The counterflow burner is a combustion device used for research on *** utilizing deep convolutional models to identify the combustion state of a counter flow burner through visible flame images,it facilitates the opti...
详细信息
The counterflow burner is a combustion device used for research on *** utilizing deep convolutional models to identify the combustion state of a counter flow burner through visible flame images,it facilitates the optimization of the combustion process and enhances combustion *** existing deep convolutional models,InceptionNeXt is a deep learning architecture that integrates the ideas of the Inception series and *** has garnered significant attention for its computational efficiency,remarkable model accuracy,and exceptional feature extraction ***,since this model still has limitations in the combustion state recognition task,we propose a Triple-Scale Multi-Stage InceptionNeXt(TSMS-InceptionNeXt)combustion state recognitionmethod based on feature extraction ***,to address the InceptionNeXt model’s limited ability to capture dynamic features in flame images,we introduce Triplet Attention,which applies attention to the width,height,and Red Green Blue(RGB)dimensions of the flame images to enhance its ability to model dynamic ***,to address the issue of key information loss in the Inception deep convolution layers,we propose a Similarity-based Feature Concentration(SimC)mechanism to enhance the model’s capability to concentrate on critical ***,to address the insufficient receptive field of the model,we propose a Multi-Scale Dilated Channel Parallel Integration(MDCPI)mechanism to enhance the model’s ability to extract multi-scale contextual ***,to address the issue of the model’s Multi-Layer Perceptron Head(MlpHead)neglecting channel interactions,we propose a Channel Shuffle-Guided Channel-Spatial Attention(ShuffleCS)mechanism,which integrates information from different channels to further enhance the representational power of the input *** validate the effectiveness of the method,experiments are conducted on the counterflow burner flame visible light image datase
In this paper, we study stealthy cyber-attacks on actuators of cyber-physical systems(CPS), namely zero dynamics and controllable attacks. In particular, under certain assumptions, we investigate and propose condition...
详细信息
In this paper, we study stealthy cyber-attacks on actuators of cyber-physical systems(CPS), namely zero dynamics and controllable attacks. In particular, under certain assumptions, we investigate and propose conditions under which one can execute zero dynamics and controllable attacks in the CPS. The above conditions are derived based on the Markov parameters of the CPS and elements of the system observability matrix. Consequently, in addition to outlining the number of required actuators to be attacked, these conditions provide one with the minimum system knowledge needed to perform zero dynamics and controllable cyber-attacks. As a countermeasure against the above stealthy cyber-attacks, we develop a dynamic coding scheme that increases the minimum number of the CPS required actuators to carry out zero dynamics and controllable cyber-attacks to its maximum possible value. It is shown that if at least one secure input channel exists, the proposed dynamic coding scheme can prevent adversaries from executing the zero dynamics and controllable attacks even if they have complete knowledge of the coding system. Finally, two illustrative numerical case studies are provided to demonstrate the effectiveness and capabilities of our derived conditions and proposed methodologies.
Schizophrenia (SC) is a complex mental disorder with diverse symptoms that make diagnosis challenging. This study aims to enhance diagnostic accuracy for SC using deep learning techniques applied to resting-state func...
详细信息
Schizophrenia (SC) is a complex mental disorder with diverse symptoms that make diagnosis challenging. This study aims to enhance diagnostic accuracy for SC using deep learning techniques applied to resting-state functional MRI (rsfMRI) data, capturing both spatial and temporal features of brain activity. We introduced a novel slice-wise classification approach using convolutional neural networks (CNNs) to analyze brain activity from rsfMRI images. Preprocessing included normalization, noise reduction, and contrast enhancement. The study utilized data from 158 subjects, including 83 schizophrenia patients and 75 healthy controls. We combined CNN-extracted features with traditional machine learning models such as support vector machines (SVM), random forest (RF), and gradient boosting (GB) to boost classification performance. Transfer learning using pre-trained models like VGG16, ResNet50, and Xception was applied to leverage advanced feature extraction. Model performance was evaluated based on precision, accuracy, recall, and F1 score. The CNN-based approach achieved significant improvements in classification accuracy, with a peak accuracy of 98.67%. The hybrid models combining CNN features with SVM, RF, and GB achieved accuracies of 97.01%, 98.44%, and 98.84%, respectively. The CNN model alone achieved a precision of 0.9826, recall of 1.0, and F1 score of 0.9912. Pre-trained models also demonstrated high performance, with ResNet50 achieving an accuracy of 98.71%. Brain regions such as the frontal lobe (slices 5 and 9) and temporal lobe (slices 15 and 25) were identified as key areas with significant differences between schizophrenia patients and healthy controls. This study demonstrates the effectiveness of deep learning models, particularly CNNs and hybrid approaches with traditional machine learning models, in enhancing schizophrenia diagnosis using rsfMRI data. Identifying key brain regions provides insights into schizophrenia’s neurobiological underpinnings. Fu
A silicon solar cell with a power conversion efficiency (PCE)of 4% was born in Bell Lab in 1954, seven decades ago. Today,silicon solar cells have reached an efficiency above 25%and achieved pervasive commercial succe...
A silicon solar cell with a power conversion efficiency (PCE)of 4% was born in Bell Lab in 1954, seven decades ago. Today,silicon solar cells have reached an efficiency above 25%and achieved pervasive commercial success [1]. In spite of the steady improvement in efficiency, the interest and enthusiasm in search for new materials and innovative device architectures for newgeneration solar cells have never diminished or subsided;
Millimeter-wave(mmWave)Non-Orthogonal Multiple Access(NOMA)with random beamforming is a promising technology to guarantee massive connectivity and low latency transmissions of future generations of mobile *** this pap...
详细信息
Millimeter-wave(mmWave)Non-Orthogonal Multiple Access(NOMA)with random beamforming is a promising technology to guarantee massive connectivity and low latency transmissions of future generations of mobile *** this paper,we introduce a cost-effective and energy-efficient mmWave-NOMA system that exploits sparse antenna arrays in the *** analysis shows that utilizing low-weight and small-sized sparse antennas in the Base Station(BS)leads to better outage probability *** also introduce an optimum low complexity Equilibrium Optimization(EO)-based algorithm to further improve the outage *** simulation and analysis results show that the systems equipped with sparse antenna arrays making use of optimum beamforming vectors outperform the conventional systems with uniform linear arrays in terms of outage probability and sum rates.
Co-saliency detection within a single image is a common vision problem that has not yet been well addressed. Existing methods often used a bottom-up strategy to infer co-saliency in an image in which salient regions a...
详细信息
Co-saliency detection within a single image is a common vision problem that has not yet been well addressed. Existing methods often used a bottom-up strategy to infer co-saliency in an image in which salient regions are firstly detected using visual primitives such as color and shape and then grouped and merged into a co-saliency map. However, co-saliency is intrinsically perceived complexly with bottom-up and top-down strategies combined in human vision. To address this problem, this study proposes a novel end-toend trainable network comprising a backbone net and two branch nets. The backbone net uses ground-truth masks as top-down guidance for saliency prediction, whereas the two branch nets construct triplet proposals for regional feature mapping and clustering, which drives the network to be bottom-up sensitive to co-salient regions. We construct a new dataset of 2019 natural images with co-saliency in each image to evaluate the proposed method. Experimental results show that the proposed method achieves state-of-the-art accuracy with a running speed of 28 fps.
With the rise of artificial intelligence and cloud computing, machine-learning-as-a-service platforms,such as Google, Amazon, and IBM, have emerged to provide sophisticated tasks for cloud applications. These propriet...
详细信息
With the rise of artificial intelligence and cloud computing, machine-learning-as-a-service platforms,such as Google, Amazon, and IBM, have emerged to provide sophisticated tasks for cloud applications. These proprietary models are vulnerable to model extraction attacks due to their commercial value. In this paper, we propose a time-efficient model extraction attack framework called Swift Theft that aims to steal the functionality of cloud-based deep neural network models. We distinguish Swift Theft from the existing works with a novel distribution estimation algorithm and reference model settings, finding the most informative query samples without querying the victim model. The selected query samples can be applied to various cloud models with a one-time selection. We evaluate our proposed method through extensive experiments on three victim models and six datasets, with up to 16 models for each dataset. Compared to the existing attacks, Swift Theft increases agreement(i.e., similarity) by 8% while consuming 98% less selecting time.
The emergence of the Internet-of-Things is anticipated to create a vast market for what are known as smart edge devices,opening numerous opportunities across countless domains,including personalized healthcare and adv...
详细信息
The emergence of the Internet-of-Things is anticipated to create a vast market for what are known as smart edge devices,opening numerous opportunities across countless domains,including personalized healthcare and advanced *** 3D integration,edge devices can achieve unprecedented miniaturization while simultaneously boosting processing power and minimizing energy ***,we demonstrate a back-end-of-line compatible optoelectronic synapse with a transfer learning method on health care applications,including electroencephalogram(EEG)-based seizure prediction,electromyography(EMG)-based gesture recognition,and electrocardiogram(ECG)-based arrhythmia *** experiments on three biomedical datasets,we observe the classification accuracy improvement for the pretrained model with 2.93%on EEG,4.90%on ECG,and 7.92%on EMG,*** optical programming property of the device enables an ultralow power(2.8×10^(-13) J)fine-tuning process and offers solutions for patient-specific issues in edge computing ***,the device exhibits impressive light-sensitive characteristics that enable a range of light-triggered synaptic functions,making it promising for neuromorphic vision *** display the benefits of these intricate synaptic properties,a 5×5 optoelectronic synapse array is developed,effectively simulating human visual perception and memory *** proposed flexible optoelectronic synapse holds immense potential for advancing the fields of neuromorphic physiological signal processing and artificial visual systems in wearable applications.
The perception in most existing vision-based reinforcement learning(RL) models for robotic manipulation relies heavily on static third-person or hand-mounted first-person cameras. In scenarios with occlusions and limi...
详细信息
The perception in most existing vision-based reinforcement learning(RL) models for robotic manipulation relies heavily on static third-person or hand-mounted first-person cameras. In scenarios with occlusions and limited maneuvering space, these carefully positioned cameras often struggle to provide effective visual observations during manipulation. Taking inspiration from human capabilities, we introduce a novel RL-based dual-arm active visual-guided manipulation model(DAVMM), which simultaneously infers “eye” actions and “hand” actions for two separate robotic arms(referred to as the vision-arm and the worker-arm) based on current observations, empowering the robot with the ability to actively perceive and interact with its environment. To handle the extensive redundant observation-action space, we propose a decouplable target-centric reward paradigm to offer stable guidance for the training process. For making fine-grained manipulation action decisions, alongside a global scene image encoder, we utilize an independent encoder to extract local target texture features,enabling the simultaneous acquisition of both global and detailed local information. Additionally, we employ residual-RL and curriculum learning techniques to further enhance our model's sample efficiency and training stability. We conducted comparative experiments and analyses of DAVMM against a set of strong baselines on three occluded and narrow-space manipulation tasks. DAVMM notably improves the success rates across all manipulation tasks and showcases rapid learning capabilities.
In the electric power equipment industry,various insulating materials and accessories are manufactured using petroleum-based epoxy ***,petrochemical resources are gradually becoming *** addition,the global surge in pl...
详细信息
In the electric power equipment industry,various insulating materials and accessories are manufactured using petroleum-based epoxy ***,petrochemical resources are gradually becoming *** addition,the global surge in plastic usage has consistently raised concerns regarding greenhouse gas emissions,leading to worsening global ***,to facilitate eco-friendly policies,industrialising epoxy systems applicable to high-pressure components using bio-based epoxy composites is *** results of the characterisation conducted in this research regarding bio-content were confirmed through thermogravimetric analysis and differential scanning calorimetry,which showed that as the bio-content increased,the thermal stability *** the operating temperature of 105℃ for the insulation spacer,structurally,no issues would be encountered if the spacer was manufactured with a bio-content of 20%(bio 20%).Subsequent tensile and flexural strength measurements revealed mechanical properties equivalent to or better than those of their petroleum-based *** impact strength tended to decrease with increasing *** the dielectric properties confirmed that the epoxy composite containing 20%biomaterial is suitable for manufacturing insulation ***,a series of tests conducted after spacer fabrication confirmed the absence of internal metals and bubbles with no external discolouration or cracks observed.
暂无评论