Leukemia is a common and highly dangerous blood disease that requires early detection and treatment. Currently, the diagnosis of leukemia types mainly relies on the pathologist’s morphological examination of blood cell images, which is a tedious and time-consuming process, and the diagnosis results are highly subjective and prone to misdiagnosis and missed diagnosis. This research suggests a blood cell image recognition technique based on an enhanced Vision Transformer to address these problems. Firstly, this paper incorporate convolutions with token embedding to replace the positional encoding which represent coarse spatial information. Then based on the Transformer’s self-attention mechanism, this paper proposes a sparse attention module that can select identifying regions in the image, further enhancing the model’s fine-grained feature expression capability. Finally, this paper uses a contrastive loss function to further increase the intra-class consistency and inter-class difference of classification features. According to experimental results, The model in this study has an identification accuracy of 92.49% on the Munich single-cell morphological dataset, which is an improvement of 1.41% over the baseline. And comparing with sota Swin transformer, this method still get greater performance. So our method has the potential to provide reference for clinical diagnosis by physicians.

In this letter, a novel general design method of quasi-orthogonal space-time block codes for four antennae is presented. Comparison with the design method proposed by Jafarkhani, this method enlarges the number of quasi-orthogonal space-time block codes. The performance of these codes is also analyzed and the simulation results show that it is similar to even better than that of the codes proposed by Jafarkhani.

Even with the recent development of new types of social networking services such as microblogs, Bulletin Board Systems (BBS) remains popular for local communities and vertical discussions. These BBS sites have high volume of traffic everyday with user discussions on a variety of topics. Therefore it is difficult for BBS visitors to find the posts that they are interested in from the large amount of discussion threads. We attempt to explore several main characteristics of BBS, including organizational flexibility of BBS texts, high data volume and aging characteristic of BBS topics. Based on these characteristics, we propose a novel method of Online Topic Detection (OTD) on BBS, which mainly includes a representative post selection procedure based on Markov chain model and an efficient topic clustering algorithm with candidate topic set generation based on Aging Theory. Experimental results show that our method improves the performance of OTD in BBS environment in both detection accuracy and time efficiency. In addition, analysis on the aging characteristic of discussion topics shows that the generation and aging of topics on BBS is very fast, so it is wise to introduce candidate topic set generation strategy based on Aging Theory into the topic clustering algorithm.

To alleviate the problem of the dependency on the quantity of the training sample data in speech emotion recognition, a weighted gradient pre-train algorithm for low-resource speech emotion recognition is proposed. Multiple public emotion corpora are used for pre-training to generate shared hidden layer (SHL) parameters with the generalization ability. The parameters are used to initialize the downsteam network of the recognition task for the low-resource dataset, thereby improving the recognition performance on low-resource emotion corpora. However, the emotion categories are different among the public corpora, and the number of samples varies greatly, which will increase the difficulty of joint training on multiple emotion datasets. To this end, a weighted gradient (WG) algorithm is proposed to enable the shared layer to learn the generalized representation of different datasets without affecting the priority of the emotion recognition on each corpus. Experiments show that the accuracy is improved by using CASIA, IEMOCAP, and eNTERFACE as the known datasets to pre-train the emotion models of GEMEP, and the performance could be improved further by combining WG with gradient reversal layer.

Cloud computing has attracted a growing number of enterprises to move their business to the cloud because of the associated operational and cost benefits. Improving availability is one of the major concerns of cloud application owners because modern applications generally comprise a large number of components and failures are common at scale. Fault tolerance enables an application to continue operating properly when failure occurs, but fault tolerance strategy is typically employed for the most important components because of financial concerns. Therefore, identifying important components has become a critical research issue. To address this problem, we propose a failure-sensitive structure-based component ranking approach (FSCRank), which integrates component failure impact and application structure information into component importance evaluation. An iterative ranking algorithm is developed according to the structural characteristics of cloud applications. The experimental results show that FSCRank outperforms the other two structure-based ranking algorithms for cloud applications. In addition, factors that affect application availability optimization are analyzed and summarized. The experimental results suggest that the availability of cloud applications can be greatly improved by implementing fault tolerance strategy for the important components identified by FSCRank.

Depression endangers people's health conditions and affects the social order as a mental disorder. As an efficient diagnosis of depression, automatic depression detection has attracted lots of researcher's interest. This study presents an attention-based Long Short-Term Memory (LSTM) model for depression detection to make full use of the difference between depression and non-depression between timeframes. The proposed model uses frame-level features, which capture the temporal information of depressive speech, to replace traditional statistical features as an input of the LSTM layers. To achieve more multi-dimensional deep feature representations, the LSTM output is then passed on attention layers on both time and feature dimensions. Then, we concat the output of the attention layers and put the fused feature representation into the fully connected layer. At last, the fully connected layer's output is passed on to softmax layer. Experiments conducted on the DAIC-WOZ database demonstrate that the proposed attentive LSTM model achieves an average accuracy rate of 90.2% and outperforms the traditional LSTM network and LSTM with local attention by 0.7% and 2.3%, respectively, which indicates its feasibility.

High-speed wireless communication systems have attracted much attention in recent years. To achieve a high-speed wireless communication system that utilizes an ultra-wide-frequency band, a broadband antenna is required. However, it is difficult to obtain an antenna that has uniform characteristics in a broad frequency band. Moreover, propagation characteristics are distorted in a multi-path environment. Thus, the communication quality tends to degrade due to the distortion in the frequency characteristics of the wideband communication system. This paper proposes a quasi-inverse filter (QIF) to improve the compensation effect for the transmitter antenna. Furthermore, we propose a method that employs the newly developed QIF that compensates for frequency characteristic distortion. We evaluate different configurations for the compensation system employing a pre-filter and post-filter in the wideband communication system. The effectiveness of the QIF in the case of severe distortion is verified by computer simulation. The proposed method is applied to a disc monopole antenna as a concrete example of a broadband antenna, and the compensation effect for the antenna is indicated.

To overcome the challenge in micro-expression recognition that it only emerge in several small facial regions with low intensity, some researchers proposed facial region partition mechanisms and introduced group sparse learning methods for feature selection. However, such methods have some shortcomings, including the complexity of region division and insufficient utilization of critical facial regions. To address these problems, we propose a novel Group Sparse Reduced Rank Tensor Regression (GSRRTR) to transform the fearure matrix into a tensor by laying blocks and features in different dimensions. So we can process grids and texture features separately and avoid interference between grids and features. Furthermore, with the use of Tucker decomposition, the feature tensor can be decomposed into a product of core tensor and a set of matrix so that the number of parameters and the computational complexity of the scheme will decreased. To evaluate the performance of the proposed micro-expression recognition method, extensive experiments are conducted on two micro expression databases: CASME2 and SMIC. The experimental results show that the proposed method achieves comparable recognition rate with less parameters than state-of-the-art methods.

To enhance the emotion feature and improve the performance of speech emotion recognition, an attention mechanism is employed to recognize the important information in both time and feature dimensions. In the time dimension, multi-heads attention is modified with the last state of the long short-term memory (LSTM)'s output to match the time accumulation characteristic of LSTM. In the feature dimension, scaled dot-product attention is replaced with additive attention that refers to the method of the state update of LSTM to construct multi-heads attention. This means that a nonlinear change replaces the linear mapping in classical multi-heads attention. Experiments on IEMOCAP datasets demonstrate that the attention mechanism could enhance emotional information and improve the performance of speech emotion recognition.

A new quadruple watermarking scheme of digital images against geometrical attacks is proposed in this letter. We treat the center and the four vertexes of the original image as the reference points and embed the same quadruple watermarks by means of polar coordinates, which is geometrically invariant. The center of an image is assumed to not to be removed after rotating, scaling and local distortions according to the general practical image processing. In the watermark extraction process, the vertexes of the image are found by a searching method. Thus watermark synchronization is obtained. Experimental results show that the scheme is robust to the geometrical distortions including rotation, scaling, cropping and local distortions.