Alzheimer’s disease (AD) is a degenerative neurological disease that occurs in the elderly with typical symptoms of decline in cognition, manifested by eye movement behaviors. The key to AD treatment requires early detection of cognitive impairment, which relies on frequent medical screening. This article proposes an Internet of Things (IoT) architecture constructed with eye-tracker (ET) nodes and cloud-based diagnosis enabled by machine learning (ML), which can provide convenient screening of oculomotor abnormalities and automatic identification of early-stage AD. The bespoke ET nodes collect 3-D oculomotor responses from diverse stereo video stimulation trials and transmit data into a dedicated multimodal ML (MMML) algorithm in the cloud. The algorithm incorporates multimodal features extracted from diverse oculomotor types to enhance the classification accuracy and optimized data dimension reduction in feature fusion to improve the classifier’s performance. From evaluation, the proposed method can distinguish AD patients from the control group with 86% accuracy (ACC), 78% true positive rate (TPR), and 90% positive predictive value (PPV). The results confirm the effectiveness of our MMML algorithm in AD diagnosis with the fusion of multimodal oculomotor features and prove the feasibility of our IoT-powered eye-tracking solution for AD screening.

Medical image fusion integrates complementary information from multimodal medical images to provide comprehensive references for clinical decision-making, such as the diagnosis of Alzheimer’s disease and the detection and segmentation of brain tumors. Although traditional and deep learning-based fusion methods have been extensively studied, they often fail to devise targeted strategies that fully utilize distinct regional or feature-specific information. This paper proposes SAFFusion, a saliency-aware frequency fusion network that integrates intensity and texture cues from multimodal medical images. We first introduce Mamba-UNet, a multiscale encoder-decoder architecture enhanced by the Mamba design, to improve global modeling in feature extraction and image reconstruction. By employing the contourlet transform in Mamba-UNet, we replace conventional pooling with multiscale representations and decompose spatial features into high- and low-frequency subbands. A dual-branch frequency feature fusion module then fuses cross-modality information according to the distinct characteristics of these frequency subbands. Furthermore, we apply latent low-rank representation (LatLRR) to assess image saliency and implement adaptive loss constraints to preserve information in salient and non-salient regions. Quantitative results on CT/MRI, SPECT/MRI, and PET/MRI fusion tasks show that SAFFusion outperforms state-of-the-art methods. Qualitative evaluations confirm that SAFFusion effectively merges prominent intensity features and rich textures from multiple sources.

Eye-tracking technology is increasingly used in applications such as 3D displays and human-computer interaction (HCI). However, most current eye trackers focus on 2D point-of-gaze (PoG) estimation and cannot provide accurate gaze depth. Concerning future applications such as HCI with 3D displays, we propose an integrated binocular eye-tracking device with stereo stimuli to provide highly accurate 3D PoG estimation. In our device, the 3D stereo imaging system can provide users with a friendly and immersive 3D visual experience without wearing any accessories. The eye-capturing system can directly record the users’ eye movements under 3D stimuli without disturbance, which can realize front views of eye images while ensuring the user’s wide field of view (FOV). A regression-based 3D eye-tracking model is built based on collected eye movement data under stereo stimuli. Our model estimates users’ 2D gaze with features defined by eye region landmarks and further estimates 3D gaze with a multi-source feature set constructed by comprehensive eye movement features and disparity features from stereo stimuli. Two test stereo scenes with different depths of field are designed to verify the model’s effectiveness. Experimental results of four-fold cross-validation show that the average error for 2D gaze estimation was 0.65°. For 3D gaze estimation, the average errors are 1.69 cm over the workspace volume 50 × 30 × 75 cm ³ and 0.14 m over the workspace volume 2.4 × 4.0 × 7.9 m ³ . Two preliminary validation experiments also demonstrate that our system has broad application prospects, such as 3D vision technologies and medical applications related to neurological diseases.

The parametric acoustic effect has gained much interest in airborne applications as parametric acoustic loudspeakers (PALs) for the unique characteristics of generating self-demodulated low-frequency acoustic waves with high directivity. The development of PAL applications currently requires advanced spatial control of demodulated audio signals for more sophisticated sound field reproduction. Targeting to enhance the control flexibility, this paper proposes an efficient, fully FPGA-based PAL system to provide multiple low-distortion audio signals of different contents to separate directions from a single PAL device. The proposed system can achieve accurate beamsteering by providing channel time delays in nanosecond resolution and can generate independent parametric beams from a time-division-multiplexing (TDM) scheme. The paper presents a compact and scalable FPGA solution for PAL in signal preprocessing, beamsteering, and multi-beam control. The proposed system is verified in simulation and demonstrative experiments for the realization of flexible steering of multiple distinct audio signals into desired directions simultaneously under the TDM control.

Sound source localization is essential for machine-based environmental perception when visual methods are not applicable. Current array-based localization methods often require many microphones and are heavy in computing. This article proposes an efficient algorithm for estimating the location of a single source in 3-D based on the time difference of arrival and interaural level difference (TDOA-ILD) with an array of only three microphones. The algorithm can compute the source 3-D coordinates with a closed-form analytical solution derived from geometrical modeling and identify the actual source from the cone of the confusion area through clustering methods. This article comprehensively evaluates the algorithm’s behavior for various array sizes and source locations in a wide range of signal-to-noise ratios (SNRs) with simulative models to prove that the algorithm achieves estimation errors close to its Cramer–Rao lower bound (CRLB). Experimental evaluation demonstrates the method’s localization feasibility in outdoor open environments with off-the-shelf sensing equipment. The proposed scheme is suitable for real-time 3-D sound source localization with cost-effective hardware.