Search

In this study, we examined plant health prediction through the Normalized Difference Vegetation Index (NDVI) calculated from satellite image derived reflectance values in the near-infrared and red spectra. The problem is formulated as a temporal data prediction problem. Using MODIS/Terra Vegetation Indices 16-Day L3 Global 250 m SIN Grid V061 dataset, we designed and implemented Reservoir Computing (RC) models and transformer-based models including pretrained language model, and compared the prediction performance of these models to traditional machine learning and deep learning methods such as Nonlinear Regression, Decision Tree, Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM) network, and DLinear. It is observed that the DLinear/LSTM model showed exceptional predictive accuracy, while the pretrained RC model significantly enhanced traditional RC model forecasts. Additionally, Frozen Pretrained Transformer (FPT), a pretrained language model, showed superior performance in predicting specific NDVI values (most often peak or lowest NDVI), suggesting its effectiveness in precise temporal predictions. Furthermore, transformer-based models, specifically PatchTST and FPT, demonstrated substantial mean squared error reductions, particularly in limited data scenarios (1 %, 5 %, 15 % and 50 % sample sizes), indicating their robustness in precise NDVI temporal predictions when data is limited. The findings in this study demonstrated the effectiveness of emerging machine learning techniques such as reservoir computing and pretrained language model for remote sensing and their contributions in precision agriculture.

The robustness of Deep Neural Networks (DNNs) against adversarial attacks is an important topic in the area of deep learning. To fully investigate the robustness of DNNs, this study examines four frequently used white box adversarial attack techniques, namely, the Fast Gradient Sign Method (FGSM), Projected Gradient Descent (PGD), Basic Iterative Method (BIM), DeepFool, and their effects on DNN models for the image classification task. The results show that ResNet152 and DenseNet201 are less vulnerable comparing to other DNN models to a variety of individual attacks, highlighting their intrinsic strength even in the lack of specific adversarial training. Further, we propose two ensemble adversarial attacks combining three individual attacks for generating adversarial examples from the tiny ImageNet, CIFAR-10, CIFAR-100, and SVHN datasets for DNN model evaluation. It is observed that the performance of the DNNs deteriorate significantly under the proposed ensemble adversarial attacks even after defensive measures have been applied. For instance, the accuracy of the most robust DNN that we tested, namely the defense distillation enhanced DenseNet201, dropped more than 59% under the proposed ensemble adversarial attacks, comparing to only 34% decrease under the individual attacks.

Image segmentation is a crucial task in computer vision. In this study, we propose a method based on inverse quantum Fourier transform (IQFT) and develop a robust IQFT-inspired algorithm for unsupervised image segmentation. The proposed method leverages the underlying mathematical mechanism of the IQFT to cluster the input image pixels automatically and efficiently into different segments. Specifically, by considering the correlation between the within-cluster mean sum of squared error (MSSE) and the probability of quantum measurements, the proposed robust algorithm significantly improves the segmentation performance. It is an unsupervised method with characteristics similar to k-means, i.e., the proposed method does not require training. Extensive evaluation of the proposed method has been carried out, showing that it outperforms the classical k-means on the PASCAL VOC 2012 segmentation benchmark by as much as 4.21%, the Flowers dataset by as much as 4.4%, and the xVIEW2 challenge dataset by as much as 11.1% in terms of Intersection-Over-Union (IoU). It is also demonstrated that the proposed method has comparable or mixed performance compared to recent more complex approaches. However, compared to approaches such as GrabCut, which require a measure of the user interaction, and deep learning-based methods, which require generative models and deep feature extraction algorithms, the proposed method does not require training or user involvement. This makes it a promising choice for applications that do not have access to data before deployment or have very limited training data.

Abstract Background This multi-center study aimed to identify factors affecting fever and delayed defervescence in bacterial meningitis (BM) patients under 3 years of age because of the variability of fever in this patient population. Methods Only BM patients under 3 years treated at 49 centers in China from November 2018 to end-April 2021 were included in the study. Univariate and multivariate logistic regression analyses were performed to determine factors associated with afebrile presentation and fever of delayed defervescence. Results A total of 863 BM patients under 3 years were included in the study. Coagulase negative staphylococcus was associated with afebrile presentation (OR = 1.176), while septicaemia and ear-nose-throat infections were associated with fever (P

Usually, it is difficult to achieve satisfactory fire retardancy of epoxy resin (EP) at low addition by adding inorganic nano-fillers alone. Herein, sepiolite nanofibers loaded with layered double metal hydroxide (a-SEP@LDH) and phosphorus/nitrogen-containing flame retardant nanosheets (PAMA) were prepared via hydrothermal method, respectively. The UL-94 V-0 rating and an limiting oxygen index (LOI) value of 31.6% were achieved for EP by loading 1 wt% a-SEP@LDH and 2 wt% PAMA. Compared to adding sole a-SEP@LDH, the thermal stability of EP/a-SEP@LDH/PAMA3 was improved significantly, the total heat release (THR) and peak heat release rate (pHRR) decreased by 10.2 and 28.8%, respectively. Additionally, the total CO2 production decreased by 12.5% and the char residue yield increased to 19.9 wt%. Moreover, the tensile strength and impact strength of the EP composites were remarkably improved owing to the incorporation of PAMA. To sum up, this work provides an environmentally benign, low-cost and efficient way for EP to achieve outstanding fire retardance, thermal stability and high mechanical properties at a low addition.

Fairness Artificial Intelligence (AI) aims to identify and mitigate bias throughout the AI development process, spanning data collection, modeling, assessment, and deployment—a critical facet of establishing trustworthy AI systems. Tackling data bias through techniques like reweighting samples proves effective for promoting fairness. This paper undertakes a systematic exploration of reweighting samples for conventional Machine-Learning (ML) models, utilizing five models for binary classification on datasets such as Adult Income and COMPAS, incorporating various protected attributes. In particular, AI Fairness 360 (AIF360) from IBM, a versatile open-source library aimed at identifying and mitigating bias in machine-learning models throughout the entire AI application lifecycle, is employed as the foundation for conducting this systematic exploration. The evaluation of prediction outcomes employs five fairness metrics from AIF360, elucidating the nuanced and model-specific efficacy of reweighting samples in fostering fairness within traditional ML frameworks. Experimental results illustrate that reweighting samples effectively reduces bias in traditional ML methods for classification tasks. For instance, after reweighting samples, the balanced accuracy of Decision Tree (DT) improves to 100%, and its bias, as measured by fairness metrics such as Average Odds Difference (AOD), Equal Opportunity Difference (EOD), and Theil Index (TI), is mitigated to 0. However, reweighting samples does not effectively enhance the fairness performance of K Nearest Neighbor (KNN). This sheds light on the intricate dynamics of bias, underscoring the complexity involved in achieving fairness across different models and scenarios.

Abstract Engine mount system affects the automobile NVH performance. Active mounts would achieve excellent vibration isolation and relative displacement control performance in a broad frequency bandwidth by outputting controlled force to the mounting system. The actuator and control method of the active mounts determine the system performance. In this paper, an active mount based on the smart material, i.e., Terfenol-D rod, is proposed, which mainly includes three parts: rubber spring, magnetostrictive actuator (MA), and hydraulic amplification mechanism (HAM). Dynamic model of the active mount is correspondingly established. A state feedback control method based on x-LMS (Least-Mean-Square) algorithm is proposed as well. Specifically, with the consideration of the unmeasurable state parameters in the active mounting system, an x-LMS state feedback controller with the system state as the reference signal is constructed by employing Sage-Husa Kalman filter to realize the state estimation of the active mounting system. Then a detailed analysis of the proposed control method is conducted, with deriving iterative formula of tap-weight vector. Sequentially, the problem of the dependence on the excitation signal in the x-LMS algorithm is addressed. The feasibility and capability of the proposed control method are verified and evaluated by simulation of a two-degree-of-freedom active mounting system.

An organo-cobalt coordination complex (Co-H4APD), based on phosphonitrile-azacycles, was prepared by hydrothermal method. The flame retardancy, smoke suppression and thermal stability of epoxy (EP) composites were investigate by means of limited oxygen index (LOI), cone calorimeter test (CONE) and thermogravimetric analysis (TGA). The flame retardant modes of action of Co-H4APD in EP were confirmed by experiments, such as thermogravimetry-Fourier transform infrared spectroscopy-gas chromatograph/mass spectrometer (TG-FTIR-GC/MS), exploring condense and gas-phase products after composites pyrolysis or combustion. Results revealed that the introduction of 6 wt.% Co-H4APD increased LOI value to 29.8% and effectively suppressed heat/smoke release of EP composites. The synergistic charring effect of Co-H4APD improved the thermal stability and char-forming ability of composites. The char strength may be well-correlated with gas release for EP/Co-H4APD, conducive to form dense and regularly expanded char layer, with more phosphorus-rich graphitic structures and cross-linking structures catalyzed by cobalt ions. This high-quality char layer was regarded as the most critical side in improving the flame retardant and smoke suppression performance of EP composites. The gas-phase function of Co-H4APD should not be overlooked due to releasing phosphorous-based radicals during pyrolysis, exhibiting flame inhibition effect in gas phase. More efficient interactions between phosphazene and cobalt within one molecule unit of Co-H4APD contributed to its more obvious reduction of the combustion and smoke production than those of the physical mixing system of CoO + H4APD.

Abstract Background Noonan syndrome is an autosomal dominant genetic disorder that can occur in men and women and has a sporadic or family history. NS can lead to abnormal bleeding, but cerebral haemorrhage is rare. This is the first case of cerebral haemorrhage with a RAF1 gene mutation that originated in the neonatal period. Case presentation This case presents a newborn with a RAF1 gene mutation resulting in NS complicated with an abnormality of chromosome 46, X, del (Y) (q12). In the course of treatment, the baby's breathing suddenly increased. After an MRI examination of the skull, haemorrhaging was found in multiple parts of the brain. Conclusions After symptomatic treatment, the baby recovered well, but the main cause of cerebral haemorrhage was not found.

Battery state of health (SOH) estimation is crucial for the estimation of the remaining driving range of electric vehicles and is one of the core functions of the battery management system (BMS). The lithium battery feature sample data used in this paper is extracted from the National Aeronautics and Space Administration (NASA) of the United States. Based on the obtained feature samples, a decision tree algorithm is used to analyze them and obtain the importance of each feature. Five groups of different feature inputs are constructed based on the cumulative feature importance, and the original support vector machine regression (SVR) algorithm is applied to perform SOH estimation simulation experiments on each group. The experimental results show that four battery features (voltage at SOC = 100%, voltage, discharge time, and SOC) can be used as input to achieve high estimation accuracy. To improve the training efficiency of the original SVR algorithm, an improved SVR algorithm is proposed, which optimizes the differentiability and solution method of the original SVR objective function. Since the loss function of the original SVR is non-differentiable, a smoothing function is introduced to approximate the loss function of the original SVR, and the original quadratic programming problem is transformed into a convex unconstrained minimization problem. The conjugate gradient algorithm is used to solve the smooth approximation objective function in a sequential minimal optimization manner. The improved SVR algorithm is applied to the simulation experiment with four battery feature inputs. The results show that the improved SVR algorithm significantly reduces the training time compared to the original SVR, with a slight trade-off in simulation accuracy.

Underwater acoustic (UWA) communications have been widely used but greatly impaired due to the complicated nature of the underwater environment. In order to improve UWA communications, modeling and understanding the UWA channel is indispensable. However, there exist many challenges due to the high uncertainties of the underwater environment and the lack of real-world measurement data. In this work, the capability of reservoir computing and deep learning has been explored for modeling the UWA communication channel accurately using real underwater data collected from a water tank with disturbance and from Lake Tahoe. We leverage the capability of reservoir computing for modeling dynamical systems and provided a data-driven approach to modeling the UWA channel using Echo State Network (ESN). In addition, the potential application of transfer learning to reservoir computing has been examined. Experimental results show that ESN is able to model chaotic UWA channels with better performance compared to popular deep learning models in terms of mean absolute percentage error (MAPE), specifically, ESN has outperformed deep neural network by 2% and as much as 40% in benign and chaotic UWA respectively.

The fast execution speed and energy efficiency of analog hardware have made them a strong contender for deploying deep learning models at the edge. However, there are concerns about the presence of analog noise which causes changes to the models’ weight, leading to performance degradation of deep learning models, despite their inherent noise-resistant characteristics. The effect of the popular batch normalization layer (BatchNorm) on the noise-resistant ability of deep learning models is investigated in this work. This systematic study has been carried out by first training different models with and without the BatchNorm layer on the CIFAR10 and the CIFAR100 datasets. The weights of the resulting models are then injected with analog noise, and the performance of the models on the test dataset is obtained and compared. The results show that the presence of the BatchNorm layer negatively impacts the noise-resistant property of deep learning models, i.e., ResNet44 and VGG16 models with BatchNorm layers trained with the CIFAR10 dataset have an average normalized inference accuracy of 41.32% and 10.75% respectively compared to 91.95% and 93.80% obtained for same ResNet44 and VGG16 model without the BatchNorm layer respectively. Furthermore, the impact of the BatchNorm layer also grows with the increase of the number of BatchNorm layers.

Misinformation refers to inaccurate information created to misguide the readers. It spreads on social platforms like Twitter with various presentations such as fake news and rumors that usually contain numbers, categorical information, texts, images, etc., which has become a global issue of cybersecurity. We propose a semi-supervised deep model based on bidirectional recurrent neural networks (Bi-RNN) to detect misinformation with limited labeled data and large unlabeled data. The proposed model consists of three components, namely, shared Bi-RNN, supervised Bi-RNN, and unsupervised Bi-RNN. Specifically, the shared Bi-RNN provides common features that input to the supervised Bi-RNN and unsupervised Bi-RNN, and they jointly optimize two losses, namely, cross-entropy loss and mean-square-error loss, using both labeled data and a large amount of unlabeled data. We validate our proposed model by testing on two benchmark datasets of misinformation: LIAR and PHEME. It is observed that the proposed model is able to achieve promising performance even with very limited labeled data for training when compared to baselines with supervised deep learning.

Background: Resting myocardial perfusion (MP) and wall motion (WM) imaging during real-time myocardial contrast echocardiography (MCE) improves the detection of coronary artery disease (CAD). However, its prognostic role in different clinical settings (emergency department and outpatient setting) remains unclear. Methods: A systematic search in PubMed and Embase databases, and the Cochrane library, was conducted to evaluate the role of resting MP and WM in predicting major adverse cardiac events (MACE), including death, nonfatal myocardial infarction (NFMI) and urgent revascularization in patients presenting to either outpatient clinics or emergency departments with suspected symptomatic CAD. Summary receiver operating characteristic (SROC) curves, sensitivity and specificity plots were applied to assess diagnostic performance using RevMan 5.3. Results: Seven studies met criteria, including 3668 patients (six with follow up ranging from 2 days to 2.6 years). The Relative Risk (RR) for predicting MACE in patients with both abnormal resting MP and WM was 6.1 (95% CI, 5.1–7.2) and 14.3 (95% CI, 10.3–19.8) for death/NFMI, when compared to normal resting MP and WM patients. Having both abnormal resting MP and WM was also more predictive of MACE (RR, 1.7; 95% CI 1.5–1.9) and death/NFMI (RR, 2.2; 95% CI, 1.8–2.7) when compared to abnormal WM with normal resting MP. Conclusion: In this meta-analysis of both ED and outpatient clinic presentations for suspected CAD, having both a resting regional MP and WM abnormality identifies the highest risk patient for adverse events.

A meta-analytic approach was used to identify potential risk factors for dry eye syndrome. PubMed, Embase, and the Cochrane library were systematically searched for studies investigated the risk factors for dry eye syndrome from their inception until September 2021. The odds ratio (OR) with 95% confidence interval (CI) was calculated using the random-effects model. Forty-eight studies comprising 493,630 individuals were included. Older age (OR: 1.82; P

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) causes coronavirus disease 2019 (COVID-19). Imaging tests such as chest X-ray (CXR) and computed tomography (CT) can provide useful information to clinical staff for facilitating a diagnosis of COVID-19 in a more efficient and comprehensive manner. As a breakthrough of artificial intelligence (AI), deep learning has been applied to perform COVID-19 infection region segmentation and disease classification by analyzing CXR and CT data. However, prediction uncertainty of deep learning models for these tasks, which is very important to safety-critical applications like medical image processing, has not been comprehensively investigated. In this work, we propose a novel ensemble deep learning model through integrating bagging deep learning and model calibration to not only enhance segmentation performance, but also reduce prediction uncertainty. The proposed method has been validated on a large dataset that is associated with CXR image segmentation. Experimental results demonstrate that the proposed method can improve the segmentation performance, as well as decrease prediction uncertainty.

In this paper, we propose Device Authentication Code (DAC), a novel method for authenticating IoT deviceswith wireless interface, by exploiting their radio frequency (RF) signatures. The proposed DAC is based on RF fingerprinting, an information-theoretic method, feature learning, and the discriminatory power of deep learning. Specifically, an autoencoder is used to automatically extract features from the RF traces and the reconstruction error is used as the DAC, and this DAC is unique to each individual device. Then Kolmogorov-Smirnov (K-S) test is used to match the distribution of the reconstruction error generated by the receiver and the DAC in the received message, and the result will determine whether the device of interest is an intruder. We validate this concept on two experimentally collected RF traces from six ZigBee devices and five universal software defined radio peripheral devices, respectively. The traces span a range of Signal-to-Noise Ratio by varying locations, mobility of the devices, channel interference, and noise to ensure robustness ofthe model. Experimental results demonstrate that DAC is able to prevent device impersonation by extracting salient features that are unique to each wireless device of interest and can be used to identify radio frequency devices. Furthermore, the proposed method does not need the RF traces of the intruder during model training to be able to identify devices not seen during training, which makes it practical.

Intelligent capabilities are of utmost importance in future wireless communication systems. For optimum resource utilization, wireless communication systems require knowledge of the prevalent situation in a frequency band through learning. To learn appropriately, it is imperative for practitioners to select the right parameters for building robust data-driven learning models as well as use the appropriate algorithms and performance evaluation methods. In this paper, we evaluate the performance of deep learning models against the performance of other machine learning methods for wireless communication systems. We explore the different wireless communication scenarios in which deep learning can be used given Radio Frequency (RF) data, and evaluate its performance in various scenarios. Furthermore, we express it as a distribution alignment problem in which deep learning models do not perform well when learning from RF data of a particular distribution and evaluating on RF data from a different distribution. We also discuss our results in the light of how signal quality affects deep learning model leveraging on the knowledge from computer vision domain. The effect of Signal-to-Noise Ratio (SNR) selection for training on the model performance as it relates to practical implementation of deep learning in communications systems is also discussed. From our analysis, we conclude that the design and use of RF spectrum learning must be tailored to each specific scenario being considered in practice.

Through machine learning, this paper changes the fundamental assumption of the traditional medium access control (MAC) layer design. It obtains the capability of retrieving the information even the packets collide by training a deep neural network offline with the historical radio frequency (RF) traces and inferring the STAs involved collisions online in near-real-time. Specifically, we propose a MAC protocol based on intelligent spectrum learning for the future wireless local area networks (WLANs), called SL-MAC. In the proposed MAC, an access point (AP) is installed with a pre-trained convolutional neural network (CNN) model to identify the stations (STAs) involved in the collisions. In contrast to the conventional contention-based random medium access methods, e.g., IEEE 802.11 distributed coordination function (DCF), the proposed SL-MAC protocol seeks to schedule data transmissions from the STAs suffering from the collisions. To achieve this goal, we develop a two-step offline training algorithm enabling the AP to sense the spectrum with the aid of the CNN. In particular, on receiving the overlapped signal(s), the AP firstly predicts the number of STAs involving collisions and then further identifies the STAs' ID. Furthermore, we analyze the upper bound of throughput gain brought by the CNN predictor and investigate the impact of the inference error on the achieved throughput. Extensive simulations show the superiority of the proposed SL-MAC and allow us to gain insights on the trade-off between performance gain and the inference accuracy.

State-of-charge (SOC) prediction is an important part of the battery management system (BMS) in electric vehicles. Since external factors (voltage, current, temperature, arrangement of the battery, etc.) impact SOC prediction differently, the SOC is difficult to model. In this article, we apply principal component analysis (PCA) to analyze the contribution of various external factors and propose a new SOC prediction method based on an improved support vector machine for regression (SVR) with data classification and training set size optimization. Three groups of simulation experiments with different inputs based on the original SVR algorithm are conducted in the software ADVISOR, and the simulation results show that the input of three features of the battery (current, voltage and temperature) can satisfy the SOC prediction accuracy. The improved SVR algorithm is then applied to the simulation experiment of the three input features. The proposed method is demonstrated to be faster and more accurate than the original SVR algorithm through a comparison of the simulation results.

Abstract Background Electronic Medical Record (EMR) comprises patients’ medical information gathered by medical stuff for providing better health care. Named Entity Recognition (NER) is a sub-field of information extraction aimed at identifying specific entity terms such as disease, test, symptom, genes etc. NER can be a relief for healthcare providers and medical specialists to extract useful information automatically and avoid unnecessary and unrelated information in EMR. However, limited resources of available EMR pose a great challenge for mining entity terms. Therefore, a multitask bi-directional RNN model is proposed here as a potential solution of data augmentation to enhance NER performance with limited data. Methods A multitask bi-directional RNN model is proposed for extracting entity terms from Chinese EMR. The proposed model can be divided into a shared layer and a task specific layer. Firstly, vector representation of each word is obtained as a concatenation of word embedding and character embedding. Then Bi-directional RNN is used to extract context information from sentence. After that, all these layers are shared by two different task layers, namely the parts-of-speech tagging task layer and the named entity recognition task layer. These two tasks layers are trained alternatively so that the knowledge learned from named entity recognition task can be enhanced by the knowledge gained from parts-of-speech tagging task. Results The performance of our proposed model has been evaluated in terms of micro average F-score, macro average F-score and accuracy. It is observed that the proposed model outperforms the baseline model in all cases. For instance, experimental results conducted on the discharge summaries show that the micro average F-score and the macro average F-score are improved by 2.41% point and 4.16% point, respectively, and the overall accuracy is improved by 5.66% point. Conclusions In this paper, a novel multitask bi-directional RNN model is proposed for improving the performance of named entity recognition in EMR. Evaluation results using real datasets demonstrate the effectiveness of the proposed model.

Background/Aims: Cardiac fibrosis is a pathological change leading to cardiac remodeling during the progression of myocardial ischemic diseases, and its therapeutic strategy remains to be explored. S100A4, a calcium-binding protein, participates in fibrotic diseases with an unclear mechanism. This study aimed to investigate the role of S100A4 in cardiac fibrosis. Methods: Cardiac fibroblasts from neonatal C57BL/6 mouse hearts were isolated and cultured. Myocardial infarction was induced by ligating the left anterior descending coronary artery (LAD). The ligation was not performed in the sham group. A volume of 5×105pfu/g adenovirus or 5 µM/g ICG-001 was intramyocardially injected into five parts bordering the infarction zone or normal region. We used Western blotting, quantitative RT-PCR, immunofluorescence, immunohistochemistry and Masson’s trichrome staining to explore the function of S100A4. Results: We found significant increases of S100A4 level and cardiac fibrosis markers, and β-catenin signaling activation in vitro and in vivo. In addition, knockdown of S100A4 significantly reduced cardiac fibrosis and β-catenin levels. Moreover, the expression of S100A4 decreased after ICG-001 inhibited β-catenin signal pathway. Conclusion: Downregulation of S100A4 alleviates cardiac fibrosis via Wnt/β -catenin pathway in mice. S100A4 may be a therapeutic target of cardiac fibrosis.

This study presents a novel neural network (NN)-based non-linear adaptive control strategy for the global stability of multi-input–multi-output state-control homogeneous bilinear system (BLS) at the equilibrium position. Although this class of non-linear system is neither piecewise nor feedback linearisable, conditionally stabilisable control system design can be utilised to generate multiple state transitions and corresponding control gains. The collected data was used to train a NN to obtain an optimal gain estimator. Then the optimal gain estimator was integrated into real-time control system operation to adaptively compute control gains, ensuring that the controller is continuously adjustable to changing behaviour of the system. The proposed design was shown, through an illustrative example, to overcome the stability limitations of traditional controllers for the investigated class of BLS. Furthermore, discussions about the utility of the traditional control and learning system integration, as well as stability analysis of the proposed scheme were presented.

Social media is a popular platform for information sharing. Any piece of information can be spread rapidly across the globe at lightning speed. The biggest challenge for social media platforms like Twitter is how to trust news shared on them when there is no systematic news verification process, which is the case for traditional media. Detecting false information, for example, detection of rumors is a non-trivial task, given the fast-paced social media environment. In this work, we proposed an ensemble model, which performs majority-voting scheme on a collection of predictions of neural networks using time-series vector representation of Twitter data for fast detection of rumors. Experimental results show that proposed neural network models outperformed classical machine learning models in terms of micro F1 score. When compared to our previous works the improvements are 12.5% and 7.9%, respectively.

An organic triazine charring agent hybrid with zinc oxide (OTCA@ZnO) was prepared and well characterized through Fourier transform infrared spectrometry (FTIR), solid-state nuclear magnetic resonance (SSNMR), transmission electron microscopy (TEM) and thermogravimetric analysis (TGA). The flame retardancy and thermal behaviour of intumescent flame retardant ethylene-vinyl acetate (EVA) composites combining OTCA@ZnO and ammonium polyphosphate (APP) were investigated using limited oxygen index (LOI), UL-94 vertical burning, cone calorimetry and TGA. The structure and morphology of chars were investigated by scanning electron microscopy (SEM), FTIR, laser Raman spectroscopy analysis (LRS) and X-ray photoelectron spectroscopy (XPS). Results revealed that OTCA@ZnO exhibited excellent thermal stability and dispersity after hybridization. The flame retardancy and smoke suppression properties of EVA were significantly improved by introducing APP/OTCA@ZnO. TGA results indicated that APP/OTCA@ZnO presented an excellent synergistic effect and promoted the char formation of EVA composites. Residue analysis results showed more char with high quality connected by richer P–O–C, P–N and P–O–Si structures was formed in APP/OTCA@ZnO system than APP/HOTCA/ZnO system, which consequently suppressed more efficiently the combustion and smoke production due to the in situ catalytic carbonization effect of hybrid.

Specific entity terms such as disease, test, symptom, and genes in Electronic Medical Record (EMR) can be extracted by Named Entity Recognition (NER). However, limited resources of labeled EMR pose a great challenge for mining medical entity terms. In this study, a novel multitask bi-directional RNN model combined with deep transfer learning is proposed as a potential solution of transferring knowledge and data augmentation to enhance NER performance with limited data. The proposed model has been evaluated using micro average F-score, macro average F-score and accuracy. It is observed that the proposed model outperforms the baseline model in the case of discharge datasets. For instance, for the case of discharge summary, the micro average F-score is improved by 2.55% and the overall accuracy is improved by 7.53%. For the case of progress notes, the micro average F-score and the overall accuracy are improved by 1.63% and 5.63%, respectively.

The theory of compressive sensing (CS) has been employed to detect available spectrum resource in cognitive radio (CR) networks recently. Capitalizing on the spectrum resource underutilization and spatial sparsity of primary user (PU) locations, CS enables the identification of the unused spectrum bands and PU locations at a low sampling rate. Although CS has been studied in the cooperative spectrum sensing mechanism in which CR nodes work collaboratively to accomplish the spectrum sensing and PU localization task, many important issues remain unsettled. Does the designed compressive spectrum sensing mechanism satisfy the Restricted Isometry Property, which guarantees a successful recovery of the original sparse signal? Can the spectrum sensing results help the localization of PUs? What are the characteristics of localization errors? To answer those questions, we try to justify the applicability of the CS theory to the compressive spectrum sensing framework in this paper, and propose a design of PU localization utilizing the spectrum usage information. The localization error is analyzed by the Cramér-Rao lower bound, which can be exploited to improve the localization performance. Detail analysis and simulations are presented to support the claims and demonstrate the efficacy and efficiency of the proposed mechanism.

The demand for wireless services is growing on a daily basis while spectral resources to support this growth are static. Therefore, there is need for the adoption of a new spectrum sharing paradigm. Cognitive Radio (CR) is a revolutionary technology aiming to increase spectrum utilization through dynamic spectrum access, as well as mitigating interference among multiple coexisting wireless networks. In many practical scenarios, multiple CR networks may coexist in the same geographical area, and they may interfere with each other and also have to yield to the primary user (PU). In this study, we investigate how much throughput a node in a CR network can achieve in the presence of another CR network and a PU. The results of this study illustrate how the transmission probability and sensing performance affect the achievable throughput of a node in coexisting CR networks. In addition, these results may serve as guidance for the deployment of multiple CR networks.

It is necessary for automated vehicles (AVs) and advanced driver assistance systems (ADASs) to have a better understanding of the traffic environment including driving behaviors. This study aims to build a driving behavior awareness (DBA) model that can infer driving behaviors such as lane change. In this study, a dynamic Bayesian network DBA model is proposed, which includes three layers, namely, the observation, hidden and behavior layer. To enhance the performance of the DBA model, the network structure is optimized by employing a distributed genetic algorithm (GA). Using naturalistic driving data in Beijing, the comparison between the optimized model and other non-optimized models such as the hidden Markov model (HMM) and HMM with a mixture of Gaussian outputs (GM-HMM) indicates that the optimized model could estimate driving behaviors earlier and more accurately.

As cancer growth and development typically involves multiple genes and pathways, combination therapy has been touted as the standard of care in the treatment of cancer. However, drug toxicity becomes a major concern whenever a patient takes 2 or more drugs simultaneously at the maximum tolerable dosage. A potential solution would be administering the drugs in a sequential or alternating manner rather than concurrently. This study therefore examines the feasibility of such an approach from a switched system control perspective. Particularly, we study how genetic regulatory systems respond to sequential (switched) drug inputs using the time-based switching mechanism. The design of the time-driven drug switching function guarantees the stability of the genetic regulatory system and the repression of the diseased genes. Simulation results using proof-of-concept models and the proliferation and survival pathways with sequential drug inputs show the effectiveness of the proposed approach.

Tree multicast configuration of smart meters (SMs) can maintain the connectivity and meet the latency requirements for the Advanced Metering Infrastructure (AMI). However, such topology is extremely weak as any single failure suffices to break its connectivity. On the other hand, the impact of a SM node failure can be more or less significant: a noncut SM node will have a limited local impact compared to a cut SM node that will break the network connectivity. In this work, we design a highly connected tree with a set of backup links to minimize the weakness of tree topology of SMs. A topology repair scheme is proposed to address the impact of a SM node failure on the connectivity of the augmented tree network. It relies on a loop detection scheme to define the criticality of a SM node and specifically targets cut SM node by selecting backup parent SM to cover its children. Detailed algorithms to create such AMI tree and related theoretical and complexity analysis are provided with insightful simulation results: sufficient redundancy is provided to alleviate data loss at the cost of signaling overhead. It is however observed that biconnected tree provides the best compromise between the two entities.

In this paper, we review multiscale modeling for cancer treatment with the incorporation of drug effects from an applied system's pharmacology perspective. Both the classical pharmacology and systems biology are inherently quantitative; however, systems biology focuses more on networks and multifactorial controls over biological processes rather than on drugs and targets in isolation, whereas systems pharmacology has a strong focus on studying drugs with regard to the pharmacokinetic (PK) and pharmacodynamic (PD) relations accompanying drug interactions with multiscale physiology as well as the prediction of dosage-exposure responses and economic potentials of drugs. Thus, it requires multiscale methods to address the need for integrating models from the molecular levels to the cellular, tissue, and organism levels. It is a common belief that tumorigenesis and tumor growth can be best understood and tackled by employing and integrating a multifaceted approach that includes in vivo and in vitro experiments, in silico models, multiscale tumor modeling, continuous/discrete modeling, agent-based modeling, and multiscale modeling with PK/PD drug effect inputs. We provide an example application of multiscale modeling employing stochastic hybrid system for a colon cancer cell line HCT-116 with the application of Lapatinib drug. It is observed that the simulation results are similar to those observed from the setup of the wet-lab experiments at the Translational Genomics Research Institute.

A joint power control and maximally disjoint routing algorithm is proposed for multihop CDMA wireless ad hoc networks. A framework of power control with QoS constraints in CDMA wireless ad hoc networks is introduced and the feasibility condition of the power control problem is identified. Both centralized solution and distributed implementations are derived to calculate the transmission power given the required throughput and the set of transmitting nodes. Then, a joint power control and maximally disjoint routing scheme is proposed for routing data traffic with minimum rate constraint while maintaining high energy efficiency and prolonged network lifetime. Furthermore, in order to provide reliable end-to-end data delivery, the proposed joint power control and maximally disjoint routing scheme is augmented by a dynamic traffic switching mechanism to mitigate the effect of node mobility or node failure. Simulation results demonstrate the effectiveness of the proposed scheme.