With the rapid development of information technology, the demand for digital agriculture is increasing. As an important agricultural production topic, crop yield has always attracted much attention. Currently, artificial intelligence, particularly machine learning, has become the leading approach for crop yield prediction. As a result, developing a machine learning method that accurately predicts crop yield has become one of the central challenges in digital agriculture. Unlike traditional regression prediction problems, crop yield prediction has a significant time correlation. For example, weather data for each county show strong temporal correlations. Moreover, geographic information from different regions also impacts crop yield to a certain extent. For example, if a county’s neighboring counties have a good harvest, then this county is likely to have high yields as well. This paper introduces a novel hybrid deep learning framework that combines convolutional neural network (CNN), graph attention network (GAT) and long short-term memory (LSTM) modules to enhance prediction accuracy. Specifically, CNN is employed to extract the features from the input data for each county in each year. GAT is introduced to model the geographical relationships between neighboring counties, allowing the model to capture spatial dependencies more effectively. LSTM is used to extract the temporal information within many years. The proposed hybrid deep learning framework CNN-GAT-LSTM captures both the temporal and spatial relationships, thereby improving the accuracy of yield prediction. We conduct experiments on a nationwide dataset that includes data from 1115 soybean-producing counties in 13 states in the United States covering the years from 1980 to 2018. We evaluate the performance of our proposed CNN-GAT-LSTM model based on three metrics, namely root of the mean squared error (RMSE), R-squared (R2) and correlation coefficient (Corr). The experimental results demonstrate that the proposed model achieves significant performance improvements over the existing state-of-the-art model, with RMSE reduced by 5%, R2 improved by 6% and Corr enhanced by 4%.
Electromyography (EMG) signals reflect hand motion intention and exhibit a certain degree of amplitude symmetry. Nowadays, recognition of hand motion intention based on EMG has enriched its burgeoning promotion in various applications, such as rehabilitation, prostheses, and intelligent supply chains. For instance, the motion intentions of humans can be conveyed to logistics equipment, thereby improving the level of intelligence in a supply chain. To enhance the recognition accuracy of multiple hand motion intentions, this paper proposes a hand motion intention recognition method that decodes EMG signals based on improved long short-term memory (LSTM). Firstly, we performed preprocessing and utilized overlapping sliding windows on EMG segments. Secondly, we chose LSTM and improved it so as to capture features and enable prediction of hand motion intention. Specifically, we introduced the optimal key hyperparameter combination in the LSTM model using a genetic algorithm (GA). We found that our proposed method achieved relatively high accuracy in detecting hand motion intention, with average accuracies of 92.0% (five gestures) and 89.7% (seven gestures), while the highest accuracy reached 100.0% (seven gestures). Our paper may provide a way to predict the motion intention of the human hand for intention communication.
Intelligent bearing diagnosis and maintenance require question-answering systems that combine asset-specific condition evidence with engineering knowledge. However, existing bearing diagnosis studies mainly predict fault labels or health states, while document-based RAG systems generally lack access to the condition of a specific asset. Digital twin-based systems provide structured condition data but offer limited support for manual-grounded diagnostic interpretation. Consequently, there is still no unified route-aware framework and benchmark for determining the evidence that is required by different diagnostic questions and evaluating route selection, DT querying, document retrieval, and answer grounding separately. To address this gap, this paper proposes a route-aware digital twin (DT) and retrieval-augmented generation (RAG) large language model (LLM) agent framework for bearing diagnosis question answering (QA). The framework routes questions to four paths: unrelated, DT-only, RAG-only, and DT+RAG. A route-specific 140-question benchmark is constructed from run-to-failure bearing data and a technical maintenance manual corpus to evaluate the router and the four processing paths. The hybrid router achieves an accuracy of 0.979, while the DT-only module obtains 0.967 query accuracy and 0.900 joint accuracy. Hybrid + reranker performs best for RAG-only Hit@5, mean reciprocal rank (MRR), and context precision, whereas hybrid performs best for DT+RAG Hit@1, MRR, faithfulness, and context precision. These results demonstrate that route-aware evidence selection provides a transparent and evaluable approach to LLM-based bearing diagnosis QA.
Surface Electromyography (sEMG)-based gesture recognition plays a crucial role in advanced human-computer interaction (HCI) scenarios, including intelligent prosthetics, rehabilitation robotics, industrial product sorting, and immersive virtual/augmented reality control. The recognition accuracies of a multitude of gross and fine gestures from sEMG signals tend to be affected by complex temporal dynamics and inter-channel variability. This paper proposes a hierarchical hybrid deep learning model that cascades Transformer, channel attention (CA), and bidirectional long short-term memory (BiLSTM) networks for effective gesture classification. In the proposed architecture, the preprocessed sEMG signals are first projected into a latent feature space and fed into a Transformer encoder to capture long-range temporal dependencies and global contextual information. A channel attention mechanism is then employed to adaptively recalibrate inter-channel feature representations, enhancing discriminative muscle activation patterns while suppressing redundant information. Subsequently, a BiLSTM module models bidirectional temporal dynamics to capture the initiation, evolution, and termination characteristics of gestures. An attention-based temporal pooling strategy further emphasizes informative time steps before the classification head. Our proposed model was evaluated on the NinaPro DB5 and BandMyo dataset comprising various gestures, including fine finger and wrist movements. Results show that our method performs better on NinaPro DB5 dataset. An overall accuracy of 81.96% and a weight F1-score of 0.82 are achieved, outperforming individual Transformer, CA, and BiLSTM. The highest accuracy of certain gesture could reach 96.55%. The comparison demonstrates that the synergistic integration of global dependency modeling, channel-wise feature refinement, and bidirectional temporal learning improves overall recognition performance, particularly for certain fine gestures. Moreover, the parameter number of our proposed model is low (0.20 million) in comparison with existing approaches. Our work may provide a potential solution for effective sEMG-based gesture recognition for real-world human-computer interaction applications.
Introduction: When the brain is regarded as a complex dynamic system, its abnormalities often show the overall network reorganization. Traditional analysis for major depressive disorder (MDD) based on single-channel features of electroencephalogram (EEG) mainly focuses on signal changes, while ignoring inter-regional functional connectivity and network topology. As a consequence, it is challenging to reveal the systemic abnormal mechanisms. Methods: To address this problem, this study built a framework of multi-frequency brain functional network (BFN) construction and recognition based on resting-state EEG. Phase-locking value (PLV) and Pearson correlation coefficient (PCC) were separately utilized to characterize phase synchronization and amplitude correlation. Abnormal BFNs in MDD were systematically evaluated from both connectivity patterns and node topology. Results: Results suggest that MDD patients exhibit increased connectivity in the left frontal, central, and parietal regions in the low-frequency bands. In the mid-frequency bands, increased fronto-central connectivity and reduced posterior connectivity are observed. In the high-frequency band, the connectivity pattern is characterized by increased fronto-temporal and centro-temporal connectivity, together with reduced connectivity in the posterior regions. At the node level, the most prominent alterations are concentrated in the parietal region, particularly in the α band, where altered betweenness centrality (BC) is consistently identified across both PLV and PCC networks. On this basis, the support vector machine (SVM) classifier was employed to evaluate the discriminative capability of PLV-Edge, PCC-Edge, PLV-Node, and PCC-Node features for MDD identification. Among the four feature types, PLV-Node features achieve the highest mean classification balanced accuracy of 81.44%, and PCC-Node features achieve a mean balanced accuracy of 79.14%. Discussion: All four feature types demonstrate discriminative potential for distinguishing patients with MDD from healthy controls (HCs). These findings suggest that functional connectivity-based brain network features may provide meaningful information for the auxiliary identification of MDD.