An infrared image contrast enhancement algorithm based on a discrete stationary wavelet transform (DSWT) and non-linear gain operator is proposed. Having implemented DSWT on an infrared image, de-noising is done using the method proposed in high frequency sub-bands which have better resolution levels and enhancement is implemented by combining the de-noising method with the non-linear gain method in high frequency sub-bands which have the worse resolution levels. According to experimental results, the new algorithm can reduce effectively the correlative noise (1/f noise), additive Gauss white noise (AGWN) and multiplicative noise (MN) in the infrared image while it also enhances contrast of the infrared image. In terms of visual quality, the algorithm is better than the traditional unshaped mask method (USM), histogram equalization method (HIS) and two methods by Gong et al. (2000) and Wu et al. (2003).
Combating fake news and misinformation propagation is a challenging task in the post-truth era. News feed and search algorithms could potentially lead to unintentional large-scale propagation of false and fabricated information with users being exposed to algorithmically selected false content. Our research investigates the effects of an Explainable AI assistant embedded in news review platforms for combating the propagation of fake news. We design a news reviewing and sharing interface, create a dataset of news stories, and train four interpretable fake news detection algorithms to study the effects of algorithmic transparency on end-users. We present evaluation results and analysis from multiple controlled crowdsourced studies. For a deeper understanding of Explainable AI systems, we discuss interactions between user engagement, mental model, trust, and performance measures in the process of explaining. The study results indicate that explanations helped participants to build appropriate mental models of the intelligent assistants in different conditions and adjust their trust accordingly for model limitations.
The identification of named entity in judicial case texts is the critical phrase of knowledge graph information extraction in judicial fields. This paper proposes a neural network model based on bi-directional long-short term memory-conditional random field algorithm for the judicial case texts, named BiLSTM-CRF-JCT. Firstly, data preprocessing utilizes BIO notation to label sentences containing key named entities in judicial case texts, and then transfers sentences containing related entities into character vectors as input data. Afterward, the BiLSTM model is utilized to process vectors in order to obtain the sentence features. Finally, the proposed approach uses the CRF model to label and extract entities to realize named entity recognition. The experimental results show that the accuracy and recall rate of the proposed model are significantly improved compared with other NER algorithm models, F1 value is about 16% higher, which certifies that the BiLSTM-CRF-JCT model has good NER performance.
Interpretable Machine Learning (IML) has become increasingly important in many real-world applications, such as autonomous cars and medical diagnosis, where explanations are significantly preferred to help people better understand how machine learning systems work and further enhance their trust towards systems. However, due to the diversified scenarios and subjective nature of explanations, we rarely have the ground truth for benchmark evaluation in IML on the quality of generated explanations. Having a sense of explanation quality not only matters for assessing system boundaries, but also helps to realize the true benefits to human users in practical settings. To benchmark the evaluation in IML, in this article, we rigorously define the problem of evaluating explanations, and systematically review the existing efforts from state-of-the-arts. Specifically, we summarize three general aspects of explanation (i.e., generalizability, fidelity and persuasibility) with formal definitions, and respectively review the representative methodologies for each of them under different tasks. Further, a unified evaluation framework is designed according to the hierarchical needs from developers and end-users, which could be easily adopted for different scenarios in practice. In the end, open problems are discussed, and several limitations of current evaluation techniques are raised for future explorations.
Formulae display:?Mathematical formulae have been encoded as MathML and are displayed in this HTML version using MathJax in order to improve their display. Uncheck the box to turn MathJax off. This feature requires Javascript. Click on a formula to zoom.
Emerging data that track the dynamics of large populations bring new potential for understanding human decision-making in a complex world and supporting better decision-making through the integration of continued partial observations about dynamics. However, existing models have difficulty with capturing the complex, diverse, evolving, and partially unknown dynamics in social networks, and with inferring system state from isolated observations about a tiny fraction of the individuals in the system. To solve real-world problems with a huge number of agents and system states and complicated agent interactions, we propose a stochastic kinetic model that captures complex decision-making and system dynamics using atomic events that are individually simple but together exhibit complex behaviors. As an example, we show how this model offers significantly better results for city-scale multi-objective driver route planning in significantly less time than models based on deep neural networks or co-evolution.
The diffused-reflectance near-infrared (NIR) spectrum of medicinal rhubarbs was collected by Fourier transform spectroscopy instrument Principal components (PC) and wavelet packet entropy (WPE) were then calculated from the spectrum. Based on these two kinds of features, the models of identification of medicinal rhubarbs were developed using Fisher classifier. The results show that the error rates of cross-validation and prediction using WPE are all lower than those using PC. The model was built by WPE feature extraction method combined with Fisher classifier, the error rate of cross-validation is 6.52%, while that for prediction is 2.04%. The research result provides a method for identifying medicinal rhubarbs quickly.
RNN models have achieved the state-of-the-art performance in a wide range of text mining tasks. However, these models are often regarded as black-boxes and are criticized due to the lack of interpretability. In this paper, we enhance the interpretability of RNNs by providing interpretable rationales for RNN predictions. Nevertheless, interpreting RNNs is a challenging problem. Firstly, unlike existing methods that rely on local approximation, we aim to provide rationales that are more faithful to the decision making process of RNN models. Secondly, a flexible interpretation method should be able to assign contribution scores to text segments of varying lengths, instead of only to individual words. To tackle these challenges, we propose a novel attribution method, called REAT, to provide interpretations to RNN predictions. REAT decomposes the final prediction of a RNN into additive contribution of each word in the input text. This additive decomposition enables REAT to further obtain phrase-level attribution scores. In addition, REAT is generally applicable to various RNN architectures, including GRU, LSTM and their bidirectional versions. Experimental results demonstrate the faithfulness and interpretability of the proposed attribution method. Comprehensive analysis shows that our attribution method could unveil the useful linguistic knowledge captured by RNNs. Some analysis further demonstrates our method could be utilized as a debugging tool to examine the vulnerability and failure reasons of RNNs, which may lead to several promising future directions to promote generalization ability of RNNs.
According to the engineering subcontract management activities of the construction enterprises,the paper explores the controlling aspects from the subcontract forms,the subcontract management system,and the implementation process of the subcontract programs,so as to improve the management of the engineering subcontract of the construction enterprises and to achieve the win-win between the two sides of the cooperation.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
'%3e%3cpath fill='%23012169' d='M0 0v30h60V0z'/%3e%3cpath stroke='%23fff' stroke-width='6' d='m0 0 60 30m0-30L0 30'/%3e%3cpath stroke='%23C8102E' stroke-width='4' d='m0 0 60 30m0-30L0 30' clip-path='url(%23b)'/%3e%3cpath stroke='%23fff' stroke-width='10' d='M30 0v30M0 15h60'/%3e%3cpath stroke='%23C8102E' stroke-width='6' d='M30 0v30M0 15h60'/%3e%3c/g%3e%3c/svg%3e)