计算机 | SCI期刊专刊信息5条

全文截稿: 2021-06-01

影响因子: 2.978

CCF分类: 无

中科院JCR分区:

• 大类 : 工程技术 - 3区

• 小类 : 自动化与控制系统 - 3区

• 小类 : 计算机：人工智能 - 3区

• 小类 : 工程：电子与电气 - 3区

• 小类 : 工程：机械 - 2区

网址：
https://www.journals.elsevier.com/mechatronics

Physical Human-Robotics Interaction (pHRI) consists of physical interactions between humans and robots in order to perform common or independent tasks in a shared and close area by ensuring certain performances, safety and human ergonomics. The interaction can optionally include contact (either continuously or intermittently) where the level of leadership of each partner (human and robot) has to be defined. Applications of pHRI are nowadays clear, such as Industry of future like Industry 4.0, human rehabilitation, sport training assistance, or medical and surgery assistance. One example of interesting and generic pHRI industrial task is co-manipulation of objects for their storage, transportation, assembly, or fabrication. In this, applying the established tools in term of modeling, control and trajectory generation from standard robotic manipulation is not anymore sufficient to accomplish the tasks. The presence of the human through the comanipulated object introduces several challenges: uncertainties in the overall model, unpredictability in the human behavior, human ergonomics and safety during the interaction, possible human tremor or fatigue disturbing the robot during the task, limited measurement for the overall interaction,…. Therefore, considerable efforts are being made to target efficient pHRI tasks and we witness an increase of publications of this field in the literature over these last years.

The objective of this special issue is to collect articles that report the most recent accomplishments and results in the area of human-robot interaction. The special issue is an opportunity for researchers and practitioners to present the context or applications of their pHRI works, the challenges they are faced with, and the scientific approaches they propose to handle these, as well as the results obtained. Contributions from industry are encouraged, submitted manuscripts are expected to report experimental results and papers must contain originality. Potential topics include but are not limited to:

Innovative mechatronic tools for pHRI

Innovative mechatronic tools for safety or ergonomics during pHRI

Actuation and measurement in pHRI

Novel robotic mechanisms and systems for pHRI

Parameters identification and signals estimation in pHRI

Control in pHRI

Tasks or trajectory planning in pHRI

Important dates

Initial submission deadline: June 1, 2021

Completion of first review: September 1, 2021

Submission of revised paper: November 1, 2021

Completion of second review: December 15, 2021

Submission of revised paper: February 1, 2022

Completion of final review: March 1, 2022

Submission of final manuscripts and Copyright forms : March 15, 2021

Publication: June 1, 2022

全文截稿: 2021-06-30

影响因子: 1.045

CCF分类: C类

中科院JCR分区:

• 大类 : 工程技术 - 4区

• 小类 : 计算机：硬件 - 4区

• 小类 : 计算机：理论方法 - 4区

• 小类 : 工程：电子与电气 - 4区

网址：
https://www.journals.elsevier.com/microprocessors-and-microsystems

Deep reinforcement learning (DRL) uses feedback from the agent to make decisions in complex problems under uncertainty. Medical applications often require processing large volumes of complex data in a challenging environment. Deep reinforcement learning can process this data by analyzing the agent's feedback that is sequential and sampled using non-linear functions. The deep reinforcement learning algorithms commonly used for medical applications include value-based methods, policy gradient, and actor-critic methods. The recent advances in the increased computational capabilities of architectures like field-programmable gate array (FPGA), graphics processing units (GPU), and digital signal processors (DSP) have made it possible to infer deep reinforcement learning algorithms on them. However, efficient implementation of these architectures should consider the issues related to their portability, wearability, and power consumption.

The main objective is to provide a platform for scientists, researchers, industry experts, and scholars to share their innovative contributions in deep reinforcement learning for medical applications on various embedded devices (ED). Research articles describing only a proof of concept are not encouraged. Authors are solicited to develop novel deep reinforcement learning algorithms on medical data and implement them either on FPGA, GPUs, or DSP. The special issue invites authors to submit papers that analyze the portability, wearability, power consumption of the deep reinforcement learning algorithms implemented either on FPGA, GPU, or DSP. The deep reinforcement learning topic includes but not restricted to:

Monte Carlo Tree Search and Deep Q-network

Dual Gradient Descent and Conjugate Gradient

Trust Region Policy Optimization and Proximal Policy Optimization.

Actor-Critic using Kronecker-Factored Trust Region

Linear Quadratic Regulator and Iterative Linear Quadratic Regulator

Twin-Delayed Deep deterministic policy gradient

Guided Policy Search and Model-Based Learning with Raw Medical Videos

Inverse Reinforcement Learning and Meta-learning

Very efficient ED for DRL in medical applications in terms of power consumption, processing efficiency and flexibility

Neuromorphic and/or brain-inspired architectures implementing DRL techniques

Efficient mapping of DRL applications to ED

New learning approaches for DRL targeting ED

High-level programming language support, tools, frameworks, and system software for DRL in medical applications implemented on ED

Security and Reliability issues for DRL on ED

DRL ED implementation in cyber-physical systems for healthcare, well-being and personal assistance (elderly, disability), sports and medicine, rehabilitation, instrumentation, lab-on-chips

Important dates

Paper submission due: June 30, 2021

First-round acceptance notification: August 30, 2021

Revision submission: October 15, 2021

Notification of final decision: December 30, 2021

Submission of final paper: January 30, 2022

Publication date: March 2022

全文截稿: 2021-08-20

影响因子: 1.045

CCF分类: C类

中科院JCR分区:

• 大类 : 工程技术 - 4区

• 小类 : 计算机：硬件 - 4区

• 小类 : 计算机：理论方法 - 4区

• 小类 : 工程：电子与电气 - 4区

网址：
https://www.journals.elsevier.com/microprocessors-and-microsystems

The Internet of Things (IoT) becomes as one of the key technological developments that provide smart infrastructure for the cloud-edge services by interconnecting physical devices and virtual things between mobile applications and embedded devices. Several embedded software and hardware systems had been developed by developers to assist IoT systems in gathering information about safety-critical fields. By increasing development of IoT ecosystems, Intelligent Decision Making (IDM) paradigm is emerging as a high potential solution for processing and navigating the information of embedded IoT devices. IDM for embedded devices in IoT systems investigates the massive quantity of complex data to help industry, transportations, medical systems, microcontrollers and other smart applications. IoT, embedded devices, sensors, microprocessors, manual data entry and online sources are a few complex data sources for IDM. IDM make use of machine learning techniques to enhance the process of complex making decisions and prediction. AI tools such as Metaheuristic, Fuzzy Logic, artificial neural networks, deep learning and intelligent agents can be integrated to IDM for embedded systems in IoT. Finally, IDM-based embedded devices can be very beneficial to a range of IoT systems where complex and critical decisions are made under time pressure, decision-makers are on the move, and the environment is dynamic and uncertain.

Despite the importance of decision making methods on embedded software and hardware systems in IoT environments, this special issue invites researchers to publish selected original papers presenting intelligent trends to solve new challenges of IDM methods. We also are interested in review articles as the state-of-the-art of this topic, showing recent major advances and discoveries, significant gaps in the research and new future issues.

Topics are as below but are not limited to:

• Memetic-based IDM for embedded applications in IoT
• Machine learning methods for IDM in embedded IoT systems
• IDM for the embedded computer-aided diagnostic system.
• IDM for industrial embedded IoT applications.
• Embedded medical instrumentation and healthcare technologies in IoT
• Decision making for Wireless Body Area Network (WBAN) in wearable IoT systems
• Formal analysis of IDM-based embedded devices in IoT
• Energy prediction on embedded sensor-based IDSS systems in IoT
• Security and privacy aspects of embedded systems based on IDM in IoT
• Blockchain technology on IDM-based embedded IoT systems
• Big data management based on IDM in IoT systems
• IDM on vehicular communications in IoT systems
• IDM for robotics and micro-robotic embedded systems in IoT
• Smart city and smart home based on IDM in embedded IoT
• Decision-making enabled embedded smart farming and agriculture in IoT
• Decision-making on multi-processor systems on a chip in IoT applications

Important Dates:
Deadline for submissions: 20 August 2021
Final Decision: 20 January 2022
Tentative Publication Date: Q3, 2022

全文截稿: 2021-09-30

影响因子: 2.911

CCF分类: 无

中科院JCR分区:

• 大类 : 管理科学 - 3区

• 小类 : 计算机：信息系统 - 3区

• 小类 : 计算机：跨学科应用 - 3区

网址：
https://www.journals.elsevier.com/electronic-commerce-research-and-applications

Data-intensive methodologies and tools have been playing a pivotal role for various research and application areas with contributions from diverse communities including computer scientists, statisticians, mathematicians, and industrial practitioners. While most data-intensive methodologies and tools are developed for general problem settings, there are often unique challenges in developing effective and efficient solutions for a specific domain or a novel real-world application. Due to the need of incorporating domain knowledge in the data modeling and analytical process and the challenge to discover actionable knowledge hidden in complex data, data-intensive research in specialized domains can be more challenging and require more manual intervention.

Such challenges are faced especially in the fast-changing e-commerce research and applications, such as e-commerce knowledge engine, product search and recommendation, online advertising, customer targeting, online-offline integration, inventory optimization, intelligent customer service, and fraud detection. Indeed, the unique challenges in e-commerce problems have attracted great attention in data science research, such as data mining, machine learning, and artificial intelligence.

To foster further advances of data-intensive research in e-commerce, this special issue aims to share the open challenges, learned lessons, and best practices in developing and applying data-driven solutions for problems from e-commerce and related applications. We hope this special issue will benefit interdisciplinary data science research in not only e-commerce but also related domains such as information systems and technology, marketing, finance and supply chain management, with methodologies involving network analytics, text mining, sequential pattern mining, predictive modeling, and reinforcement learning.

Topics

The topics of interest include but not limited to:

E-commerce data collection and processing

E-commerce information systems and knowledge graph

Data mining theories and applications in e-commerce

Multi-modal mining of e-commerce data

Cross-domain/multi-view learning of e-commerce data

Data mining for electronic auctions

Consumer behavior mining

Customer relationship management and data mining

Recommender systems and collaborative filtering

Personalization in e-commerce services and products

Mobile-commerce and ubiquitous computing

Data mining for e-government

Data mining for supply chain and inventory management

Inter-organizational systems in e-commerce

Emerging technologies and technological innovation in e-commerce

Schedule

Initial Submission: September 30, 2021

First round of decision: January 15, 2022

Revision: March 15, 2022

Final Decision: May 15, 2022