Search

Aiming at the security issues during the multi-types data storage and data transmission in autonomous Internet of Things (IoT) systems, this paper proposes an AI algorithm for data enhanced encryption used in the ends and the intermediate nodes of IoTs. The algorithm in this paper first constructs a three-dimensional Arnold transformation matrix for data unit value encryption in the end of IoTs, and designs a quantum logic intelligent mapping that effectively diffuses the encrypted data units to reduce the linear correlation of the image data and to improve the security performance of IoT edge data. Furthermore, the algorithm designs an AI access strategy for scrambling sequence nodes and builds a random-access route for the elements of the scrambling sequence which can reduce the calculation cost and improve the operating efficiency of IoT system in the ends and intermediate nodes. Finally, the data shared matrix is used to share the encrypted data to achieve the (k, n) threshold strategy. Experimental results prove that the algorithm has high plaintext and key sensitivity and can effectively resist brute force attacks, statistical analysis and differential attacks. The algorithm in this paper provides an AI solution for data security encryption in the ends and the intermediate nodes of autonomous IoT systems.

Traditional anti-collision protocols for RFID tags identification assume that the tags and reader are stationary, i.e., no tag is coming in or leaving during tags identification. If not, the reader cannot ensure that the tags are all identified. However, in the mobile RFID system, the reader or tags or all of them are moving continuously, and the tags dynamically enter and leave the reading area. Therefore, traditional protocols are not suitable for the mobile RFID system. This letter presents a dynamic anti-collision protocol, called dynamic collision tree protocol, to be used in the mobile RFID identification system to identify RFID tags that dynamically move into and leave the reading area.

Opinion target extraction and opinion term extraction are two fundamental tasks in Aspect Based Sentiment Analysis (ABSA). Many recent works on ABSA focus on Target-oriented Opinion Words (or Terms) Extraction (TOWE), which aims at extracting the corresponding opinion words for a given opinion target. TOWE can be further applied to Aspect-Opinion Pair Extraction (AOPE) which aims at extracting aspects (i.e., opinion targets) and opinion terms in pairs. In this paper, we propose Target-Specified sequence labeling with Multi-head Self-Attention (TSMSA) for TOWE, in which any pre-trained language model with multi-head self-attention can be integrated conveniently. As a case study, we also develop a Multi-Task structure named MT-TSMSA for AOPE by combining our TSMSA with an aspect and opinion term extraction module. Experimental results indicate that TSMSA outperforms the benchmark methods on TOWE significantly; meanwhile, the performance of MT-TSMSA is similar or even better than state-of-the-art AOPE baseline models.

Neural topic models have attracted much attention for their high efficiencies in training, in which, the methods based on variational auto-encoder capture approximative distributions of data, and those based on Generative Adversarial Net (GAN) are able to capture an accurate posterior distribution. However, the existing GAN-based neural topic model fails to model the document-topic distribution of input samples, making it difficult to get the representations of data in the latent topic space for downstream tasks. Moreover, to utilize the topics discovered by these topic models, it is time-consuming to manually interpret the meaning of topics, label the generated topics, and filter out interested topics. To address these limitations, we propose a Reward-Modulated Adversarial Topic Model (RMATM). By integrating a topic predictor and a reward function in GAN, our RMATM can capture the document-topic distribution and discover interested topics according to topic-related seed words. Furthermore, benefit from the reward function using topic-related seed words as weak supervision, RMATM is able to classify unlabeled documents. Extensive experiments on four benchmark corpora have well validated the effectiveness of RMATM.

Existing assessment models have inconvenient statistics of fuzzy factors and lack of intuitive graphical implementation methods. This paper proposes an information system security situation assessment model based on fuzzy Petri nets (ISSSAF). Firstly, a general hierarchical assessment index system is established. According to the assessment system, a fuzzy Petri net (FPN) model is built and a fuzzy inference algorithm is designed. Secondly, the credibility of each proposition is calculated by inference, and the security situation of the system is graded by grey assessment and inference algorithm. Finally, an assessment experiment of a domestic departure control system (DCS) is carried out. The experimental results verify the effectiveness of ISSSAF. Compared with the traditional methods, it is more objective and accurate, which can help the relevant personnel to formulate effective security protection strategies for the information system.

Poly-centrality is an essential feature of megaregions and is generally considered an important source of megaregional vitality and competitiveness. Numerous studies have highlighted the growing trends of poly-centrality across different megaregions worldwide. However, with accelerated urbanization, some observations suggest that the existing polycentric urban theories must be improved and that decision-makers require more knowledge on the potential trends, spatial characteristics and influencing factors of polycentric development to implement sustainable regional governance under this context. This paper proposes a series of hypotheses on spatiotemporal dynamics of polycentric megaregion evolution and verifies them in an empirical study on the Megaregion around Hangzhou Bay (MAHB). A new algorithm, which is applicable for long time series data, is proposed to evaluate and monitor the status of polycentric development in MAHB. In particular, landscape metrics and average nearest neighbor analysis are employed in the first stage of our algorithm which is designed to implement data compression. Then, the gravity model, minimum spanning tree (MST) and weighed betweenness centrality indicator form the second stage which aims to construct and explore the polycentric megaregional network. Results show that: (1) the speed and patterns of built-up land expansion significantly affect the number and distribution of megaregion centers; (2) the value of poly-centrality reaches a maximum in approximately 2013 and then declines, which can be well fitted by a Gaussian curve; and (3) the variation of poly-centrality is successively dominated by an increase and decrease in the number of centers with urbanization. This paper renews the assumptions in current polycentric evolution models and provides evidences for single-peaked change of megaregion center number instead of “wave-like”, “scaling-up” or monotonous change proposed in existing urban theories. The proposed algorithm and assumed mechanisms can also be applied to model and explore poly-centrality dynamics of other megaregions around the world. The results are believed to provide critical implications for polycentric policies.

Given the important role of protected areas (PAs) in biological conservation and the huge investment required to establish and manage them, it is essential to accurately assess the effectiveness of PAs. Previous studies typically used the difference between the PA and a non-protected area to measure the effectiveness and presented many space constraints to enhance the comparability between treatment and control groups. In contrast, however, researchers have given less consideration to time constraints, and there is still no consensus on the choice of period for assessing the effectiveness. Here, we explored this issue and assessed the effectiveness of 2,975 PAs worldwide using the difference in differences (DID) model. We found that 56.2% of PAs were effective in maintaining plant productivity, and PAs in forests were more effective than those in non-forests. However, the effectiveness of PAs in improving ecological stability was limited. The stability rose only in the regions where PAs could effectively maintain plant productivity (e.g., needleleaf forest, woodland or Central Europe). Further, an event-study analysis showed that global PAs had been playing a positive and persistent role in maintaining plant productivity. In addition to providing these new assessment results, we compared the assessment results derived from different methods and confirmed that the impact of not using the DID model was greater than that of not using the propensity score matching (PSM) method. We therefore recommend the use of the DID model in future effectiveness assessments.