【计算机类】高引SCI期刊专刊信息8条

全文截稿: 2017-03-01

影响因子: 3.997

期刊难度: ★★★

CCF分类: C类

网址: http://www.journals.elsevier.com/future-generation-computer-systems/

Information and Communication Technologies are becoming the prime enabler for smart and sustainable cities in recent years. This is mainly due to realising and making effective use of the ever-increasing data generated in urban environments. Sensors, smart phones, geo-tagged devices, RFIDs, smart gadgets and Internet of Things are major source of collecting ever increasing temporal and geo-coded land-use, built-environment, transport, energy, health, socio-economic and environmental Big Data. Often data is kept in different repositories and managed by different departments, which raise data access, harmonisation, processing and information visualisation challenges for generating new insights and knowledge.

Cloud and Fog/Edge are becoming enablers for managing cross-departmental temporal and geocoded Big Data, developing cross-thematic applications and providing necessary computation power to perform data analytics and present new knowledge to city stakeholders for awareness raising, city planning, policy development and decision making. High-performance visual processing techniques provide opportunity to intuitively present temporal and geo-coded information from neighbourhood scale to city or city-region scale and fosters innovation, co-creation and co-designing sustainable future cities.

In the above context, the real value of smart city big data is gained by applying data mining, machine learning or new statistical methods for data analytics, visualisation and decision making. This becomes challenging when applied to large scale or real time data and hence requires appropriate tools and techniques to be applied using Cloud and Fog/Edge computing. These applications also require dealing with privacy and data security issues to avoid sharing intrusive details of citizens or other stakeholders.

Topics of interest include use of cloud and fog computing in smart cities but are not limited to:
- Smart city data analytics
- Geo-processing and innovative visualisation techniques
- Spatial data techniques and tools for analytics
- City data quality, harmonisation, integration and processing
- Real-time city data processing and visualisation
- Predictive analytics, visualisation and simulation for future city models
- Visual computing and analytics for city applications
- Interactive data analysis and visualisation
- Smart city services and applications platforms
- Security and privacy solutions for smart city applications
- Crowd sourcing and establishing trust on data sources
- Internet of Things for cross-thematic city applications
- Methods and techniques for city data collection and curation
- Automated and intelligent city data processing methods
- Design patterns and computing models for smart city applications
- Open government data for automated processing and knowledge generation
- Decision support systems for smart cities
- Data provenance techniques for city applications, decision making and policy making
- Smart city applications: mobility, energy, public administration & governance, economy, health, security and environment.

全文截稿: 2017-09-01

影响因子: 3.997

期刊难度: ★★★

CCF分类: C类

网址: http://www.journals.elsevier.com/future-generation-computer-systems/

Smart city’s IoT-based infrastructures envision improvement in quality of life through optimal utilization of resources. Integrating diverse sensors through communication technologies generate big data which is collected, processed, and analyzed, revealing knowledge and information to realize the goals of smart cities. Multimedia sensors serve as the eyes and ears of smart city administrators, enabling them to monitor activities and assets. The big multimedia data generated by these sensors contain a wealth of information, needed to be processed and analyzed for knowledge extraction. However, the huge volume of this data and its inherent complexity hinders ability of traditional computing infrastructures and algorithms to effectively process and extract actionable intelligence from it. There is a growing demand for efficient yet powerful algorithms to consume internet of multimedia things (IoMT)-generated big data and extract needed information from it to run the affairs of smart cities. Deep learning based methods for multimedia data processing and understanding has shown great promise in the recent years. This special issue aims to highlight problems and future challenges in smart cities and invite researchers working towards smart cities and associated technologies like IoMTs, machine learning for big data, and embedded/cloud computing, to develop novel methods for addressing issues related to the transmission, processing, representation, and storage of IoMT-generated big data. It also invites novel deep learning based solutions for real-time data processing, learning from multi-modal big data, distributed learning paradigms with embedded processing, and efficient inference.

This special issue calls for original works revealing the latest research on deep learning from big multimedia data for smart cities. The proposed non-exhaustive list of topics in this special issue is as follows:
- Data collection and storage for deep learning in smart cities
- Supervised, semi-supervised, and unsupervised feature learning from IoMT big data
- Scalable and semantics-driven indexing of big multimedia data in smart cities
- Context-based summarization and abstraction of IoMT big data
- Online stream processing of IoMT big data for smarter cities applications
- Efficient and scalable inference of IoMT-oriented deep models
- Real-time vision through efficient deep convolutional neural networks (CNN)
- Optimizing deep CNNs for embedded vision in smart cities
- Utilizing embedded processing for ingesting big multimedia data in IoMT sensor networks
- Physical cyber systems related solutions for big data security and privacy in smart cities
- Smarter surveillance
- Real-time emergency detection through visual analytics and response invocation
- Information hiding solutions (steganography, watermarking) in smart cities

全文截稿: 2017-10-31

影响因子: 3.997

期刊难度: ★★★

CCF分类: C类

网址: http://www.journals.elsevier.com/future-generation-computer-systems/

Interoperability allows the interfaces of a system to work with other system without any restricted access or implementation. This interoperability can be syntactic (intercommunication and data exchange between two or more systems), semantic (automatically interpret the information exchanged meaningfully and accurately in order to produce users defined useful results) or cross domain (Multiple social, organizational, political, legal entities working together for a common interest and/or information exchange) from the perspective of internet connected objects i.e. Internet of Things (IoT). Deployment of these objects put forth a long list of strategic, operational, tactical and technological challenges especially from the perspective of interoperability. Interoperability is one of the biggest barriers keeping businesses from adopting the IoT. Lack of related standards and algorithms significantly increase the complexity, inefficiencies, customer frustration and the cost as well. Exhibiting the intelligence by the IoT objects can adhod big contribution in making this interoperability possible. To resolve thisissue, innovative list of solutions can be hired from computational intelligence domain (Fuzzy Logic, Neural Networks, Artificial Intelligence, Swarm Intelligence, and Genetic Algorithms), Machine learning, Deep learning and their state-of-the-art extensions.

Future Generation Computer Systems Journal is soliciting high quality manuscripts presenting original contributions for its specialissue. Thisspecialissueaims to provide a forum that brings together researchers from academia, practicing engineers from industry, standardization bodies, and government to meet and exchange ideas on Intelligent Algorithms and Standards for Interoperability in Internet of Things.

Topics of interests include (but are not limited to) the following categories:
- Intelligent standards and algorithms for infrastructures, platforms, architectures and designs supporting Interoperability in IoT
- Intelligent Algorithms and Standards for interoperability in IoT environment at various levels (data, device, middleware, networking, and application service)
- Intelligent Semantic Interoperability Solutions for the IoT
- Messaging protocols (MQTT, CoAP, AMQP, and REST) within IoT to enhance the interoperability of various interactive systems
- Security- and privacy-aware IoT
- Monitoring performances and QoS in applications based on heterogeneous IoT solutions.
- Intelligent algorithms for gap Analysis of interoperability in IoT
- Intelligent standards and algorithms for Interoperability between different IoT implementations (Agriculture, smart cities, military, surveillance, ocean, transportation and logistics, m-Heath, etc.)
- Survey on suitability of intelligent standards and algorithms for interoperability and heterogeneity in IoT infrastructures
- Formal and informal methods for intelligent interoperability in IoT
- Intelligent algorithms standards for low cost interoperability in IoT
- Low power signal processing for embedded IoT devices
- Signal processing algorithms and platforms for IoT big data processing

全文截稿: 2017-11-30

影响因子: 3.997

期刊难度: ★★★

CCF分类: C类

网址: http://www.journals.elsevier.com/future-generation-computer-systems/

Recently, the Internet of Things (IoT) has emerged as a revolutionary technology that promises to offer a fully connected “smart” world. It enables billions of everyday objects such as consumer goods, enduring products, vehicles, utility components, sensors, and other physical devices to be connected with the global Internet that aims to transform the way we live, work, and play. However, a wide-scale realization of IoT is hindered due to the significant constraints of IoT devices in terms of memory, processing resources, energy, or communication bandwidth. The rise of Cloud-assisted Internet of Things or Cloud-of-Things (CoT) paradigm has been seen as an enabler to solve many of these issues as it offers networked and remote computing resources to process, manage, store and share huge volume of IoT data. It has stimulated the development of various innovative and novel applications in areas such as smart cities, smart homes, smart grids, smart agriculture, smart transportation, smart healthcare, etc. to improve all aspects of people’s life.

However, currently the CoT paradigm is facing increasing difficulty to handle the Big data that IoT generates from these application use cases. As billions of previously unconnected devices are now generating more than two exabytes of data each day, it is challenging to ensure low latency and network bandwidth consumption, optimal utilization of computational recourses, scalability and energy efficiency of IoT devices while moving all data to the Cloud. To cope with these challenges, a recent trend is to deploy anEdge Computinginfrastructure between IoT systems and Cloud computing. This new paradigm termed asEdge-of-Things(EoT) computing, allows data computing, storage and service supply to be moved from Cloud to the local Edge devices such as smart phones, smart gateways or routers and local PCs that can offer computing and storage capabilities on a smaller scale in real-time. EoT pushes data storage, computing and controls closer to the IoT data source(s); therefore, enables each Edge device to play its own role of determining what information should be stored or processed locally and what needs to be sent to the Cloud for further use. Thus, EoT complements CoT paradigm in terms of high scalability, low delay, location awareness, and allowing of using local client computing capabilities in real time.

While researchers and practitioners have been making progress within the area of Edge-of Things computing, still there exists several issues that need to be addressed for its large-scale adoption. Some of these issues are: novel network architecture and middleware platform for EoT paradigm considering emerging technologies such as 5G wireless networks, software defined network and semantic computing; Edge analytics for IoT Big data; novel security and privacy methods for EoT; social intelligence into the Edge node to host IoT applications; and context-aware service management on the EoT with effective quality of service (QoS) support and other issues.

This special issue targets a mixed audience of researchers, academics and investigators from different communities to share and exchange new ideas, approaches, theories and practice to resolve the challenging issues associated with the leveraging of Edge computing for Edge-of-Things paradigm. Therefore, the suggested topics of interest for this special issue include, but are not limited to:
- Novel middleware architecture design for EoT paradigm
- Semantic Edge computing for IoT
- Edge analytics for Big data in IoT
- Edge-enabled 5G network architecture and protocols for IoT
- Software Defined Networking for EoT paradigm
- Social intelligence in EoT system
- EoT operating system design and validation
- Interoperability and mobility for Edge to IoT connectivity
- Trust, security and privacy issues in EoT system
- Resource, service and context management on Edge computing for IoT applications
- Software and simulation platform for EoT paradigm
- Energy-aware resource scheduling in Edge computing for IoT applications
- Emerging Edge commuting services and applications for IoT
- Industrial Edge computing in IoT paradigm

全文截稿: 2017-12-15

影响因子: 3.997

期刊难度: ★★★

CCF分类: C类

网址: http://www.journals.elsevier.com/future-generation-computer-systems/

This special issue addresses core topics on the design, the use and the evaluation of Big Data enabling technologies to build next-generation context-aware applications and computing systems for future intelligent environments. Disruptive paradigm shifts such as the Internet of Things (IoT) and Cyber-Physical Systems (CPS) will create a wealth of streaming context information. Large-scale context-awareness combining IoT and Big Data will drive to creation of smarter application ecosystems in diverse vertical domains, including smart health, finance, smart grids and cities, transportation, Industry 4.0, etc. However, effectively tapping into growing amounts of disparate contextual information streams remains a challenge, especially for large-scale application and service providers that need timely and relevant information to support adequate decision-making. A deeper understanding is necessary on the strengths and weaknesses of state-of-the-art big data processing and analytics systems (Hadoop, Spark, Storm, Samza, Flume, Kafka, Kudu, etc.) to realize large-scale context-awareness and build Big Context architectures. In particular, the key question is how one can help identify relevant context information, ascertain the quality of the context information, extract semantic meaning from heterogeneous distributed information sources, and do this data processing effectively for many concurrent context-aware applications with different requirements for adequate decision-making. At the same time, fundamental research is necessary to understand how context information about these large-scale distributed data processing infrastructures itself can offer the intelligence to self-adapt the configuration of these systems to optimize resource usage, such as the networking, data storage, and computation required to process context data. The particular focus of this special issue is on Big Context solutions covering the modeling, designing, implementation, assessment and systematic evaluation of large-scale context-aware applications and intelligent Big Data systems.

We are soliciting high-quality, original research papers and encourage submissions that cover the broad range of research topics combining Big Data and context-aware applications or intelligent environments, including practical applications and case studies, application design methodologies, empirical evaluation of systems and metrics, underpinning theories, and more technical/scientific research topics. The possible topics include but are not limited to:
- Big Data architectures for large-scale context-aware applications
- Context models and query languages for heterogeneous data streams
- Distributed context reasoning with Big Data technologies
- Machine learning and prediction of situational awareness with Big Data
- Effective data collection and processing for concurrent context-aware applications
- Modeling of Quality of Service constraints and enforcing of Service Level Agreements
- Context-aware dynamic decision making on streaming Big Data
- Context-driven monitoring, adaptation and optimization of Big Data systems
- Large-scale Quality of Context management
- Systematic comparison of Big Data technologies for context-aware applications
- Big Context solutions for finance, health, smart cities, industry 4.0, etc.
- Security, privacy, scalability, and sustainability concerns Big Context systems

全文截稿: 2017-12-31

影响因子: 3.997

期刊难度: ★★★

CCF分类: C类

网址: http://www.journals.elsevier.com/future-generation-computer-systems/

In today’s Internet-connected world where technologies underpin almost every facet of our society, cyber security and forensics specialists are increasingly dealing with wide ranging cyber threats in almost real-time conditions. The capability to detect, analyze and defend against such threats in near real-time conditions is not possible without employment of threat intelligence, big data and machine learning techniques. For example, when a significant amount of data is collected from or generated by different security monitoring solutions, intelligent and next generation big-data analytical techniques are necessary to mine, interpret and extract knowledge of these unstructured/structured (big) data. Thus, this gives rise to cyber threat intelligence and analytics solutions, such as big data, artificial intelligence and machine learning, to perceive, reason, learn and act against cyber adversaries tactics, techniques and procedures.

Cyber threat intelligence and analytics is among one of the fastest growing interdisciplinary fields of research bringing together researchers from different fields such as digital forensics, political and security studies, criminology, cyber security, big data analytics, machine learning, etc. to detect, contain and mitigate advanced persistent threats and fight against malicious cyber activities (e.g. organized cyber crimes and state-sponsored cyber threats).

This special issue is focused on cutting-edge research from both academia and industry, with a particular emphasis on novel techniques, combination of tools and so forth to perceive, reason, learn and act on a wide range of cyber threat data collected from different intrusion attempts, malware campaigns and indications of compromise. Only technical papers describing previously unpublished, original, state-of-the-art research, and not currently under review by a conference or a journal will be considered. Extended work must have a significant number of "new and original" contributions along with more than 60% brand "new" material.

Specifically, this issue welcomes two categories of papers: (1) invited articles from qualified experts; and (2) contributed papers from open call with list of addressed topics. Topics of interest include but not limited to:
- Detection and analysis of advanced threat actors tactics, techniques and procedures
- Analytics techniques for detection and analysis of cyber threats
- Application of machine learning tools and techniques in cyber threat intelligence
- Theories and models for detection and analysis of advanced persistent threats
- Automated and smart tools for collection, preservation and analysis of digital evidences
- Threat intelligence techniques for constructing, detecting, and reacting to advanced intrusion campaigns
- Applying machines learning tools and techniques for malware analysis and fighting against cyber crimes
- Intelligent forensics tools, techniques and procedures for cloud, mobile and data-centre forensics
- Intelligent analysis of different types of data collected from different layers of network security solutions
- Threat intelligence in cyber security domain utilising big data solutions such as Hadoop
- Intelligent methods to manage, share, and receive logs and data relevant to variety of adversary groups
- Interpretation of cyber threat and forensic data utilising intelligent data analysis techniques
- Infer intelligence of existing cyber security data generated by different monitoring and defense solutions
- Automated and intelligent methods for adversary profiling
- Automated integration of analysed data within incident response and cyber forensics capabilities