Search

Machine learning has been highly successful in data-intensive applications but is often hampered when the data set is small. Recently, Few-shot Learning (FSL) is proposed to tackle this problem. Using prior knowledge, FSL can rapidly generalize to new tasks containing only a few samples with supervised information. In this article, we conduct a thorough survey to fully understand FSL. Starting from a formal definition of FSL, we distinguish FSL from several relevant machine learning problems. We then point out that the core issue in FSL is that the empirical risk minimizer is unreliable. Based on how prior knowledge can be used to handle this core issue, we categorize FSL methods from three perspectives: (i) data, which uses prior knowledge to augment the supervised experience; (ii) model, which uses prior knowledge to reduce the size of the hypothesis space; and (iii) algorithm, which uses prior knowledge to alter the search for the best hypothesis in the given hypothesis space. With this taxonomy, we review and discuss the pros and cons of each category. Promising directions, in the aspects of the FSL problem setups, techniques, applications, and theories, are also proposed to provide insights for future research. [ABSTRACT FROM AUTHOR]

Efficient spectrum sensing is essential for the successful application of the Dynamic Spectrum Assignment (DSA) technology in Cognitive Radio Networks (CRNs). In conventional spectrum sensing schemes, secondary users (SUs) have to intelligently schedule their sensing and accessing so that the spectrum opportunities are thoroughly exploited while the primary users are not harmed. In this article, we propose a new sensing servicemodel in which a Spectrum Sensor Network (SSN) is employed for spectrum sensing tasks.We will describe the general framework for this SSN-enabled CRN and present the major challenges in such an architecture. We will address one of these challenges and formulate it as a boundary detection problem with unknown erroneous inputs. A novel cooperative boundary detection algorithm is designed which explores recent advances in Support Vector Machines (SVM) and computational geometry.We prove that cooperative spectrum sensing can asymptotically approach the optimal solution. Real testbed as well as comprehensive simulation experiments are conducted, and the results show that, compared with the traditional schemes, cooperative boundary detection can dramatically reduce the spectrum sensing overhead and improve the effectiveness of DSA. [ABSTRACT FROM AUTHOR]

Ocean and water basically cover the major parts of our planet. To obtain the best utilization of the underlying resources on these parts of the Earth, people have made some research advancements. Specifically, the research on underwater wireless acoustic sensor networks (UWA-SNs) has made great progress. However, wide deployment of UWA-SNs is far from a reality due to several reasons. One important reason is that offshore deployment and field-level experiments of ocean-centric applications are both expensive and labor intensive. Other alternatives to attain this objective are to conduct simulation or experimentation that can reduce cost and accelerate the research activities and their outcomes. However, designing efficient and reliable simulation and experimentation platforms have proven to be more challenging beyond the expectation. In this article, we explore the main techniques (including their pros and cons) and components to develop simulation and experimentation platforms and provide a comprehensive survey report in this area. We classify simulation and experimentation platforms based on some typical criteria and then provide useful guidelines for researchers on choosing suitable platforms in accordance with their requirements. Finally, we address some open and un-resolved issues in this context and provide some suggestions on future research. [ABSTRACT FROM AUTHOR]

With the marvelous development of wireless techniques and ubiquitous deployment of wireless systems indoors, myriad indoor location-based services (ILBSs) have permeated into numerous aspects of modern life. The most fundamental functionality is to pinpoint the location of the target via wireless devices. According to how wireless devices interact with the target, wireless indoor localization schemes roughly fall into two categories: device based and device free. In device-based localization, a wireless device (e.g., a smartphone) is attached to the target and computes its location through cooperation with other deployed wireless devices. In device-free localization, the target carries no wireless devices, while the wireless infrastructure deployed in the environment determines the target's location by analyzing its impact on wireless signals. This article is intended to offer a comprehensive state-of-the-art survey on wireless indoor localization from the device perspective. In this survey, we review the recent advances in both modes by elaborating on the underlying wireless modalities, basic localization principles, and data fusion techniques, with special emphasis on emerging trends in (1) leveraging smartphones to integrate wireless and sensor capabilities and extend to the social context for device-based localization, and (2) extracting specific wireless features to trigger novel human-centric device-free localization. We comprehensively compare each scheme in terms of accuracy, cost, scalability, and energy efficiency. Furthermore, we take a first look at intrinsic technical challenges in both categories and identify several open research issues associated with these new challenges. [ABSTRACT FROM AUTHOR]

Anomaly detection (a.k.a., outlier or burst detection) is a well-motivated problem and a major data mining and knowledge discovery task. In this article, we study the problem of population anomaly detection, one of the key issues related to event monitoring and population management within a city. Through studying detected population anomalies, we can trace and analyze these anomalies, which could help to model city traffic design and event impact analysis and prediction. Although a significant and interesting issue, it is very hard to detect population anomalies and retrieve anomaly trajectories, especially given that it is difficult to get actual and sufficient population data. To address the difficulties of a lack of real population data, we take advantage of mobile phone networks, which offer enormous spatial and temporal communication data on persons. More importantly, we claim that we can utilize these mobile phone data to infer and approximate population data. Thus, we can study the population anomaly detection problem by taking advantages of unique features hidden in mobile phone data. In this article, we present a system to conduct Population Anomaly Detection (PAD). First, we propose an effective clustering method, correlation-based clustering, to cluster the incomplete location information from mobile phone data (i.e., from mobile call volume distribution to population density distribution). Then, we design an adaptive parameter-free detection method, R-scan, to capture the distributed dynamic anomalies. Finally, we devise an efficient algorithm, BT-miner, to retrieve anomaly trajectories. The experimental results from real-life mobile phone data confirm the effectiveness and efficiency of the proposed algorithms. Finally, the proposed methods are realized as a pilot system in a city in China. [ABSTRACT FROM AUTHOR]