Recent progress in vision-based fire detection is driven by convolutional neural networks. However, the existing methods fail to achieve a good tradeoff among accuracy, model size, and speed. In this paper, we propose an accurate fire detection method that achieves a better balance in the abovementioned aspects. Specifically, a multiscale feature extraction mechanism is employed to capture richer spatial details, which can enhance the discriminative ability of fire-like objects. Then, the implicit deep supervision mechanism is utilized to enhance the interaction among information flows through dense skip connections. Finally, a channel attention mechanism is employed to selectively emphasize the contribution between different feature maps. Experimental results demonstrate that our method achieves 95.3% accuracy, which outperforms the suboptimal method by 2.5%. Moreover, the speed and model size of our method are 3.76% faster on the GPU and 63.64% smaller than the suboptimal method, respectively.

Radar-based maritime target detection plays an important role in ocean monitoring. Considering the practical application, pulse-compression radar is widely used in terms of civilian offshore surface target detection. The existence of sea clutter will greatly interfere the detection performance of pulse-compression radar. This leads to the low detection performance of traditional algorithms like CFAR (Constant False Alarm Rate). Deep learning methods have made strides in many fields recently, such as natural language processing and speech recognition. Inspired by this idea, we propose a maritime radar target detection method in sea clutter based on CNN (Convolution Neural Network) and dual-perspective attention. The proposed method first encodes the radar echo in high-dimensional space and then extracts the correlation features from the global and local perspectives through the attention mechanism. We deployed the X-band pulse-compression radar on the coast of Hainan, China, and collected a lot of measured data. Experimental results demonstrate that the detection performance of our method outperforms the traditional CFAR methods and the latest deep learning-based methods. In the measured dataset, our proposed method can reach a detection probability of 93.59% under a false alarm rate of 1e-3, reaching the practical application level.

Steganographic algorithms in low-bit-rate compressed speech bring convenience to realize covert communication, meanwhile result in safety issues. The existing steganalysis methods are normally designed for one specific category of steganographic methods, thus lacking generalization capability. In this paper, we propose a general steganalysis method based on code element (CE) embedding, Bi-LSTM and CNN with attention mechanisms. Firstly, CEs in each frame are converted to a multi-hot vector. And each multi-hot vector will be mapped into a fixed-length embedding vector to get a more compact representation by utilizing dictionaries. Then, Bi-LSTM and CNN are applied to extract the contextual information and the local characteristics respectively of these embedding vectors. In addition, the attention mechanisms are introduced in different layers of the network to assign different weights to the output feature within each layer. Finally, the prediction results can be generated by the fully connected layer. Experimental results show that our method performs better than the existing steganalysis methods for detecting multiple steganography methods in the low-bit-rate compressed speech streams.

Covert communication channels can be easily constructed using text steganography based on social media. Offenders can easily utilize these channels to engage in various criminal activities, which brings great challenges in maintaining the security of cyberspace. Among the text information hiding methods, generative linguistic steganography poses the biggest threat to network security because it does not need the original carrier and has high embedding efficiency. The existing generative linguistic steganalysis methods fail to deeply mine text word relation, hence the detection performance is relatively unsatisfactory. In this paper, we prove that there is explicit and latent steganography-sensitive text word relation. Based on this, we propose a generative linguistic steganalysis method based on Explicit and Latent text word relation Mining, named ELM. Firstly, we employ a distributed readin module to convert words into real number vectors. Then, MRA (Mining Relation by Attentions) is proposed to mine the explicit and latent text word relation. Finally, global adaptive classification module is presented to exploit the mined relation feature to predict whether secret information is embedded in the current text segment. Experimental results demonstrate that the detection performance of ELM is better than the existing generative linguistic steganalysis methods.

Radar detection of maritime targets plays an important role in marine environment monitoring. For civil maritime detection in the areas of inshore coastal, pulse-compression radar is universally used owing to its low cost. The complex sea clutter in the practical application will greatly affect the received radar echoes. Due to the inability to accurately describe the differences in characteristics between sea clutter and maritime targets, the detection performance of methods based on mathematical derivation is not satisfactory in actual deployment. Recently, neural-based methods have made strides in many pattern recognition tasks, such as computer vision and natural language processing. The sophisticated deep neural models can be applied to different downstream tasks due to their powerful learning ability. Inspired by this idea, we propose a maritime radar target detection method in sea clutter based on deep learning. To better model the sequence correlation of radar echoes, we propose a Self-Adaption Local Augmented Long Short-Term Memory (SALA-LSTM) structure. The proposed SALA-LSTM integrates adaptive convolution into vanilla LSTM cells, which not only maintains the inherent overall sequence modeling ability of vanilla LSTM, but also strengthens its ability to perceive the correlation on a small scale in the local scope. Based on SALA-LSTM and other neural structures, we propose a radar target detection network. A measured dataset containing different typical scenarios is utilized to evaluate the detection probability and false alarm rate. The detection performance of our proposed network is superior to that of the existing methods.