Organizational Data Classification Based on the Importance Concept of Complex Networks

Improving the Timing Resolution of Positron Emission Tomography Detectors Using Boosted Learning-A Residual Physics Approach

Artificial intelligence (AI) is entering medical imaging, mainly enhancing image reconstruction. Nevertheless, improvements throughout the entire processing, from signal detection to computation, potentially offer significant benefits. This work presents a novel and versatile approach to detector optimization using machine learning (ML) and residual physics. We apply the concept to positron emission tomography (PET), intending to improve the coincidence time resolution (CTR). PET visualizes metabolic processes in the body by detecting photons with scintillation detectors. Improved CTR performance offers the advantage of reducing radioactive dose exposure for patients. Modern PET detectors with sophisticated concepts and read-out topologies represent complex physical and electronic systems requiring dedicated calibration techniques. Traditional methods primarily depend on analytical formulations successfully describing the main detector characteristics. However, when accounting for higher-order effects, additional complexities arise matching theoretical models to experimental reality. Our work addresses this challenge by combining traditional calibration with AI and residual physics, presenting a highly promising approach. We present a residual physics-based strategy using gradient tree boosting and physics-guided data generation. The explainable AI framework SHapley Additive exPlanations (SHAPs) was used to identify known physical effects with learned patterns. In addition, the models were tested against basic physical laws. We were able to improve the CTR significantly (more than 20%) for clinically relevant detectors of 19 mm height, reaching CTRs of 185 ps (450-550 keV).

Complex network-based classification of radiographic images for COVID-19 diagnosis

In this work, we present a network-based technique for chest X-ray image classification to help the diagnosis and prognosis of patients with COVID-19. From visual inspection, we perceive that healthy and COVID-19 chest radiographic images present different levels of geometric complexity. Therefore, we apply fractal dimension and quadtree as feature extractors to characterize such differences. Moreover, real-world datasets often present complex patterns, which are hardly handled by only the physical features of the data (such as similarity, distance, or distribution). This issue is addressed by complex networks, which are suitable tools for characterizing data patterns and capturing spatial, topological, and functional relationships in data. Specifically, we propose a new approach combining complexity measures and complex networks to provide a modified high-level classification technique to be applied to COVID-19 chest radiographic image classification. The computational results on the Kaggle COVID-19 Radiography Database show that the proposed method can obtain high classification accuracy on X-ray images, being competitive with state-of-the-art classification techniques. Lastly, a set of network measures is evaluated according to their potential in distinguishing the network classes, which resulted in the choice of communicability measure. We expect that the present work will make significant contributions to machine learning at the semantic level and to combat COVID-19.

An Event-Triggering Approach to Recursive Filtering for Complex Networks With State Saturations and Random Coupling Strengths

In this article, the recursive filtering problem is investigated for a class of time-varying complex networks with state saturations and random coupling strengths under an event-triggering transmission mechanism. The coupled strengths among nodes are characterized by a set of random variables obeying the uniform distribution. The event-triggering scheme is employed to mitigate the network data transmission burden. The purpose of the problem addressed is to design a recursive filter such that in the presence of the state saturations, event-triggering communication mechanism, and random coupling strengths, certain locally optimized upper bound is guaranteed on the filtering error covariance. By using the stochastic analysis technique, an upper bound on the filtering error covariance is first derived via the solution to a set of matrix difference equations. Next, the obtained upper bound is minimized by properly parameterizing the filter parameters. Subsequently, the boundedness issue of the filtering error covariance is studied. Finally, two numerical simulation examples are provided to illustrate the effectiveness of the proposed algorithm.

Neural Network-Based Information Transfer for Dynamic Optimization

In dynamic optimization problems (DOPs), as the environment changes through time, the optima also dynamically change. How to adapt to the dynamic environment and quickly find the optima in all environments is a challenging issue in solving DOPs. Usually, a new environment is strongly relevant to its previous environment. If we know how it changes from the previous environment to the new one, then we can transfer the information of the previous environment, e.g., past solutions, to get new promising information of the new environment, e.g., new high-quality solutions. Thus, in this paper, we propose a neural network (NN)-based information transfer method, named NNIT, to learn the transfer model of environment changes by NN and then use the learned model to reuse the past solutions. When the environment changes, NNIT first collects the solutions from both the previous environment and the new environment and then uses an NN to learn the transfer model from these solutions. After that, the NN is used to transfer the past solutions to new promising solutions for assisting the optimization in the new environment. The proposed NNIT can be incorporated into population-based evolutionary algorithms (EAs) to solve DOPs. Several typical state-of-the-art EAs for DOPs are selected for comprehensive study and evaluated using the widely used moving peaks benchmark. The experimental results show that the proposed NNIT is promising and can accelerate algorithm convergence.

Particle swarm optimization for network-based data classification

Complex networks provide a powerful tool for data representation due to its ability to describe the interplay between topological, functional, and dynamical properties of the input data. A fundamental process in network-based (graph-based) data analysis techniques is the network construction from original data usually in vector form. Here, a natural question is: How to construct an "optimal" network regarding a given processing goal? This paper investigates structural optimization in the context of network-based data classification tasks. To be specific, we propose a particle swarm optimization framework which is responsible for building a network from vector-based data set while optimizing a quality function driven by the classification accuracy. The classification process considers both topological and physical features of the training and test data and employing PageRank measure for classification according to the importance concept of a test instance to each class. Results on artificial and real-world problems reveal that data network generated using structural optimization provides better results in general than those generated by classical network formation methods. Moreover, this investigation suggests that other kinds of network-based machine learning and data mining tasks, such as dimensionality reduction and data clustering, can benefit from the proposed structural optimization method.