With the flourish of the smart devices and their applications, controlling devices using gestures has attracted increasing attention for ubiquitous sensing and interaction. Recent works use acoustic signals to track hand movement and recognize gestures. However, they suffer from low robustness due to frequency selective fading, interference and insufficient training data. In this work, we propose RobuCIR, a robust contact-free gesture recognition system that can work under different usage scenarios with high accuracy and robustness. RobuCIR adopts frequency-hopping mechanism to mitigate frequency selective fading and avoid signal interference. To further increase system robustness, we investigate a series of data augmentation techniques based on a small volume of collected data to emulate different usage scenarios. The augmented data is used to effectively train neural network models and cope with various influential factors (e.g., gesture speed, distance to transceiver, etc.). Our experiment results show that RobuCIR can recognize 15 gestures and outperform state-of-the-art works in terms of accuracy and robustness.

While it is well understood that edge computing can significantly facilitate IoT-related applications by deploying edge servers close to IoT devices, it also faces many challenges with numerous IoT devices connected and interacted. One of the most important issues is how to efficiently deploy edge servers under a certain budget with the explosive growth of data scale and user base. Existing studies for edge server placement fail to consider user’s query preferences since individual users may be interested in events in particular regions and are keen to receive up-to-date data streams that originate in regions of interest. In this article, we present a preference-aware edge server placement approach that offers better workload distribution in terms of both minimizing query latency and balancing the load of edge servers. To achieve this, we formulate edge server placement with multiobjective optimization as a ${p}$ -center problem and design two progressive approaches. We first propose quadratic integer programming (QIP) for small-scale data sets. Since the ${p}$ -center problem is an NP-hard problem, we thus propose a heuristic algorithm named TAKG (TAbu search with $K$ -means and Genetic algorithm) for large-scale data sets. To evaluate the utility of the proposed models, we have conducted a comprehensive evaluation on a large data set that is collected by more than 1900 IoT devices during 30 days. Experimental results indicate our approaches outperform all baselines significantly in terms of both query latency and load balancing.

Detecting shopping groups is gaining popularity as it enables various applications ranging from marketing to advertising. Existing methods exploit WiFi probe requests to detect shopping groups by identifying co-located customers. However, the probe request is prone to suffer from device heterogeneity which might pose a severe data sparseness problem. More importantly, we find that a certain amount of shopping groups would separate sometimes which makes traditional methods unreliable. In this paper, we propose a shopping group detection system using WiFi (SNOW). Instead of collecting probe requests, SNOW utilizes the WiFi data from smartphones associated with the deployed access points (APs). We could thus obtain data from different devices and even ensure a data granularity of seconds using Arping. Besides, we exploit an effective heuristic extracted from two observations of shopping group dynamics to improve the detection performance. First, the probability of group separation differs in diverse areas. Second, the proportion of group participation and individual engagement differs in different activities of the mall. Therefore, APs under which shopping groups appear more frequently and barely separate should contribute more in measuring customer similarity. Lastly, we represent the measured similarity into a matrix format and apply matrix factorization with a sparsity constraint to derive grouping results directly. According to our experiments in a large shopping mall, SNOW improves the detection performance of baseline approaches by 13.2% on average.

Configuration synthesis is a fundamental technology in the context of self-driving networks, aimed at mitigating network outages by intelligently and automatically generating configurations that align with network intents. However, existing tools often fall short in meeting the practical requirements of network operators, particularly in terms of generality and scalability. Moreover, these tools disregard manual configuration which remains the primary method employed for daily network management. To address these challenges, this paper introduces ConfigReco, a novel, versatile, and scalable configuration recommendation tool tailored for manual configuration. ConfigReco facilitates the automatic generation of configuration templates based on the network operator’s intent. First, ConfigReco leverages existing configurations as input and models them using a knowledge graph. Second, graph neural networks are employed by ConfigReco to estimate the significance of nodes within the configuration knowledge graph. Lastly, configuration recommendations are made by ConfigReco based on the computed importance scores. A prototype system has been implemented to substantiate the effectiveness of ConfigReco, and its performance has been evaluated using real-world configurations. The experimental results demonstrate that ConfigReco achieves a coverage rate of 93.35% while concurrently maintaining a redundancy rate of 23.07% within a configuration knowledge graph comprising 890,464 edges and 40,885 nodes. Furthermore, ConfigReco exhibits high scalability, enabling its applicability to arbitrary datasets, while simultaneously providing efficient recommendations within a response time of 1 second.