scored. Furthermore, obtained propensity scores were used to analyze physicochemical properties of human transporters.

Keywords: dipeptide composition, physicochemical property, human transmembrane transporter proteins, human transmembrane transporters binding propensity, scoring card method

Procedia PDF Downloads 370

Authors: Byung Ho Jung, Dong Hoon Lim

Abstract:

Logistic regression is a statistical method for analyzing a dataset in which there are one or more independent variables that determine an outcome. Logistic regression is used extensively in numerous disciplines, including the medical and social science fields. In this paper, we address the problem of estimating parameters in the logistic regression based on MapReduce framework with RHadoop that integrates R and Hadoop environment applicable to large scale data. There exist three learning algorithms for logistic regression, namely Gradient descent method, Cost minimization method and Newton-Rhapson's method. The Newton-Rhapson's method does not require a learning rate, while gradient descent and cost minimization methods need to manually pick a learning rate. The experimental results demonstrated that our learning algorithms using RHadoop can scale well and efficiently process large data sets on commodity hardware. We also compared the performance of our Newton-Rhapson's method with gradient descent and cost minimization methods. The results showed that our newton's method appeared to be the most robust to all data tested.

Keywords: big data, logistic regression, MapReduce, RHadoop

Procedia PDF Downloads 285

Authors: Arya Prakash Padhi, Anupam Chakrabarti, Rajib Chowdhury

Abstract:

Topology or layout optimization often gives better performing economic structures and is very helpful in the conceptual design phase. But traditionally it is being done in finite element-based optimization schemes which, although gives a good result, is very time-consuming especially in 3D structures. Among other alternatives machine learning, especially deep learning-based methods, have a very good potential in resolving this computational issue. Here convolutional neural network (3D-CNN) based variational auto encoder (VAE) is trained using a dataset generated from commercially available topology optimization code ABAQUS Tosca using solid isotropic material with penalization (SIMP) method for compliance minimization. The encoded data in latent space is then fed to a 3D generative adversarial network (3D-GAN) to generate the outcome in 64x64x64 size. Here the network consists of 3D volumetric CNN with rectified linear unit (ReLU) activation in between and sigmoid activation in the end. The proposed network is seen to provide almost optimal results with significantly reduced computational time, as there is no iteration involved.

Keywords: 3D generative adversarial network, deep learning, structural topology optimization, variational auto encoder

Procedia PDF Downloads 175

Authors: Anung Style Bukhori, Ani Dijah Rahajoe

Abstract:

Poverty poses a significant challenge in Indonesia, requiring an effective analytical approach to understand and address this issue. In this research, we applied the Naïve Bayes classification method to examine and classify poverty data in Indonesia. The main focus is on classifying data using RapidMiner, a powerful data analysis platform. The analysis process involves data splitting to train and test the classification model. First, we collected and prepared a poverty dataset that includes various factors such as education, employment, and health..The experimental results indicate that the Naïve Bayes classification model can provide accurate predictions regarding the risk of poverty. The use of RapidMiner in the analysis process offers flexibility and efficiency in evaluating the model's performance. The classification produces several values to serve as the standard for classifying poverty data in Indonesia using Naive Bayes. The accuracy result obtained is 40.26%, with a moderate recall result of 35.94%, a high recall result of 63.16%, and a low recall result of 38.03%. The precision for the moderate class is 58.97%, for the high class is 17.39%, and for the low class is 58.70%. These results can be seen from the graph below.

Keywords: poverty, classification, naïve bayes, Indonesia

Procedia PDF Downloads 61

Authors: Jonathan H. Westover, Ruthann Cunningham, Jaron Harvey

Abstract:

Purpose: Job satisfaction is one of the most critical attitudes among employees. Understanding whether employees are satisfied with their jobs and what is driving that satisfaction is important for any employer, but particularly for healthcare organizations. This study looks at the question of job satisfaction and drivers of job satisfaction among healthcare professionals at a global scale, looking for trends that generalize across 37 countries. Study: This study analyzed job satisfaction responses to the 2015 Work Orientations IV wave of the International Social Survey Programme (ISSP) to understand differences in antecedents for and levels of job satisfaction among healthcare professionals. A total of 18,716 respondents from 37 countries participated in the annual survey. Findings: Respondents self-identified their occupational category based on corresponding International Standard Classification of Occupations (ISCO-08) codes. Results suggest that mean overall job satisfaction was highest among health service managers and generalist medical practitioners and lowest among environmental hygiene professionals and nursing professionals. Originality: Many studies have addressed the issue of job satisfaction in healthcare, examining small samples of specific healthcare workers. In this study, using a large international dataset, we are able to examine questions of job satisfaction across large groups of healthcare workers in different occupations within the healthcare field.

Keywords: job satisfaction, healthcare industry, global comparisons, workplace

Procedia PDF Downloads 146

Authors: Gorkem Algan, Ilkay Ulusoy, Saban Gonul, Banu Turgut, Berker Bakbak

Abstract:

Computer vision systems recently made a big leap thanks to deep neural networks. However, these systems require correctly labeled large datasets in order to be trained properly, which is very difficult to obtain for medical applications. Two main reasons for label noise in medical applications are the high complexity of the data and conflicting opinions of experts. Moreover, medical imaging datasets are commonly tiny, which makes each data very important in learning. As a result, if not handled properly, label noise significantly degrades the performance. Therefore, a label-noise-robust learning algorithm that makes use of the meta-learning paradigm is proposed in this article. The proposed solution is tested on retinopathy of prematurity (ROP) dataset with a very high label noise of 68%. Results show that the proposed algorithm significantly improves the classification algorithm's performance in the presence of noisy labels.

Keywords: deep learning, label noise, robust learning, meta-learning, retinopathy of prematurity

Procedia PDF Downloads 162

Authors: Chiung-Ju Huang, Yuan-Hong Ho

Abstract:

This study utilizes the International Monetary Fund (IMF) Fiscal Rules Dataset focusing on four specific fiscal rules such as expenditure rule, revenue rule, budget balance rule, and debt rule and five main characteristics of each fiscal rule those are monitoring, enforcement, coverage, legal basis, and escape clause to construct the Fiscal Rule Index for nine countries in the Asia-Pacific region from 1996 to 2015. After constructing the fiscal rule index for each country, we utilize the Panel Generalized Method of Moments (Panel GMM) by using the constructed fiscal rule index to examine the effectiveness of fiscal rules in reducing procyclicality. Empirical results show that national fiscal rules have a significantly negative impact on procyclicality of government expenditure. Additionally, stricter fiscal rules combined with high government effectiveness are effective in reducing procyclicality of government expenditure. Results of this study indicate that for nine Asia-Pacific countries, policymakers’ use of fiscal rules and government effectiveness to reducing procyclicality of fiscal policy are effective.

Keywords: counter-cyclical policy, fiscal rules, government efficiency, procyclical policy

Procedia PDF Downloads 282

Authors: Geetha Baskaran, Andrzej Barjiela, Rong Qu

Abstract:

Motivation: Nurse scheduling is a complex combinatorial optimization problem. It is also known as NP-hard. It needs an efficient re-scheduling to minimize some trade-off of the measures of violation by reducing selected constraints to soft constraints with measurements of their violations. Problem Statement: In this paper, we extend our novel approach to solve the nurse scheduling problem by transforming it through Information Granulation. Approach: This approach satisfies the rules of a typical hospital environment based on a standard benchmark problem. Generating good work schedules has a great influence on nurses' working conditions which are strongly related to the level of a quality health care. Domain transformation that combines the strengths of operation research and artificial intelligence was proposed for the solution of the problem. Compared to conventional methods, our approach involves judicious grouping (information granulation) of shifts types’ that transforms the original problem into a smaller solution domain. Later these schedules from the smaller problem domain are converted back into the original problem domain by taking into account the constraints that could not be represented in the smaller domain. An Integer Programming (IP) package is used to solve the transformed scheduling problem by expending the branch and bound algorithm. We have used the GNU Octave for Windows to solve this problem. Results: The scheduling problem has been solved in the proposed formalism resulting in a high quality schedule. Conclusion: Domain transformation represents departure from a conventional one-shift-at-a-time scheduling approach. It offers an advantage of efficient and easily understandable solutions as well as offering deterministic reproducibility of the results. We note, however, that it does not guarantee the global optimum.

Keywords: domain transformation, nurse scheduling, information granulation, artificial intelligence, simulation

Procedia PDF Downloads 397