With the development of the Internet-of-Things (IoT) technology, the applications of gas sensors in the fields of smart homes, wearable devices, and smart mobile terminals have developed by leaps and bounds. In such complex sensing scenarios, the gas sensor shows the defects of cross sensitivity and low selectivity. Therefore, smart gas sensing methods have been proposed to address these issues by adding sensor arrays, signal processing, and machine learning techniques to traditional gas sensing technologies. This review introduces the reader to the overall framework of smart gas sensing technology, including three key points; gas sensor arrays made of different materials, signal processing for drift compensation and feature extraction, and gas pattern recognition including Support Vector Machine (SVM), Artificial Neural Network (ANN), and other techniques. The implementation, evaluation, and comparison of the proposed solutions in each step have been summarized covering most of the relevant recently published studies. This review also highlights the challenges facing smart gas sensing technology represented by repeatability and reusability, circuit integration and miniaturization, and real-time sensing. Besides, the proposed solutions, which show the future directions of smart gas sensing, are explored. Finally, the recommendations for smart gas sensing based on brain-like sensing are provided in this paper.
With the development of Internet of Things (IoT), more and more sensors, actuators and mobile devices have been deployed into our daily lives. The result is that tremendous data are produced and it is urgent to dig out hidden information behind these volumous data. However, IoT data generated by multi-modal sensors or devices show great differences in formats, domains and types, which poses challenges for machines to process and understand. Therefore, adding semantics to Internet of Things becomes an overwhelming tendency. This paper provides a systematic review of data semantization in IoT, including its backgrounds, processing flows, prevalent techniques, applications, existing challenges and open issues. It surveys development status of adding semantics to IoT data, mainly referring to sensor data and points out current issues and challenges that are worth further study.
With the development of sensing and intelligent technologies, ambient sensor-based activity recognition is attracting more attention for a wide range of applications. One of the technology challenges is the recognition of the activity performer in a multi-occupancy scenario. This paper proposes a multilabel Markov Logic Network classification method to recognize resident types based on their activity habits and preference. The activity preference mainly includes time sequence preference, duration and period preference, and the location preference of a basic entity or action events. According to the resident type (gender, age bracket, job), the further reasoning work is the family role (mother, father, daughter and so on.) recognition. We have designed simple and combined preferences to test and evaluate our proposed method. Initial experiments have produced good performance in many cases proving this solution is an efficient and feasible method for resident type recognition which could be applied to real-world scenarios.
The Internet of Things (IoT) is emerging as an attractive paradigm involving physical perceptions, cyber interactions, social correlations and even cognitive thinking through a cyber-physical-social-thinking hyperspace. In this context, energy management with the purposes of energy saving and high efficiency is a challenging issue. In this work, a taxonomy model is established in reference to the IoT layers (i.e., sensor-actuator layer, network layer, and application layer), and IoT energy management is addressed from the perspectives of supply and demand to achieve green perception, communication, and computing. A smart home scenario is presented as a case study involving the main enabling technologies with supply-side, demand-side, and supply-demand balance considerations, and open issues in the field of IoT energy management are also discussed.
With the rapid development and large-scale uptake of the Internet of Things, smart home is evolving from a vision towards a realistically viable solution for assisted living. Activity recognition is one of the fundamental tasks in order to provide accurate and timely assistance and service. As daily living scenarios are full of similar activities, missing data, and noise, inferring complex activities using knowledge-driven reasoning algorithms suffers from several drawbacks, e.g., real-time raw sensor data segmentation, poor generalization, higher computational complexity, and scalability. To address these problems, this paper proposes a hybrid approach to complex daily activity recognition by merging the first-order logic and probability graphic modeling. Specifically, we develop a novel "Markov logic network" combining data-driven multi-feature and simplified rule-based modeling and inference, thus enabling and supporting the applicability and robustness of daily activity recognition. To evaluate the approach and associated methods, we design a testing scenario with a number of similar activity groups, missing data, or disturbance test datasets in a multi-modeling sensor scene. Initial results show our approach outperforms the traditional approach with a better accuracy in the situations of similar activities with missing data and noise disturbance. Experiments are also conducted to compare the Gibbs sampling and MC-SAT sampling algorithms for Markov logic network, and the results show that the Gibbs is better in our experimental settings.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.