Medical image datasets inherently suffer from class imbalance, label scarcity, and intra-class heterogeneity. Under semi-supervised learning, pseudo-label selection remains a central research focus. Class prototypes constructed in the latent space have been studied for pseudo-label selection, particularly because sub-class prototypes can effectively represent within-class heterogeneity in medical imaging datasets. However, since sub-class prototypes are constructed using a relatively small number of samples, they may lead to local optima during prototype updating and usage. In addition, loss weight rebalancing is commonly used to mitigate attention bias in model. Existing methods tend to focus exclusively on improving the minority class, without taking into account ambiguous samples, which are often difficult to learn and contain valuable information. Here, a prototype-driven framework PDMatch is proposed, incorporating Prototype-Driven Expert Voting (PDEV), Majority-class Pseudo-label Under-Sampling (MPUS) and Dual-Balanced Loss (DBL). First, an Expert Prototype Set is constructed, and hierarchical updating is proposed to sufficiently capture the feature distributions. PDEV then generates and filters pseudo-labels through prototype-driven voting, where multiple candidate sub-class prototypes are jointly considered. Second, MPUS offers a concise post-processing strategy that reduces imbalance in the pseudo-label distribution. Finally, Dual-Balanced Loss rebalances loss weights to jointly account for class distribution and sample difficulty. Comprehensive experiments are conducted on three datasets with distinct imbalance structures, demonstrating that our model addresses inherent data challenges and consistently outperforms state-of-the-art methods across multiple metrics. Additionally, we compare our model with clinical expert assessments to underscore its practical value in real-world applications. Source code is available at https://github.com/wang-su-lei/PDMatch .

Channel-state information (CSI)-based fingerprinting for WIFI indoor localization has attracted lots of attention very recently. The frequency diverse and temporally stable CSI better represents the location-dependent channel characteristics than the coarse received signal strength (RSS). However, the acquisition of CSI requires the cooperation of access points (APs) and involves only data frames, which imposes restrictions on real-world deployment. In this article, we present CRISLoc, the first CSI fingerprinting-based localization prototype system using ubiquitous smartphones. CRISLoc operates in a completely passive mode, overhearing the packets on-the-fly for his own CSI acquisition. The smartphone CSI is sanitized via calibrating the distortion enforced by WiFi amplifier circuits. CRISLoc tackles the challenge of altered APs with a joint clustering and outlier detection method to find them. A novel transfer learning approach is proposed to reconstruct the high-dimensional CSI fingerprint database on the basis of the outdated fingerprints and a few fresh measurements, and an enhanced KNN approach is proposed to pinpoint the location of a smartphone. Our study reveals important properties about the stability and sensitivity of smartphone CSI that has not been reported previously. Experimental results show that CRISLoc can achieve a mean error of around 0.29 m in a 6 m × 8 m research laboratory. The mean error increases by 5.4 and 8.6 cm upon the movement of one and two APs, which validates the robustness of CRISLoc against environmental changes.

Owing to the ubiquitous penetration of Wi-Fi in our daily lives, Wi-Fi indoor localization has attracted intensive attentions in the last decade or so. Despite some significant progresses, the high accuracy of existing systems is still achieved at the cost of dense access point (AP) deployment. The more practical single AP localization is largely left as an open problem because the hardware-induced time delay “contaminates” the measurement of signal propagation time in the air. In this article, we design and implement M3to tackle this challenge with commodity Wi-Fi cards. M3exploits a multipath-assisted approach that turns the harmful multipath from foe to friend to enable single AP localization: a device can be pinpointed through the combination of azimuths and the relative time of flight (ToF) of Line-of-Sight (LoS) signal and reflection signals, eliminating the need for multiple APs along with their absolute ToF measurements. M3further utilizes frequency hopping to combine multiple channels to form a virtually wider-spectrum channel for higher ToF resolution. As a prominent feature of M3, the channels do not need to be adjacent. Comprehensive experiments demonstrate that M3outperforms the state-of-the-art systems and achieves a median localization accuracy of 71 cm in three environments with a single AP.

In theory, the capacity of a wireless network grows linearly with the number of users and antennas equipped at the communication devices, and hence large-scale MU-MIMO can scale up the network throughput. However, three main challenges are impeding the implementation of this promising technology in the state-of-the-art WLANs. Firstly, the current large-scale MU-MIMO technology demands a large number of high-priced RF chains. Secondly, the wireless access points (APs) are overwhelmed by channel state information (CSI) feedback for nulling multi-user and -antenna interference. Thirdly, the lack of scalable user selection scheme limits the capability of APs to serve a large user population. To address these problems, we design BUSH, a large-scale MU-MIMO prototype that performs scalable beam user selection with hybrid beamforming for phased-array antennas in legacy WLANs. We design a low complexity algorithm that assigns each pair of RF chain and analog beam to the users to effectively reduce channel correlation and cross-talk interference without instantaneous CSI feedbacks. As a prerequisite of user selection, BUSH presents a low-overhead probing scheme in multi-carrier WLANs and designs a highly accurate blind Power Azimuth Spectrum (PAS) estimation algorithm using a single RF chain. For reducing the number of RF-chains used, the phased-array antennas use analog beamforming to steer beams toward each selected downlink user, and multiple RF chains use beamforming to further mitigate the interference among users. We implement BUSH on a software-defined radio platform and evaluate its performance in more than 30 indoor scenarios. The experimental results reveal that for throughput, BUSH outperforms the legacy 802.11ac by 2.08×, and an alternative benchmark system by 1.22× on average.

Multiuser MIMO (MU-MIMO) empowers access points (APs) with multiple antennas to transmit multiple data streams concurrently to users by exploiting spatial multiplexing. In MU-MIMO, users need to estimate channel state information (CSI) and report it to APs, thus opening a backdoor to attackers who may forge CSI to eavesdrop the content of victims. In this paper, we explore the eavesdropping attack in a novel and practical context in which CSI forgery entangles MU-MIMO user selection in a many-users regime. The attacker hopes to optimize both the eavesdropping opportunity of being selected with the victim and the corresponding decoding quality. We propose new attack and defense mechanisms: (1) USE Attack that enables attackers to achieve near optimal eavesdropping opportunity and high decoding quality through constructing orthogonal CSI against victims followed by stepwise refinements; (2) AngleSec that exploits channel reciprocity for attacker detection without any modification to legacy CSI feedback in which CSI forgery induces a mismatching of downlink and uplink angular spectra at the AP. We implement and evaluate USE Attack and AngleSec in a software defined radio platform WARPv3. Extensive experiments manifest that USE Attack significantly improves the overall eaves-dropping quality compared with state-of-the-art counterparts and AngleSec is able to detect CSI forgery attackers almost for sure.

Large-scale MU-MIMO is a promising technology to scale network capacity and the capacity gain grows linearly with the numbers of antennas and users in theory. However, its practical deployment faces three critical challenges in the state-of-the-art WLANs: i) the demand of a large number of expensive RF chains; ii) the linear growth of feedback overheads with the number of antennas; iii) the lack of scalable user selection scheme for a large user population. In this paper, we design BUSH, a large-scale MU-MIMO prototype that performs scalable beam user selection with hybrid beamforming for phased-array antennas in legacy WLANs. The architecture of BUSH consists of three components. Firstly, a low complexity algorithm assigns each pair of RF chain and analog beam to the users to effectively reduce channel correlation and cross-talk interference without instantaneous CSI feedbacks. Secondly, as a prerequisite of user selection, BUSH presents a low-overhead probing scheme in multi-carrier WLANs, and designs a highly accurate blind Power Azimuth Spectrum (PAS) estimation algorithm using a single RF chain. Thirdly, the phased-array antennas use analog beamforming to steer spatial beams toward each selected downlink user, and the finite number of RF chains use beamforming to further mitigate the interference among users. We implement BUSH on the WARPv3 boards and evaluate its performance in more than 30 indoor scenarios. The experimental results show that in terms of total throughput BUSH outperforms the legacy 802.11ac by 2.08×, and an alternative benchmark system by 1.22× on average.