This study proposes a multifunctional absorber in the terahertz (THz) regime based on vanadium dioxide (VO₂) and graphene with either–or band selector applications, which can be realized by electrically and thermally controlling the Fermi energy level of graphene and vanadium dioxide, respectively. The broadband absorption can be achieved with absorptance exceeding 90%, when the VO₂ film is in the metallic phase and the Fermi energy levels of the upper and lower graphene layers are simultaneously set to 0.6 and 0 eV, respectively. The double narrowband can be realized when the VO₂ film is in the insulating phase and the Fermi energy levels in upper and lower graphene layers are set as 0 and 0.8 eV, respectively. By flexibly shifting between the broadband and the double narrowband, the proposed absorber can be used as an either–or band selector, corresponding optional bandwidth from 2.05 to 2.35 THz, and 3.25 to 3.6 THz. Furthermore, single narrowband absorption can be achieved by setting the conductivity of the VO₂ film to appropriate values. The proposed absorber can be used in the THz regime in applications such as multifunctional devices, switches, cloaking objects, and band selectors.

Traditional fish farming methods suffer from backward production, low efficiency, low yield, and environmental pollution. As a result of thorough research using deep learning technology, the industrial aquaculture model has experienced gradual maturation. A variety of complex factors makes it difficult to extract effective features, which results in less-than-good model performance. This paper proposes a fish detection method that combines a triple attention mechanism with a You Only Look Once (TAM-YOLO)model. In order to enhance the speed of model training, the process of data encapsulation incorporates positive sample matching. An exponential moving average (EMA) is incorporated into the training process to make the model more robust, and coordinate attention (CA) and a convolutional block attention module are integrated into the YOLOv5s backbone to enhance the feature extraction of channels and spatial locations. The extracted feature maps are input to the PANet path aggregation network, and the underlying information is stacked with the feature maps. The method improves the detection accuracy of underwater blurred and distorted fish images. Experimental results show that the proposed TAM-YOLO model outperforms YOLOv3, YOLOv4, YOLOv5s, YOLOv5m, and SSD, with a mAP value of 95.88%, thus providing a new strategy for fish detection.

A broadband absorber based on metamaterials of graphene and vanadium dioxide (VO₂) is proposed and investigated in the terahertz (THz) regime, which can be used for switch applications with a dynamically variable bandwidth by electrically and thermally controlling the Fermi energy level of graphene and the conductivity of VO₂, respectively. The proposed absorber turns ‘on’ from 1.5 to 5.4 THz, with the modulation depth reaching 97.1% and the absorptance exceeding 90% when the Fermi energy levels of graphene are set as 0.7 eV, and VO₂ is in the metallic phase. On the contrary, the absorptance is close to zero and the absorber turns ‘off’ with the Fermi energy level setting at 0 eV and VO₂ in the insulating phase. Furthermore, other four broadband absorption modes can be achieved utilizing the active materials graphene and VO₂. The proposed terahertz absorber may benefit the areas of broadband switch, cloaking objects, THz communications and other applications.

Predicting drug-target affinity is crucial in the field of drug discovery. To further improve the accuracy of predictions, this paper proposes a drug-target affinity prediction model, GRAM-DTA, based on graph representation and attention fusion mechanisms. The model represents the input features of drugs and targets as graph data and utilizes deep graph isomorphism networks and graph neural network modules combining graph convolutional networks and graph attention networks to process the feature information of drugs and targets, respectively. In the feature fusion stage, an attention mechanism is introduced to simulate the interactions between drug molecules and amino acids, dynamically adjust the importance of features, and capture the interaction patterns between drugs and targets. Experiments were conducted on the Davis and KIBA benchmark datasets, and the model was compared with current state-of-the-art models.The experimental results show that our model achieved a 3.1% and 3.4% improvement in the r_m^2 value compared to the best-performing baseline model, significantly outperforming other traditional methods and baseline models.