Information, Volume 11, Issue 2 (February 2020) – 69 articles

Data augmentation is a commonly used technique for increasing both the size and the diversity of labeled training sets by leveraging input transformations that preserve corresponding output labels. In computer vision, image augmentations have become a common implicit regularization technique to combat overfitting in deep learning models and are ubiquitously used to improve performance. While most deep learning frameworks implement basic image transformations, the list is typically limited to some variations of flipping, rotating, scaling, and cropping. Moreover, image processing speed varies in existing image augmentation libraries. We present Albumentations, a fast and flexible open source library for image augmentation with many various image transform operations available that is also an easy-to-use wrapper around other augmentation libraries. We discuss the design principles that drove the implementation of Albumentations and give an overview of the key features and distinct capabilities. Finally, we provide examples of image augmentations for different computer vision tasks and demonstrate that Albumentations is faster than other commonly used image augmentation tools on most image transform operations. Full article

In the modern business environment, characterized by rapid technological advancements and globalization, abetted by IoT and Industry 5.0 phenomenon, innovation is indispensable for competitive advantage and economic growth. However, many organizations are facing problems in its true implementation due to the absence of a practical innovation management framework, which has made the implementation of the concept elusive instead of persuasive. The present study has proposed a new innovation management framework labeled as “Absolute Innovation Management (AIM)” to make innovation more understandable, implementable, and part of the organization’s everyday routine by synergizing the innovation ecosystem, design thinking, and corporate strategy to achieve competitive advantage and economic growth. The current study used an integrative literature review methodology to develop the “Absolute Innovation Management” framework. The absolute innovation management framework links the innovation ecosystem with the corporate strategy of the firm by adopting innovation management as a strategy through design thinking. Thus, making innovation more user/human-centered that is desirable by the customer, viable for business and technically feasible, creating both entrepreneurial and customer value, and boosting corporate venturing and corporate entrepreneurship to achieve competitive advantage and economic growth while addressing the needs of IoT and Industry 5.0 era. In sum, it synergizes innovation, design thinking, and strategy to make businesses future-ready for IoT and industry 5.0 revolution. The present study is significant, as it not only make considerable contributions to the existing literature on innovation management by developing a new framework but also makes the concept more practical, implementable and part of an organization’s everyday routine. Full article

The Treemap is one of the most relevant information visualization (InfoVis) techniques to support the analysis of large hierarchical data structures or data clusters. Despite that, Treemap still presents some challenges for data representation, such as the few options for visual data mappings and the inability to represent zero and negative values. Additionally, visualizing high dimensional data requires many hierarchies, which can impair data visualization. Thus, this paper proposes to add layered glyphs to Treemap’s items to mitigate these issues. Layered glyphs are composed of N partially visible layers, and each layer maps one data dimension to a visual variable. Since the area of the upper layers is always smaller than the bottom ones, the layers can be stacked to compose a multidimensional glyph. To validate this proposal, we conducted a user study to compare three scenarios of visual data mappings for Treemaps: only Glyphs (G), Glyphs and Hierarchy (GH), and only Hierarchy (H). Thirty-six volunteers with a background in InfoVis techniques, organized into three groups of twelve (one group per scenario), performed 8 InfoVis tasks using only one of the proposed scenarios. The results point that scenario GH presented the best accuracy while having a task-solving time similar to scenario H, which suggests that representing more data in Treemaps with layered glyphs enriched the Treemap visualization capabilities without impairing the data readability. Full article

Deep learning models contributed to reaching unprecedented results in prediction and classification tasks of Artificial Intelligence (AI) systems. However, alongside this notable progress, they do not provide human-understandable insights on how a specific result was achieved. In contexts where the impact of AI on human life is relevant (e.g., recruitment tools, medical diagnoses, etc.), explainability is not only a desirable property, but it is -or, in some cases, it will be soon-a legal requirement. Most of the available approaches to implement eXplainable Artificial Intelligence (XAI) focus on technical solutions usable only by experts able to manipulate the recursive mathematical functions in deep learning algorithms. A complementary approach is represented by symbolic AI, where symbols are elements of a lingua franca between humans and deep learning. In this context, Knowledge Graphs (KGs) and their underlying semantic technologies are the modern implementation of symbolic AI—while being less flexible and robust to noise compared to deep learning models, KGs are natively developed to be explainable. In this paper, we review the main XAI approaches existing in the literature, underlying their strengths and limitations, and we propose neural-symbolic integration as a cornerstone to design an AI which is closer to non-insiders comprehension. Within such a general direction, we identify three specific challenges for future research—knowledge matching, cross-disciplinary explanations and interactive explanations. Full article

Sophisticated and high performance embedded systems are present in an increasing number of application domains. In this context, formal-based design methods have been studied to make the development process robust and scalable. Models of computation (MoC) allows the modeling of an application at a high abstraction level by using a formal base. This enables analysis before the application moves to the implementation phase. Different tools and frameworks supporting MoCs have been developed. Some of them can simulate the models and also verify their functionality and feasibility before the next design steps. In view of this, we present a novel method for analysis and identification of possible automation approaches applicable to embedded systems design flow supported by formal models of computation. A comprehensive case study shows the potential and applicability of our method. Full article

The number of damaging cyberattacks is increasing exponentially due in part to lack of user awareness of risky online practices, such as visiting unsafe websites, ignoring warning messages, and communicating with unauthenticated entities. Although research has established the role that game-based learning can play in cognitive development and conceptual learning, relatively few serious mobile games have been developed to educate users about different forms of cyberattack and ways of avoiding them. This paper reports the development of an effective augmented reality (AR) game designed to increase cybersecurity awareness and knowledge in an active and entertaining way. The Cybersecurity Awareness using Augmented Reality (CybAR) game is an AR mobile application that teaches not only cybersecurity concepts, but also demonstrates the consequences of actual cybersecurity attacks through feedback. The design and evaluation of the application are described in detail. A survey was conducted to verify the effectiveness of the game received positive responses from 91 participants. The results indicate that CybAR is useful for players to develop an understanding of cybersecurity attacks and vulnerabilities. Full article

Traffic lights have been used for decades to control and manage traffic flows crossing road intersections to increase traffic efficiency and road safety. However, relying on fixed time cycles may not be ideal in dealing with the increasing congestion level in cities. Therefore, we propose a new Adaptive Traffic Light Control System (ATLCS) to assist traffic management authorities in efficiently dealing with traffic congestion in cities. The main idea of our ATLCS consists in synchronizing a number of traffic lights controlling consecutive junctions by creating a delay between the times at which each of them switches to green in a given direction. Such a delay is dynamically updated based on the number of vehicles waiting at each junction, thereby allowing vehicles leaving the city centre to travel a long distance without stopping (i.e., minimizing the number of occurrences of the ‘stop and go’ phenomenon), which in turn reduces their travel time as well. The performance evaluation of our ATLCS has shown that the average travel time of vehicles traveling in the synchronized direction has been significantly reduced (by up to 39%) compared to non-synchronized fixed time Traffic Light Control Systems. Moreover, the overall achieved improvement across the simulated road network was 17%. Full article

This paper examines how social media are affecting Japanese civil society organizations, in relation to efficacy and political participation. Using data from the 2017 Japan Interest Group Study survey, we analyzed how the flow of information leads to the political participation of civil society organizations. The total number of respondents (organizations) were 1285 (942 organizations in Tokyo and 343 from Ibaraki). In the analysis of our survey we focused on the data portion related to information behavior and efficacy and investigated the meta-cognition of efficacy in lobbying among civil society organizations in Tokyo and Ibaraki. We found that organizations that use social media were relatively few. However, among the few organizations that use social media, we found that these organizations have a much higher meta-cognition of political efficacy in comparison to those that do not use social media. For instance, social media usage had a higher tendency of having cognition of being able to exert influence upon others. We also found that organizations that interact with citizens have a higher tendency to use social media. The correspondence analysis results point towards a hypothesis of how efficacy and participation are mutually higher among the organizations that use social media in Japan. Full article

The application of the General Data Protection Regulation (GDPR) 2016/679/EC, the Regulation for the protection of personal data, is a challenge and must be seen as an opportunity for the redesign of the systems that are being used for the processing of personal data. An unexplored area where systems are being used to collect and process personal data are the e-Participation environment. The latest generations of such environments refer to sociotechnical systems based on the exploitation of the increasing use of Social Media, by using them as valuable tools, able to provide answers and decision support in public policy formulation. This work explores the privacy requirements that GDPR imposes in such environments, contributing to the identification of challenges that e-Participation approaches have to deal with, with regard to privacy protection. Full article

Aiming at the problem that the assembly body model is difficult to classify and retrieve (large information redundancy and poor data consistency), an assembly body retrieval method oriented to key structures was presented. In this paper, a decision formal context is transformed from the 3D structure model. The 3D assembly structure model of parts is defined by the adjacency graph of function surface and qualitative geometric constraint graph. The assembly structure is coded by the linear symbol representation of compounds in chemical database. An importance or cohesion as the weight to a decision-making objective on the context is defined by a rough set method. A weighted concept lattice is introduced on it. An important formal concept means a key structure, since the concept represents the relations between parts’ function surfaces. It can greatly improve the query efficiency. Full article

In the development of highly automated driving systems (L3 and 4), much research has been done on the subject of driver takeover. Strong focus has been placed on the takeover quality. Previous research has shown that one of the main influencing factors is the complexity of a traffic situation that has not been sufficiently addressed so far, as different approaches towards complexity exist. This paper differentiates between the objective complexity and the subjectively perceived complexity. In addition, the familiarity with a takeover situation is examined. Gold et al. show that repetition of takeover scenarios strongly influences the take-over performance. Yet, both complexity and familiarity have not been considered at the same time. Therefore, the aim of the present study is to examine the impact of objective complexity and familiarity on the subjectively perceived complexity and the resulting takeover quality. In a driving simulator study, participants are requested to take over vehicle control in an uncritical situation. Familiarity and objective complexity are varied by the number of surrounding vehicles and scenario repetitions. Subjective complexity is measured using the NASA-TLX; the takeover quality is gathered using the take-over controllability rating (TOC-Rating). The statistical evaluation results show that the parameters significantly influence the takeover quality. This is an important finding for the design of cognitive assistance systems for future highly automated and intelligent vehicles. Full article

Most studies on users’ perception of highly automated driving functions are focused on first contact/single usage. Nevertheless, it is expected that with repeated usage, acceptance and usage of automated driving functions might change this perception (behavioural adaptation). Changes can occur in drivers’ evaluation, in function usage and in drivers’ reactions to take-over situations. In a driving simulator study, N = 30 drivers used a level 3 (L3) automated driving function for motorways during six experimental sessions. They were free to activate/deactivate that system as they liked and to spend driving time on self-chosen side tasks. Results already show an increase of experienced trust and safety, together with an increase of time spent on side tasks between the first and fourth sessions. Furthermore, attention directed to the road decreases with growing experience with the system. The results are discussed with regard to the theory of behavioural adaptation. Results indicate that the adaptation of acceptance and usage of the highly automated driving function occurs rather quickly. At the same time, no behavioural adaptation for the reaction to take-over situations could be found. Full article

Orthogonal frequency division multiplexing (OFDM) is a widely used technology for wireless broadband communications. However, it also suffers from some drawbacks. One of the critical limitations is the problem of high peak-to-average power ratio (PAPR), which causes distortions of some nonlinear components such as power amplifiers. A number of techniques have been proposed to reduce the PAPR of OFDM signals, among which the clipping-based methods have gained a lot of attention due to the effective PAPR reduction and simplicity of implementation. This paper proposes a novel clipping-based method to reduce the PAPR of OFDM signals. Based on the recently proposed clipping noise compression (CNC) method, the proposed scheme introduces a preset normalization factor to replace the calculation of average amplitude of clipping noise in the original CNC method during compression processing. Comparative simulations were carried out, and the results exhibit that the proposed method achieves better bit-error-ratio performance with equal level of PAPR reduction compared to the original CNC method. Full article

Perfect information about an environment allows a robot to plan its actions optimally, but often requires significant investments into sensors and possibly infrastructure. In applications relevant to human–robot interaction, the environment is by definition dynamic and events close to the robot may be more relevant than distal ones. This suggests a non-trivial relationship between sensory sophistication on one hand, and task performance on the other. In this paper, we investigate this relationship in a simulated crowd navigation task. We use three different environments with unique characteristics that a crowd navigating robot might encounter and explore how the robot’s sensor range correlates with performance in the navigation task. We find diminishing returns of increased range in our particular case, suggesting that task performance and sensory sophistication might follow non-trivial relationships and that increased sophistication on the sensor side does not necessarily equal a corresponding increase in performance. Although this result is a simple proof of concept, it illustrates the benefit of exploring the consequences of different hardware designs—rather than merely algorithmic choices—in simulation first. We also find surprisingly good performance in the navigation task, including a low number of collisions with simulated human agents, using a relatively simple A*/NavMesh-based navigation strategy, which suggests that navigation strategies for robots in crowds need not always be sophisticated. Full article

Access control has become problematic in several organizations because of the difficulty in establishing security and preventing malicious users from mimicking roles. Moreover, there is no flexibility among users in the participation in their roles, and even controlling them. Several role-based access control (RBAC) mechanisms have been proposed to alleviate these problems, but the security has not been fully realized. In this work, however, we present an RBAC model based on blockchain technology to enhance user authentication before knowledge is accessed and utilized in a knowledge management system (KMS). Our blockchain-based system model and the smart contract ensure that transparency and knowledge resource immutability are achieved. We also present smart contract algorithms and discussions about the model. As an essential part of RBAC model applied to KMS environment, trust is ensured in the network. Evaluation results show that our system is efficient. Full article

Digital image authentication is an extremely significant concern for the digital revolution, as it is easy to tamper with any image. In the last few decades, it has been an urgent concern for researchers to ensure the authenticity of digital images. Based on the desired applications, several suitable watermarking techniques have been developed to mitigate this concern. However, it is tough to achieve a watermarking system that is simultaneously robust and secure. This paper gives details of standard watermarking system frameworks and lists some standard requirements that are used in designing watermarking techniques for several distinct applications. The current trends of digital image watermarking techniques are also reviewed in order to find the state-of-the-art methods and their limitations. Some conventional attacks are discussed, and future research directions are given. Full article

The pace and scale of the digitalization of today’s global information society open up new opportunities for business. At the same time, they set new challenges for business owners and managers in the field of marketing. Given this fact, the purpose of the study was to present the impact of digitalization on the marketing activity of the enterprise in the field of services by promoting the use of online sales via electronic distribution channels, social networks, and mobile applications. A comparative system of estimating the parameters of the influence of digitalization on the marketing activity of the enterprise was proposed as a confirmation of this impact. Based on the developed “tree of goals,” the dynamics of the digitalization of services were projected and the prospects of development of this sphere of activity were outlined. For testing the proposed methodology, the railway passenger transportation company (JSC “Ukrzaliznytsia”) was chosen as the object of the research. Research methods used in the study include: (1) statistical; (2) SWOT analysis; (3) systematization, comparative, and structural-dynamic analysis; and (4) an expert survey. As a result of revealing the impact of individual elements of digitalization on the level of marketing activity, the number of recommendations regarding the development of digitalization of electronic ticket sales services and their accounting for enterprises dealing with railway passenger transportation were proposed. Full article

fastai is a deep learning library which provides practitioners with high-level components that can quickly and easily provide state-of-the-art results in standard deep learning domains, and provides researchers with low-level components that can be mixed and matched to build new approaches. It aims to do both things without substantial compromises in ease of use, flexibility, or performance. This is possible thanks to a carefully layered architecture, which expresses common underlying patterns of many deep learning and data processing techniques in terms of decoupled abstractions. These abstractions can be expressed concisely and clearly by leveraging the dynamism of the underlying Python language and the flexibility of the PyTorch library. fastai includes: a new type dispatch system for Python along with a semantic type hierarchy for tensors; a GPU-optimized computer vision library which can be extended in pure Python; an optimizer which refactors out the common functionality of modern optimizers into two basic pieces, allowing optimization algorithms to be implemented in 4–5 lines of code; a novel 2-way callback system that can access any part of the data, model, or optimizer and change it at any point during training; a new data block API; and much more. We used this library to successfully create a complete deep learning course, which we were able to write more quickly than using previous approaches, and the code was more clear. The library is already in wide use in research, industry, and teaching. Full article

The location and grade setting of a timber logistics center is an important link in the optimization of the timber logistics system, the rationality of which can effectively improve the efficiency of the timber logistics supply chain. There is a long distance between the main forested areas in China, and more than 55% of the timber demand depends on imports. Research and practice of systematically planning timber logistics centers in the whole country have not been well carried out, which reduces the efficiency of timber logistics. In this paper, 47 timber trading markets with a certain scale in China are selected as the basis for logistics center selection. Based on their transportation network relationship and the number of enterprises in the market, combined with the complex network theory and data analysis method, the network characteristics of three different transportation networks are measured. After determining the transportation capacity indicator, the logistics capacity coefficient is measured based on the freight volume of each node. Then, the important nodes are identified, and each node is graded to systematically set up the timber logistics center. Full article

In general, patients who are unwell do not know with which outpatient department they should register, and can only get advice after they are diagnosed by a family doctor. This may cause a waste of time and medical resources. In this paper, we propose an attention-based bidirectional long short-term memory (Att-BiLSTM) model for service robots, which has the ability to classify outpatient categories according to textual content. With the outpatient text classification system, users can talk about their situation to a service robot and the robot can tell them which clinic they should register with. In the implementation of the proposed method, dialog text of users in the Taiwan E Hospital were collected as the training data set. Through natural language processing (NLP), the information in the dialog text was extracted, sorted, and converted to train the long-short term memory (LSTM) deep learning model. Experimental results verify the ability of the robot to respond to questions autonomously through acquired casual knowledge. Full article

The development and integration of information technology and industrial control networks have expanded the magnitude of new data; detecting anomalies or discovering other valid information from them is of vital importance to the stable operation of industrial control systems. This paper proposes an incremental unsupervised anomaly detection method that can quickly analyze and process large-scale real-time data. Our evaluation on the Secure Water Treatment dataset shows that the method is converging to its offline counterpart for infinitely growing data streams. Full article

Open innovation is a concept in flux; from the practice of large-scale, internet-mediated collaboration, to a strategic option and business model for firms. However, the scope and breadth of its transformative dynamic is arguably restrained. Despite the theoretical and empirical benefits of openness, established firms face significant challenges deploying the coordination patterns of open innovation communities, further reducing the potential of spill-overs in the supply chain. Viewed differently, open innovation presents more user-centric and responsible innovation paths. These are manifested in the processes and outputs of open innovation by empowering participation and by successfully employing the capacities of user communities. To reap the benefits of open innovation, a rapid reconfiguration of the production and exchange structures is needed in intrafirm and interfirm relations. Sensorica is an open enterprise that achieves such forms of organization and a unique techno-social infrastructure supporting them. It illustrates a potential path that can realize the full potential of open innovation, for users, firms, and the economic system as a whole. Full article

In this work, we compare and analyze a variety of approaches in the task of medical publication retrieval and, in particular, for the Technology Assisted Review (TAR) task. This problem consists in the process of collecting articles that summarize all evidence that has been published regarding a certain medical topic. This task requires long search sessions by experts in the field of medicine. For this reason, semi-automatic approaches are essential for supporting these types of searches when the amount of data exceeds the limits of users. In this paper, we use state-of-the-art models and weighting schemes with different types of preprocessing as well as query expansion (QE) and relevance feedback (RF) approaches in order to study the best combination for this particular task. We also tested word embeddings representation of documents and queries in addition to three different ranking fusion approaches to see if the merged runs perform better than the single models. In order to make our results reproducible, we have used the collection provided by the Conference and Labs Evaluation Forum (CLEF) eHealth tasks. Query expansion and relevance feedback greatly improve the performance while the fusion of different rankings does not perform well in this task. The statistical analysis showed that, in general, the performance of the system does not depend much on the type of text preprocessing but on which weighting scheme is applied. Full article

Algorithms and abstract automata (abstract machines) are used to describe, model, explore and improve computers, cell phones, computer networks, such as the Internet, and processes in them. Traditional models of information processing systems—abstract automata—are aimed at performing transformations of data. These transformations are performed by their hardware (abstract devices) and controlled by their software (programs)—both of which stay unchanged during the whole computational process. However, in physical computers, their software is also changing by special tools such as interpreters, compilers, optimizers and translators. In addition, people change the hardware of their computers by extending the external memory. Moreover, the hardware of computer networks is incessantly altering—new computers and other devices are added while other computers and other devices are disconnected. To better represent these peculiarities of computers and computer networks, we introduce and study a more complete model of computations, which is called a triadic automaton or machine. In contrast to traditional models of computations, triadic automata (machine) perform computational processes transforming not only data but also hardware and programs, which control data transformation. In addition, we further develop taxonomy of classes of automata and machines as well as of individual automata and machines according to information they produce. Full article

The rise of social networks is rapidly spreading in China. Using social platforms, individuals are no longer just receivers of Internet information, as consumers generate and share contents with others. Social interaction and spontaneous promotion activities are carried out among consumers, but with the growth of traditional e-commerce slowing down, social commerce derived from social networks is gradually taking shape. Based on Hajli’s theoretical model, this study uses the social support theory and social commerce construct to study consumers’ social commerce behavior from a total of 1277 valid sample questionnaires that were distributed in a social platform environment in China. Through the empirical research evaluation using PLS-SEM, the statistical analysis results prove that social commerce constructs do promote social interaction of consumers. Such constructs have a positive effect on social support and social commerce intentions. In this regard, social support is embodied in information support and emotional support, and has a positive effect on social commerce intention. This study also conducts cross-cultural empirical comparisons. In comparison with Hajli’s research, this study has the same results in evaluation of Chinese samples. Among the users who exhibit social commerce intentions, social commerce construction is more important than social support. Full article

Mobile crowd sensing is an innovative and promising paradigm in the construction and perception of smart cities. However, multi-task allocation in real-world scenarios is a huge challenge. There are many unexpected factors in the execution of mobile crowd sensing tasks, such as traffic jams or accidents, that make participants unable to reach the target area. In addition, participants may quit halfway due to equipment failure, network paralysis, dishonest behavior, etc. Previous task allocation approaches mainly ignored some of the heterogeneity of participants and tasks in the real-world scenarios. This paper proposes a real-world-oriented multi-task allocation approach based on multi-agent reinforcement learning. Firstly, under the premise of fully considering the heterogeneity of participants and tasks, the approach enables participants as agents to learn multiple solutions independently, based on modified soft Q-learning. Secondly, two cooperation mechanisms are proposed for obtaining the stable joint action, which can minimize the total sensing time while meeting the sensing quality constraint, which optimizes the sensing quality of mobile crowd sensing (MCS) tasks. Experiments verify that the approach can effectively reduce the impact of emergencies on the efficiency of large-scale MCS platform and outperform baselines based on a real-world dataset under different experiment settings. Full article

Storm drains and sanitary sewers are prone to backups and overflows due to extra amount wastewater entering the pipes. To prevent that, it is imperative to efficiently monitor the urban underground infrastructure. The combination of sensors system and wireless underground communication system can be used to realize urban underground IoT applications, e.g., storm water and wastewater overflow monitoring systems. The aim of this article is to establish a feasibility of the use of wireless underground communications techniques, and wave propagation through the subsurface soil and asphalt layers, in an underground pavement system for storm water and sewer overflow monitoring application. In this paper, the path loss analysis of wireless underground communications in urban underground IoT for wastewater monitoring has been presented. The dielectric properties of asphalt, sub-grade aggregates, and soil are considered in the path loss analysis for the path loss prediction in an underground sewer overflow and wastewater monitoring system design. It has been shown that underground transmitter was able to communicate through thick asphalt (10 cm) and soil layers (20 cm) for a long range of up to 4 km. Full article

Knowledge base (KB) is an important aspect in artificial intelligence. One significant challenge faced by KB construction is that it contains many noises, which prevent its effective usage. Even though some KB cleansing algorithms have been proposed, they focus on the structure of the knowledge graph and neglect the relation between the concepts, which could be helpful to discover wrong relations in KB. Motived by this, we measure the relation of two concepts by the distance between their corresponding instances and detect errors within the intersection of the conflicting concept sets. For efficient and effective knowledge base cleansing, we first apply a distance-based model to determine the conflicting concept sets using two different methods. Then, we propose and analyze several algorithms on how to detect and repair the errors based on our model, where we use a hash method for an efficient way to calculate distance. Experimental results demonstrate that the proposed approaches could cleanse the knowledge bases efficiently and effectively. Full article

The cyber security toolkit, CyberSecTK, is a simple Python library for preprocessing and feature extraction of cyber-security-related data. As the digital universe expands, more and more data need to be processed using automated approaches. In recent years, cyber security professionals have seen opportunities to use machine learning approaches to help process and analyze their data. The challenge is that cyber security experts do not have necessary trainings to apply machine learning to their problems. The goal of this library is to help bridge this gap. In particular, we propose the development of a toolkit in Python that can process the most common types of cyber security data. This will help cyber experts to implement a basic machine learning pipeline from beginning to end. This proposed research work is our first attempt to achieve this goal. The proposed toolkit is a suite of program modules, data sets, and tutorials supporting research and teaching in cyber security and defense. An example of use cases is presented and discussed. Survey results of students using some of the modules in the library are also presented. Full article

As an emerging network architecture and technology, mobile edge computing (MEC) can alleviate the tension between the computation-intensive applications and the resource-constrained mobile devices. However, most available studies on computation offloading in MEC assume that the edge severs host various applications and can cope with all kinds of computation tasks, ignoring limited computing resources and storage capacities of the MEC architecture. To make full use of the available resources deployed on the edge servers, in this paper, we study the cross-server computation offloading problem to realize the collaboration among multiple edge servers for multi-task mobile edge computing, and propose a greedy approximation algorithm as our solution to minimize the overall consumed energy. Numerical results validate that our proposed method can not only give near-optimal solutions with much higher computational efficiency, but also scale well with the growing number of mobile devices and tasks. Full article