Knowledge Based Systems (KBS) are systems that use artificial intelligence techniques in the problem solving process. This text is designed to develop an appreciation of KBS and their architecture and to help users understand a broad variety of knowledge based techniques for decision support and planning. It assumes basic computer science skills and a math background that includes set theory, relations, elementary probability, and introductory concepts of artificial intelligence. Each of the 12 chapters are designed to be modular providing instructors with the flexibility to model the book to their own course needs. Exercises are incorporated throughout the text to highlight certain aspects of the material being presented and to stimulate thought and discussion.

Knowledge-Based Systems

Mathematical programming

Learning graphs from data automatically have shown encouraging performance on clustering and semisupervised learning tasks. However, real data are often corrupted, which may cause the learned graph to be inexact or unreliable. In this paper, we propose a novel robust graph learning scheme to learn reliable graphs from the real-world noisy data by adaptively removing noise and errors in the raw data. We show that our proposed model can also be viewed as a robust version of manifold regularized robust principle component analysis (RPCA), where the quality of the graph plays a critical role. The proposed model is able to boost the performance of data clustering, semisupervised classification, and data recovery significantly, primarily due to two key factors: 1) enhanced low-rank recovery by exploiting the graph smoothness assumption and 2) improved graph construction by exploiting clean data recovered by RPCA. Thus, it boosts the clustering, semisupervised classification, and data recovery performance overall. Extensive experiments on image/document clustering, object recognition, image shadow removal, and video background subtraction reveal that our model outperforms the previous state-of-the-art methods.

Robust Graph Learning From Noisy Data

A plethora of multi-view subspace clustering (MVSC) methods have been proposed over the past few years. Researchers manage to boost clustering accuracy from different points of view. However, many state-of-the-art MVSC algorithms, typically have a quadratic or even cubic complexity, are inefficient and inherently difficult to apply at large scales. In the era of big data, the computational issue becomes critical. To fill this gap, we propose a large-scale MVSC (LMVSC) algorithm with linear order complexity. Inspired by the idea of anchor graph, we first learn a smaller graph for each view. Then, a novel approach is designed to integrate those graphs so that we can implement spectral clustering on a smaller graph. Interestingly, it turns out that our model also applies to single-view scenario. Extensive experiments on various large-scale benchmark data sets validate the effectiveness and efficiency of our approach with respect to state-of-the-art clustering methods.

/pdf/large-scale-multi-view-subspace-clustering-in-linear-time-hlcbjj6ll3.pdf

Large-Scale Multi-View Subspace Clustering in Linear Time

Partition level multiview subspace clustering.

Multi-view clustering is an important yet challenging task due to the difficulty of integrating the information from multiple representations. Most existing multi-view clustering methods explore the heterogeneous information in the space where the data points lie. Such common practice may cause significant information loss because of unavoidable noise or inconsistency among views. Since different views admit the same cluster structure, the natural space should be all partitions. Orthogonal to existing techniques, in this paper, we propose to leverage the multi-view information by fusing partitions. Specifically, we align each partition to form a consensus cluster indicator matrix through a distinct rotation matrix. Moreover, a weight is assigned for each view to account for the clustering capacity differences of views. Finally, the basic partitions, weights, and consensus clustering are jointly learned in a unified framework. We demonstrate the effectiveness of our approach on several real datasets, where significant improvement is found over other state-of-the-art multi-view clustering methods.

/pdf/multiple-partitions-aligned-clustering-52vkh7f4sh.pdf

Multiple Partitions Aligned Clustering

Data similarity is a key concept in many data-driven applications. Many algorithms are sensitive to similarity measures. To tackle this fundamental problem, automatically learning of similarity information from data via self-expression has been developed and successfully applied in various models, such as low-rank representation, sparse subspace learning, semisupervised learning. However, it just tries to reconstruct the original data and some valuable information, e.g., the manifold structure, is largely ignored. In this paper, we argue that it is beneficial to preserve the overall relations when we extract similarity information. Specifically, we propose a novel similarity learning framework by minimizing the reconstruction error of kernel matrices, rather than the reconstruction error of original data adopted by existing work. Taking the clustering task as an example to evaluate our method, we observe considerable improvements compared to other state-ofthe-art methods. More importantly, our proposed framework is very general and provides a novel and fundamental building block for many other similarity-based tasks. Besides, our proposed kernel preserving opens up a large number of possibilities to embed high-dimensional data into low-dimensional space.

/pdf/similarity-learning-via-kernel-preserving-embedding-6fpufps5o6.pdf

Similarity Learning via Kernel Preserving Embedding.

In this work, the core-satellite optoplasmonic particle comprised of the central dielectric silica sphere and the surrounding gold nanorods (AuNRs) with varied aspect ratio (AR) were fabricated through electrostatic-assisted self-assembly. The manipulation over the optoplasmonic resonance of the hybrid material was accomplished through tuning the AR of AuNRs at the perimeter of the silica microsphere, which enables the optimization of local plasmonic-photonic electric field enhancement in accordance with the incident wavelength. The monolayer structure assembled by the hybrid particles, termed as optoplasmonic surface, serves as a robust surface-enhanced Raman spectroscopy (SERS) sensing substrate because the building block is surprisingly agglomeration-resistive under severe conditions including the dryness and salination. The optimal SERS excitation plane of the optoplasmonic surface was found to be the equatorial one due to the geometrical factor holding the higher density of AuNRs, the plasmonic-photonic interaction between adjacent optoplasmonic particles and the light guiding effect. The fabricated optoplasmonic surface (silica sphere diameter = 4 µm, AR of AuNR = 3.2) was implemented for the SERS sensing of 3,4-methylenedioxymethamphetamine (MDMA) and the corresponding precursors including safrole and piperonal, achieving a limit of detection (LOD) down to the magnitude of 5 nM with the excitation wavelength at 785 nm. Practical SERS tests on the glassware surface and mimic drug demonstrate the compatibility of the optoplasmonic sensing platform in cooperation with the portable Raman spectrometers. This hybrid probe with engineerable resonance and elevated stability is a promising candidate for the application of SERS inspection in forensic activities. 

Yuanzhang Su

Papers

Multiple Partitions Aligned Clustering

Similarity Learning via Kernel Preserving Embedding.

Multiple Partitions Aligned Clustering

Engineered Optoplasmonic Core-Satellite Microspheres for SERS Determination of Methamphetamine Derivative and its Precursors

Sterculia lychnophora seed-derived porous carbon@CoFe2O4 composites with efficient microwave absorption performance