Graph Convolutional Network With Connectivity Uncertainty for EEG-Based Emotion Recognition.

Automatic emotion recognition based on multichannel Electroencephalography (EEG) holds great potential in advancing human-computer interaction. However, several significant challenges persist in existing research on algorithmic emotion recognition. These challenges include the need for a robust model to effectively learn discriminative node attributes over long paths, the exploration of ambiguous topological information in EEG channels and effective frequency bands, and the mapping between intrinsic data qualities and provided labels. To address these challenges, this study introduces the distribution-based uncertainty method to represent spatial dependencies and temporal-spectral relativeness in EEG signals based on Graph Convolutional Network (GCN) architecture that adaptively assigns weights to functional aggregate node features, enabling effective long-path capturing while mitigating over-smoothing phenomena. Moreover, the graph mixup technique is employed to enhance latent connected edges and mitigate noisy label issues. Furthermore, we integrate the uncertainty learning method with deep GCN weights in a one-way learning fashion, termed Connectivity Uncertainty GCN (CU-GCN). We evaluate our approach on two widely used datasets, namely SEED and SEEDIV, for emotion recognition tasks. The experimental results demonstrate the superiority of our methodology over previous methods, yielding positive and significant improvements. Ablation studies confirm the substantial contributions of each component to the overall performance.

From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networks.

Deep neural networks (DNNs) have been widely used in many artificial intelligence (AI) tasks. However, deploying them brings significant challenges due to the huge cost of memory, energy, and computation. To address these challenges, researchers have developed various model compression techniques such as model quantization and model pruning. Recently, there has been a surge in research on compression methods to achieve model efficiency while retaining performance. Furthermore, more and more works focus on customizing the DNN hardware accelerators to better leverage the model compression techniques. In addition to efficiency, preserving security and privacy is critical for deploying DNNs. However, the vast and diverse body of related works can be overwhelming. This inspires us to conduct a comprehensive survey on recent research toward the goal of high-performance, cost-efficient, and safe deployment of DNNs. Our survey first covers the mainstream model compression techniques, such as model quantization, model pruning, knowledge distillation, and optimizations of nonlinear operations. We then introduce recent advances in designing hardware accelerators that can adapt to efficient model compression approaches. In addition, we discuss how homomorphic encryption can be integrated to secure DNN deployment. Finally, we discuss several issues, such as hardware evaluation, generalization, and integration of various compression approaches. Overall, we aim to provide a big picture of efficient DNNs from algorithm to hardware accelerators and security perspectives.

Local-Global Correlation Fusion-Based Graph Neural Network for Remaining Useful Life Prediction.

Remaining useful life (RUL) prediction is an essential component for prognostics and health management of a system. Due to the powerful ability of nonlinear modeling, deep learning (DL) models have emerged as leading solutions by capturing temporal dependencies within time series sensory data. However, in RUL prediction tasks, data are typically collected from multiple sensors, introducing spatial dependencies in the form of sensor correlations. Existing methods are limited in effectively modeling and capturing the spatial dependencies, restricting their performance to learn representative features for RUL prediction. To overcome the limitations, we propose a novel LOcal-GlObal correlation fusion-based framework (LOGO). Our approach combines both local and global information to model sensor correlations effectively. From a local perspective, we account for local correlations that represent dynamic changes of sensor relationships in local ranges. Simultaneously, from a global perspective, we capture global correlations that depict relatively stable relations between sensors. An adaptive fusion mechanism is proposed to automatically fuse the correlations from different perspectives. Subsequently, we define sequential micrographs for each sample to effectively capture the fused correlations. Graph neural network (GNN) is introduced to capture the spatial dependencies within each micrograph, and the temporal dependencies between these sequential micrographs are then captured. This approach allows us to effectively model and capture the dependency information within the data for accurate RUL prediction. Extensive experiments have been conducted, verifying the effectiveness of our method.

ECG-CL: A Comprehensive Electrocardiogram Interpretation Method Based on Continual Learning.

The value of Electrocardiogram (ECG) monitoring in early cardiovascular disease (CVD) detection is undeniable, especially with the aid of intelligent wearable devices. Despite this, the requirement for expert interpretation significantly limits public accessibility, underscoring the need for advanced diagnosis algorithms. Deep learning-based methods represent a leap beyond traditional rule-based algorithms, but they are not without challenges such as small databases, inefficient use of local and global ECG information, high memory requirements for deploying multiple models, and the absence of task-to-task knowledge transfer. In response to these challenges, we propose a multi-resolution model adept at integrating local morphological characteristics and global rhythm patterns seamlessly. We also introduce an innovative ECG continual learning (ECG-CL) approach based on parameter isolation, designed to enhance data usage effectiveness and facilitate inter-task knowledge transfer. Our experiments, conducted on four publicly available databases, provide evidence of our proposed continual learning method's ability to perform incremental learning across domains, classes, and tasks. The outcome showcases our method's capability in extracting pertinent morphological and rhythmic features from ECG segmentation, resulting in a substantial enhancement of classification accuracy. This research not only confirms the potential for developing comprehensive ECG interpretation algorithms based on single-lead ECGs but also fosters progress in intelligent wearable applications. By leveraging advanced diagnosis algorithms, we aspire to increase the accessibility of ECG monitoring, thereby contributing to early CVD detection and ultimately improving healthcare outcomes.

Self-Supervised Contrastive Representation Learning for Semi-Supervised Time-Series Classification.

Learning time-series representations when only unlabeled data or few labeled samples are available can be a challenging task. Recently, contrastive self-supervised learning has shown great improvement in extracting useful representations from unlabeled data via contrasting different augmented views of data. In this work, we propose a novel Time-Series representation learning framework via Temporal and Contextual Contrasting (TS-TCC) that learns representations from unlabeled data with contrastive learning. Specifically, we propose time-series-specific weak and strong augmentations and use their views to learn robust temporal relations in the proposed temporal contrasting module, besides learning discriminative representations by our proposed contextual contrasting module. Additionally, we conduct a systematic study of time-series data augmentation selection, which is a key part of contrastive learning. We also extend TS-TCC to the semi-supervised learning settings and propose a Class-Aware TS-TCC (CA-TCC) that benefits from the available few labeled data to further improve representations learned by TS-TCC. Specifically, we leverage the robust pseudo labels produced by TS-TCC to realize a class-aware contrastive loss. Extensive experiments show that the linear evaluation of the features learned by our proposed framework performs comparably with the fully supervised training. Additionally, our framework shows high efficiency in few labeled data and transfer learning scenarios.

A systematic review of image-guided, surgical robot-assisted percutaneous puncture: Challenges and benefits.

Percutaneous puncture is a common medical procedure that involves accessing an internal organ or tissue through the skin. Image guidance and surgical robots have been increasingly used to assist with percutaneous procedures, but the challenges and benefits of these technologies have not been thoroughly explored. The aims of this systematic review are to furnish an overview of the challenges and benefits of image-guided, surgical robot-assisted percutaneous puncture and to provide evidence on this approach. We searched several electronic databases for studies on image-guided, surgical robot-assisted percutaneous punctures published between January 2018 and December 2022. The final analysis refers to 53 studies in total. The results of this review suggest that image guidance and surgical robots can improve the accuracy and precision of percutaneous procedures, decrease radiation exposure to patients and medical personnel and lower the risk of complications. However, there are many challenges related to the use of these technologies, such as the integration of the robot and operating room, immature robotic perception, and deviation of needle insertion. In conclusion, image-guided, surgical robot-assisted percutaneous puncture offers many potential benefits, but further research is needed to fully understand the challenges and optimize the utilization of these technologies in clinical practice.

Self-supervised Learning for Label-Efficient Sleep Stage Classification: A Comprehensive Evaluation.

The past few years have witnessed a remarkable advance in deep learning for EEG-based sleep stage classification (SSC). However, the success of these models is attributed to possessing a massive amount of labeled data for training, limiting their applicability in real-world scenarios. In such scenarios, sleep labs can generate a massive amount of data, but labeling can be expensive and time-consuming. Recently, the self-supervised learning (SSL) paradigm has emerged as one of the most successful techniques to overcome labels' scarcity. In this paper, we evaluate the efficacy of SSL to boost the performance of existing SSC models in the few-labels regime. We conduct a thorough study on three SSC datasets, and we find that fine-tuning the pretrained SSC models with only 5% of labeled data can achieve competitive performance to the supervised training with full labels. Moreover, self-supervised pretraining helps SSC models to be more robust to data imbalance and domain shift problems.

Privacy-Preserving Cross-Environment Human Activity Recognition.

Recent studies have demonstrated the success of using the channel state information (CSI) from the WiFi signal to analyze human activities in a fixed and well-controlled environment. Those systems usually degrade when being deployed in new environments. A straightforward solution to solve this limitation is to collect and annotate data samples from different environments with advanced learning strategies. Although workable as reported, those methods are often privacy sensitive because the training algorithms need to access the data from different environments, which may be owned by different organizations. We present a practical method for the WiFi-based privacy-preserving cross-environment human activity recognition (HAR). It collects and shares information from different environments, while maintaining the privacy of individual person being involved. At the core of our approach is the utilization of the Johnson-Lindenstrauss transform, which is theoretically shown to be differentially private. Based on that, we further design an adversarial learning strategy to generate environment-invariant representations for HAR. We demonstrate the effectiveness of the proposed method with different data modalities from two real-life environments. More specifically, on the raw CSI dataset, it shows 2.18% and 1.24% improvements over challenging baselines for two environments, respectively. Moreover, with the discrete wavelet transform features, it further yields 5.71% and 1.55% improvements, respectively.

SSA-ICL: Multi-domain adaptive attention with intra-dataset continual learning for Facial expression recognition.

Facial expression recognition (FER) is a kind of affective computing that identifies the emotional state represented in facial photographs. Various methods have been developed for completing this critical task. In spite of this progress, three significant obstacles, the interaction between spatial action units, the inadequacy of semantic information about spectral expressions and the unbalanced data distribution, are not well addressed. In this work, we propose SSA-ICL, a novel approach for FER, and solve these three difficulties inside a coherent framework. To address the first two challenges, we develop a Spectral and Spatial Attention (SSA) module that integrates spectral semantics with spatial locations to improve the performance of the model. We provide an Intra-dataset Continual Learning (ICL) module to combat the issue of long-tail distribution in FER datasets. By subdividing a single long-tail dataset into multiple sub-datasets, ICL repeatedly trains well-balanced representations from each subset and finally develop a independent classifier. We performed extensive experiments on two publicly available datasets, AffectNet and RAFDB. In comparison to existing attention modules, our SSA achieves an accuracy improvement of 3.8%∼6.7%, as evidenced by testing results. In the meanwhile, our proposed SSA-ICL can achieve superior or comparable performance to state-of-the-art FER methods (65.78% on AffectNet and 89.44% on RAFDB).

Diagnostic Significance of Combined Calcitoninogen, Platelet, and D-Dimer Assay in Severe Heatstroke: with Clinical Data Analysis of 70 Patients with Severe Heatstroke.

The significance of calcitoninogen detection among inpatients was discussed by analyzing the clinical characteristics of severe heatstroke (HS). HS patients who were admitted to the Second Hospital of Nantong University, Jiangsu Province, China, between July 1, 2015, and October 30, 2020, were reviewed. Patients' clinical characteristics and laboratory data were recorded, and they were divided into three groups, that is, a control group (heat cramps and heat exhaustion), an exertional HS (EHS) group, and a classical HS (CHS) group to compare the differences among them. Receiver operating characteristic (ROC) curves were plotted to evaluate patients' clinical utility. (1) The body temperatures in the EHS and CHS groups were significantly higher than in the control group (all p < 0.05). (2) The D-dimer (DD), procalcitonin (PCT), and Acute Physiology and Chronic Health Evaluation (APACHE) II score of the EHS group were significantly higher compared with the control and CHS groups (all p < 0.05); the platelets (PLT), C-reactive protein (CRP), blood sodium (Na), and intravenous glucose (GLU) of the EHS group were lower than in the control and CHS groups (all p < 0.05). (3) The ROC curve analysis showed the performance results for DD (area under the curve [AUC] 0.670, 95% confidence interval [CI] 0.547-0.777), PCT (AUC 0.705, 95% CI 0.584-0.808), and PLT (AUC 0.791, 95% CI 0.677-0.879). The sensitivity was 40.48%, 100%, and 73.81%, and the specificity was 96.43%, 32.14%, and 78.57%, respectively. Using three combined analyses, an elevated AUC of 0.838, 95% CI 0.731-0.916, with a sensitivity of 71.43% and a specificity of 85.71%, respectively, was revealed. Patients in the EHS group had higher DD, PCT, and APACHE II values, whereas PLT, CRP, Na, and GLU were reduced. The apparent decrease in the PLT, as well as the increase in PCT and DD values, could be considered as early sensitivity indicators of severe HS. A combined test of these three indicators presented significant diagnostic value for detecting severe cases of HS.

Aligning Correlation Information for Domain Adaptation in Action Recognition.

Domain adaptation (DA) approaches address domain shift and enable networks to be applied to different scenarios. Although various image DA approaches have been proposed in recent years, there is limited research toward video DA. This is partly due to the complexity in adapting the different modalities of features in videos, which includes the correlation features extracted as long-range dependencies of pixels across spatiotemporal dimensions. The correlation features are highly associated with action classes and proven their effectiveness in accurate video feature extraction through the supervised action recognition task. Yet correlation features of the same action would differ across domains due to domain shift. Therefore, we propose a novel adversarial correlation adaptation network (ACAN) to align action videos by aligning pixel correlations. ACAN aims to minimize the distribution of correlation information, termed as pixel correlation discrepancy (PCD). Additionally, video DA research is also limited by the lack of cross-domain video datasets with larger domain shifts. We, therefore, introduce a novel HMDB-ARID dataset with a larger domain shift caused by a larger statistical difference between domains. This dataset is built in an effort to leverage current datasets for dark video classification. Empirical results demonstrate the state-of-the-art performance of our proposed ACAN for both existing and the new video DA datasets.

Bioinformatics analysis of BIRC5 in human cancers.

Background: An inhibitor of apoptosis (IAP) family member, baculoviral IAP repeat containing five (BIRC5) plays an important role in the occurrence and development of tumors. However, the underlying mechanism in human cancers remains unclear. Methods: In this study, we investigated BIRC5 expression and explored the prognostic value of BIRC5 in different human cancers via bioinformatics analysis, including the databases of Oncomine, Gene Expression Profiling Interactive Analysis (GEPIA), UALCAN, GEPIA, DriverDBv3, GeneMANIA, WEB-based Gene Set Analysis Tool (WebGestalt) and TIMER. Results: In most human cancers, BIRC5 usually had higher expression compared to normal human tissues. High expression of BIRC5 could increase the mortality of patients with adrenocortical carcinoma (ACC), kidney renal clear cell carcinoma (KIRC), low-grade glioma (LGG), liver hepatocellular carcinoma (LIHC), and lung adenocarcinoma (LUAD) (P<0.05). Cox analysis demonstrated that high BIRC5 expression was an independent factor for poor overall survival (OS) [hazard ratio, (HR) >1, P<0.05]. There were differences in BIRC5 expression in the case of TP53 mutation, different tumor grades, and stages. Interactive genes for BIRC5 mainly participated in apoptosis, cell division, cell cycle, and cancer pathways, strongly suggesting its oncogenic role in promoting cancer cell proliferation and cancer development. In addition, BIRC5 expression exhibited a close correlation with immune infiltration, which was related to the cumulative survival rate, especially in LGG. The elevated expression of BIRC5 could be regulated through TP53 mutation, tumor stage, and tumor grade (P<0.05). Conclusions: As a result of our findings, BIRC5 appears to be an independent unfavourable prognostic biomarker in human cancers. BIRC5 may become a potential clinical target in the future for the treatment of cancers.

Organochlorine pesticides (OCPs) in corals and plankton from a coastal coral reef ecosystem, south China sea.

Recent studies have indicated that coral mucus plays an important role in the bioaccumulation of a few organic pollutants by corals, but no relevant studies have been conducted on organochlorine pesticides (OCPs). Previous studies have also indicated that OCPs widely occur in a few coral reef ecosystems and have a negative effect on coral health. Therefore, this study focused on the occurrence and bioaccumulation of a few OCPs, such as dichlorodiphenyltrichloroethanes (DDTs), hexachlorobenzene (HCB) and p,p'-methoxychlor (MXC), in the coral tissues and mucus as well as in plankton and seawater from a coastal reef ecosystem (Weizhou Island) in the South China Sea. The results indicated that DDTs were the predominant OCPs in seawater and marine biota. Higher concentrations of OCPs in plankton may contribute to the enrichment of OCPs by corals. The significantly higher total OCP concentration (∑8OCPs) found in coral mucus than in coral tissues suggested that coral mucus played an essential role in resisting enrichment of OCPs by coral tissues. This study explored the different functions of coral tissues and mucus in OCP enrichment and biodegradation for the first time, highlighting the need for OCP toxicity experiments from both tissue and mucus perspectives.

Mechanosensitive Channel PIEZO1 Senses Shear Force to Induce KLF2/4 Expression via CaMKII/MEKK3/ERK5 Axis in Endothelial Cells.

Shear stress exerted by the blood stream modulates endothelial functions through altering gene expression. KLF2 and KLF4, the mechanosensitive transcription factors, are promoted by laminar flow to maintain endothelial homeostasis. However, how the expression of KLF2/4 is regulated by shear stress is poorly understood. Here, we showed that the activation of PIEZO1 upregulates the expression of KLF2/4 in endothelial cells. Mice with endothelial-specific deletion of Piezo1 exhibit reduced KLF2/4 expression in thoracic aorta and pulmonary vascular endothelial cells. Mechanistically, shear stress activates PIEZO1, which results in a calcium influx and subsequently activation of CaMKII. CaMKII interacts with and activates MEKK3 to promote MEKK3/MEK5/ERK5 signaling and ultimately induce the transcription of KLF2/4. Our data provide the molecular insight into how endothelial cells sense and convert mechanical stimuli into a biological response to promote KLF2/4 expression for the maintenance of endothelial function and homeostasis.

MAPK/ERK-CBP-RFPL-3 Mediates Adipose-Derived Stem Cell-Induced Tumor Growth in Breast Cancer Cells by Activating Telomerase Reverse Transcriptase Expression.

Adipose-derived stem cells (ASCs) improve the self-renewal and survival of fat grafts in breast reconstruction after oncology surgery. However, ASCs have also been found to enhance breast cancer growth, and its role in tumor proliferation remains largely elusive. Here, we explored a novel mechanism that mediates hTERT reactivation during ASC-induced tumor growth in breast cancer cells. In this study, we found the proliferative ability of breast cancer cells markedly increased with ASC coculture. To explore the molecular mechanism, we treated cells with anibody/inhibitor and found that the activation of MEK-ERK pathway was triggered in breast cancer cells by SCF secreted from ASCs, leading to the nuclear recruitment of CBP. As a coactivator of hTERT, CBP subsequently coordinated with RFPL-3 upregulated hTERT transcription and telomerase activity. The inhibition of CBP and RFPL-3 abrogated the activation of hTERT transcription and the promotion of proliferation in breast cancer cells with cocultured ASCs in vitro and in vivo. Collectively, our study findings indicated that CBP coordination with RFPL-3 promotes ASC-induced breast cancer cell proliferation by anchoring to the hTERT promoter and upregulating telomerase activity, which is activated by the MAPK/ERK pathway.

Self-Supervised Autoregressive Domain Adaptation for Time Series Data.

Unsupervised domain adaptation (UDA) has successfully addressed the domain shift problem for visual applications. Yet, these approaches may have limited performance for time series data due to the following reasons. First, they mainly rely on the large-scale dataset (i.e., ImageNet) for source pretraining, which is not applicable for time series data. Second, they ignore the temporal dimension on the feature space of the source and target domains during the domain alignment step. Finally, most of the prior UDA methods can only align the global features without considering the fine-grained class distribution of the target domain. To address these limitations, we propose a SeLf-supervised AutoRegressive Domain Adaptation (SLARDA) framework. In particular, we first design a self-supervised (SL) learning module that uses forecasting as an auxiliary task to improve the transferability of source features. Second, we propose a novel autoregressive domain adaptation technique that incorporates temporal dependence of both source and target features during domain alignment. Finally, we develop an ensemble teacher model to align class-wise distribution in the target domain via a confident pseudo labeling approach. Extensive experiments have been conducted on three real-world time series applications with 30 cross-domain scenarios. The results demonstrate that our proposed SLARDA method significantly outperforms the state-of-the-art approaches for time series domain adaptation. Our source code is available at: https://github.com/mohamedr002/SLARDA.

Circ_0039960 regulates growth and Warburg effect of breast cancer cells via modulating miR-1178/PRMT7 axis.

BACKGROUND: Breast cancer (BC) is a serious threat to women's life and healthy. Increasing evidence indicated that blocking Warburg effect could attenuate the development of BC. Circular RNAs (circRNAs) has been found to be dysregulated in various carcinomas, including BC. Our study aims to illustrate the role and regulatory mechanism of circ_0039960 in BC development. METHODS: RT-qPCR and western blotting were utilized to evaluate the expression of circ_0039960 in tissues recruited from 32 cases of BC patients and also BC cell lines. Circ_0039960 shRNA was transfected into cells to explore its function on cell processes. CCK-8, flow cytometry and ELISA were used to measure cell viability, cell cycle and apoptosis. Warburg effect was detected by using commercial kits. Besides, bioinformatic prediction, RIP and luciferase reporter assays were performed to validate the interactions between circ_0039960, miR-1178 and PRMT7. RESULTS: The results showed that circ_0039960 and PRMT7 were both up-regulated, while miR-1178 was down-regulated, in BC tissues and cells. Silencing circ_0039960 effectively inhibited cell viability and Warburg effect of BC cells, also, induced cell cycle arrest and apoptosis. Moreover, we validated that circ_0039960 positively mediated PRMT7 expression via directly targeting to miR-1178. The inhibition of miR-1178 and overexpression of PRMT7 reversed the effect of circ_0039960 knockdown on BC cell growth and Warburg effect. CONCLUSION: In general, our research demonstrated that circ_0039960 regulates cell growth and Warburg effect in BC cells via miR-1178/PRMT7 axis. This may provide new evidence for the exploration of BC diagnostic and therapeutic targets.

An Attention-Based Deep Learning Approach for Sleep Stage Classification With Single-Channel EEG.

Automatic sleep stage mymargin classification is of great importance to measure sleep quality. In this paper, we propose a novel attention-based deep learning architecture called AttnSleep to classify sleep stages using single channel EEG signals. This architecture starts with the feature extraction module based on multi-resolution convolutional neural network (MRCNN) and adaptive feature recalibration (AFR). The MRCNN can extract low and high frequency features and the AFR is able to improve the quality of the extracted features by modeling the inter-dependencies between the features. The second module is the temporal context encoder (TCE) that leverages a multi-head attention mechanism to capture the temporal dependencies among the extracted features. Particularly, the multi-head attention deploys causal convolutions to model the temporal relations in the input features. We evaluate the performance of our proposed AttnSleep model using three public datasets. The results show that our AttnSleep outperforms state-of-the-art techniques in terms of different evaluation metrics. Our source codes, experimental data, and supplementary materials are available at https://github.com/emadeldeen24/AttnSleep.

Over-fitting suppression training strategies for deep learning-based atrial fibrillation detection.

Nowadays, deep learning-based models have been widely developed for atrial fibrillation (AF) detection in electrocardiogram (ECG) signals. However, owing to the inevitable over-fitting problem, classification accuracy of the developed models severely differed when applying on the independent test datasets. This situation is more significant for AF detection from dynamic ECGs. In this study, we explored two potential training strategies to address the over-fitting problem in AF detection. The first one is to use the Fast Fourier transform (FFT) and Hanning-window-based filter to suppress the influence from individual difference. Another is to train the model on the wearable ECG data to improve the robustness of model. Wearable ECG data from 29 patients with arrhythmia were collected for at least 24 h. To verify the effectiveness of the training strategies, a Long Short-Term Memory (LSTM) and Convolution Neural Network (CNN)-based model was proposed and tested. We tested the model on the independent wearable ECG data set, as well as the MIT-BIH Atrial Fibrillation database and PhysioNet/Computing in Cardiology Challenge 2017 database. The model achieved 96.23%, 95.44%, and 95.28% accuracy rates on the three databases, respectively. Pertaining to the comparison of the accuracy rates on each training set, the accuracy of the model trained in conjunction with the proposed training strategies only reduced by 2%, while the accuracy of the model trained without the training strategies decreased by approximately 15%. Therefore, the proposed training strategies serve as effective mechanisms for devising a robust AF detector and significantly enhanced the detection accuracy rates of the resulting deep networks.

Key Nodes Selection in Controlling Complex Networks via Convex Optimization.

Key nodes are the nodes connected with a given number of external source controllers that result in minimal control cost. Finding such a subset of nodes is a challenging task since it impossible to list and evaluate all possible solutions unless the network is small. In this paper, we approximately solve this problem by proposing three algorithms step by step. By relaxing the Boolean constraints in the original optimization model, a convex problem is obtained. Then inexact alternating direction method of multipliers (IADMMs) is proposed and convergence property is theoretically established. Based on the degree distribution, an extension method named degree-based IADMM (D-IADMM) is proposed such that key nodes are pinpointed. In addition, with the technique of local optimization employed on the results of D-IADMM, we also develop LD-IADMM and the performance is greatly improved. The effectiveness of the proposed algorithms is validated on different networks ranging from Erdos-Rényi networks and scale-free networks to some real-life networks.