Search

In this article, we investigate the prescribed performance tracking control problem for high-order nonlinear multiagent systems (MASs) under directed communication topology and unknown control directions. Different from most existing prescribed performance consensus control methods where certain initial conditions are needed to be satisfied, here the restriction related to the initial conditions is removed and global tracking result irrespective of initial condition is established. Furthermore, output consensus tracking is achieved asymptotically with arbitrarily prescribed transient performance in spite of the directed topology and unknown control directions. Our development benefits from the performance function and prescribed-time observer. Both theoretical analysis and numerical simulation confirm the validity of the developed control scheme.

Lots of emerging techniques can natively realize majority-of-three (MAJ) gates. Although enhanced gates such as exclusive-OR (XOR) gates can be implemented by several MAJ gates, there exists much efficient XOR design which directly derived by the physical attributes of emerging techniques. In this brief, we proposed multi-digit binary coded decimal (BCD) adder designs represented based on three-input exclusive-OR (XOR3) and MAJ gates. BCD adder is widely used in financial, commercial, and industrial computing. We implemented the designs using quantum-dot cellular automata (QCA) technology. The proposed logic representations are validated using different types of binary adders as well as QCA design strategies. The introduction of XOR3 gates is conducive to achieve compact logic representations, which positively affect both the area and delay of QCA layouts. Compared with the existing best designs, the proposed 1-digit BCD adder has 50% less area and 10% less delay, and the 8-digit BCD adder has a $3.42\times $ improvement of area-delay product.

The application of multi-label text classification in charge prediction aims at forecasting all kinds of charges related to the content of judgment documents according to the actual situation, which plays a vital role in the judgment of criminal cases. Existing classification algorithms have high accuracy for the single-charge prediction, but their accuracy for the multi-charge prediction is low. To solve this problem, in this paper we introduce a novel hierarchical nested attention structure model with relevant law article information to predict the multi-charge classification of legal judgment documents. By considering the correlation between different charges, the accuracy of multi-charge prediction is greatly improved. Experimental results on real-world datasets demonstrate that our proposed model achieves significant and consistent improvements over other state-of-the-art baselines.

Although water is one of the most important nutrients and is essential for various physiological processes within the body, it does not receive adequate consideration when ensuring optimal nutrition and growth performance in piglets. This study was conducted to investigate the effects of drinking water temperature (DWT) and flow rate (DWF) on growth performance, nutrient digestibility and cecum microflora in weaned piglets during cold weather. Sixty-four piglets with an average body weight of 8.60 &plusmn, 0.5 kg were allotted into four groups with four replicates in each group and four pigs in each replicate. The DWT and DWF were set for each group as follows: (1) 13 &deg, C + 300 mL/min, (2) 13 &deg, C + 700 mL/min, (3) 30 &deg, C + 300 mL/min and (4) 30 &deg, C + 700 mL/min, respectively. All groups were fed the same diet during the 28 d trial. The body weight at day 0 and day 29, as well as daily feed intake, were recorded. Diarrhea severity was assessed every day. Fresh fecal samples were collected for four consecutive days at the end of the experiment for the digestibility test. Cecum content was collected after sacrifice for microbial composition analysis. The results indicated that: (1) DWT at 30 &deg, C promoted the average daily gain (ADG) of weaned piglets considerably (p = 0.043) and decreased feed to weight ratio when compared with DWT at 13 &deg, C (p = 0.045). DWF had no substantial effect on the growth performance of piglets (p &gt, 0.05). (2) The 30 &deg, C DWT groups had higher apparent digestibility of crude protein, crude fat and energy than the 13 &deg, C DWT groups (p &lt, 0.05), while DWF had no significant effect on the apparent digestibility of nutrients (p &gt, 0.05). (3) DWT at 30 &deg, C increased the Bacteroidetes abundance and decreased the Proteobacteria abundance in cecum digesta. The change in these two factors may be related to a decrease in diarrhea and the improvement of growth performance. Different DWF had no substantial effect on the cecum microbial structure. To sum up, providing a DWT of 30 &deg, C to weaned piglets in cold weather reduced the abundance of harmful bacteria in the cecum and improved the apparent nutrient digestibility, which is beneficial for maintaining a healthy intestinal microenvironment and promoting growth performance. A lower DWF of 300 mL/min had no adverse effect on growth performance. Therefore, a combination of 30 &deg, C + 300 mL/min is recommended for weaned piglets during cold weather for the consideration of animal welfare and production efficiency.

Multi-label text classification (MLC) task, as one of the sub-tasks of natural language processing, has broad application prospects. On the basis of studying the previous research work, this research takes the relationship among text information, leading label information and predictive label information as the frame and analyzes the information loss of original text and leading label, decoding error accumulation. We propose an improved multi-step multi-classification model to mitigate the phenomenon of error prediction, label repetition and error accumulation. The model uses multi-step and multi-classification task to complete multi-label prediction. It uses the leading label and the original text as input, and the next to-be-predicted label as output. The co-attention mechanism is operated between the original text and the leading label. The attention of the original text to the leading label is helpful to filter out the error accumulation problem caused by the error prediction. The features is combined in a manner of difference and concatenation, which highlights the auxiliary effect of the model structure on feature extraction. In order to avoid the influence of the feature dimension on the performance of long short-term memory (LSTM), a multi-layer fully-connected classifier is used instead to predict the label. Through experimental validation, the performance of our model on the multi-label text classification task shows the current optimal level, which fully proves the superiority of our model.

Legal judgment prediction (LJP), as an effective and critical application in legal assistant systems, aims to determine the judgment results according to the information based on the fact determination. In real-world scenarios, to deal with the criminal cases, judges not only take advantage of the fact description, but also consider the external information, such as the basic information of defendant and the court view. However, most existing works take the fact description as the sole input for LJP and ignore the external information. We propose a Transformer-Hierarchical-Attention-Multi-Extra (THME) Network to make full use of the information based on the fact determination. We conduct experiments on a real-world large-scale dataset of criminal cases in the civil law system. Experimental results show that our method outperforms state-of-the-art LJP methods on all judgment prediction tasks.

Relation classification is one of the most fundamental tasks in the area of cross-media, which is essential for many practical applications such as information extraction, question&answer system, and knowledge base construction. In the cross-media semantic retrieval task, in order to meet the needs of cross-media uniform representation and semantic analysis, it is necessary to analyze the semantic potential relationship and construct semantic-related cross-media knowledge graph. The relationship classification technology is an important part of solving semantic correlation classification. Most of existing methods regard relation classification as a multi-classification task, without considering the correlation between different relationships. However, two relationships in the opposite directions are usually not independent of each other. Hence, this kind of relationships are easily confused in the traditional way. In order to solve the problem of confusing the relationships of the same semantic with different entity directions, this paper proposes a neural network fusing discrimination information for relation classification. In the proposed model, discrimination information is used to distinguish the relationship of the same semantic with different entity directions, the direction of entity in space is transformed into the direction of vector in mathematics by the method of entity vector subtraction, and the result of entity vector subtraction is used as discrimination information. The model consists of three modules: sentence representation module, relation discrimination module and discrimination fusion module. Moreover, two fusion methods are used for feature fusion. One is a Cascade-based feature fusion method, and another is a feature fusion method based on convolution neural network. In addition, this paper uses the new function added by cross-entropy function and deformed Max-Margin function as the loss function of the model. The experimental results show that the proposed discriminant feature is effective in distinguishing confusing relationships, and the proposed loss function can improve the performance of the model to a certain extent. Finally, the proposed model achieves 84.8% of the F1 value without any additional features or NLP analysis tools. Hence, the proposed method has a promising prospect of being incorporated in various cross-media systems.

As complementary metal-oxide semiconductor（CMOS） technology reaches its physical limitation, a large number of nanotechnologies are emerging. Quantum-dot Cellular Automata (QCA) is one of such emerging computation technology. Arithmetic circuit make extensive use of majority-of-three (MAJ) and exclusive-or(XOR) operation. In this paper, we proposed an efficient design of decimal full adder (DFA) using QCA. Compared to previous work which only adopts MAJ operations, we extend the state-of-the-art design by introducing XOR operations. The simulation results indicate our approach can reduce area and delay by 11.2% and 16.7%, respectively.