One of the most critical functions an intelligent transportation system (ITS) is to provide accurate and real-time prediction traffic condition. This paper develops a short-term condition model based on k-nearest neighbor algorithm. In model, time-varying continuous characteristic flow considered, multi-time-step proposed single-time-step model. To test accuracy GPS data taxis in Foshan city, China, are used. The results show that with spatial-temporal parameters provides good performance...

A multifunctional organohydrogel can be used as an information platform and a self-healing anti-freezing strain sensor.

The paradigm of pre-training and fine-tuning graph neural networks has attracted wide research attention. In previous studies, the pre-trained models are viewed as universally versatile, applied for a diverse range downstream tasks. many situations, however, this practice results in limited or even negative transfer. This paper, first time, emphasizes specific application scope models: not all tasks can effectively benefit from model. light this, we introduce measure task consistency to...

Content-Based medical image retrieval (CBMIR) is been highly active research area from past few years. The performance of a CBMIR system crucially depends on the feature representation, which have extensively studied by researchers for decades. Although variety techniques proposed, it remains one most challenging problems in current research, mainly due to well-known "semantic gap" issue that exists between low-level pixels captured machines and high-level semantic concepts perceived...

Crime Hot Spots refer to the areas in which crime rates are above average level, therefore Prediction is primary mission of Public Security Prevention and Control. By encoding area-specific incidents, hot spots has been classified them into different heat levels, rendering conversion prediction a multi-class classification problem. The new model uses time sequence temporal distance important holidays, neighborhood features establish crude mixed spatial-temporal characteristics. As with...

Recently, the chaos based cryptographic algorithms have suggested some meaningful techniques to develop efficient image encryption schemes. In this paper, we propose a new digital scheme on piecewise linear chaotic map (PWLCM) in order meet requirements of secure encryption. The proposed is described detail, along with security analyses including key space analysis, sensitivity information entropy analysis and differential attack analysis. results show that has properties desirable good cryptosystem.

In this paper, a novel block digital image encryption scheme based on chaotic coupled map lattices (CML) is reported. Within scheme, an original decomposed into sub-blocks with given size, and external secret key 192-bit used mapped to the system parameters, which are employed generate spatiotemporal binary sequence matrix encrypt image. Besides, former sub-block encrypted result will be acted as feedback following process. The proposed described in detail, along security analyses such space...

In this paper, a novel block encryption cipher based on chaotic dynamical system is proposed. The algorithm operates 64-bit plaintext blocks, and the key 128 bits long. round function, logistic map three algebraic group operations are mixed. As Feistel network, it can be used for both decryption. Furthermore, security of analyzed in details. cryptanalyse results indicate that has good diffusion confusion properties, very sensitive to plaintexts keys. Finally, by using differential...

Abstract In order to avoid defects (e.g. dust, scratch, static electricity) caused by manual detection, this research proposes a non-contact defect detection approach for circuit board through use of template matching method. the proposed approach, images both be detected and selected as are obtained respectively from multiple views. Then index (DI) each view is constructed based on corresponding results between image image. Finally, total integrating all DI views, which can characterize...

It is very difficult to accurately control the speed of paper roller and sword cutting machine, proportions two paces have greater randomness. Alterable fuzzy-PI arithmetic put forward based on PLC. The alterable fuzzy controller PI adjustor are realized by This system has solved problem that grain flow equilibrium, not stably does kind. practical results show this can restrain effect time relaying effectively good stability strong robustness.

In order to improve the accuracy of linear motion computer numerical control (CNC) machine tools, a novel method based on new type 1-D (1-dimensional) artifact is proposed measure geometric errors. Based properties displacement measurement revolutionary paraboloid and angle plane mirrors, can be applied identify position errors Meanwhile, concrete 6 degrees-of-freedom error identification described in this paper sufficient detail. Through measuring horizontally vertically using tool,...

Based on wind-turbine character analyzing, maximum wind energy tracking is selected as active power control target. A method of using fuzzy logic principles to deduce optimum turbine speed was proposed, keep tip rate operating without the velocity measurement. dual-passage excitation strategy based dynamic synchronous reference frame applied proposed optimal stator and reactive power. The operational performances system with DFIG variation were analyzed compared by Matlab/Simulink. results...

During the conversations among human and machine, how to comprehend user's intention according context is a crucial issue, which very difficult. The commonly used Convolutional Neural Network (CNN) does not work well in this situation: due short length local features of dialogue sentences, CNN cannot capture global semantic information. In paper, we propose an intent classification dual-channel Networks (ICDC NN): first extract by using Word2vec Embedding layer train word vector; then, two...

In this paper, we propose a novel feedback block chaotic cipher algorithm (FBCCA) based on the time-delay neuron system and feistel network. The inherent features of make cryptosystem more complex difficult to be analyzed or predicted. FBCCA, output ciphertext corresponding current input plaintext is fed back into generation process number round, which will used for encrypting next block. Furthermore, round numbers (times iterated each block) sequence S-box (used in round) have closely...

The social security prevention and control is a process of dynamic management, which possesses three characteristics strategy, integration systematicness. It difficult to achieve the optimal input-output ratio in absence optimization working structure. In this paper, we proposed structure strategy public based on analytic hierarchy (AHP). Firstly, four basic elements (i.e., people, case, time space) impacting were extracted. And then driving modes under different structures concluded....

In recent years, with the development of Internet and network learning community rapid development, information technology is changing people's ways e-learning amazing speed.At same time, trek, knowledge overload problems gradually emerged.Personalized recommendation has become an important means for people to quickly learn master knowledge, but also reflects people-oriented personalized mode.However, algorithm based on collaborative filtering still faces such as sparsity, scalability, cold...

Virtual learning community is a kind of environment based on network new type organization. However, Learning Community in the teaching data often messy, fragmentary, it's value difficult to be detected and reasonable use mining techniques deal with will give us analysis study effect get twice result half effort. Personalized has always been point research, extraction characteristics learner's basis personalized teaching. The purpose this paper through acquisition virtual behavior record...