A generalized multi-skill aggregation method for cognitive diagnosis.

Online education brings more possibilities for personalized learning, in which identifying the cognitive state of learners is conducive to better providing learning services. Cognitive diagnosis is an effective measurement to assess the cognitive state of students through response data of answering the problems(e.g., right or wrong). Generally, the cognitive diagnosis framework includes the mastery of skills required by a specified problem and the aggregation of skills. The current multi-skill aggregation methods are mainly divided into conjunctive and compensatory methods and generally considered that each skill has the same effect on the correct response. However, in practical learning situations, there may be more complex interactions between skills, in which each skill has different weight impacting the final result. To this end, this paper proposes a generalized multi-skill aggregation method based on the Sugeno integral (SI-GAM) and introduces fuzzy measures to characterize the complex interactions between skills. We also provide a new idea for modeling multi-strategy problems. The cognitive diagnosis process is implemented by a more general and interpretable aggregation method. Finally, the feasibility and effectiveness of the model are verified on synthetic and real-world datasets.

Towards Exploring Large Molecular Space: An Efficient Chemical Genetic Algorithm.

Generating molecules with desired properties is an important task in chemistry and pharmacy. An efficient method may have a positive impact on finding drugs to treat diseases like COVID-19. Data mining and artificial intelligence may be good ways to find an efficient method. Recently, both the generative models based on deep learning and the work based on genetic algorithms have made some progress in generating molecules and optimizing the molecule's properties. However, existing methods need to be improved in efficiency and performance. To solve these problems, we propose a method named the Chemical Genetic Algorithm for Large Molecular Space (CALM). Specifically, CALM employs a scalable and efficient molecular representation called molecular matrix. Then, we design corresponding crossover, mutation, and mask operators inspired by domain knowledge and previous studies. We apply our genetic algorithm to several tasks related to molecular property optimization and constraint molecular optimization. The results of these tasks show that our approach outperforms the other state-of-the-art deep learning and genetic algorithm methods, where the z tests performed on the results of several experiments show that our method is more than 99% likely to be significant. At the same time, based on the experimental results, we point out the insufficiency in the experimental evaluation standard which affects the fair evaluation of previous work. Supplementary Information: The online version contains supplementary material available at 10.1007/s11390-021-0970-3.

Shading-based absolute phase unwrapping.

Absolute phase unwrapping in the phase-shifting profilometry (PSP) is significant for dynamic 3-D measurements over a large depth range. Among traditional phase unwrapping methods, spatial phase unwrapping can only retrieve a relative phase map, and temporal phase unwrapping requires auxiliary projection sequences. We propose a shading-based absolute phase unwrapping (SAPU) framework for in situ 3-D measurements without additional projection patterns. First, the wrapped phase map is calculated from three captured images. Then, the continuous relative phase map is obtained using the phase histogram check (PHC), from which the absolute phase map candidates are derived with different fringe orders. Finally, the correct absolute phase map candidate can be determined without additional patterns or spatial references by applying the shading matching check (SMC). The experimental results demonstrate the validity of the proposed method.

Discriminative repair approach to remove shadow-induced error for typical digital fringe projection.

In a typical digital fringe projection (DFP) system, the shadows in the fringe images cause errors in the phase map. We propose a novel discriminative repair approach to remove the shadow-induced error in the phase map. The proposed approach first classifies the shadow area in the phase map obtained by the DFP into two categories: valid shadow area and invalid shadow area. Then the valid shadow area is repaired by a proposed neighboring information fusion phase estimation (NIFPE) method, which fuses the phase gradient into the result of kernel density estimation (KDE) through the Kalman filter (KF) algorithm. The invalid shadow area is repaired by a proposed background phase matching (BPM) method. The experimental results demonstrate that the shadow-induced error in the phase map can be removed, which verifies the effectiveness of the proposed approach.

Dynamic 3-D shape measurement in an unlimited depth range based on adaptive pixel-by-pixel phase unwrapping.

Pixel-by-pixel phase unwrapping (PPU) has been employed to rapidly achieve three-dimensional (3-D) shape measurement without additional projection patterns. However, the maximum measurement depth range that traditional PPU can handle is within 2π in phase domain; thus PPU fails to measure the dynamic object surface when the object moves in a large depth range. In this paper, we propose a novel adaptive pixel-by-pixel phase unwrapping (APPU), which extends PPU to an unlimited depth range. First, with PPU, temporary phase maps of objects are obtained referring to the absolute phase map of a background plane. Second, we quantify the difference between the image edges of the temporary phase maps and the practical depth edges of dynamic objects. Moreover, according to the degree of the edge difference, the temporary phase maps are categorized into two classes: failed phase maps and relative phase maps. Third, by combining a mobile reference phase map and the edge difference quantization technique, the failed phase maps are correspondently converted into relative phase maps. Finally, the relative phase maps are innovatively transformed into the absolute phase maps using a new shadow-informed depth estimation method (SDEM). The proposed approach is suitable for high-speed 3-D shape measurement without depth limitations or additional projection patterns.

Phase-shifting profilometry for the robust 3-D shape measurement of moving objects.

Arbitrary two-dimensional (2-D) motion introduces coordinate errors and phase errors to three-dimensional (3-D) shape measurement of objects in phase-shifting profilometry (PSP). This paper presents a new robust 3-D reconstruction method for arbitrary 2-D moving objects by introducing an adaptive reference phase map and the motion estimation based on fence image. First, a composite fence image is used to track object motion. Second, to obtain the transformation matrixes and remove the coordinate errors among object images, the angle extraction technique and the 1-D hybrid phase correlation method (1-D HPCM) are integrated to automatically estimate the sub-pixel motion of objects. Third, the phase errors are compensated to obtain the rough absolute phase map of objects by combining the transformation matrixes with the reference phase map. Finally, the absolute phase map is refined to reconstruct the 3-D surfaces of moving objects with adaptive reference phase map. The proposed computational framework can accurately and automatically realize 3-D shape measurement of arbitrary objects with 2-D movement. The results of experiment verify the effectiveness of our computational framework.

Boosting Factorization Machines via Saliency-Guided Mixup.

Factorization machines (FMs) are widely used in recommender systems due to their adaptability and ability to learn from sparse data. However, for the ubiquitous non-interactive features in sparse data, existing FMs can only estimate the parameters corresponding to these features via the inner product of their embeddings. Undeniably, they cannot learn the direct interactions of these features, which limits the model's expressive power. To this end, we first present MixFM, inspired by Mixup, to generate auxiliary training data to boost FMs. Unlike existing augmentation strategies that require labor costs and expertise to collect additional information such as position and fields, these augmented data are only by the convex combination of the raw ones without any professional knowledge support. More importantly, if non-interactive features exist in parent samples to be mixed respectively, MixFM will establish their direct interactions. Second, considering that MixFM may generate redundant or even detrimental instances, we further put forward a novel Factorization Machine powered by Saliency-guided Mixup (denoted as SMFM). Guided by the customized saliency, SMFM can generate more informative neighbor data. Through theoretical analysis, we prove that the proposed methods minimize the upper bound of the generalization error, which positively enhances FMs. Finally, extensive experiments on seven datasets confirm that our approaches are superior to baselines. Notably, the results also show that "poisoning" mixed data benefits the FM variants.

Unsupervised user similarity mining in GSM sensor networks.

Mobility data has attracted the researchers for the past few years because of its rich context and spatiotemporal nature, where this information can be used for potential applications like early warning system, route prediction, traffic management, advertisement, social networking, and community finding. All the mentioned applications are based on mobility profile building and user trend analysis, where mobility profile building is done through significant places extraction, user's actual movement prediction, and context awareness. However, significant places extraction and user's actual movement prediction for mobility profile building are a trivial task. In this paper, we present the user similarity mining-based methodology through user mobility profile building by using the semantic tagging information provided by user and basic GSM network architecture properties based on unsupervised clustering approach. As the mobility information is in low-level raw form, our proposed methodology successfully converts it to a high-level meaningful information by using the cell-Id location information rather than previously used location capturing methods like GPS, Infrared, and Wifi for profile mining and user similarity mining.

An equivariant generative framework for molecular graph-structure Co-design.

Designing molecules with desirable physiochemical properties and functionalities is a long-standing challenge in chemistry, material science, and drug discovery. Recently, machine learning-based generative models have emerged as promising approaches for de novo molecule design. However, further refinement of methodology is highly desired as most existing methods lack unified modeling of 2D topology and 3D geometry information and fail to effectively learn the structure-property relationship for molecule design. Here we present MolCode, a roto-translation equivariant generative framework for molecular graph-structure Co-design. In MolCode, 3D geometric information empowers the molecular 2D graph generation, which in turn helps guide the prediction of molecular 3D structure. Extensive experimental results show that MolCode outperforms previous methods on a series of challenging tasks including de novo molecule design, targeted molecule discovery, and structure-based drug design. Particularly, MolCode not only consistently generates valid (99.95% validity) and diverse (98.75% uniqueness) molecular graphs/structures with desirable properties, but also generates drug-like molecules with high affinity to target proteins (61.8% high affinity ratio), which demonstrates MolCode's potential applications in material design and drug discovery. Our extensive investigation reveals that the 2D topology and 3D geometry contain intrinsically complementary information in molecule design, and provide new insights into machine learning-based molecule representation and generation.

LadRa-Net: Locally Aware Dynamic Reread Attention Net for Sentence Semantic Matching.

Sentence semantic matching requires an agent to determine the semantic relation between two sentences, which is widely used in various natural language tasks, such as natural language inference (NLI) and paraphrase identification (PI). Much recent progress has been made in this area, especially attention-based methods and pretrained language model-based methods. However, most of these methods focus on all the important parts in sentences in a static way and only emphasize how important the words are to the query, inhibiting the ability of the attention mechanism. In order to overcome this problem and boost the performance of the attention mechanism, we propose a novel dynamic reread (DRr) attention, which can pay close attention to one small region of sentences at each step and reread the important parts for better sentence representations. Based on this attention variation, we develop a novel DRr network (DRr-Net) for sentence semantic matching. Moreover, selecting one small region in DRr attention seems insufficient for sentence semantics, and employing pretrained language models as input encoders will introduce incomplete and fragile representation problems. To this end, we extend DRr-Net to locally aware dynamic reread attention net (LadRa-Net), in which local structure of sentences is employed to alleviate the shortcoming of byte-pair encoding (BPE) in pretrained language models and boost the performance of DRr attention. Extensive experiments on two popular sentence semantic matching tasks demonstrate that DRr-Net can significantly improve the performance of sentence semantic matching. Meanwhile, LadRa-Net is able to achieve better performance by considering the local structures of sentences. In addition, it is exceedingly interesting that some discoveries in our experiments are consistent with some findings of psychological research.