Benchmarking Internet of Things Deployment: Frameworks, Best Practices, and Experiences

Organization that scatters over different regions that perform multi-state business transaction are always interested I identifying novel patterns of interest given augmenting nosiness volumes. On a daily basis, we encounter an unparalleled increase in data from many sources, which adds to the concept of big data in terms of its size, speed, and diversity. These datasets provide significant obstacles to analytics frameworks and processing resources, so making the total study arduous for extracting useful information promptly. Therefore, in order to overcome these types of difficulties, it is crucial to create a very effective framework for analyzing large amounts of data. Therefore, in order to tackle these difficulties by harnessing non-linear connections from extensive and complex information, analytics frameworks are using machine (ML) and (DL) methods. Apache Spark is widely recognized as the most efficient tool for processing large amounts of data. It is particularly useful for solving complex machine learning problems that need several iterations. Spark MLlib, a distributed machine learning library, is used for this purpose. When dealing with research problems in the real world, architectures like Long Short-Term Memory in deep learning are a useful method for addressing practical challenges like as decreased accuracy, long-term sequence dependence, and the problem of disappearing and expanding gradients in traditional deep architectures. This study proposes a very efficient analytics system that combines a progressive machine learning method with Spark-based linear models, Multilayer Perceptron , and Long Short-Term Memory. The accuracy of the system's predictions is improved by the use of a two-stage cascade structure. The architecture that we provide makes it possible to organize statistical analysis of large amounts of data in a way that is not only scalable but also effective. We applied the cascading structure on two different real-world datasets in order to illustrate the effectiveness of our framework. Furthermore, the results of the experiments show that our analytical framework is superior to the approaches that are considered to be state-of-the-art in terms of classification accuracy.

Science and technology are expected to establish a new scientific methodology for studies of services to raise service-sector productivity and to support new services. However, no consensus exists on how to study services because of their specific nature. This paper first provides an overview of previous studies of services using an academic database. Then it presents a new classification of service models considering the relationships among service providers, service receivers, and service environments toward value creation. We also discuss scientific strategies to co-create new service values in the real world.

Nowadays, large bodies of data in different domains are collected and stored. An efficient extraction of useful knowledge from these data becomes a huge challenge. This leads to the need for developing distributed data mining techniques (DDM). Moreover, it creates a complex problem of the management of the mined results. To solve this problem, we propose the Knowledge Map Ontology (KMO) architecture that allows an efficient representation of knowledge to guide the users in the extraction of such knowledge. KMO uses repositories built from Ontologies. The distribution of this architecture is done according to Tree P2P (TreeP) because Ontologies are structured as trees. We show that this architecture is very efficient and necessary in the field, where knowledge is distributed, varied, and representing very large quantities of data.

MP20-02 Aquablation at 4-years: the largest, real world, single-center study and longest follow-up data for this innovative BPH treatment

One of the major impediments in deployment of Autonomous Driving Systems (ADS) is their safety and reliability. The primary reason for the complexity of testing ADS is that it operates in an open world characterized by its non-deterministic, high-dimensional and non-stationary nature where the actions of other actors in the environment are uncontrollable from the ADS's perspective. This leads to a state space explosion problem and one way of mitigating this problem is by concretizing the scope for the system under test (SUT) by testing for a set of behavioral competencies which an ADS must demonstrate. A popular approach to testing ADS is scenario-based testing where the ADS is presented with driving scenarios from real world (and synthetically generated) data and expected to meet defined safety criteria while navigating through the scenario. We present SAFR-AV, an end-to-end ADS testing platform to enable scenario-based ADS testing. Our work addresses key real-world challenges of building an efficient large scale data ingestion pipeline and search capability to identify scenarios of interest from real world data, creating digital twins of the real-world scenarios to enable Software-in-the-Loop (SIL) testing in ADS simulators and, identifying key scenario parameter distributions to enable optimization of scenario coverage. These along with other modules of SAFR-AV would allow the platform to provide ADS pre-certifications.

Data Science is associated with new discoveries, the discovery of value from the data. It is a practice of deriving insights and developing business strategies through transformation of data in to useful information. It has been evaluated as a scientific field and research evolution in disciplines like statistics, computing science, intelligence science, and practical transformation in the domains like science, engineering, public sector, business and lifestyle. The field encompasses the larger areas of artificial intelligence, data analytics, machine learning, pattern recognition, natural language understanding, and big data manipulation. It also tackles related new scientific challenges, ranging from data capture, creation, storage, retrieval, sharing, analysis, optimization, and visualization, to integrative analysis across heterogeneous and interdependent complex resources for better decision-making, collaboration, and, ultimately, value creation. In this paper we entitled epicycles of analysis, formal modeling, from data analysis to data science, data analytics -A keystone of data science, The Big data is not a single technology but an amalgamation of old and new technologies that assistance companies gain actionable awareness. The big data is vital because it manages, store and manipulates large amount of data at the desirable speed and time. Big data addresses detached requirements, in other words the amalgamate of multiple un-associated datasets, processing of large amounts of amorphous data and harvesting of unseen information in a time-sensitive generation.
 As businesses struggle to stay up with changing market requirements, some companies are finding creative ways to use Big Data to their growing business needs and increasingly complex problems. As organizations evolve their processes and see the opportunities that Big Data can provide, they struggle to beyond traditional Business Intelligence activities, like using data to populate reports and dashboards, and move toward Data Science- driven projects that plan to answer more open-ended and sophisticated questions.
 Although some organizations are fortunate to have data scientists, most are not, because there is a growing talent gap that makes finding and hiring data scientists in a timely manner is difficult. This paper, aimed to demonstrate a close view about Data science, big data, including big data concepts like data storage, data processing, and data analysis of these technological developments, we also provide brief description about big data analytics and its characteristics , data structures, data analytics life cycle, emphasizes critical points on these issues.

Abstract. Natural disasters have a significant impact on the environment and economies of all countries around the world, and a large amount of multi-source heterogeneous geographic information data is generated every day. However, due to a lack of knowledge transformation capabilities, these nations continue to struggle with the issue of "a large amount of data and little knowledge". Therefore, it is of great significance how to extract geographic knowledge related to disasters from the vast data and construct a geographic knowledge graph integrating disaster information. Based on the theory related to knowledge extraction, this paper proposes a method to construct a natural disaster knowledge graph integrating geographic information. The core of this knowledge graph is to construct the association relationship between natural disaster concepts, research areas, and spatial data. The vocabulary and relationships associated with disaster concepts are primarily transformed by an existing word list of geographic narratives, which then provide rich semantic relationships of domain concepts for the entire knowledge graph. The research areas and spatial data types are mainly obtained through knowledge entity extraction and disambiguation methods. This disaster knowledge graph can support applications well such as natural disaster visualization and analysis, data recommendation systems, and intelligent Q&A systems, which can further improve the intelligence of natural disaster knowledge services and is expected to promote the sharing and reuse of domain knowledge graphs to a certain extent.

The Multivariate time series prediction problem has always been an important and hot issue in the human society. This problem has attracting a large number of researchers to conduct related research. However, the time series data in the real world is highly complex and the data size is large, which brings great inconvenience and challenge to the research work. The RNN-based model made some great progress on the traditional Sequence to Sequence problem such as NLP nowadays. But using the RNN-based model to predict the multivariate time series data still have some problems. For example, the time series data in the real world usually has a certain periodicity, the RNN-based model is hard to capture the global information. In this paper, we propose a CNN-based model called LHCnn(Low-High Cnn). LHCnn combines the CNN with the Attention mechanisms. The model uses multi-layer CNNs to extract the surface and the deep features of the data. Then we combine these two kinds of features with the Attention mechanisms to produce the final prediction. We also train the model in parallel on multiple GPUs to accelerate the training process. In the final part of this paper, we discuss the effort of real-time series data in the experiment, and then proved that this model not only can ensure reliability and stability, but also can achieve higher accuracy. Analyzing working principle of many time series sequencing models and comparing them each other, this one is better than others right now.

We present a system from friction measurement to haptic rendering with ONE point-based haptic device. To present a high definition virtual object by haptic rendering, it is necessary to present a haptic impression such as the asperity, friction and stiffness while controlling the haptic device at more than 300-1000 Hz update rate. We have proposed several texture-based haptic rendering techniques at small amount of calculation and with high definition. However, in our previous techniques, the haptic texture such as the height map, normal map, friction map and stiffness map are not based on the measurement data in the real world. To present more realistic haptic impression, it is necessary to calculate the reaction force based on the measurement data in the real world. Therefore, we firstly developed a prototype system of a friction measurement and friction map generation. Secondly, we attempted a haptic rendering based on the measurement data. It is notable that our system enables these functions with ONE point-based haptic device. This paper describes a system from friction measurement to haptic rendering with one point-based haptic device.

Technological advances have enabled the collection of large quantities of valuable data for health-related use. Particularly, a growing number of scholars are paying attention to the application of health analytics to business topics. A comprehensive analysis of health analytics application in business research is necessary to realize the commercial value of health analytics. In this article, we summarize peer-reviewed articles that have been published in business journals, with an eye toward formulating a roadmap for applying health analytics across multiple business domains. First, we demonstrate how health-related data can be harnessed to inform business research. Second, we endeavor to consolidate the available datasets and analytical techniques commonly employed to explore health analytics in business domains. Finally, we discuss the practical challenges confronting scholars in health analytics, as well as future research opportunities. Insights from our study yields insights that can be leveraged by business scholars interested in health analytics research.

Identifying and monitoring business and technological trends are crucial for innovation and competitiveness of businesses. Exponential growth of data across the world is invaluable for identifying emerging and evolving trends. On the other hand, the vast amount of data leads to information overload and can no longer be adequately processed without the use of automated methods of extraction, processing, and generation of knowledge. There is a growing need for information systems that would monitor and analyse data from heterogeneous and unstructured sources in order to enable timely and evidence-based decision-making. Recent advancements in computing and big data provide enormous opportunities for gathering evidence on future developments and emerging opportunities. The present study demonstrates the use of text-mining and semantic analysis of large amount of documents for investigating in business trends in mobile commerce (m-commerce). Particularly with the on-going COVID-19 pandemic and resultant social isolation, m-commerce has become a large technology and business domain with ever growing market potentials. Thus, our study begins with a review of global challenges, opportunities and trends in the development of m-commerce in the world. Next, the study identifies critical technologies and instruments for the full utilization of the potentials in the sector by using the intelligent big data analytics system based on in-depth natural language processing utilizing text-mining, machine learning, science bibliometry and technology analysis. The results generated by the system can be used to produce a comprehensive and objective web of interconnected technologies, trends, drivers and barriers to give an overview of the whole landscape of m-commerce in one business intelligence (BI) data mart diagram.

Triplestores or resource description framework (RDF) stores are purpose-built databases used to organise, store and share data with context. Knowledge extraction from a large amount of interconnected data requires effective tools and methods to address the complexity and the underlying structure of semantic information. We propose a method that generates an interpretable multilayered network from an RDF database. The method utilises frequent itemset mining (FIM) of the subjects, predicates and the objects of the RDF data, and automatically extracts informative subsets of the database for the analysis. The results are used to form layers in an analysable multidimensional network. The methodology enables a consistent, transparent, multi-aspect-oriented knowledge extraction from the linked dataset. To demonstrate the usability and effectiveness of the methodology, we analyse how the science of sustainability and climate change are structured using the Microsoft Academic Knowledge Graph. In the case study, the FIM forms networks of disciplines to reveal the significant interdisciplinary science communities in sustainability and climate change. The constructed multilayer network then enables an analysis of the significant disciplines and interdisciplinary scientific areas. To demonstrate the proposed knowledge extraction process, we search for interdisciplinary science communities and then measure and rank their multidisciplinary effects. The analysis identifies discipline similarities, pinpointing the similarity between atmospheric science and meteorology as well as between geomorphology and oceanography. The results confirm that frequent itemset mining provides an informative sampled subsets of RDF databases which can be simultaneously analysed as layers of a multilayer network.

Cardiovascular disease is the leading cause of death. In recent days, most people are living with cardiovascular disease because of their unhealthy lifestyle and the most alarming issue is the majority of them do not get any symptoms in the early stage. This is why this disease is becoming more deadly. However, medical science has a large amount of data regarding cardiovascular disease, so this data can be used to apply data mining techniques to predict cardiovascular disease at the early stage to reduce its deadly effect. Here, five data mining classification techniques, such as: Naïve Bayes, K-Nearest Neighbors, Support Vector Machine, Random Forest and Decision Tree were implemented in the WEKA tool to get the best accuracy rate and a dataset of 12 attributes with more than 300 instances was used to apply all the data mining techniques to get the best accuracy rate. After doing this research people who are at the early stage of cardiovascular disease or probably going to be a victim can be identified more accurately.

The Energy industry is facing a set of changes. The old grids need to be replaced, alternative energy market is increasing and consumers want more control of their consumption. On the other hand, the ever-increasing pervasiveness of technology together with the smart paradigm, are becoming the reference point of anyone involved in innovation, and energy management issues. In this context, the information that can potentially be made available by technological innovation is obvious. Nevertheless, in order to turn it into better and more efficient decisions, it is necessary to keep in mind three sets of issues: those related to the management of generated data streams , those related to the quality of the data and finally those related to their usability for human decision-maker. In smart grid , large amounts of and various types of data, such as device status data, electricity consumption data, and user interaction data are collected. Then, as described in several scientific papers, many data analysis techniques, including optimization, forecasting, classification and other, can be applied on the large amounts of smart grid big data . There are several techniques, based on Big Data analysis using computational intelligence techniques, to optimize power generation and operation in real time, to predict electricity demand and electricity consumption and to develop dynamic pricing mechanisms. The aim of the chapter is to critically analyze the way Big Data is utilized in the field of Energy Management in Smart Grid addressing problems and discussing the important trends.

PCP65 - KEY CONSIDERATIONS FOR THE COLLECTION OF PATIENT REPORTED OUTCOME (PRO) DATA IN REAL WORLD (RW) STUDIES