Search

Byline: Zhi-Mei. Huang, Chun-Xiao. Lai, Meng-Xuan. Zuo, Chao. An, Xiu-Chen. Wang, Jin-Hua. Huang, Eerdunbagena. Ning Objective: To investigate the safety and therapeutic efficacy of adjuvant cytokine-induced killer (CIK) cells to [...]

As a group of complex neurodevelopmental disorders, autism spectrum disorder (ASD) has been reported to have a high overall prevalence, showing an unprecedented spurt since 2000. Due to the unclear pathomechanism of ASD, it is challenging to diagnose individuals with ASD merely based on clinical observations. Without additional support of biochemical markers, the difficulty of diagnosis could impact therapeutic decisions and, therefore, lead to delayed treatments. Recently, accumulating evidence have shown that both genetic abnormalities and chemical toxicants play important roles in the onset of ASD. In this work, a new multilabel classification (MLC) model is proposed to identify the autistic risk genes and toxic chemicals on a large-scale data set. We first construct the feature matrices and partially labeled networks for autistic risk genes and toxic chemicals from multiple heterogeneous biological databases. Based on both global and local measure metrics, the simulation experiments demonstrate that the proposed model achieves superior classification performance in comparison with the other state-of-the-art MLC methods. Through manual validation with existing studies, 60% and 50% out of the top-20 predicted risk genes are confirmed to have associations with ASD and autistic disorder, respectively. To the best of our knowledge, this is the first computational tool to identify ASD-related risk genes and toxic chemicals, which could lead to better therapeutic decisions of ASD. [ABSTRACT FROM AUTHOR]

With the increasing prevalence of autism spectrum disorder (ASD), it is important to identify ASD patients for effective treatment and intervention, especially in early childhood. Neuroimaging techniques have been used to characterize the complex biomarkers based on the functional connectivity anomalies in the ASD. However, the diagnosis of ASD still adopts the symptom-based criteria by clinical observation. The existing computational models tend to achieve unreliable diagnostic classification on the large-scale aggregated data sets. In this work, we propose a novel graph-based classification model using the deep belief network (DBN) and the Autism Brain Imaging Data Exchange (ABIDE) database, which is a worldwide multisite functional and structural brain imaging data aggregation. The remarkable connectivity features are selected through a graph extension of K-nearest neighbors and then refined by a restricted path-based depth-first search algorithm. Thanks to the feature reduction, lower computational complexity could contribute to the shortening of the training time. The automatic hyperparameter-tuning technique is introduced to optimize the hyperparameters of the DBN by exploring the potential parameter space. The simulation experiments demonstrate the superior performance of our model, which is 6.4% higher than the best result reported on the ABIDE database. We also propose to use the data augmentation and the oversampling technique to identify further the possible subtypes within the ASD. The interpretability of our model enables the identification of the most remarkable autistic neural correlation patterns from the data-driven outcomes. [ABSTRACT FROM AUTHOR]

A new domain decomposition method (DDM) is proposed to solve the electromagnetic scattering from microstrip antennas and arrays conformally mounted on a perfect electrically conducting (PEC) platform. Based on the local geometrical structures and material properties, the complex composite structures is first decomposed into independent sub-domains, following the philosophy of divide and conquer . The combined field integral equation (CFIE), the electric field integral equation (EFIE), and the Poggio–Miller–Chang–Harrington–Wu–Tsai (PMCHWT) formulation are then combined seamlessly in the framework of DDM. These equations are applied for different sub-domains: CFIE is used for the platform (closed PEC) sub-domains and EFIE–PMCHWT is employed for the microstrip (composite structure with dielectric substrate and open PEC sheet) sub-domains. To ensure the continuities of fields, the transmission conditions (TCs) are applied on the touching-faces. Compared with the traditional method, the newly developed DDM not only releases the burden of geometry preparation, but also results in a better conditioned matrix. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new multiattribute decision making (MADM) method based on the interval-valued intuitionistic fuzzy weighted geometric average (IIFWGA) operator, the accuracy function of interval-valued intuitionistic fuzzy values (IVIFVs) and particle swarm optimization (PSO) techniques, where the weights of attributes and the evaluating values of alternatives with respect to attributes are represented by IVIFVs. First, the proposed method uses an accuracy function to transform the decision matrix given by the decision maker and represented by IVIFVs into a transformed decision matrix represented by real values in [ − 1 , 1 ] . Then, it produces the optimal weights of the attributes based on the obtained transformed decision matrix and PSO techniques. It determines the weighted evaluating IVIFV of each alternative based on the IIFWGA operator, the obtained optimal weights of the attributes and the decision matrix given by the decision maker represented by IVIFVs. Finally, it calculates the transformed value of the weighted evaluating IVIFV of each alternative based on the accuracy function to get the preference order of the alternatives. The main contribution of this paper is that we propose a new MADM method based on the IIFWGA operator of IVIFVs, the accuracy function of IVIFVs and PSO techniques, which can overcome the drawbacks of the existing MADM methods for MADM in interval-valued intuitionistic fuzzy (IVIF) environments. [ABSTRACT FROM AUTHOR]

In recent years, some multiattribute decision making (MADM) methods have been presented based on interval-valued intuitionistic fuzzy sets (IVIFSs). In this paper, we propose a new MADM method based on interval-valued intuitionistic fuzzy values (IVIFVs) and the linear programming methodology, where the weights of attributes and the evaluating values of attributes of the alternatives given by the decision maker are represented by IVIFVs. The linear programming methodology is used to obtain the optimal weights of the attributes. The proposed method has the advantage that it can overcome the drawbacks of the existing MADM methods for MADM in interval-valued intuitionistic fuzzy environments. The proposed method provides us with a very useful way for MADM in interval-valued intuitionistic fuzzy environments. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new autocratic decision making method using group recommendations based on ranking interval type-2 fuzzy sets. First, the proposed method calculates the ranking values of interval type-2 fuzzy sets appearing in the weighting vectors and the evaluating matrices given by decision makers, respectively, to construct the ranking weighting vectors and the ranking evaluating matrices of the decision makers, respectively. Then, it constructs the weighted evaluating matrix of each decision maker and calculates the aggregated evaluating value of each alternative with respect to each decision maker for constructing the aggregated evaluating matrix of all decision makers. Then, it gets the numerical preference order of the alternatives with respect to each decision maker represented by a preference vector. Then, it calculates the aggregated group evaluating value of each alternative with respect to all decision makers to get the numerical preference order of the alternatives with respect to all decision makers represented by a group preference vector. Then, it calculates the similarity degree between the obtained preference vector of each decision maker and the obtained group preference vector of all decision makers. Then, it gets the normalized aggregated evaluating value of each alternative with respect to each decision maker to construct the normalized aggregated evaluating vector of each decision maker. Then, it gets the normalized aggregated group evaluating value of each alternative with respect to all decision makers to construct the normalized aggregated group evaluating vector of all decision makers. Finally, it calculates the similarity degree between the obtained normalized aggregated evaluating vector of each decision maker and the obtained normalized aggregated group evaluating vector of all decision makers for changing the weights of the decision makers until the group consensus degree is larger than or equal to a predefined consensus threshold value. We apply the proposed method to deal with the “system analysis engineers” selection problem, the cars selection problem and the “table tennis players” selection problem. The proposed method can overcome the drawbacks of the existing group decision making methods in interval type-2 fuzzy sets environments. [ABSTRACT FROM AUTHOR]

Camera traps are widely used in wildlife surveys because they are non‐invasive, low‐cost, and highly efficient. Camera traps deployed in the wild often produce large datasets, making it increasingly difficult to manually classify images. Deep learning is a machine learning method that provides a tool to automatically identify images, but it requires labeled training samples and high‐performance servers with multiple Graphics Processing Units (GPUs). However, manually preparing large‐scale training images for training deep learning models is labor intensive, and the high‐performance servers with multiple GPUs are often not available for wildlife management agencies and field researchers. Our study explores an adaptive deep learning method to use small‐scale training sets and a commonly‐available, desktop personal computer (PC) to achieve automatic filtering of empty camera images. Our results showed that by using 29,192 training samples, the overall error, commission error, and omission error of the proposed method on a PC were 2.69%, 6.82%, and 6.45%, respectively. Moreover, the accuracy of our method can be adaptively improved on PCs in actual ecological monitoring projects, which would benefit researchers in field settings when only a PC is available. © 2021 The Wildlife Society. : An adaptive automatic method of empty camera trap images was proposed, which used a small‐scale training set to complete the training of a deep learning model on a common PC. The method will benefit researchers in the field setting when only one PC is available. It can also greatly reduce the workload of manually labeling training samples. [ABSTRACT FROM AUTHOR]