Borko Furht

Florida Atlantic University | FAU

With the continuous modernization of water plants, the risk of cyberattacks on them potentially endangers public health and the economic efficiency of water treatment and distribution. This article signifies the importance of developing improved techniques to support cyber risk management for critical water infrastructure, given an evolving threat...

This article describes a teaching strategy that synergizes computing and management, aimed at the running of complex projects in industry and academia, in the areas of civil engineering, physics, geosciences, and a number of other related fields. The course derived from this strategy includes four parts: (a) Computing with a selected set of modern...

This article presents a taxonomy and represents a repository of open problems in computing for numerically and logically intensive problems in a number of disciplines that have to synergize for the best performance of simulation-based feasibility studies on nature-oriented engineering in general and civil engineering in particular. Topics include b...

The execution time of a high performance computing algorithm depends on multiple factors: the algorithm scalability, the chosen hardware, the communication speed between processing elements, etc. This work is based on a hybrid processor consisting of both the control-flow and dataflow hardware, where the control-flow hardware includes manycore arch...

Cyber threats and attacks induced by exploiting advanced heterogeneous technologies to target smart cities worldwide are evolving rapidly. Thus, failing to control these cyber threats undermines the trustworthiness of the transformational projects that aim at making cities more sustainable and livable for their citizens. Although research and opera...

The increased number of cyber-attacks against critical infrastructure, in particular, their vulnerable network-assessable automated control systems, paved the way for new approaches to defining cyber situational awareness and forensic methods for smart cities. This chapter defines the activities required to enforce a sound situational awareness pro...

Facing the socio-economic challenges in urbanization, worldwide governments and industries embrace the smart city concept and establish transformation projects that demonstrate tremendous growth. These projects combine information and communication technologies to engage and integrate citizens, visitors, and business communities into an intelligent...

Cyber-attacks on water facilities, including water treatment plants, water distribution systems, or wastewater utility companies, can cause significant damage and endanger the well-being of citizens. The attacks against water systems have several dimensions, such as physical damage and chemical or biological hazards, which can have social and finan...

Cyber situational awareness is a vital component of a holistic view of cybersecurity. This chapter puts forward a new perspective on sustained cyber situational awareness for smart cities. It explores the methods that build a foundation for analytics-driven cyber situational awareness at different levels. This chapter explores monitoring and attack...

Given the extensive worldwide growth of smart cities, it is intuitive and essential to acknowledge the debilitating and disrupting effects of cyber-attacks on these initiatives. Protecting smart cities from cyber-attacks is a crucial mission for their survival. Although cybersecurity is among the critical challenges for smart cities, examining cybe...

Drowsy drivers cause the most car accidents thus, adopting an efficient drowsiness detection system can alert the driver promptly and precisely which will reduce the numbers of accidents and also save a lot of money. This paper discusses many tactics and methods for drowsy driving warning. The non-intrusive nature of most of the strategies mentione...

Natural Language Processing (NLP) is one of the most captivating applications of Deep Learning. In this survey, we consider how the Data Augmentation training strategy can aid in its development. We begin with the major motifs of Data Augmentation summarized into strengthening local decision boundaries, brute force training, causality and counterfa...

The early detection of the coronavirus disease 2019 (COVID-19) outbreak is important to save people's lives and restart the economy quickly and safely. People's social behavior, reflected in their mobility data, plays a major role in spreading the disease. Therefore, we used the daily mobility data aggregated at the county level beside COVID-19 sta...

Natural Language Processing (NLP) is one of the most captivating applications of Deep Learning. In this survey, we consider how the Data Augmentation training strategy can aid in its development. We begin with the major motifs of Data Augmentation summarized into strengthening local decision boundaries, brute force training, causality and counterfa...

With the continuous modernization of water plants, malicious, often state-sponsored attacks continue to create havoc in such critical realms. Motivated by this, this paper proposes an unsupervised data-driven approach to support cyber forensics in such unique setups. Specifically, the proposed approach aims at inferring and attributing cyber attack...

The early detection of the coronavirus disease 2019 (COVID-19) outbreak is important to save people's lives and restart the economy quickly and safely. People’s social behavior as captured by their mobility data plays a role in spreading the disease. Therefore, we used the daily mobility data aggregated at the county level beside COVID-19 statistic...

This project is funded by the US National Science Foundation (NSF) through their NSF RAPID program under the title “Modeling Corona Spread Using Big Data Analytics.” The project is a joint effort between the Department of Computer & Electrical Engineering and Computer Science at FAU and a research group from LexisNexis Risk Solutions. The novel cor...

This survey explores how Deep Learning has battled the COVID-19 pandemic and provides directions for future research on COVID-19. We cover Deep Learning applications in Natural Language Processing, Computer Vision, Life Sciences, and Epidemiology. We describe how each of these applications vary with the availability of big data and how learning tas...

A modern urban infrastructure no longer operates in isolation, but instead, leverages the latest technologies to collect, process, and distribute aggregated knowledge in order to improve the quality of the provided services and promote the efficiency of resource consumption. This technological development, however, manifests in the form of new vuln...

Abstract In this paper, we comprehensively explain how we built a novel implementation of the Random Forest algorithm on the High Performance Computing Cluster (HPCC) Systems Platform from LexisNexis. The algorithm was previously unavailable on that platform. Random Forest’s learning process is based on the principle of recursive partitioning and a...

In this paper, we developed cloud-based skin lesion diagnosis system using convolutional neural networks, which consists of the following: (a) Deep learning based classifier that processes user submitted lesion images which runs on a server connected to the cloud based database. (b) Deep learning based classifier performs quality checks and filters...

In this chapter we present a program in which the user can embed an image onto another image. The user selects two images, one used as the background, and one to place on top, and can select wherever on the background image to place the second image. As shown in Fig. 10.1, we can select a background image, in this case a TV in Times Square, and emb...

Every chapter in this book includes a demo program to explain the material, the theory behind digital image topics, and provides code that the reader can run and manipulate. Instead of writing command line demo programs with little user interaction, we opted to write programs with a User Interface (UI) that includes essential UI elements such as bu...

The main reasons for compression in multimedia systems are: (1) large storage requirements of multimedia data, (2) relatively slow storage devices which do not allow playing back uncompressed multimedia data in real time, and (3) the network bandwidth which does not allow real-time video data transmission.

The project was completed by the FAU student Connor as part of the Introduction to Image and Video Processing class at Florida Atlantic University taught in Spring 2018.

Steganography is the art of hiding a piece of data within a transferred message. The secret data must be concealed in a way such that anyone observing the message should not notice any artifacts of its concealment. In our case, the message is an image file and the secret piece of data is any file we wish to hide.

In slideshow applications or video editors that are transition animations that reveal the next slide or image in various visual styles which may include fading in and out between the two images. The focus of this chapter is the transition from one image to another over time as can be seen in Fig. 9.2. Transition animations are applied over a period...

So far, we have only dealt with topics involving one or two images. The program demos were mostly about loading an image and performing a task e.g. converting to grayscale or hiding data in an image. With image retrieval, however, our task is to search for images from a large collection or database that are similar, in some manner, to a selected im...

Image is a two-dimensional array of samples or pixels, as illustrated in Fig. 1.1.

The project aims to use the ImGui libraries to create a program with friendly user interface. The project was completed by the FAU student Mila Manastasova as part of the Introduction to Image and Video Processing class at Florida Atlantic University taught in Spring 2018.

In this chapter, we discuss the basics on how to create color histograms for images. A histogram is a graphical representation of the number of pixels in an image. As an example, assume a 10 × 6 pixel image shown in Fig. 4.1. The pixels are one-byte data, and their values are between 0 and 255. The histogram for this simple image is shown in Fig. 4...

JPEG and PNG are some of the most popular digital image file types. Pixel values are compressed with some form of compression in these file, and as a result it is not possible to open a digital image file and directly read the pixel values. The image must be first be decoded, which returns the decompressed pixel values along with other necessary in...

In image processing, detecting change in color between pixels is necessary for tasks like image compression and object recognition. For this chapter, we have a written a program that shows how to compute differences in RGB values of a pixel and its right and bottom neighbors. If the difference is significant, the main pixel is colored red to distin...

The project for this chapter was completed by the FAU student Mila Manastasova as part of the Introduction to Image and Video Processing class at Florida Atlantic University taught in Spring 2018.

Context plays an important role in performance of object detection. There are two popular considerations in building context models for computer vision applications; type of context (semantic, spatial, scale) and scope of the relations (pairwise, high-order). In this paper, a new unified framework is presented that combines multiple sources of cont...

Melanoma is a fatal form of skin cancer when left undiagnosed. Computer-aided diagnosis systems powered by convolutional neural networks (CNNs) can improve diagnostic accuracy and save lives. CNNs have been successfully used in both skin lesion segmentation and classification. For reasons heretofore unclear, previous works have found image segmenta...

Epidemics have disturbed human lives for centuries causing massive numbers of deaths and illness among people and animals. Due to increase in urbanization, the possibility of worldwide epidemic is growing too. Infectious diseases like Ebola remain among the world’s leading causes of mortality and years of life lost. Addressing the significant disea...

In this chapter we briefly describe several case studies of using HPCCC systems in social network analytics.

In this chapter we present the basic terms and concepts in Big Data computing. Big data is a large and complex collection of data sets, which is difficult to process using on-hand database management tools and traditional data processing applications. Big Data topics include the following activities:

As a result of the continuing information explosion, many organizations are experiencing what is now called the “Big Data” problem. This results in the inability of organizations to effectively use massive amounts of their data in datasets which have grown to big to process in a timely manner. Data-intensive computing represents a new computing par...

This paper details the architecture and describes the preliminary experimentation with the proposed framework for anomaly detection in medical wireless body area networks for ubiquitous patient and healthcare monitoring. The architecture integrates novel data mining and machine learning algorithms with modern sensor fusion techniques. Knowing wirel...

Traffic incidents usually imply a great amount of data regarding them. Currently there is a lack of software that can be regarded as efficient incident management visualization. Most incident management systems’ structures make the estimation of the actual road conditions an arduous task. It requires traffic operator to navigate through many tables...

With increasing traffic on arterials and intersections controlled by traffic signals, the problem with delays for road users, specifically during periods of peak hours, escalates. The delays are often a consequence of not efficient operation of the traffic signals on that arterials. Many researchers proposed different analytical and heuristic metho...

The rapid growth of urban population and number of private cars in this modern era, results in increasingly urgent transportation problem in cities throughout the world. Road traffic congestion is an omnipresent problem, which leads to delays, time loss, human stress, energy consumption, environmental pollution etc. In order to decrease traffic con...

This book introduces three applications for effective presentation of complex traffic data on web. These visualization tools can be implemented to facilitate the monitoring, interpretation, estimation and analysis of significant amount of road traffic data: congestion levels on the roads, incidents data, volume per capacity ratio, level of service,...

Vehicle traffic has been an important research issue. Numerous studies have been conducted providing insights from various levels and perspectives. Researchers analyze traffic in terms of speed, flow rate, density, volume, occupancy, congestion, etc.

In this paper, a new framework for scene understanding using multi-modal high-ordered context-model is introduced. Spatial and semantical interactions are considered as sources of context which are incorporated in the model using a single object-scene relevance measure that quantifies high-order object relations. This score is used to minimize sema...

Context plays an important role in performance of object detection. There are two popular considerations in building context models for computer vision applications; type of context (semantic, spatial, scale) and scope of the relations (pairwise, high-order). In this paper, a new unified framework is presented that combines multiple sources of cont...

In this paper we describe the design of an educational smart building and the innovative technologies that were implemented. In January of 2011, Florida Atlantic University opened its new LEED Platinum-Certified “Engineering East” building. The building was designed as both a model of how new technologies can drastically decrease the energy require...

In response to the need to improve road traffic operation, researchers implement advanced technologies and integration of systems and data, and develop state-of-the-art applications to assist traffic engineers. This SpringerBrief introduces three novel Web applications which can be an exceptional resource and a good visualization tool for traffic o...

The objective of this book is to introduce the basic concepts of big data computing and then to describe the total solution of big data problems using HPCC, an open-source computing platform. The book comprises 15 chapters broken into three parts. The first part, Big Data Technologies, includes introductions to big data concepts and techniques; bi...

This paper details the architecture and describes the preliminary experimentation with the proposed framework for anomaly detection in medical wireless body area networks for ubiquitous patient and healthcare monitoring. The architecture integrates novel data mining and machine learning algorithms with modern sensor fusion techniques. Knowing wirel...

This chapter provides an overview of commercial solutions—developed by either automobile manufacturers or independent companies—whose goals are to increase driver’s safety and detect potentially dangerous driving situations that may have been caused by driver drowsiness.

This chapter presents an overview of the research aspects associated with the development of driver drowsiness detection solutions, particularly vehicle-mounted solutions that monitor the driver?s head and face for behavioral signs of potential drowsiness, such as nodding, yawning, or blinking. It summarizes relevant technologies, popular algorithm...

This chapter provides an overview of driver drowsiness detection (DDD) and measurement methods and organizes them by category. The five main categories are: subjective, physiological, vehicle-based, behavioral, and hybrid. Most DDD systems being developed today rely on either vehicle-based measures?notably the steering wheel movement (SWM) and the...

This chapter provides examples of recent research work on driver drowsiness detection solutions. The systems and methods discussed in this chapter complement the commercial solutions surveyed in Chap. 3. The chapter also includes highlights of the authors’ ongoing work on the topic.

In order to see how mobile virtualization affects the BYOD user, a pilot was done with Divide from Enterproid, one of the mobile virtualization technologies described previously that is based on a application container approach. The pilot was run for 12 weeks with over 1,100 registered users out of which 817 were activated. Users were all employees...

In order to achieve increased adoption and sustainability “bring your own device” (BYOD) schemes within the enterprise, mobile virtualization is rapidly becoming a very attractive choice because it provides both employee and enterprise with flexibility while addressing the privacy concerns of the user and meeting the organizations security requirem...

The explosion of mobile devices in the consumer space has been quite a disruptor for the mobile enterprise where corporate managed platforms are well defined, well contained and fairly secure. However, now with the emergence of the consumer mobile devices from Apple iOS and Google Android, the enterprise has been forced to make functional tradeoffs...

A way to help analyze which system is most appropriate for your environment is to do a comparative analysis of the various solutions available. Here we compare four solutions: Divide from Enterproid, Horizon Mobile from VMWare, BlackBerry Balance from RIM and Good Dynamics from Good Technology. In order to analyze and understand these various solut...

In the previous chapter we presented a case study on how mobile virtualization affects applications from the user perspective where the results were directly related to the user’s perception of performance, usability and security. In this chapter, through benchmark analysis, the effects of three mobile virtualization technologies are compared to th...

An agile, lightweight, but secure extensible hybrid application container and deployment mechanism for mobile devices has the potential to provide improved cross platform support, reduced development lifecycle time and a consistent application security model within large organizations. Such an architecture can provide a set of security and mobile d...

There exists a multitude of standards with regards to health information systems (HIS) and the electronic exchange of commercial transactions containing private data that must be used amongst various service providers to adequately perform their duties to patients. The evolution of health information systems has been guided by business interests as...

This book presents effective ways to partition mobile devices such that the enterprise system access and its information are completely separated from the personal information. For those using mobile devices for personal and business purposes, the ability to keep the data secure and separate is critical. The applications for security in smart platf...

Managing Information Technology (IT) assets in data centers is a time consuming and error prone process. IT personnel typically identify misplaced assets manually by cross checking and visually inspecting assets. An automated way of keeping track of assets using portable devices reduces human error and improves productivity. The proposed asset mana...

Hospital readmission is an important quality of care indicator. It reflects challenges in quality of in-patient care and the difficulty of coordination of care after the transition back into the community. It is also a significant financial burden, especially as it relates to Medicare and Medicaid costs now and into the future. Chronic Obstructive...

Increasing elderly populations, medical facility under-staffing, and increased governmental spending on healthcare have created a shaky climate which could ultimately lead to bankrupting government healthcare programs and generally lower qualities of healthcare for all individuals. This chapter proposes a secure and reliable web-based architecture...

This chapter discusses the integration between theHealth Record Systems and Patient Record System. The chapter also highlights the importance of a Patient CentricHealth Record system. Such systems can empower patients to participate in improving health care quality. It would also provide an economically viable solution to the need for better health...

The invention of high data connectivity on mobile devices has opened the doors of innovative applications in healthcare and medical technologies. The current generations of smart phones are considered as handheld computers rather than as phones. Smart phones have advantages like continuous uninterrupted data stream, powerful computing power, portab...

Wireless Sensor Networks are vulnerable to a plethora of different fault types and external attacks after their deployment. We focus on sensor networks used in healthcare applications for vital sign collection from remotely monitored patients. These types of personal area networks must be robust and resilient to sensor failures as their capabilitie...

Wireless Sensor Networks are vulnerable to a plethora of different fault types and external attacks after their deployment. We focus on sensor networks used in healthcare applications for vital sign collection from remotely monitored patients. These types of personal area networks must be robust and resilient to sensor failures as their capabilitie...

An agile, lightweight, but secure extensible hybrid application container and deployment mechanism for mobile devices has the potential to provide improved cross platform support, reduced development lifecycle time and a consistent application security model within large organizations. We demonstrate how such an architecture can provide a set of se...

Various implementations of wireless sensor networks (i.e. personal area-, wireless body area- networks) are prone to node and network failures by such characteristics as limited node energy resources and hardware damage incurred from their surrounding environment (i.e. flooding, forest fires, a patient falling). This may jeopardize their reliabilit...

In this paper we present work on exploiting visual temporal masking phenomenon applied to video compression. Our results show that it is possible to reduce bitrate of the compressed video sequence without affecting subjective quality and quality of experience (perceptually lossless). The principles we present here are applicable to all modern hybri...

In current mobile system environment there is a huge gap between the personal smart phone and the enterprise smart phone due to the issues related to security, enterprise policies and freedom of use. In the current environment, data-plans on mobile systems have become so prevalent that the rate of adaptation of data plan for the current customers h...

Adaptive streaming over Hyper-Text Transport protocol (HTTP) is the new trend in video delivery on the Internet and is expected to be supported by consumer electronic devices such as Blu-ray players and DVRs. Proprietary solutions have been around for a couple of years and standardization efforts are entering the final stage. In order to make this...

As a General Co-Chair of the 2012 International Conference in Information Science and Applications, it is my great honor to welcome you and wish you both, professional success at the conference, and a great time in the beautiful city of Seoul. In the new global economy, it is a challenge to discover innovative technologies and find new directions i...

Adaptive video streaming over HTTP is fast becoming a preferred way for delivering on-demand as well as live video service. The MPEG committee is finalizing a standard for Dynamic Adaptive Streaming over HTTP (DASH) and there is significant industry interest in this solution. DASH assumes/specifies MPEG AVC for content delivery. We analyze the use...

We evaluate the impact of content encoding and present an improved encoding scheme for preparation of video content for adaptive streaming over HTTP. Current solutions are content agnostic and do not take advantage of frame level information such as scene changes. Experiments show that by using our model we can achieve savings in bitrate of up to 1...