9^th International Conference on Big Data Analysis and Data Mining August 03-04, 2022 Rome, Italy

Biography:

Mehran Dizbadi is a researcher at the Faculty of Plastics Engineering and Surveying, University of Applied Sciences Wurzburg-Schweinfurt (FHWS), Bavaria, Germany

Abstract:

Rapid and uncontrolled expansion of cities has led to unplanned aerial development. In this way, modeling and predicting the urban growth of a city helps decision-makers. In this study, the aspect of sustainable urban development has been studied for the city of Mashhad. In general, the prediction of urban aerial development is one of the most important topics of modern town management. In this research, using the Cellular Automaton (CA) model and perceptron neural network method with satellite data developed for geo data of Geographic Information Systems (GIS) and presenting a simple and powerful model, a simulation of complex urban processes has been done. In finally our accuracy has been better compared to other researches that have been done in this field and we have slightly improved and optimize the final results approximately %92.1.

Keywords: Urban Modeling, sustainable development, Fuzzy Cellular Automaton, Geo-Information System. Perceptron neural network, Landsat 

Biography:

Mekranfar Zohra done Engineer studies at space technology center; I got a master’s degree specializing in geographic information system. I am mainly interested in data mining and spatial olap. I use different techniques of spatial information system and solap. I have ease with data warehouse, and during my work I took a lot of interest in geomatics. In addition, I have been able to use several tools, through GIS software such as ArcGis and QGIS

Abstract:

Geographic Information Systems (GIS) current ones stand out as remarkable tools for the processing and analysis of spatially referenced data. However, they are difficult to use as an efficient decision support tools exploiting this spatial dimension. Their limits are established when it comes to aggregating several multidimensional criteria in the analysis process. This is in a context that approaches based on Data mining, Data Warehouse and "On-Line Analytical Processing" (OLAP) all seem appropriate to better characterize information related to the territory. The OLAP technology, which combines both bases multidimensional analysis and the concepts of the data mining, provides powerful tools allowing the highlighting inductions and information not obvious by the traditional tools. However, these OLAP tools become more complex in the presence of the spatial dimension. The integration of OLAP with a GIS is the future solution for geographic and spatial information. A necessity for the Developing of data mining of spatial data requires structuring of a Spatial Data Warehouse (SDW). This SDW must be easily usable by GIS and by tools Offered by an OLAP system. The work aims at the development of methods resulting from Analysis more adapted to problems of multidimensional spatial analysis. We present in this paper an application made for generating a SDW from geodatabase, based in a GIS-dominating solution. This work is a part of a project for developing and implementing a SOLAP solution in a spatial data mining intelligent Process. The implementation of the application, we opted for the creation and update of a Spatial Data Warehouse (SDW) comparable to a layer of information in a GIS system. This approach allows us more readability and more efficiency in the validation and implementation of SDW.

Biography:

Rafael Diniz is Computer Scientist (UNICAMP) and holds masters in Informatics from PUC-Rio and PhD from University of Brasilia. Has experience in the area of digital TV and radio (broadcasting), hypermedia and multimedia systems, computer vision, quality assessment of 2D and volumetric video and electromagnetic spectrum management. He is a Member of the Telemidia Lab at PUC-Rio (since 2013) and the GPDS (Digital Signal Processing Group) at University of Brasilia (since 2016).

Abstract:

The new visual immersive media formats provide a 3D visual representation of real objects and scenes. In this new visual format, objects can be captured, compressed, transmitted and visualized in real-time not anymore as a flat 2D image, but as 3D content. This new dimension of image capture is easily possible given the introduction of affordable yet powerful depth (or range) sensors. One of the most popular formats for immersive media is Point Cloud (PC), which is composed by points with 3 geometry coordinates plus color information, and sometimes, other information like reflectance and transparency. The proposed work considers the introduction of novel PC feature extractors [Figure 1] which are obtained by using both color and geometry information of a given scene or selected volumetric element of a larger object or scene. Initially, these feature descriptors were design for the purpose of objective quality assessment of volumetric images, but they can also be used to provide valuable information of the volumetric content. The use of PCs as input for machine learning algorithms is showing potential in providing greater accuracy for many types of machine learning algorithms for computer vision. The proposed descriptors are based on local-neighborhood luminance and surface geometry distances among the volumetric elements (voxels). The joint use of features based on color texture and geometry information is also proposed, and presents a better correlation to the Human Vision System (HVS) when such features are used as quality estimation.

Biography:

Mohamed A. Hamada, PhD and Associate professor in Information system, Information Systems Department, IITU, Almaty, Kazakhstan

Abstract:

Nowadays Big Data are becoming a vital instrument for many different disciplines especially for the environmental and ecosystems aspects, it considers a new way of thinking, whereas big data analytics and data mining are organizing and analyzing large sets of data to generate and discover new patterns and themes that can solve issues and challenges arises in the society. The main purpose of this speech is to clarify the evidential role of big data analytics and data mining in business sustainability achievement. This objective has achieved through developing a big data analytics framework to support a large scale of business organization to achieve its business sustainability and market survival, this framework is based on the modern data mining algorithms such as regression and classification

Biography:

Brian Ngac is Deputy to the Vice President of Digital Engineering Research & Development Programs at Parsons Corporation’s Defense & Intelligence Unit, and a PhD Candidate (ABD) at George Mason University’s College of Engineering & Computing. He holds 12 internationally recognized cyber security and management certifications including the C|CISO, CISSP, ISSMP, CISM, and PMP. His areas of expertise are in cyber security, digital engineering (RDT&E), and business process improvement (solving business challenges with technology solutions). His research focus are in cyber executive management, expert crowdsourcing, and decision analytics. The ultimate goal of Brian’s research endeavors is to publish rigorous papers that are impactful to the area of cyber security management so that his findings will be read, understood, shared, and practiced by cyber professionals, managers, executives, and leaders. He has also developed an experiential learning course for students to work on real projects with real clients prior to their graduation

Abstract:

The cyber security environment, its threats, and its defense strategies are constantly changing. Educational programs and their curriculum are known to be slowing changing and at times out-of-date, resulting in content that may not be as relevant to their students and the industry [1]. This presentation will 1– present an overview of the curriculum development process when using curriculum committees and their hindrance, 2 – describe the concept of crowdsourcing and its benefits when using domain experts, 3 – propose the Curriculum Development using Crowdsourcing Framework (CDC-F) (Figure 1) to integrate expert crowdsourcing into parts of the curriculum development process (specifically the identification of industry-relevant topics and sub-topics for further curriculum content development), 4 – present the process and results of an experiment utilizing the CDC-F, and 5 – discuss how the Parsons Digital Engineering Framework (PDEF) can utilize the expert crowd’s inputs to optimize a relevant list of Topics and Subtopics for the curriculum development decision-makers [2,3]. While this particular experiment was a smaller effort consisting of around 30 domain experts over two rounds of crowdsourcing, it yielded many semi-structure and unstructured inputs that needed to be analyzed, aggregated, categorized, and decided on [4]. Overall, it was found that including domain experts in the curriculum development process benefited the curriculum development effort in identifying more relevant domain topics – which were not initially identified by the curriculum owner [5]. It was also determined that implementing the CDC-F through a more automated effort is necessary to scale the effort for efficiency purposes. This may be through using technologies like PDEF or Argupedia to better retrieve inputs, categorize and aggregate the inputs, as well as present visualizations for easier decision making [6].

Biography:

Mahdi Fahmideh is a senior lecturer at the University of Southern Queensland (USQ). He received a PhD degree in Information Systems from the Business School of University of New South Wales (UNSW), Sydney, Australia. Mahdi’s research outcomes, which lie at the intersection of Internet-based computing technologies, can be in the form of conceptual models, system development methodologies, and decision-making frameworks. Before joining academia, Mahdi has worked as a software engineer in different industry sectors including accounting, insurance, and publishing

Abstract:

Reaping the benefits of blockchain technologies to empower information systems has received increasing interest among scholars and practitioners. The multi-faceted nature of blockchain technologies as sociotechnical artefacts entails the adoption of Information System Development (ISD) methods (a.k.a software engineering methods) that support the systematic implementation of systems leveraging blockchain smart contracts. In line with this, there is a growing awareness that the end-to-end development lifecycle for this class of systems requires new innovative guiding methods to bind together technical programming models, platforms (e.g., Ethereum), and technologies (e.g., Bitcoin scripting languages). We present characterize the development of blockchain based systems on the key aspects of theoretical foundations, processes, models, and roles. Based on these aspects, we present a rich repertoire of development tasks, design principles, models, roles, challenges, and resolution techniques. The outcome of this research provides a consolidated body of knowledge about current blockchain based system development and under pins a starting point for further research in this field.

Biography:

Jie You has his expertise in machine learning and big data technologies, and particularly applications of artificial intelligence in autonomous driving. His reinforcement-learning based auto-labeling and AI computation framework creates new pathways for facilitating algorithmic researches and improving efficiency and accuracy of autonomous driving controlling strategies. He has built this framework and relevant algorithms after years of experience in research, evaluation, and development both in research institutions and enterprises. Jie You received his PhD from Heidelberg University and M.S degree from Huazhong University of Science & Technology. He is now working as Chief Technology Officer in Mingshang Technologies Ltd. in China. Mingshang Technologies was founded in 2004, which provides smart devices for vehicles and autonomous driving solutions. Mingshang has customers from China, Russia, USA and Southeast Asia, including GMC, Ford, BYD, Dongfeng, SANYI, and Caterpillar etc.

Abstract:

Data labeling is crucial in database and machine learning applications. Traditional methods rely heavily on humans to engineer labels. However, human works are highly costly for large datasets and even unaffordable in some special cases which require people to have multiple-domain knowledge’s. Additionally, the quality of human labeling largely relies on individual’s professional and attentiveness that may entail biases to the labels. In autonomous-driving algorithm research, the datasets are so massively huge that only relying on human labeling is neither economically nor practically feasible. In this research we design a reinforcement-learning based auto labeling framework which achieves online data-labeling while vehicles are driving (with driver or driverless). Firstly, we reframe the problem of data labeling as a semantic segmentation problem which maximizes specific goals. Then we propose a deep reinforcement-learning procedure with multi-objective rewarding functions designed, which determines the semantic segmentation strategy and the labeling process, achieving long-term goals of maximizing the labels precision for training autonomous driving algorithms. This framework is deployed on fleets of vehicles which distributedly implement the deep reinforcement-learning agent to compete the labelling tasks among which the ones optimize the objectives are selected. By exploiting this auto labelling framework in the development of autonomous driving systems, we reduce the cost by more than 50%, while achieving 5%-25% higher accuracy.

Biography:

Boubakeur Annane has received his PhD in Computer Science at University Utara Malaysia, Malaysia, during 2016-2020. Currently, he is working as Assistant Professor in Ferhat Abbas Setif-1 University, Setif, Algeria. Meanwhile, He is an online Tutor at Unicaf University, Cyprus. He is a member of the Network and Distributed System Laboratory and he is a member of the IEEE Computer Society. Dr. Annane has conducted various projects on cloud-based data security such as “Data Breach Prevention Model for Securing Data Privacy and Confidentiality on Cloud Computing Using Enhanced AES. FRGS research grant, University Utara Malaysia (Code S/O:14174) during 01/01/2020 until 30/06/2020”. He has published several articles for international journals and conferences. He has served as an expert reviewer for journals and conferences like “Internet Applications, Protocols, and Services (Netapps2020)”. His research interests are Mobile Cloud Computing, Cloud Computing, Data Security and Privacy, Virtualization, Network and Distributed System Security.

Abstract:

Nowadays, advancements in health technology have characterized modern illness diagnosis methods in the global healthcare system. The World Health Organization (WHO) has received a large number of respiratory disease patients in recent years, resulting in billions of Personal Health Records (PHRs) being created and transmitted via Cloud with the aim taking precautions and restricting the disease. The transmission of PHR through Internet has generated significant security and privacy concerns for the global health care system. Furthermore, the potential change in the patient's health situation at any time needs immediate and secure healthcare access. For robust authentication and optimal confidentiality, it is necessary to reinforce the access control policies. As a result, various security schemes have been developed but lack efficiency while deploying cloud-based e-health applications, where the Cloud providers are honest but curious and may obtain sensitive data without the consent of users. In this research, we present anew security scheme for e-health mobile applications based on hybrid Cipher text-Policy Attribute Access Control, Block chain, and ContextAwareness (Cx-CP-ABE). The approach is based on reinforcing security policies pertaining to the continuous evolution of the patient’s state and context changes and the improvement of the patient's data confidentiality. The proposed security scheme has been evaluated under various patient contexts, and its performance has been measured in terms of sensitivity, number of health attributes, and execution time.

Biography:

Dr Sunil K. Singh, Professor is expertise in the areas of High-Performance Computing, Linux/Unix, Data Mining, Internet of Things, Machine Learning, Computer Architecture & Organization, Embedded System and Computer Network. He has published more than 90 research papers in reputed international/national journals and conferences. He has also received 01 patent granted and 02 patents published, and some are in pipeline too. He is also member of the expert advisory committee working on various book writing projects (definitional directory and technological glossary) of CSTT, Ministry of Education, Government of India, Delhi.

Abstract:

Sustainable Smart Cities’ idea and business resilience concepts are attracting significant attention from governments, academicians, practitioners and international institutions across the world, as a response to future environmental challenges, economic issues as well as increased urbanization. Smart City initiatives driven by technological progress is said to have positive impact on quality of life by preserving the natural environmental resources. It is expected that there will be about 10 billion people in urban cities by 2030 worldwide. With increasing global population, the major chunk of problems pertains to difficulties faced by the Public Authorities of the respective nations in managing the municipalities and cities. Managing urban areas remains a challenging task in the face of limited resources of urban areas with this ever-growing shift from rural to urban locality. Need of providing urban systems a liveable future with better quality of life therefore drives efforts towards building the cities smarter and economic systems more sustainable. Smart cities not only aim at improving the infrastructure, communication, and services for better outcome but also at responding more efficiently, effectively and dynamically to the urban sustainability issues. The concept of "smart cities" can help cities growing more resilient and responsive in response to disasters and crises. Smart city solutions is also expected to bring significant business prospects, However, smart cities may disrupt some of existing businesses because digital solution might significantly change the value chain and the cities’ landscape. Better quality, cost, and efficiency expectations from customers may require mass customization and adaptability almost in all areas ranging from public transportation to healthcare. In fact, socio-economic consequences of recent pandemic and resultant global crises have necessitated the adoption of digital tools and emerging key technologies. This has also generated a new stimulus for business organizations for embracing resilience perspective. Resilience as a virtue or strength of an organization is built up through a conducive far-sighted management philosophy that can look beyond the present, remains prepared for the worst scenario and tides over any crisis within a reasonable time. In this regard, recently developed frontier technologies like block chain, artificial intelligence (AI) and Industrial Internet of things (IoT) have become viable which means capable of meeting global urban demands and contributing towards resilience building.