Knowledge graphs (KG) include large amounts of structured data in many different domains. Knowledge or information is captured by entities and relationships between them in KG. One of the open problems in knowledge graphs area is "link prediction", that is predicting new relationships or links between the given existing entities in KG. A recent approach in graph-based learning problems is "graph embedding", in which graphs are represented as low-dimensional vectors. Then, it is easier to make link predictions using these vector representations. We also use graph embedding for graph representations. A sub-problem of link prediction in KG is the link prediction in the presence of literal values, and specifically numeric values, on the receiving end of links. This is a harder problem because of the numeric literal values taking arbitrary values. For such entries link prediction models cannot work, because numeric entities are not embedded in the vector space. There are several studies in this area, but they are all complex approaches. In this study, we propose a novel approach for link prediction in KG in the presence of numerical values. To overcome the embedding problem of numeric values, we used a clustering approach for clustering these numerical values in a knowledge graph and then used the clusters for performing link prediction. Then we clustered the numerical values to enhance the prediction rates and evaluated our method on a part of Freebase knowledge graph, which includes entities, relations, and numerical literals. Test results show that a considerable increase in link prediction rate can be achieved in comparison to previous studies.

Recently, studies in the field of Natural Language Processing and its related applications continue to mount up. Machine learning is proven to be predominantly data-driven in the sense that generic model building methods are used and then tailored to specific application domains. Needless to say, this has proven to be a very effective approach in modeling the complicated data dependencies we frequently experience in practice, making very few assumptions, and allowing the information to talk for themselves. Examples of these applications can be found in chemical process engineering, climate science, healthcare, and linguistic processing systems for natural languages, to name a few. Text classification is one of the important machine learning tasks that is used in many digital applications today; such as in document filtering, search engines, document management systems, and many more. Text classification is the process of categorizing of text documents into a given set of labels. Furthermore, multi-label text classification is the task of categorization of text documents into one or more labels simultaneously. Over the years, many methods for classifying text documents have been proposed, including the popularly known bag of words (BoW) method, support vector machine (SVM), tree induction, and label-vector embedding, to mention a few. These kinds of tools can be used in many digital applications, such as document filtering, search engines, document management systems, etc. Lately, deep learning-based approaches are getting more attention, especially in extreme multi-label text classification case. Deep learning has proven to be one of the major solutions to many machine learning applications, especially those involving high-dimensional and unstructured data. However, it is of paramount importance in many applications to be able to reason accurately about the uncertainties associated with the predictions of the models. In this paper, we explore and compare the recent deep learning-based methods for multi-label text classification. We investigate two scenarios. First, multi-label classification model with ordinary embedding layer, and second with Glove, word2vec, and FastText as pre-trained embedding corpus for the given models. We evaluated these different neural network model performances in terms of multi-label evaluation metrics for the two approaches, and compare the results with the previous studies.

General Inquirer is a word-affect association vocabulary having 11896 entries. Ranging from rectitude to expressiveness, it comes with a flavor of categories. Despite the extensive content, a mapping from "To be or not to be." to "How much?" can be beneficial for word representation. In this work, we apply a method of window based analysis to obtain real valued General Inquirer attributes. Sentence Completion task is chosen to calculate the effectiveness of the operation. After whitening post-process, total cosine similarity convention is followed to concentrate on embedding improvement. Results indicate that our quantity focused variant is considerable.

Internet of Things world is getting bigger everyday with new developments in all fronts. The new IoT world requires better handling of big data and better usage with more intelligence integrated in all phases. Here we present MIS-IoT (Modular Intelligent Server Based Internet of Things Framework with Big Data and Machine Learning) framework, which is "modular" and therefore open for new extensions, "intelligent" by providing machine learning and deep learning methods on "big data" coming from IoT objects, "server-based" in a service-oriented way by offering services via standart Web protocols. We present an overview of the design and implementation details of MIS-IoT along with a case study evaluation of the system, showing the intelligence capabilities in anomaly detection over real-time weather data.

The diffusion of digital content is very fast in today's technology. The velocity of gathering data might cause unlawful distribution of content. The major problem in content authorization is the robustness of methodology. Since frangible methodologies result unauthorized content access quicker, more robust solutions are essential for copyright protection. Watermarking technology is considered as a robust solution for copyright protection and authentication. In watermarking, quality of the image is a challenge. Applying a watermark on a medical image might cause corruption in original image, which leads to misleading content. The proposed copyright protection mechanism includes Quadtree algorithm which finds a region of non-interest to apply watermark on medical image in Discrete Wavelet Domain to provide authentication of the content without altering region of interest. Furthermore, in this paper, the visual quality of watermark implemented medical images and sample values are also discussed with the experimental results as well.

Internet of Things (IoT) has been growing rapidly due to recent advancements in communications and sensor technologies. Meanwhile, with this revolutionary transformation, researchers, implementers, deployers, and users are faced with many challenges. IoT is a complicated, crowded, and complex field; there are various types of devices, protocols, communication channels, architectures, middleware, and more. Standardization efforts are plenty, and this chaos will continue for quite some time. What is clear, on the other hand, is that IoT deployments are increasing with accelerating speed, and this trend will not stop in the near future. As the field grows in numbers and heterogeneity, “intelligence” becomes a focal point in IoT. Since data now becomes “big data,” understanding, learning, and reasoning with big data is paramount for the future success of IoT. One of the major problems in the path to intelligent IoT is understanding “context,” or making sense of the environment, situation, or status using data from sensors, and then acting accordingly in autonomous ways. This is called “context-aware computing,” and it now requires both sensing and, increasingly, learning, as IoT systems get more data and better learning from this big data. In this survey, we review the field, first, from a historical perspective, covering ubiquitous and pervasive computing, ambient intelligence, and wireless sensor networks, and then, move to context-aware computing studies. Finally, we review learning and big data studies related to IoT. We also identify the open issues and provide an insight for future study areas for IoT researchers.

In recent years, big data and Internet of Things (IoT) implementations started getting more attention. Researchers focused on developing big data analytics solutions using machine learning models. Machine learning is a rising trend in this field due to its ability to extract hidden features and patterns even in highly complex datasets. In this study, we used our Big Data IoT Framework in a weather data analysis use case. We implemented weather clustering and sensor anomaly detection using a publicly available dataset. We provided the implementation details of each framework layer (acquisition, ETL, data processing, learning and decision) for this particular use case. Our chosen learning model within the library is Scikit-Learn based k-means clustering. The data analysis results indicate that it is possible to extract meaningful information from a relatively complex dataset using our framework.

We present the project SpEnD, a complete SPARQL endpoint discovery and analysis portal. In a previous study, the SPARQL endpoint discovery and analysis steps of the SpEnD system were explained in detail. In the SpEnD portal, the SPARQL endpoints are extracted from the web by using web crawling techniques, monitored and analyzed by live querying the endpoints systematically. After many sustainability improvements in the SpEnD project, the SpEnD system is now online as a portal. SpEnD portal currently serves 1487 SPARQL endpoints, out of which 911 endpoints are uniquely found by SpEnD only when compared to the other existing SPARQL endpoint repositories. In this portal, the analytic results and the content information are shared for every SPARQL endpoint. The endpoints stored in the repository are monitored and updated continuously.

Social Network Analysis (SNA) has become a very important and increasingly popular topic among researchers in recent years especially after emerging Semantic Web and Big Data technologies. Social networking services such as Facebook, Google+, Twitter, etc. provide large amounts of data that can be used for social network analysis by researchers. Semantic Web technology plays an important role for collecting, merging, and aggregating social network data from heterogeneous sources more easily, robustly and in an interoperable manner. Today, data scientists use several different frameworks for querying, integrating and analyzing datasets located at different sources. Meanwhile, most of the big social data is in unstructured or semi-structured format. Big data architectures allow researchers to analyze unstructured data in a time and cost-efficient way. New approaches for SNA are needed to combine Semantic Web and Big Data technologies in order to utilize and add capabilities to existing solutions. To be able to analyze large scale social networks, algorithms should have scalable designs in order to benefit from the emerging Big Data technologies. This survey focuses on recently developed systems for SNA and summarizes the state-of-the-art technologies used by them and points out to future research directions.

Trolls in social media are `malicious' users trying to propagate an opinion or distort the general perceptions. Identifying trolls in social media is a task of interest for many big data applications since data cannot be analyzed effectively without eliminating such users from the crowd. In this paper, we present a solution for troll detection and also the results of measuring terror awareness among social media users. We used Twitter platform only, and applied several machine learning techniques and big data methodologies. For machine learning we used k-Nearest Neighbour (kNN), Naive Bayes, and C4.5 decision tree algorithms. Hadoop/Mahout and Hadoop/Hive platforms were used for big data processing. Our tests show that C4.5 has a better performance on troll detection.

Due to increasing urban population and growing number of motor vehicles, traffic congestion is becoming a major problem of the 21st century. One of the main reasons behind traffic congestion is accidents which can not only result in casualties and losses for the participants, but also in wasted and lost time for the others that are stuck behind the wheels. Early detection of an accident can save lives, provides quicker road openings, hence decreases wasted time and resources, and increases efficiency. In this study, we propose a preliminary real-time autonomous accident-detection system based on computational intelligence techniques. Istanbul City traffic-flow data for the year 2015 from various sensor locations are populated using big data processing methodologies. The extracted features are then fed into a nearest neighbor model, a regression tree, and a feed-forward neural network model. For the output, the possibility of an occurrence of an accident is predicted. The results indicate that even though the number of false alarms dominates the real accident cases, the system can still provide useful information that can be used for status verification and early reaction to possible accidents.

Many experts claim that data will be the most valuable commodity in the 21st century. At the same time, two of the most influential components of this era, Big Data and IoT are moving very fast, on a collision course with the methodologies that are associated with conventional data processing and database systems. As a result, new approaches like NoSQL databases, distributed architectures, etc. started appearing on the stage. Meanwhile, another technology, ontology and semantic data processing can be a very convenient catalyzer that might assist in smoothly providing this transformation process. In this paper, we propose a combined framework that brings Big Data, IoT, and semantic web together to build an augmented framework for this new era. We not only list the components of such a system and define the necessary bindings that needs to be integrated together, but also provide a realistic use case that demonstrates how the model can implement the desired functionality and achieve the goals of such a model.

The ever-increasing complexity and challenges of the higher education coupled with more public scrutiny for its efficacy necessitate more in depth analysis and evaluation of the educational best practices. One such practice is the cooperative (co-op) education. While co-op education has been around for more than a century, its implementation is still barely more than nominal in higher education. Even though there are studies published to demonstrate its effectiveness, more in depth studies, both spatial and temporal, seem to be warranted to narrow the widening gap between students' jobs-first and institutions' intellectual-experience-first expectations. In this paper, we summarize the first and highly successful co-op program in Turkey at TOBB University of Economics and Technology (TOBB ETU). Our analysis include a taxonomy of different co-op programs to contextualize TOBB ETU's. Further, we touch upon the theoretical underpinnings from a variety of generally accepted foundational work. As part of the evaluation of the program, we provide a preliminary assessment of a longitudinal study as the first from Turkey and one of a very few from the non-US, international institutions. We believe that ours is the first to report an evaluation of co-op programs in terms of pre-co-op, post-co-op and graduated students separately.

We recently developed "system on mobile devices" (SyD) middleware for rapidly developing and deploying collaborative distributed applications over a collection of autonomous Web objects and data-stores, independent of the underlying device, data, or network. SyDListener is a key component of SyD middleware. SyDListener provides a set of interfaces and classes that allows distributed SyD-based application components to communicate seamlessly in mobile environments. SyDListener provides a uniform object view of the underlying server application and enables client applications to remotely invoke those methods using XML messages. SyDListener is implemented as a multi-threaded wrapper with simple persistence management and asynchronous invocation functionality for J2ME mobile information device profile (MIDP) on connected limited device configuration (CLDL) devices. We discuss the functionality, architecture, implementation, and performance of SyDListener. We believe it is the first comprehensive working prototype of its kind for Java-enabled handhelds with a small footprint of 10 KB.

Article Free Access Share on Real-time transactions with execution histories: priority assignment and load control Authors: Erdoğan Doğdu Department of Computer Engineering and Science, Case Western Reserve University, Cleveland, OH Department of Computer Engineering and Science, Case Western Reserve University, Cleveland, OHView Profile , Gültekin Özsoyoğlu Department of Computer Engineering and Science, Case Western Reserve University, Cleveland, OH Department of Computer Engineering and Science, Case Western Reserve University, Cleveland, OHView Profile Authors Info & Claims CIKM '97: Proceedings of the sixth international conference on Information and knowledge managementJanuary 1997 Pages 301–308https://doi.org/10.1145/266714.266915Online:01 January 1997Publication History 1citation258DownloadsMetricsTotal Citations1Total Downloads258Last 12 Months3Last 6 weeks0 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteeReaderPDF

A methodology to dynamically adjust the multimedia presentations as a result of user interactions during the playout is introduced. A constraint-driven approach is described for the automated assembly, organization and playout of presentations from multimedia databases. To allow interactive user control over the playout of an automatically generated presentation, a set of control buttons are provided. Using these buttons, the user can control and change the flow of the presentation in a variety of ways. Interactive user control during the presentation playout, however, can introduce new delays in the original presentation schedule of multimedia segments and possibly change playout constraints. To account for these delays and changes, strategies to (a) dynamically reorganize the subpresentations into a presentation, (b) replace segments with their compacted clips, and (c) delete segments on the presentation graph are proposed.