This study examines the difference in people’s perceptions of an embodied and a nonembodied conversational agent. It also discusses the potential use of embodied AI in the telehealth industry. A GPT assistant was created with the instruction to act as an empathetic doctor, and an embodied conversation agent system was designed for it to use in interactions. Research participants interacted with both embodied and nonembodied versions of the assistant and recorded their experience through a survey. Results showed that participants had higher standards for an embodied AI and desired a more human-like interaction. If these expectations are not met, their preference shifts in favor of nonembodied AI. Users would be comfortable using embodied AI in telehealth settings, however, a preference still exists for actual doctors. Measures would also have to be taken to ensure their medical information is kept secure.

Topic evolution is a recently introduced field of research as a substitute for a more traditional text-based topic evolution, allowing the tracking of more complex evolutionary events with the use of network structures. Network-based topic evolution showed that the neighborhood characteristics of newly introduced topics can be utilized to determine when a topic would emerge in a given domain. Predicting emerging topics requires a method for generating pseudo-neighbors of previously unseen topics as the neighborhood for an emerging topic is not known before its appearance. The authors proposed the Descendant-Aware Clustering algorithm to generate a set of neighborhood candidates for future emerging topics, surpassing existing algorithms in both performances and computation times. Optimizing the algorithm parameters enhances the performance even further. Significant performance improvements were observed when NSGA-III multi-objective algorithm was applied to over 100 research domains. A set of enhanced default values are introduced to the proposed algorithm removing the necessity for dataset-specific optimization, cementing the position of the Descendant-Aware Clustering as the best clustering algorithm for detecting ancestors of future emerging topics.

Topic evolution automatically tracks a set of concepts within a given dataset over time, assisting researchers to overview various research domains. Network-based topic evolution is one of the recent approaches incorporating relational models instead of traditional text-based models for allowing the detection of topic correlation events. Topics are represented with co-occurrence relationships instead of word vectors, connected over time through their positions in a network instead of their semantic similarities. This paper shows that the topics and their network representations share meaningfully similar semantics. The existence of such contextual relationships allows topics to be labeled without having enough direct textual appearances in the document collection. Forty fields-of-study keywords with 64,215 to 5.8 million related articles were selected from the Microsoft Academic Graph dataset containing more than 200 million publications. The semantics of topics within forty topic networks were found using three sets of word embeddings trained from a collection of 10.5 million Medline abstracts from the year 2000 to 2016, and word embeddings of the topics are compared against their network-based representations, which are their neighborhoods in the previous timeslot. Cosine similarities between topics and their neighbors consistently resulted in moderate correlations from the year 2001 to 2015, showing higher values for topics that were already present in the topic networks compared to newly emerging topics. The result suggested that labeling topics based on the network structure are possible without semantic analysis, which is necessary for predicting topic evolutions such as the topic emergence when future documents are unavailable.

Online portfolio selection, one of the major fundamental problems in finance, has been explored quite extensively in recent years by machine learning and artificial intelligence communities. Recent state-of-the-art methods have focused on Mean Reversion significantly and have demonstrated outstanding performance. Another version of the same phenomenon, Median Reversion, has also performed well and demonstrated its ability to be robust against noises and outliers. Another important characteristic is Momentum. In this paper, a Bayesian ensembling approach to extract knowledge from both Mean Reversion and Median Reversion simultaneously based on the momentum associated with each one is proposed for the online portfolio selection task. The proposed method demonstrates its effectiveness by outperforming current state-of-the-art algorithms on several datasets.

As the Age of Information has evolved over the last several decades, the demand for technology which stores, analyzes, and utilizes data has increased substantially. Countless industries such as the medical, the retail, and the aircraft rely on this technology to guide their decision making. In the present paper, we propose a hybrid machine learning algorithm consisting of Decision Trees and Neural Networks which can effectively and efficiently classify data of varying volume and variety. The structure of the hybrid algorithm consists of a decision tree where each node of the tree is a neural network trained to classify a specific category of the output using binary classification. The data with which we used to train and test the classification ability of our algorithm is the Federal Aviation Administration's (FAA's) Boeing 737 maintenance dataset which consists of 137,236 unique records each composed of 72 variables. We perform this by classifying the discrepancy, or cause, of the incident into whether or not the incident occurred during scheduled maintenance operations and then further classifying specific details relating to the incident. Our results indicate that our hybrid algorithm is able to effectively classify incidents with high accuracy and precision. Additionally the algorithm is able to identify the most significant inputs regarding a classification allowing for higher performance and greater optimization. This demonstrates the algorithm's applicability in real-world scenarios while also showcasing the benefits of combining decision trees and neural networks as opposed to using them individually.

Researchers often rely on the byline order in a publication to estimate relative contributions made by its authors, an assumption on which existing author contribution measures are based. This byline-based approach is, however, incompatible with the alphabetical author ordering, a practice still employed by many research fields. Manually requesting authors to state their contributions can overcome the limitation of the existing methods. Such approaches, however, require resource-intensive data acquisition and preprocessing, rendering them ungeneralizable to existing bodies of bibliographic records. The present paper proposed a possibility of order-independent automatic author contribution measure by focusing on distinguishing the main contributors from the rest of the authors using machine learning algorithms, bypassing the limitation of both the byline-based numerical author contribution methods and ungeneralizable manual approaches. The experiment validated the proposed approach by successfully classifying both the primary and the corresponding authors shown as the first and the last author without utilizing byline orders. The Random Forest classifier showed the best performances, successfully classifying the first author, the last author, and both with the accuracy of 0.90, 0.89, and 0.76 respectively.

Understanding the current research topics and their histories allow researchers to focus their capabilities on the current research trends. The field of topic evolution helps the understanding by automatically model and detect the set of shared research fields in the academic papers as topics. The authors propose a novel topic evolution method for identifying and predicting the emergence of new topics under the assumption that neighborhoods of new topics in the future have distinguishable structural features. Eight journals were selected from the Microsoft Academic Graph dataset, each representing topics networks with varying size, history, and research domains. Both retrospective classification and prospective prediction showed promising performance with classifications above 0.89 for six journals and coefficients of determination exceeding 0.95 for five journals. The result showed both the retrospective identification and the prospective prediction can be done, validating the assumption that topic evolution events can be predicted with a network-based approach.

A foundational step in the study of any animal is the establishment of an accurate behavioral model. Building a model that is capable of defining and predicting an animal's behavior is critical to advancing ethological theory and research, however many animal models fail to be sufficiently thorough or often do not exist at all. Great pools of data are available for improving these models through recorded video of animals posted on video hosting sites throughout the internet, however these sources are largely left unused due to their sheer quantity being too much for researchers to manually observe and annotate. This paper proposes a method for efficiently converting video of animals at any length into models capable of making accurate behavioral prediction. This predictive model is developed through a data processing pipeline merging an ensemble meta-algorithm for behavior classification with a long short-term memory network for temporal pattern recognition and prediction. The application of this pipeline produced results with a higher degree of predictive accuracy compared to more traditional autoregressive techniques. These findings suggest the method has significant potential as a tool for efficiently developing new models and findings in the study of animal behavior. The method's performance in prediction also suggests that it may have further application in building models for the prediction of events or failures in inorganic, semi-stochastic processes such as video monitored mechanical systems and equipment.

Journey by aircraft is the only option for long distance transportation and also one of the frequently used modes of transportation of passengers. As a result, safety of passengers and efficiency of the aircraft depend on maintaining efficient running conditions. Although many safety standards are followed in the design of the aircraft and thus there are fewer accidents, it is necessary to perform a thorough analysis to avoid risks that may occur during flight time. In the present work, we propose a maintenance strategy, Failing And Not Falling (F&!F), based on the Federal Aviation Administration (FAA) data in the United States. We work with the dataset of Boeing 737. The data consists of 72 features with 137,236 records which describe an aircraft accident or incident. These features are used to predict whether an incident will be identified during aircraft maintenance or during aircraft operation and what specific type of incident will occur. The prediction method is based on the integration of a decision tree and a unique neural network at each node of the decision tree. The results obtained using different architectures show how deep the neural networks should be, how to identify the relevant features, and the success of combining decision trees and neural networks. Moreover the neural networks and the decision tree approach also successfully identified the important features of maintenance. This method can be used for the maintenance of any data in multiple domains.

Recently, research in machine learning has become more reliant on data-driven approaches. However, understanding the general theory behind optimal neural network architecture is, arguably, just as important. With the proliferation of deep learning and neural networks, finding optimal neural network architecture is vital for both accuracy and performance. Recently, extensive research on neural network architecture has been performed [3],[4]. Additionally, while there has been plenty of research on hidden layer neural network architecture [2], activation functions are often not considered. In a network, an activation function defines the output of a neuron and introduces non-linearities into the neural network, enabling it to be a universal function approximator [12]. In terms of activation functions, one significant paper is Krizhevsky's seminole work on ImageNet classification and the creation of the ReLU activation function [1]. In the paper, Krizhevsky outlines the construction of an image recognition model using the Rectified Linear Unit activation function (ReLU) for the ImageNET LSVRC-2010 competition which outperformed the state-of-the-art image recognition systems at the time [1]. Since then, ReLU has increased in popularity. In their 2018 conference paper, Bircanoğlu and Arica, with the assistance of 231 distinct training procedures, found ReLU to be the best general activation function [12]. In addition to comparisons of activation functions, Nwankpa, Ijomah, Gachagan, and Marshall conducted a meta analysis of the field of research centered around activation functions and found ReLU to be the most popular activation function choice [5]. In terms of optimizers, gradient descent has historically been the most popular loss optimization algorithm, but with Kingma and Ba's 2014 paper [8], Adam: A Method for Stochastic Optimization, Adam optimizer is slowly becoming the industry standard [11]. In their paper, Kingma and Ba cleverly combine momentum descent, RMSprop, and Adagrad optimization into one algorithm, Adam (or adaptive moment estimation) [8]. In addition to Adam, there are plenty of other optimizers to choose from, including gradient descent, RMSprop [9], Adagrad [10], and Adadelta [7]. Recently, many breakthroughs have been made in terms of neural network performance, improved GPU performance and adaptation to deep learning tasks has created massive efficiency increases for the whole field of machine learning. Furthermore, as machine learning becomes increasingly optimized, the importance of efficiency improvements will continue to rise. Thus, understanding the optimal activation function and optimizer choice for a neural network is relevant. The goal of this paper is to make comparisons between activation functions, optimizers, and, more generally, entire neural network architectures, through measured error in a training environment. In this paper, we examine the performance of a wide variety of neural network configurations on randomly generated polynomial data sets of fixed degree. To do this, we compare various neural network activation functions and optimizers while controlling for hidden layer configurations and degree of the underlying polynomial dataset. Curiously, we find that the Sigmoid activation function is more accurate than ReLU and Tanh for regression tasks on low-featured polynomial data. We also reach the same conclusion regarding Stochastic Gradient Descent (SGD) in comparison to the Adam optimization function and Root Mean Square Propagation (RMSprop). Additionally, we observe that SGD is more efficient in the short term for finding local minimums than Adam or RMSprop; however, after sufficiently many epochs, performance differences between the optimizers vanished.

The large volume of scientific publications is likely to have hidden knowledge that can be used for suggesting new research topics. We propose an automatic method that is helpful for generating research hypotheses in the field of physics using the massive number of physics journal publications. We convert the text data of titles and abstract sections in publications to a bipartite graph, extracting words of physical matter composed of chemical elements and extracting related keywords in the articles. The proposed method predicts the formation of new links between matter and keyword nodes based on collaborative filtering and matter popularity. The formation of links represents research hypotheses, as it suggests the new possible relationships between physical matter and keywords for physical properties or phenomena. The suggested method has better performance than existing methods for link prediction in the entire bipartite graph and the subgraph that contains only a specific keyword, such as `antiferromagnetism' or `superconductivity.' Our suggested concept for generating research hypotheses can be easily extended to various other research topics or industrial topics using patent literature.

The exponential rise in the volume of publications and the prevalence of multidisciplinary practice in scientific domains has made it increasingly difficult to keep track of changes in research trends. In this paper, we propose a framework for determining persistent and emerging research topics in scientific literature. The topics were represented as non-overlapping communities of keywords in a dynamic cooccurrence network derived from 21 million articles in PubMed that were published from 1980 to 2016. We detected a set of communities for each snapshot of the network and traced their instances in consecutive periods using a similarity threshold. Our approach provides a retrospective analysis of changes in research topics: their formation, growth, shrinkage, survival, merging, splitting, and dissolution. We also show that a feature set comprising of 43 temporal and structural attributes from these keyword communities can be used to predict their evolution. In particular, we found that the frequency of co-occurrences and the appearance of new keywords within the community are highly predictive of its persistence or dissolution in the next five years.

Single objective evolutionary constrained optimization has been widely researched by plethora of researchers in the last two decades whereas multi-objective constraint handling using evolutionary algorithms has not been actively proposed. However, real-world multi-objective optimization problems consist of one or many non-linear and non-convex constraints. In the present work, we develop an evolutionary algorithm based on hybrid constraint handling methodology (HyCon) to deal with constraints in bi-objective optimization problems. HyCon is a combination of an Evolutionary Multi-objective Optimization (EMO) coupled with classical weighted sum approach and is an extended version of our previously developed constraint handling method for single objective optimization. A constrained bi-objective problem is converted into a tri-objective problem where the additional objective is formed using summation of constrained violation. The performance of HyCon is tested on four constrained bi-objective problems. The non-dominated solutions are compared with a standard evolutionary multi-objective optimization algorithm (NSGA-II) with respect to hypervolume and attainment surface. The simulation results illustrates the effectiveness of the HyCon method. The HyCon either outperformed or produced similar performance as compared to NSGA-II.

Video is an increasingly important method of information-sharing on the Web. Services such as YouTube, Vimeo, and Liveleak are platforms that support uploading User-Generated Content. Users tend to seek related information during or after watching an informative video by finding and reading comments on Web services. However, existing services only support sorting by recentness (newest) or rating (LIKES score), as opposed to related information. We suggest a novel method to find informative comments by considering original content and its relevance. We conducted a qualitative study of participants watching informative videos and analyzed how users interacted with the comments, the feature preferences, and the criteria for evaluation. We developed methods to measure informativeness priority, the user-provided level of information, classify intention of information posted, and cluster duplicate themes. Analysis of 1,861 TED talk videos and 380,619 comments show suggested methods can find more informative comments compared to existing methods (LIKES).

This article aims to deepen understanding of these mass interactions in online sports viewing through studying Naver Sports, the largest online sports viewing service in Korea. We examined the diverse aspects of mass interactions, including interactive experiences, usage motives, and relationships between usage patterns and motives, through analysis of almost 6 million chats from Naver Sports and from self-reporting survey data from 1,123 users. First, we found that online sports viewing provides unique interactive experiences when compared to other settings such as offline sports viewing and social TV viewing with friends. Second, we found the key motives inspiring online sports viewing include the following: sharing feelings/thoughts, wanting to be entertained, sharing information, and wanting to feel membership in a group. Third, these motives were significantly related to specific usage patterns. Finally, we explored how the study’s key findings can offer practical design implications to enhance online sports viewing services, and to show system designers how to support particular usage patterns to better accommodate specific user motives.

The paper suggests a method for analyzing technology trends. The process, which investigates development of technologies overtime, identifies main technologies displaying the fastest growth compared to greater influence of new inventions. The method analyzes term frequency and change over time of technological terms in academic articles and patents to identify the prior technologies that lead to a new technology and to detect technologies that have the biggest impact. The analysis was performed on 4,354,054 patents from the US Patent Office dating from 1975 until today. In addition, academic articles were analyzed as a trend forecasting data set to identify patents trends 4-5 years in advance and technology trends up to 9 years in advance. The forecasting method was extensively validated using a large repository of real-world technology terms, and the results were verified against Gartner technology predictions, Web searches, news articles, and book publications. The method shows higher accuracy than existing forecasting methods do. Some correlation is displayed between technology trends and future US stock market performance.

The last decade has witnessed a tremendous growth of web services as a major technology for sharing data, computing resources, and programs on the web. With increasing adoption and presence of web services, designing novel approaches for efficient and effective web service recommendation has become of paramount importance. Most existing web service discovery and recommendation approaches focus on either perishing UDDI registries, or keyword-dominant web service search engines, which possess many limitations such as poor recommendation performance and heavy dependence on correct and complex queries from users. It would be desirable for a system to recommend web services that align with users’ interests without requiring the users to explicitly specify queries. Recent research efforts on web service recommendation center on two prominent approaches:collaborative filteringandcontent-based recommendation. Unfortunately, both approaches have some drawbacks, which restrict their applicability in web service recommendation. In this paper, we propose a novel approach that unifies collaborative filtering and content-based recommendations. In particular, our approach considers simultaneously both rating data (e.g., QoS) and semantic content data (e.g., functionalities) of web services using a probabilistic generative model. In our model, unobservable user preferences are represented by introducing a set of latent variables, which can be statistically estimated. To verify the proposed approach, we conduct experiments using 3,693 real-world web services. The experimental results show that our approach outperforms the state-of-the-art methods on recommendation performance.

With increasing adoption and presence of Web services, designing novel approaches for efficient Web services recommendation has become steadily more important. Existing Web services discovery and recommendation approaches focus on either perishing UDDI registries, or keyword-dominant Web service search engines, which possess many limitations such as insufficient recommendation performance and heavy dependence on the input from users such as preparing complicated queries. In this paper, we propose a novel approach that dynamically recommends Web services that fit users' interests. Our approach is a hybrid one in the sense that it combines collaborative filtering and content-based recommendation. In particular, our approach considers simultaneously both rating data and content data of Web services using a three-way aspect model. Unobservable user preferences are represented by introducing a set of latent variables, which is statistically estimated. To verify the proposed approach, we conduct experiments using 3, 693 real-world Web services. The experimental results show that our approach outperforms the two conventional methods on recommendation performance.

Ontologies have become the de-facto modeling tool of choice, employed in many applications and prominently in the semantic web. Nevertheless, ontology construction remains a daunting task. Ontological bootstrapping, which aims at automatically generating concepts and their relations in a given domain, is a promising technique for ontology construction. Bootstrapping an ontology based on a set of predefined textual sources, such as web services, must address the problem of multiple, largely unrelated concepts. In this paper, we propose an ontology bootstrapping process for web services. We exploit the advantage that web services usually consist of both WSDL and free text descriptors. The WSDL descriptor is evaluated using two methods, namely Term Frequency/Inverse Document Frequency (TF/IDF) and web context generation. Our proposed ontology bootstrapping process integrates the results of both methods and applies a third method to validate the concepts using the service free text descriptor, thereby offering a more accurate definition of ontologies. We extensively validated our bootstrapping method using a large repository of real-world web services and verified the results against existing ontologies. The experimental results indicate high precision. Furthermore, the recall versus precision comparison of the results when each method is separately implemented presents the advantage of our integrated bootstrapping approach.

Abstract: The analysis of medical documents necessitates context recognition for diverse purposes such as classification, performance analysis and decision making. Traditional methods of context recognition have focused on the textual part of documents. Images, however, provide a rich source of information that can support the context recognition process. A method is proposed for integrating computer vision in context recognition using the web as a knowledge base. The method is implemented on medical case studies to determine the main symptoms or achieve possible diagnoses. In experiments the method for integrating computer vision in context recognition achieves better results than term frequency and inverse document frequency and only context recognition. The proposed method can serve as a basis for an image and text based decision support system to assist the physician in reviewing medical records.

In this work, we propose a two-step, context-based semantic approach to the problem of matching and ranking Web services for possible service composition. We present an analysis of different methods for classifying Web services for possible composition and supply a context-based semantic matching method for ranking these possibilities. Semantic understanding of Web services may provide added value by identifying new possibilities for compositions of services. The semantic matching ranking approach is unique since it provides the Web service designer with an explicit numeric estimation of the extent to which a possible composition ldquomakes sense.rdquo First, we analyze two common methods for text processing, TF/IDF and context analysis; and two types of service description, free text and WSDL. Second, we present a method for evaluating the proximity of services for possible compositions. Each Web service WSDL context descriptor is evaluated according to its proximity to other services' free text context descriptors. The methods were tested on a large repository of real-world Web services. The experimental results indicate that context analysis is more useful than TF/IDF. Furthermore, the method evaluating the proximity of the WSDL description to the textual description of other services provides high recall and precision results.