今年暑假不回家！8条期刊专刊截稿信息陪你过暑假

1. Journal of Parallel and Distributed Computing

-----------------------

全文截稿：2017-08-15

期刊：Journal of Information Security and Applications

专刊：Special Issue on Mobile Networks and Devices Security, Privacy and Trust

领域：网络与信息安全

难度：★★★

CCF分类：C类

影响因子：暂无

网址：http://www.journals.elsevier.com/journal-of-information-security-and-applications/

-----------------------

Mobile networks and devices are currently developing at a rapid pace. With the rapid growth of mobile users, how to protect mobile networks against various attacks has become a big challenge. Taking mobile devices as an example, these devices are tiny, and users may lose them easily. In addition, these devices are very attractive to thieves because of their popularity and resale value. In recent years, security experts have predicted the rise of malware and attacks on mobile networks and devices. As a result, there is an increasing need for secure solutions to protect users' sensitive and private information in the mobile environment.

This special issue will focus on mobile context and aims to solicit original research papers that discuss the security, privacy and trust of mobile networks and devices.

Topics of interest include, but are not limited to:

- Adversarial modeling

- Vulnerability Assessment and testing

- Intrusion detection and prevention schemes

- Tracing back mobile attackers

- Impact of human social behavior on mobile usage

- Secure routing and access control

- Mobile authentication mechanisms

- Security testing of new or existing usability features

- Agent based intrusion surveillance

- Wireless Access Technologies

- Multimedia security issues for tackling intruders

- Trust evaluation on mobile networks/devices

- Detection of malicious information propagation in mobile networks

- Models, methods, and tools for testing the security of mobile networks

-----------------------

全文截稿：2017-08-15

期刊：Mobile Networks and Applications

专刊：Special Issue on Recent Advances in Mining Intelligence and Context-Awareness on IoT-based Platforms

领域：计算机网络

难度：★★★

CCF分类：C类

影响因子：1.538

网址：http://www.springer.com/journal/11036/about

-----------------------

To develop innovative and intelligent machines that are fit for futuristic use, it is necessary to take a holistic approach in order to recognize various situations and environmental issues. To do this, various types of machine learning mechanisms have been developed during past decades.Recently, deep Learning has been proposed as a new area of Machine Learning and Mining researches, which have been investigated with the objective of moving Machine Learning closer to one of its original goals. Deep learning is being tried to apply for various recognition fields where researchers feel difficulty, but can achieve very promising result such as Alphago by Google deep mind. This kind of learning mechanism can cooperate with various sensors, which are able to gather large information.

Also, the development of sensor networks, particularly in the last years, has extended their applicability in various domains, such as heritage preservation, environmental motoring and human activity recognition. Especially, to achieve highly natural interpretation of the environmental situation, various kinds of sensors should be widely employed in recognition system.

Therefore, integration of sensor data with intelligent machine learning scheme is a natural choice and henceforth the sensor-based recognition technology is emerging as an important field of research including artificial intelligence (AI). This special issue aims to highlight the latest research results and advances on algorithms and technologies for various sensor-based recognition systems. It will include related topics and demonstrate original research work in this field of research. It will also cover the results of investigation on these topics featuring novel solutions and discuss the future trend of research in this domain. The MIKE2017 will be an interdisciplinary conference that brings together researchers and practitioners from the domains of learning algorithms, data mining, machine learning, knowledge exploration, large-scale data analytics, big data, soft computing, information systems, and so on. The selected outstanding papers from MIKE2017 will be recommended to this special issue.

Topics of interest include, but are not limited to, the following scope:

- Advances in Machine Learning

- Algorithms for Intelligent Learning

- Analogical, cognitive, and creative reasoning

- Business Intelligence

- Case Based Recommender Systems

- Collective Learning and Tagging

- Context and location aware techniques

- Cross / Multi Language content mining

- Crowdsourcing & Crowd Mining Algorithms and Systems

- Big Data Search (HANA, Terracotta, Hadoop)

- Visual analytics for text mining /exploration Visual Exploration

- Real-time applications of data mining

- Learning mechanisms from wireless sensor systems

- Self-learning structure and framework

- Security problem in multimedia data mining and distribution

- Emotion and expression recognition algorithms for human interactive applications

- Bioinformatics

- Reasoning and Learning

- Distributed and Peer-to-peer Search

- Distributed Mining of Human expertise

- Image Processing and Understanding

- IoT solutions and platforms for information mining

- Human sensors-based applications for intelligent context recognition

- Real-time signal processing algorithms for recognition system

-----------------------

全文截稿：2017-08-15

期刊：Pattern Recognition

专刊：Special Issue on Deep Learning for Computer Aided Cancer Detection and Diagnosis with Medical Imaging

领域：人工智能

难度：★★★★

CCF分类：B类

影响因子：3.399

网址：http://www.journals.elsevier.com/pattern-recognition/

-----------------------

Computer aided cancer detection and diagnosis (CAD) has made significant strides in the past 10 years, with the result that many  successful  CAD systems have been developed. However, the accuracy of these  systems  still requires  significant improvement,  so that the can meet the needs of real  world diagnostic  situations.. Recent progress in machine learning offers new prospects   for computer aided  cancer detection and diagnosis. A major recent development is the massive success resulting from the use of  deep learning techniques, which has attracted attention from both  the academic research and commercial application communities. Deep learning is the fastest-growing field in machine learning and is widespread uses in  cancer detection and diagnosis. Recent research has demonstrated that deep learning can increase cancer detection accuracy significantly. Thus, deep learning techniques offer the  promise not only  of  more accurate CAD systems for cancer detection and diagnosis, but may also  revolutionize their design.

This  special issue seeks  high-quality  original research papers  on cancer detection and diagnosis in medical imaging and image processing.  The topics of interest include, but are not limited to:

- Deep learning for cancer tissue classification

- Deep learning for cancer image segmentation

- Deep learning for cancer location

- Deep learning for cancer image retrieval 

- Deep learning for high accuracy computer-aided detection/diagnosis systems

- Deep learning architecture for big cancer data 

- GPU implementation of deep learning techniques for cancer detection/ diagnosis

- Real-time deep learning techniques for cancer detection/diagnosis

- Learning from multiple modalities of imaging data for cancer detection/diagnosis

- Deep learning for big image data analysis and its applications to cancer detection/diagnosis

-----------------------

全文截稿：2017-08-30

期刊：Soft Computing

专刊：Special Issue on Advanced Computer Science and Applications for Soft Computing of Converged IT environments

领域：人工智能

难度：★★★

CCF分类：C类

影响因子：1.63

网址：http://www.springer.com/journal/500/about

-----------------------

This special issue is to gather new soft computing trends and methodological recent advances on a wide range of problems arising in different fields to handle practical data of converged environment. Many advanced computational methods have been successfully applied to a range of optimization and classification problems in soft computing, but there are still many practical problems tackled by traditional methods that are generally difficult to solve experimentally in practical converged data. More specifically, many computational problems arising in fields of scientific programming have been addressed in AI, HPC, large-scale data mining and etc that handles practical converged data. Submissions are welcomed on scientific programming applied to optimization in practical data. We invite researchers and practitioners to submit their original research articles and theoretical articles.

This special issue is soliciting high quality technical papers addressing research practices and challenges in the areas of ubiquitous computing. It will reflect the state-of-the-art of the computational methods, involving theory, algorithm, numerical simulation, error and uncertainty analysis and/or novel application of new processing techniques in engineering, science, and other disciplines related to ubiquitous computing. Potential topics include, but are not limited to:

- Mobile and ubiquitous computing

- Dependable, reliable and autonomic computing

- Security and trust management

- Multimedia systems and services

- Networking and communications

- Database and data mining

- Game and software engineering

- Grid and scalable computing

- Embedded system and software

- Artificial intelligence

- Distributed and parallel algorithms

- Web and internet computing

- IT policy and business management

-----------------------

全文截稿：2017-08-31

期刊：Multimedia Tools and Applications

专刊：Special Issue on Few-shot Learning for Multimedia Content Understanding

领域：计算机图形学与多媒体

难度：★★★

CCF分类：C类

影响因子：1.331

网址：http://www.springer.com/journal/11042/about

-----------------------

The multimedia analysis and machine learning communities have long attempted to build models for understanding real-world applications. Driven by the innovations in the architectures of deep convolutional neural network (CNN), tremendous improvements on object recognition and visual understanding have been witnessed in the past few years. However, it should be noticed that the success of current systems relies heavily on a lot of manually labeled noise-free training data, typically several thousand examples for each object class to be learned, like ImageNet. Although it is feasible to build learning systems this way for common categories, recognizing objects 'in the wild' is still very challenging. In reality, many objects follow a long-tailed distribution: they do not occur frequently enough to collect and label a large set of representative exemplars in contrast to common objects. For example, in some real-world applications, such as anomalous object detection in a video surveillance scenario, it is difficult to collect sufficient positive samples because they are 'anomalous' as defined, and fine-grained object recognition, annotating fine-grained labels requires expertise such that the labeling expense is prohibitively costly.

The expensive labeling cost motivates the researchers to develop learning techniques that utilize only a few noise-free labeled data for model training. Recently, some few-shot learning, including the most challenging task zero-shot learning, approaches have been proposed to reduce the number of necessary labeled samples by transferring knowledge from related data sources. In the view of the promising results reported by these works, it is fully believed that the few-shot learning has strong potential to achieve comparable performance with the sufficient-shot learning techniques and significantly save the labeling efforts. There still remains some important problems. For example, a general theoretical framework for few-shot learning is not established, the generalized few-shot learning which recognizes common and uncommon objects simultaneously is not well investigated, and how to perform online few-shot learning is also an open issue.

The primary goal of this special issue is to invite original contributions reporting the latest advances in fewshot learning for multimedia (e.g., text, video and audio) content understanding towards addressing these challenges, and to provide the opportunity for researchers and product developers to discuss the state-of-theart and trends of few-shot learning for building intelligent systems. The topics of interest include, but are not limited to:

- Few-shot/zero-shot learning theory;

- Novel machine learning techniques for few-shot/zero-shot learning;

- Generalized few-shot/zero-shot learning;

- Online few-shot/zero-shot learning;

- Few-shot/zero-shot learning with deep CNN;

- Few-shot/zero-shot learning with transfer learning;

- Few-shot/zero-shot learning with noisy data;

- Few-shot learning with actively data annotation (active learning);

- Few-shot/zero-shot learning for fine-grained object recognition;

- Few-shot/zero-shot learning for anomaly detection;

- Few-shot/zero-shot learning for visual feature extraction;

- Weakly supervised learning and its applications;

- Attribute learning and its applications;

- Leaning to hash and its applications;

- Applications in object recognition and visual understanding with few-shot learning;