LoRa technology holds great promise for wide-area wireless sensing, owing to its long-range connectivity and strong penetration capability. However, existing LoRa sensing systems face a fundamental limitation, i.e., they assume that the gateway only receives signals from the sensing node, without any interference from other communication nodes. This is because transmissions from communication nodes inevitably distort the sensing pattern extracted from the received sensing signal, leading to sensing failure. To address this challenging issue, we propose InterSen, a novel solution specifically designed to address communication interference on LoRa sensing. We conduct an in-depth analysis of how communication interference disrupts LoRa sensing and design innovative signal processing methods to recover the sensing pattern corrupted by interference. We evaluate the performance of InterSen across three real-world sensing applications, i.e., respiration monitoring, walking sensing, and gesture recognition. Comprehensive experiments demonstrate that InterSen achieves accurate sensing even in the presence of multiple communication nodes. This brings LoRa sensing one step closer to practical deployment in real-world scenarios.

LoRa technology has become critical in numerous IoT applications, offering long-range connections with low energy consumption. However, their low-power nature makes them vulnerable to cross-technology interference (CTI) from other wireless technologies sharing the same unlicensed frequency bands. Existing solutions address this issue through signal analysis and coding techniques. Despite these efforts, the research on CTI mitigation needs to go one step further - to design a systematic framework for enhanced interference resilience. This article proposes SLoRa+, a systematic framework that integrates symbol recovery with soft decoding to achieve synergic interference resilience for LoRa. SLoRa+’s symbol recovery employs a two-stage analysis to recover corrupted LoRa symbols at a low cost. It also estimates the confidence of the recovered symbols by considering the characteristics of both LoRa and CTI. This confidence information is then utilized in soft decoding to improve error correction capabilities. Supported by theoretical analysis and real testbed evaluations, including commercial LoRa nodes and USRP B210, our experiments under different settings, i.e., various CTI sources and frequency bands, demonstrate SLoRa+’s effectiveness. Compared with state-of-the-art techniques, SLoRa+ enhances CTI protection capability by 1.6× with only 1% of the computation cost.

General-purpose text decoding approaches are usually adopted for dialogue response generation.Although the quality of the generated responses can be improved with dialogue-specific encoding methods, conversational decoding methods are still under-explored.Inspired by Wu et al. (2023) that a good dialogue feature space should follow the rules of locality and isotropy, we present a fine-grained conversational decoding method, termed isotropic and proximal search (IPS).Our method is designed to generate the semantic-concentrated response, while still maintaining informativeness and discrimination against the context.Experiments show that our approach outperforms existing decoding strategies in the dialogue field across both automatic and human evaluation metrics.More in-depth analyses further confirm the effectiveness of our approach.

By offering long-range wireless connections with low energy consumption, Low-Power Wide Area Networks (LP- WANs) have been widely deployed in many critical Internet-of- Things (IoT) applications. However, LPWAN's low-power nature leads to inevitable packet corruption under cross-technology interference (CTI) emitted from other wireless technologies that coexist in the same unlicensed band. To address this fundamental issue, researchers propose multiple lines of solutions, such as signal analysis and coding. Despite these efforts, the research on CTI mitigation needs to go one step further - to design a systematic framework for enhanced interference resilience. This paper introduces SLoRa, a systematic framework inte-grating symbol recovery with soft decoding for synergic inter-ference resilience. Without loss of generality, we focus on LoRa, the dominating LPWAN technology. SLoRa's symbol recovery examines the corrupted signal through a two-stage analysis to recover incorrect LoRa symbols accurately at a low cost. To estimate the confidence of recovered symbols, SLoRa examines the statuses of LoRa and CTI, and it further leverages the estimated confidence via soft decoding to improve the error correction capability. We analyze SLoRa theoretically and evaluate it with real testbeds, including SX1280 LoRa chips and USRP B210. Experiments across multiple settings, e.g., different CTI sources and frequency bands, demonstrate that SLoRa effectively enhances interference resilience at a low cost. Compared with the state-of-the-art technique, SLoRa improves the CTI protection capability by 1.4x while only requiring 1 % computation cost.

Assessment of the contribution rates of weapon system-of-systems is an extremely uncertain and complex problem that should be addressed by domain experts. Addressing these problems, which is often hesitant, fuzzy, and linguistic, requires evaluation of multiple indices of different types. Hesitant Pythagorean fuzzy sets combined with linguistic term sets are powerful tools to handle this kind of problem. In this paper, recent studies on hesitant Pythagorean fuzzy sets (HPFSs) are first reviewed and linguistic HPFSs (LHPFSs) are proposed. To efficiently solve the evaluation problem, the axiomatic properties of entropies for HPFSs and LHPFSs are defined. According to these properties, novel entropy measures for HPFSs and LHPFSs are introduced. A novel method that can better reveal the characteristics of HPFSs and LHPFS to represent the HPF and LHPF numbers is also introduced. On this foundation, the definitions of distance measures for HPFSs and LPFSs are proposed, and a set of distance measures for HPFSs and LHPFSs are developed. Moreover, the Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) method is modified through hierarchical thought by using the presented entropy and distance measures for LHPFSs; the improved TOPSIS method is applied preferably to the case of contribution of weapon system-of-systems and shows better validity and distinguishability than other methods under the LHPFS environment in the examples. The hierarchical TOPSIS method can better solve the problem of weight allocation in case of a lot of indices.

Group re-identification (Re-ID) is an important task of computer vision and involves multiple challenges. In this paper, we propose a Hybrid Attention Model (HAM) to address the problem of group Re-ID, solving the spatial variation in the challenging still-image-based group Re-ID task. HAM consists of both the position and channel attention to make the network focus more on the crucial areas and features of the group images. Furthermore, we propose a novel Least Squares Residual Distance (LSRD) based on the least squares algorithm. LSRD can leverage the residual of the fitting function achieved by least squares method, better learning the metric between group image pairs. To evaluate the performance, we propose a new largest group Re-ID dataset. Extensive experimental results conducted on the dataset demonstrate the effectiveness of our approaches.