Development and evaluation of a real-time pedestrian counting system for high-volume conditions based on 2D LiDAR

Embedded systems are supporting the trend of moving away from centralised, high-cost products towards low-cost and high-volume products; yet, the non-functional constraints and the device heterogeneity can lead to system complexity. In this regard, Service-Oriented Architecture (SOA) is the best methodology for developing a loosely coupled, dynamic, flexible, distributed, and cost-effective application. SOA relies heavily on services, and the Semantic Web, as the advanced form of the Web, handles the application complexity and heterogeneity with the help of ontology. With an ever-increasing number of similar Web services in UDDI, a functional description of Web services is not sufficient for the discovery process. It is also difficult to rank the similar services based on their functionality. Therefore, the Quality of Service (QoS) description of Web services plays an important role in ranking services within many similar functional services. Context-awareness has been widely studied in embedded and real-time systems and can also play an important role in service ranking as an additional set of criteria. In addition, it can enhance human-computer interaction with the help of ontologies in distributed and heterogeneous environments. In order to address the issues involved in ranking similar services based on the QoS and context-awareness, the authors propose a service discovery framework for distributed embedded real-time systems in this chapter. The proposed framework considers user priorities, QoS, and the context-awareness to enable the user to select the best service among many functional similar services.

Download Full-text

Real-Time Tomato Detection, Classification, and Counting System Using Deep Learning and Embedded Systems

Advances in Intelligent Systems and Computing - Proceedings of the International e-Conference on Intelligent Systems and Signal Processing ◽

10.1007/978-981-16-2123-9_39 ◽

2021 ◽

pp. 511-522

Author(s):

Stavan Ruparelia ◽

Monil Jethva ◽

Ruchi Gajjar

Keyword(s):

Deep Learning ◽

Embedded Systems ◽

Real Time ◽

Counting System ◽

Tomato Detection

Download Full-text

Data-driven decision support under concept drift in streamed big data

Complex & Intelligent Systems ◽

10.1007/s40747-019-00124-4 ◽

2019 ◽

Vol 6 (1) ◽

pp. 157-163 ◽

Cited By ~ 2

Author(s):

Jie Lu ◽

Anjin Liu ◽

Yiliao Song ◽

Guangquan Zhang

Keyword(s):

Decision Making ◽

Big Data ◽

Real Time ◽

Concept Drift ◽

High Volume ◽

Streaming Data ◽

Data Driven ◽

Research Directions ◽

Decision Outcomes ◽

Past Data

Abstract Data-driven decision-making ($$\mathrm {D^3}$$D3M) is often confronted by the problem of uncertainty or unknown dynamics in streaming data. To provide real-time accurate decision solutions, the systems have to promptly address changes in data distribution in streaming data—a phenomenon known as concept drift. Past data patterns may not be relevant to new data when a data stream experiences significant drift, thus to continue using models based on past data will lead to poor prediction and poor decision outcomes. This position paper discusses the basic framework and prevailing techniques in streaming type big data and concept drift for $$\mathrm {D^3}$$D3M. The study first establishes a technical framework for real-time $$\mathrm {D^3}$$D3M under concept drift and details the characteristics of high-volume streaming data. The main methodologies and approaches for detecting concept drift and supporting $$\mathrm {D^3}$$D3M are highlighted and presented. Lastly, further research directions, related methods and procedures for using streaming data to support decision-making in concept drift environments are identified. We hope the observations in this paper could support researchers and professionals to better understand the fundamentals and research directions of $$\mathrm {D^3}$$D3M in streamed big data environments.

Download Full-text