Explore the vast range of titles available.

We describe a state-of-the-art sentiment analysis system that detects (a) the sentiment of short informal textual messages such as tweets and SMS (message-level task) and (b) the sentiment of a word or a phrase within a message (term-level task). The system is based on a supervised statistical text classification approach leveraging a variety of surface-form, semantic, and sentiment features. The sentiment features are primarily derived from novel high-coverage tweet-specific sentiment lexicons. These lexicons are automatically generated from tweets with sentiment-word hashtags and from tweets with emoticons. To adequately capture the sentiment of words in negated contexts, a separate sentiment lexicon is generated for negated words. The system ranked first in the SemEval-2013 shared task `Sentiment Analysis in Twitter' (Task 2), obtaining an F-score of 69.02 in the message-level task and 88.93 in the term-level task. Post-competition improvements boost the performance to an F-score of 70.45 (message-level task) and 89.50 (term-level task). The system also obtains state-of-the-art performance on two additional datasets: the SemEval-2013 SMS test set and a corpus of movie review excerpts. The ablation experiments demonstrate that the use of the automatically generated lexicons results in performance gains of up to 6.5 absolute percentage points.

The rapid development of unmanned aerial vehicle (UAV) technology necessitates reliable recognition methods. Radio frequency (RF)-based recognition is promising, but conventional real-valued CNNs (RV-CNNs) typically discard phase information from RF spectrograms, leading to degraded performance under low-signal-to-noise ratio (SNR) conditions. To address this, this paper proposes a complex-valued CNN (CV-CNN) that operates on a constructed complex representation, where the real part is the logarithmic power spectral density (PSD) and the imaginary part is derived from Sobel edge detection. This enables genuine complex convolutions that fuse magnitude and structural cues, enhancing noise resilience. As complex-valued networks are known to be sensitive to architectural choices, we conduct comprehensive ablation experiments to investigate the impact of key hyperparameters on model performance, revealing critical stability constraints (e.g., performance collapse beyond 4–5 network depth). Evaluated on the 25-class DroneRFa dataset, the proposed model achieves 100.00% accuracy under noise-free conditions. Crucially, it demonstrates significantly superior robustness in low-SNR regimes: at −20 dB SNR, it attains 15.58% accuracy, over seven times higher than a dual-channel RV-CNN (2.20%) with identical inputs; at −15 dB, it reaches 45.86% versus 14.03%. These results demonstrate that the CV-CNN exhibits potentially superior robustness and interference resistance in comparison to its real-valued counterpart, maintaining high recognition accuracy even under low-SNR conditions.

This study proposes BAGWO, a novel hybrid optimization algorithm that integrates the Beetle Antennae Search algorithm (BAS) and the Grey Wolf Optimizer (GWO) to leverage their complementary strengths while enhancing their original strategies. BAGWO introduces three key improvements: the charisma concept and its update strategy based on the sigmoid function, the local exploitation frequency update strategy driven by the cosine function, and the switching strategy for the antennae length decay rate. These improvements are rigorously validated through ablation experiments. Comprehensive evaluations on 24 benchmark functions from CEC 2005 and CEC 2017, along with eight real-world engineering problems, demonstrate that BAGWO achieves stable convergence and superior optimization performance. Extensive testing and quantitative statistical analyses confirm that BAGWO significantly outperforms competing algorithms in terms of solution accuracy and stability, highlighting its strong competitiveness and potential for practical applications in global optimization.

DNA computing is one of the more popular computational methods currently studied, but the requirements for nucleic acid molecules in DNA sequences are high, and it is an important challenge to design reasonable and high-quality DNA sequences while satisfying various constraints. Evolutionary algorithms have good applications in DNA sequence optimization problems, but they still have some limitations. To this end, this paper proposes a JAYA algorithm based on normal clouds, referred to as IJAYA, which uses a combinatorial learning approach to update the optimal and worst positions, which is used to manipulate the subsequent merit search means, and then enhances the local search ability of individuals through the normal cloud model, and finally rejects the worst solutions through a harmony search algorithm to find more reasonable and high-quality solutions. The validity of IJAYA is verified in six benchmark functions, in comparison with multiple variants of JAYA and two statistical tests. In the DNA sequence design optimization problem, the average DNA metrics optimized by IJAYA are: 0 (Continuity), 0 (Hairpin), 59.43 (H-measure), 46.57 (Similarity) and 63.79 (Similarity). The feasibility and practicality of IJAYA was verified by comparing it with the solution algorithms proposed in recent years and ablation experiments.

This study aims to enhance the accuracy and efficiency of energy consumption prediction during exercise training and address the limitations of existing methods in terms of data feature extraction, model complexity, and adaptability to practical applications. This study proposes an optimized energy consumption prediction model based on accelerometer sensor data and deep learning techniques. In this study, a model architecture integrating Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory (Bi-LSTM) network, and an attention mechanism is constructed, with a focus on optimizing local feature extraction, temporal modeling, and dynamic weight allocation capabilities. Additionally, by analyzing the relationship between the X, Y, and Z-axis accelerations, overall magnitude, and energy consumption, a multidimensional feature analysis framework is proposed to enhance the model’s comprehensive understanding of motion data. To verify the performance of the model, performance comparison experiments and ablation experiments are designed. The experimental results demonstrate that the optimized model achieves a Mean Squared Error (MSE) of 0.273, an R 2 of 0.887, and a standard deviation of 0.046 on acceleration data, significantly outperforming comparison models such as Temporal Convolutional Network (TCN), Gated Recurrent Unit with Attention Mechanism (GRU-ATT), and Self-Supervised Transformer (SST). Furthermore, ablation experiments reveal that the synergistic effects of the convolutional network, Bi-LSTM, and attention mechanism significantly improve prediction accuracy and model robustness. Further analysis shows that the optimized model achieves a correlation of 0.829 between overall magnitude and energy consumption, validating its ability to capture complex motion features. Therefore, this study provides an efficient, accurate, and highly adaptable solution for the field of energy consumption prediction in exercise, contributing to research on intelligent motion monitoring, health management, and personalized training program development.

With the rapid development of renewable energy, surface defect detection of photovoltaic panels has become an important link in improving photoelectric conversion efficiency and ensuring safety. However, there are various types of surface defects on photovoltaic panels with complex backgrounds, and traditional detection methods face challenges such as low efficiency and insufficient accuracy. This article proposes a lightweight improved model AE-YOLO (YOLOv11+Adown +ECA) based on YOLOv11, which improves detection performance and efficiency by introducing a lightweight dynamic down-sampling module (Adown) and an Efficient Channel Attention (ECA). The Adown module reduces the complexity of computational and parameters through steps such as average pooling preprocessing, channel dimension segmentation, branch feature processing, and feature fusion. The ECA mechanism enhances the model's response to defect sensitive feature channels and improves its ability to discriminate low contrast small defects through adaptive average pooling, one-dimensional convolution, and sigmoid activation. The experimental results indicate that the AE-YOLO model performs well on the PVEL-AD dataset. mAP@0.5 reached 90.3%, the parameter count decreased by 18.7%, the computational load decreased by 19%, and the inference speed reached 259.56 FPS. The ablation experiment further validated the complementarity between Adown and ECA modules, providing an innovative solution for real-time and accurate defect detection of photovoltaic panels in industrial scenarios.

The recognition technology of coal and gangue is one of the key technologies of intelligent mine construction. Aiming at the problems of the low accuracy of coal and gangue recognition models and the difficult recognition of small-target coal and gangue caused by low-illumination and high-dust environments in the coal mine working face, a coal and gangue recognition model based on the improved YOLOv7-tiny target detection algorithm is proposed. This paper proposes three model improvement methods. The coordinate attention mechanism is introduced to improve the feature expression ability of the model. The contextual transformer module is added after the spatial pyramid pooling structure to improve the feature extraction ability of the model. Based on the idea of the weighted bidirectional feature pyramid, the four branch modules in the high-efficiency layer aggregation network are weighted and cascaded to improve the recognition ability of the model for useful features. The experimental results show that the average precision mean of the improved YOLOv7-tiny model is 97.54%, and the FPS is 24.73 f·s−1. Compared with the Faster-RCNN, YOLOv3, YOLOv4, YOLOv4-VGG, YOLOv5s, YOLOv7, and YOLOv7-tiny models, the improved YOLOv7-tiny model has the highest recognition rate and the fastest recognition speed. Finally, the improved YOLOv7-tiny model is verified by field tests in coal mines, which provides an effective technical means for the accurate identification of coal and gangue.

Accurate parcel identification in disordered logistics environments poses significant challenges due to varying package sizes, materials, and orientations. This study presents an improved YOLOv8-Efficiency algorithm tailored for such complex scenarios. The proposed algorithm introduces the C2f-OR module to reduce parameters and computation, the Conv-Ghost module for efficient feature extraction, and the HIoU loss function to enhance identification accuracy. By constructing a dataset of 4689 photos, experiments demonstrate the algorithm's effectiveness, achieving a 93.2% mAP, a 1.6% recall rate improvement, and a significant reduction in computational complexity (9.9% decrease in FLOPs). This work provides a robust solution for real-time parcel identification in disordered logistics, facilitating automation and efficiency in logistics operations.

MicroRNAs (miRNAs) are endogenous non-coding RNAs approximately 23 nucleotides in length, playing significant roles in various cellular processes. Numerous studies have shown that miRNAs are involved in the regulation of many human diseases. Accurate prediction of miRNA-disease associations is crucial for early diagnosis, treatment, and prognosis assessment of diseases. In this paper, we propose the Autoencoder Inductive Matrix Completion (AEIMC) model to identify potential miRNA-disease associations. The model captures interaction features from multiple similarity networks, including miRNA functional similarity, miRNA sequence similarity, disease semantic similarity, disease ontology similarity, and Gaussian interaction kernel similarity between miRNAs and diseases. Autoencoders are used to extract more complex and abstract data representations, which are then input into the inductive matrix completion model for association prediction. The effectiveness of the model is validated through cross-validation, stratified threshold evaluation, and case studies, while ablation experiments further confirm the necessity of introducing sequence and ontology similarities for the first time.

In response to the low accuracy and slow detection speed of chili recognition in natural environments, this study proposes a chili pepper object detection method based on the improved YOLOv8n. Evaluations were conducted among YOLOv5n, YOLOv6n, YOLOv7-tiny, YOLOv8n, YOLOv9, and YOLOv10 to select the optimal model. YOLOv8n was chosen as the baseline and improved as follows: (1) Replacing the YOLOv8 backbone with the improved HGNetV2 model to reduce floating-point operations and computational load during convolution. (2) Integrating the SEAM (spatially enhanced attention module) into the YOLOv8 detection head to enhance feature extraction capability under chili fruit occlusion. (3) Optimizing feature fusion using the dilated reparam block module in certain C2f (CSP bottleneck with two convolutions). (4) Substituting the traditional upsample operator with the CARAFE(content-aware reassembly of features) upsampling operator to further enhance network feature fusion capability and improve detection performance. On a custom-built chili dataset, the F0.5-score, mAP0.5, and mAP0.5:0.95 metrics improved by 1.98, 2, and 5.2 percentage points, respectively, over the original model, achieving 96.47%, 96.3%, and 79.4%. The improved model reduced parameter count and GFLOPs by 29.5% and 28.4% respectively, with a final model size of 4.6 MB. Thus, this method effectively enhances chili target detection, providing a technical foundation for intelligent chili harvesting processes.