Probabilistic Rule Learning Systems

This survey provides an overview of rule learning systems that can learn the structure of probabilistic rules for uncertain domains. These systems are very useful in such domains because they can be trained with a small amount of positive and negative examples, use declarative representations of background knowledge, and combine efficient high-level reasoning with the probability theory. The output of these systems are probabilistic rules that are easy to understand by humans, since the conditions for consequences lead to predictions that become transparent and interpretable. This survey focuses on representational approaches and system architectures, and suggests future research directions.

Download Full-text

A Generic Guide for Using Membrane Computing in Robot Control

Advances in Computational Intelligence and Robotics - Membrane Computing for Distributed Control of Robotic Swarms ◽

10.4018/978-1-5225-2280-5.ch005 ◽

2017 ◽

pp. 86-96

Keyword(s):

Operating Systems ◽

Membrane Computing ◽

Task Complexity ◽

Future Research ◽

Research Directions ◽

Robot Controller ◽

Swarm Algorithms ◽

Future Research Directions ◽

High Level ◽

Generic Algorithms

As various theoretical and practical details of using membrane computing models have been presented throughout the book, certain details might be hard to find at a later time. For this reason, this chapter provides the reader with a set of checkmark topics that a developer should address in order to implement a robot controller using a membrane computing model. The topics discussed address areas such as: (1) robot complexity, (2) number of robots, (3) task complexity, (4) simulation versus real world execution, (5) sequential versus parallel implementations. This chapter concludes with an overview of future research directions. These directions offer possible solutions for several important concerns: the development of complex generic algorithms that use a high level of abstraction, the design of swarm algorithms using a top-down (swarm-level) approach and ensuring the predictability of a controller by using concepts such as those used in real-time operating systems.

Download Full-text

How Job Tenure Weakens the Positive Influence of Education on Creative Performance through Task Performance

Sustainability ◽

10.3390/su14010537 ◽

2022 ◽

Vol 14 (1) ◽

pp. 537

Author(s):

Lu Yang ◽

Jun Wei ◽

Jinyi Zhou

Keyword(s):

Task Performance ◽

Positive Influence ◽

Future Research ◽

Job Tenure ◽

Creative Performance ◽

Research Directions ◽

Future Research Directions ◽

Indirect Relationship ◽

High Level ◽

Practical Implications

Researchers indicate that employees with a high level of education tend to have better creative performance. However, few studies have investigated the boundary conditions of this association. The componential model of creativity demonstrates that both task-relevant skills and creativity-relevant skills are indispensable factors of creative performance. Job tenure, which generally hinders employees from acquiring creativity-relevant skills, is regarded as a potential boundary condition. In this study, we investigate how job tenure weakens positive influence of education on creative performance through task performance. Using a sample of 368 employees and 43 leaders in a provincial bank in China, we indeed find that job tenure negatively moderates the indirect relationship between education and creative performance via task performance. Specifically, the positive relationship is weakened when job tenure is high than when it is low. We also discuss the theoretical and practical implications of our study and highlight future research directions.

Download Full-text

Leveraging Human Guidance for Deep Reinforcement Learning Tasks

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2019/884 ◽

2019 ◽

Author(s):

Ruohan Zhang ◽

Faraz Torabi ◽

Lin Guan ◽

Dana H. Ballard ◽

Peter Stone

Keyword(s):

Reinforcement Learning ◽

Future Research ◽

Sequential Decision ◽

Research Directions ◽

Learning Agents ◽

Learning Tasks ◽

Future Research Directions ◽

Human Effort ◽

High Level ◽

Learning Frameworks

Reinforcement learning agents can learn to solve sequential decision tasks by interacting with the environment. Human knowledge of how to solve these tasks can be incorporated using imitation learning, where the agent learns to imitate human demonstrated decisions. However, human guidance is not limited to the demonstrations. Other types of guidance could be more suitable for certain tasks and require less human effort. This survey provides a high-level overview of five recent learning frameworks that primarily rely on human guidance other than conventional, step-by-step action demonstrations. We review the motivation, assumption, and implementation of each framework. We then discuss possible future research directions.

Download Full-text

Diffusion of Electronic Commerce in Australia

Electronic Commerce ◽

10.4018/978-1-878289-76-6.ch006 ◽

2011 ◽

pp. 102-114

Author(s):

Mohammed A. Quaddus

Keyword(s):

Diffusion Process ◽

Electronic Commerce ◽

New Technology ◽

Future Research ◽

Research Directions ◽

Simple Diffusion ◽

Future Research Directions ◽

Simple Diffusion Model ◽

High Level ◽

Flexible Model

Diffusion is the process by which a new technology spreads in its usage among a population. This chapter analyses the diffusion process of one aspect of the consumer-to-business electronic commerce (EC) in Australia, namely Internet shopping. The chapter first reviews three popular logistics diffusion models from the literature and then applies them to the EC diffusion data. Results show that the most flexible model is not significant, while the simple diffusion model (Blackman’s) is. It was also found that the past diffusion process had been mostly influenced by the “internal” interactions between the adopters and the potential adopters of EC. Further analysis of the Blackman’s model revealed some high level policy guidelines to enhance the diffusion process further into the future. Limitations of the study and future research directions were also identified.

Download Full-text

Data Tagging In Medical Images: A Survey of the State-of-art

Current Medical Imaging Formerly Current Medical Imaging Reviews ◽

10.2174/1573405616666200218130043 ◽

2020 ◽

Vol 16 ◽

Cited By ~ 1

Author(s):

Jyotismita Chaki ◽

Nilanjan Dey

Keyword(s):

Medical Image ◽

Medical Images ◽

Medical Data ◽

Future Research ◽

Research Directions ◽

Data Intensive ◽

Different Types ◽

Future Research Directions ◽

High Level ◽

State Of Art

: A huge amount of medical data is generated every second, and a significant percentage of them are images that need to be analyzed and processed. One of the key challenges in this regard is the recovery of medical images. The medical image recovery procedure should be done automatically by the computers that are the method of identifying object concepts and assigning homologous tags to them. To discover the hidden concepts in the medical images, the low-level characteristics should be used to achieve high-level concepts and that is a challenging task. In any specific case, it requires human involvement to determine the significance of the image. To allow machine-based reasoning on the medical evidence collected, the data must be accompanied by additional interpretive semantics; a change from a pure data-intensive methodology to a model of evidence rich in semantics. In this state-of-art, data tagging methods related to medical images are surveyed which is an important aspect for the recognition of a huge number of medical images. Different types of tags related to the medical image, prerequisites of medical data tagging, different techniques to develop medical image tags, different medical image tagging algorithms and different tools that are used to create the tags are discussed in this paper. The aim of this state-of-art paper is to produce a summary and a set of guidelines for using the tags for the identification of medical images and to identify the challenges and future research directions of tagging medical images.

Download Full-text

Modular Reconfigurable Robotics

Annual Review of Control Robotics and Autonomous Systems ◽

10.1146/annurev-control-053018-023834 ◽

2019 ◽

Vol 2 (1) ◽

pp. 63-88 ◽

Cited By ~ 12

Author(s):

Jungwon Seo ◽

Jamie Paik ◽

Mark Yim

Keyword(s):

State Of The Art ◽

Low Cost ◽

Future Research ◽

Research Directions ◽

Current State ◽

Robot Systems ◽

Technical Issues ◽

Future Research Directions ◽

Reconfigurable Robot ◽

High Level

This article reviews the current state of the art in the development of modular reconfigurable robot (MRR) systems and suggests promising future research directions. A wide variety of MRR systems have been presented to date, and these robots promise to be versatile, robust, and low cost compared with other conventional robot systems. MRR systems thus have the potential to outperform traditional systems with a fixed morphology when carrying out tasks that require a high level of flexibility. We begin by introducing the taxonomy of MRRs based on their hardware architecture. We then examine recent progress in the hardware and the software technologies for MRRs, along with remaining technical issues. We conclude with a discussion of open challenges and future research directions.

Download Full-text

A Survey on Mobile Social Networks: Applications, Platforms, System Architectures, and Future Research Directions

IEEE Communications Surveys & Tutorials ◽

10.1109/comst.2014.2371813 ◽

2015 ◽

Vol 17 (3) ◽

pp. 1557-1581 ◽

Cited By ~ 102

Author(s):

Xiping Hu ◽

Terry H. S. Chu ◽

Victor C. M. Leung ◽

Edith C.-H. Ngai ◽

Philippe Kruchten ◽

...

Keyword(s):

Social Networks ◽

Future Research ◽

Mobile Social Networks ◽

Research Directions ◽

System Architectures ◽

Future Research Directions

Download Full-text

Privacy-Enhancing Technologies

Handbook of Research on Social and Organizational Liabilities in Information Security ◽

10.4018/978-1-60566-132-2.ch013 ◽

2009 ◽

pp. 203-227 ◽

Cited By ~ 14

Author(s):

Yang Wang

Keyword(s):

Analytical Framework ◽

Future Research ◽

Research Directions ◽

Privacy Concerns ◽

Privacy Enhancing Technologies ◽

Future Research Directions ◽

High Level

Privacy-enhancing technologies (PETs), which constitute a wide array of technical means for protecting users’ privacy, have gained considerable momentum in both academia and industry. However, existing surveys of PETs fail to delineate what sorts of privacy the described technologies enhance, which in turn makes it difficult to differentiate between the various PETs. Moreover, those surveys could not consider very recent important developments with regard to PET solutions. The goal of this chapter is two-fold. First, we provide an analytical framework to differentiate various PETs. This analytical framework consists of high-level privacy principles and concrete privacy concerns. Secondly, we use this framework to evaluate representative up-to-date PETs, specifically with regard to the privacy concerns they address, and how they address them (i.e., what privacy principles they follow). Based on findings of the evaluation, we outline several future research directions.

Download Full-text