Emotion recognition remains an intricate task at the crossroads of psychology and artificial intelligence, necessitating real-time, accurate discernment of implicit emotional states. Here, we introduce a pioneering wearable dual-modal device, synergizing functional near-infrared spectroscopy (fNIRS) and electroencephalography (EEG) to meet this demand. The first-of-its-kind fNIRS-EEG ensemble exploits a temporal convolutional network (TC-ResNet) that takes 24 fNIRS and 16 EEG channels as input for the extraction and recognition of emotional features. Our system has many advantages including its portability, battery efficiency, wireless capabilities, and scalable architecture. It offers a real-time visual interface for the observation of cerebral electrical and hemodynamic changes, tailored for a variety of real-world scenarios. Our approach is a comprehensive emotional detection strategy, with new designs in system architecture and deployment and improvement in signal processing and interpretation. We examine the interplay of emotions and physiological responses to elucidate the cognitive processes of emotion regulation. An extensive evaluation of 30 subjects under four emotion induction protocols demonstrates our bimodal system’s excellence in detecting emotions, with an impressive classification accuracy of 99.81% and its ability to reveal the interconnection between fNIRS and EEG signals. Compared with the latest unimodal identification methods, our bimodal approach shows significant accuracy gains of 0.24% for EEG and 8.37% for fNIRS. Moreover, our proposed TC-ResNet-driven temporal convolutional fusion technique outperforms conventional EEG-fNIRS fusion methods, improving the recognition accuracy from 0.7% to 32.98%. This research presents a groundbreaking advancement in affective computing that combines biological engineering and artificial intelligence. Our integrated solution facilitates nuanced and responsive affective intelligence in practical applications, with far-reaching impacts on personalized healthcare, education, and human–computer interaction paradigms.

Distributed optical fiber vibration sensing system (DVS) base on phase-sensitive OTDR is widely used for its simple structure and high sensitivity. Signal recognition is crucial for DVS because it can help to classify the different types of vibration events. Deep learning provides accurate event classification and can automatically extract features according to sample distribution. However, almost all current methods focus on closed set recognition, which misclassifies unknown events into known categories thus reduces the recognition accuracy of sensing system. In this paper, we propose a novel open set event recognition model based on one-dimension residual learning convolution neural network (1-D RL-CNN) with OpenMax algorithm for DVS, which is capable of processing the signals of known and unknown categories. The experimental results show that the proposed recognition model improves the classification accuracy greatly compared with conventional 1-D CNN signal classification method. The overall open-set classification accuracy of 1-D RL-CNN with OpenMax is 91.19%, which is improved of 18.47% and 7.57% compared with 1-D CNN with SoftMax and 1-D CNN with OpenMax.

Optical fiber sensors are used for partial discharge detection in many applications due their advantage of strong anti-electromagnetic interference capability. Multi-point distributed partial discharge detection and location are important for electrical equipment. In this paper, a distributed partial discharge location and detection scheme based on optical fiber Rayleigh backscattering light interference is experimentally demonstrated. At the same time, the location and extraction algorithm is used to demodulate the partial discharge signal; furthermore, the high-pass filter is used to reduce the system low-frequency noise and environment noise. It is clear that the proposed system can detect a partial discharge signal generated by metal needle sensitivity, and the detectable frequency range is 0–2.5 kHz. We carried out 10 locating tests for two sensing units, the experimental results show that the maximum location error is 1.0 m, and the maximum standard deviation is 0.3795. At same time, the signal-to-noise ratio (SNR) of sensing unit 1 and sensing unit 2 are greatly improved after demodulation, which are 39.7 and 38.8, respectively. This provides a new method for a multipoint-distributed optical fiber sensor used for detecting and locating a long-distance electrical equipment partial discharge signal.

Distributed optical fiber vibration sensing systems (DVS) are widely employed in perimeter security for their high sensitivity, simplicity, and strong immunity to electromagnetic interference. However, these systems are facing with two serious challenges: accurately classifying closed-set signals (known events) and detecting open-set signals (unknown events). To address this, we propose an open-set recognition framework, ResEff-OpenGAN-LN. By integrating layer normalization into the OpenGAN architecture, this framework mitigates instability caused by input feature variations while leveraging ResEff for efficient feature extraction to enhance closed-set classification. Experimental results show that ResEff achieves 99.92% accuracy on closed-set tasks, and ResEff-OpenGAN-LN obtains an AUROC of 0.9900 with 96.63% overall accuracy on mixed datasets containing open-set and closed-set signals, validating its potential to improve intrusion detection and reduce false alarms.

Existing deep learning models often underperform in cross-domain few-shot tasks for distributed vibration sensing (DVS), largely due to domain shifts introduced by variations in device types and deployment scenarios. To address this challenge, we introduce the cross-domain few-shot learning (CDFSL) paradigm to the field of distributed fiber-optic vibration signal recognition for the first time and propose a novel framework, the cosine-initialized masked autoencoder (Cosine-Initialized-MAE). This approach begins with self-supervised pretraining on large-scale unlabeled source-domain data using a masked autoencoder (MAE), enabling the extraction of transferable, general-purpose feature representations. Subsequently, the model is efficiently adapted to the target domain using only a few labeled samples, via a single-step fine-tuning procedure that incorporates weight imprinting and cosine similarity classification. Departing from conventional episodic evaluation, our method employs a fixed evaluation protocol: the model is fine-tuned once on a k-shot support set (k $\in $ {1, 5, 10}) and then evaluated on the remaining (500−k) samples per class. The proposed framework achieves accuracies of 78.92%, 87.84%, and 91.80% on 5-way 1-shot, 5-shot, and 10-shot tasks, respectively—substantially outperforming established self-supervised and few-shot learning baselines. These results highlight the framework’s strong generalization under limited supervision and underscore its potential for low-resource cross-domain recognition in DVS systems.