Interest in multimodal optimization function is expanding rapidly since real-world optimization problems often require the location of multiple optima in the search space. In this context, fitness sharing has been used widely to maintain population diversity and permit the investigation of manly peaks in the feasible domain. This paper reviews various strategies of sharing and proposes new recombination schemes to improve its efficiency. Some empirical results are presented for high and a limited number of fitness function evaluations. Finally, the study compares the sharing method with other niching techniques.

Fitness Sharing and Niching Methods Revisited

Internet of Things IoT is considered as the developing tendency of network technology, generally it refers to the networked interconnection of different kinds of things objects. Compared with the Internet, IoT provides a wider platform to share more information. In this situation, the information service in IoT is necessary to organize the process of getting and sharing information for the IoT user. This paper considers that IoT service should have active, personalized, and intelligent features. The architecture for IoT service is given, which consists of three layers: perception layer, network layer, and service layer. Correspondingly, models ftoor identify users need and service coordination are proposed. E-commerce is one of the most important applications on the Internet and is a typical format of information service. Thus, this paper chooses e-commerce as the application case to research and show how IoT service works in reality.

Internet of Things IoT Service Architecture and its Application in E-Commerce

Deep learning is a popular direction in computer vision and digital image processing. It is widely utilized in many fields, such as robot navigation, intelligent video surveillance, industrial inspection, and aerospace. With the extensive use of deep learning techniques, classification and object detection algorithms have been rapidly developed. In recent years, with the introduction of the concept of “unmanned retail,” object detection, and image classification play a central role in unmanned retail applications. However, open-source datasets of traditional classification and object detection have not yet been optimized for application scenarios of unmanned retail. Currently, classification and object detection datasets do not exist that focus on unmanned retail solely. Therefore, in order to promote unmanned retail applications by using deep learning-based classification and object detection, in this article we collected more than 30 000 images of unmanned retail containers using a refrigerator affixed with different cameras under both static and dynamic recognition environments. These images were categorized into ten kinds of beverages. After manual labeling, images in our constructed dataset contained 155 153 instances, each of which was annotated with a bounding box. We performed extensive experiments on this dataset using ten state-of-the-art deep learning-based models. Experimental results indicate great potential of using these deep learning-based models for real-world smart unmanned vending machines.

Toward New Retail: A Benchmark Dataset for Smart Unmanned Vending Machines

Modern business background can be seen as a logical effect of eBusiness, advanced integrated networks, Internet of Things (IoT), and software services. In such an environment, the IoT-centered application deployment and delivery models have revolutionized the way businesses interact, collaborate and transact with customers, suppliers, partners, employees and shareholders. Hence, with wide deployment of the distributed inter-enterprise Service Delivery Platforms (SDPs) over the Internet, there is an urgent need to understand and solve service traffic issues of the fast evolving architectures. Accordingly, the purpose of our work is to develop a conceptual model for performance analysis of software services availability vs. interoperability in order to facilitate enterprises to attach their customers more tightly by an effective service delivery, which in turn optimizes business processes at different steps. Thus, we introduce and deliberate in this chapter a hypothetical model for the performance analysis of services availability and interoperability on the IoT-enabled inter-enterprise SDPs. We also figure and analyze imperative performance features of the model. The related open issues and future work are briefed correspondingly.

Conceptual Model of Business Services Availability vs. Interoperability on Collaborative IoT-enabled eBusiness Platforms

Nowadays in communication and network business, structure and system are independently constructed with existing IT services and new services (e.g., 3G services) without considering common functions between them. Consequently, the study of standardized Service Delivery Platform (SDP) structure and interfaces can efficiently provide the methodology of existing or new services to users and easier environment for development to service providers. Therefore in this paper, we will find solutions about the SDP structure and then describe the implementation of presence service related to the SDP.

The IMS/SDP Structure and Implementation of Presence Service

Nowadays in communication and network businesses, architectures and systems are independently constructed with existing service or new service deployment without considering common functions and services between them. Consequently, the study of standardized Service Delivery Platform (SDP) structure and its related interfaces is needed to provide the methodology of existing or new services in an efficient way. Therefore, in this paper, we intend to view various solutions about SDP structure with the proposed interfaces which are able to support them, and then recommend various application services which SDP can offer to end users.

Deploying application services using service delivery platform (SDP)

The structures and systems of network and communication are independently constructed with existing based-IT service and 3G services without considering common functions between them. Consequently, the study of standardized Service Delivery Platform (SDP) structure and its related interfaces are needed to provide the methodology of existing or new services in an efficient way. Therefore, in this paper, we suggest the structure of common service enablers (i.e., PoC, Presence) for the SDP and show the way of interaction between them. Finally, we will describe an implementation of the components of the SDP using them.

An implementation of the SDP using common service enablers

The IP Multimedia Subsystem (IMS) has brought us feasibilities by separating control functions from bearer and services. Multi-Access technology enables us connecting the IMS Core by kinds of network such as wireless, wire-line network and Internet. By IMS Service Delivery Platform (SDP) richness of services have been developed and deployed into realization through its common protocols and interfaces. Push-to-talk over Cellular (PoC) as the outstanding half-duplex Voice over IP (VoIP) application service enables traditional walkie-talkie service over mobile network.. In this paper we will focus on the advantage of PoC service and PoC architecture firstly, and then describes the session flows of PoC service and its simple simulation. At last we make some conclusions.

IMS Based PoC Service Deployment

This paper shows the implementations of a Horizontal M2M Network Services Platform over IP Multimedia Subsystem (IMS). We describe the call flow of the proposed architecture and the entities operating in each process. We also present a prototype results.

Jae-Oh Lee

Papers

The IMS/SDP Structure and Implementation of Presence Service

Deploying application services using service delivery platform (SDP)

An implementation of the SDP using common service enablers

IMS Based PoC Service Deployment

A M2M horizontal services platform implementation over IP multimedia subsystem (IMS)