The ubiquity of mobile devices has driven advancements in mobile object detection.However,challenges in multi-scale object detection in open,complex environments persist due to limited computational resources.Traditio...The ubiquity of mobile devices has driven advancements in mobile object detection.However,challenges in multi-scale object detection in open,complex environments persist due to limited computational resources.Traditional approaches like network compression,quantization,and lightweight design often sacrifice accuracy or feature representation robustness.This article introduces the Fast Multi-scale Channel Shuffling Network(FMCSNet),a novel lightweight detection model optimized for mobile devices.FMCSNet integrates a fully convolutional Multilayer Perceptron(MLP)module,offering global perception without significantly increasing parameters,effectively bridging the gap between CNNs and Vision Transformers.FMCSNet achieves a delicate balance between computation and accuracy mainly by two key modules:the ShiftMLP module,including a shift operation and an MLP module,and a Partial group Convolutional(PGConv)module,reducing computation while enhancing information exchange between channels.With a computational complexity of 1.4G FLOPs and 1.3M parameters,FMCSNet outperforms CNN-based and DWConv-based ShuffleNetv2 by 1%and 4.5%mAP on the Pascal VOC 2007 dataset,respectively.Additionally,FMCSNet achieves a mAP of 30.0(0.5:0.95 IoU threshold)with only 2.5G FLOPs and 2.0M parameters.It achieves 32 FPS on low-performance i5-series CPUs,meeting real-time detection requirements.The versatility of the PGConv module’s adaptability across scenarios further highlights FMCSNet as a promising solution for real-time mobile object detection.展开更多
The integration of cloud computing into traditional industrial control systems is accelerating the evolution of Industrial Cyber-Physical System(ICPS),enhancing intelligence and autonomy.However,this transition also e...The integration of cloud computing into traditional industrial control systems is accelerating the evolution of Industrial Cyber-Physical System(ICPS),enhancing intelligence and autonomy.However,this transition also expands the attack surface,introducing critical security vulnerabilities.To address these challenges,this article proposes a hybrid intrusion detection scheme for securing ICPSs that combines system state anomaly and network traffic anomaly detection.Specifically,an improved variation-Bayesian-based noise covariance-adaptive nonlinear Kalman filtering(IVB-NCA-NLKF)method is developed to model nonlinear system dynamics,enabling optimal state estimation in multi-sensor ICPS environments.Intrusions within the physical sensing system are identified by analyzing residual discrepancies between predicted and observed system states.Simultaneously,an adaptive network traffic anomaly detection mechanism is introduced,leveraging learned traffic patterns to detect node-and network-level anomalies through pattern matching.Extensive experiments on a simulated network control system demonstrate that the proposed framework achieves higher detection accuracy(92.14%)with a reduced false alarm rate(0.81%).Moreover,it not only detects known attacks and vulnerabilities but also uncovers stealthy attacks that induce system state deviations,providing a robust and comprehensive security solution for the safety protection of ICPS.展开更多
Objective:To explore the situation of patients and the compare the effect between two methods,which are preserving spontaneous breathing without intubation and endotracheal intubation with one lung ventilation in the ...Objective:To explore the situation of patients and the compare the effect between two methods,which are preserving spontaneous breathing without intubation and endotracheal intubation with one lung ventilation in the single-hole thoracoscopic bulla suture.Method:42 patients who received single-hole thoracoscopic pulmonary bullae suture in our hospital from January 2020 to December 2021 were selected as the study subjects,including 19 patients who underwent endotracheal intubation and one lung ventilation as the control group and 23 patients who underwent single-hole thoracoscopic pulmonary bullae suture without intubation as the study group.The relevant indexes,postoperative general conditions,complications and pneumothorax recurrence of the two groups were analyzed and observed.Results:In the control group,the scores of anesthesia time(points),resuscitation time(points),surgical visual field score(points),surgical time(points),and surgical bleeding volume(points)were 20.8±4.6,19.9±7.9,1.7±0.5,44.9±7.9,and 11.4±2.4 respectively.In the study group,the scores of anesthesia time(points),resuscitation time(points),surgical visual field score(points),surgical time(points),and scores of surgical bleeding(points)were 17.9±4.3,15.4±3.4,1.9±0.4,48.4±7.1,10.9±2.2,respectively.There was no statistical difference in surgical visual field score,surgical time and surgical bleeding whereas there was a statistical difference between anesthesia time and resuscitation time.In the control group after operation,VAS score at 6 hours after operation,SaO_(2)(%)after operation,PaCO_(2)(mmHg)after operation,drainage volume(ML)after operation,feeding time(H)after operation,retention time of thoracic tube after operation(H),WBC(109)on the first day after operation,hospitalization time(d),and total hospitalization cost(RMB 1000)were 2.1±0.7,98.2±1.4,42.4±4.9,139.1±23.1,6.9±1.6,37.1±5.4,7.9±2.1,6.6±1.3,and 2.6±0.3 respectively.As for the study group,the VAS score at 6 hours after operation,SaO_(2)(%)after operation,PaCO_(2)(mmHg)after operation,drainage volume(ML)after operation,feeding time(H)after operation,retention time of thoracic tube after operation(H),WBC(109)on the first day after operation,hospitalization time(d),and total hospitalization cost(RMB 1000)were 1.9±0.4,97.9±1.2,42.8±5.1,151.8±21.9,4.3±1.4,15.3±2.6,5.2±2.3,4.2±1.2,and 1.8±0.4 respectively.Among them,there were no significant differences in visual analog scale(VAS)score at 6 hours after operation,SaO_(2) after operation and PaCO_(2) after operation between the two groups,but there were significant differences in other factors.The complication rate of the control group was 36.84%,which was significantly higher than that of the study group(4.35%),with statistical difference.The recurrence rate of the control group was 21.05%,which was not significantly different from that of the study group(4.35%).Conclusion:The single-hole thoracoscopic bullae suture without intubation can reduce the anesthesia time and resuscitation time of patients,reduce the hospitalization cost of patients,reduce the treatment burden,shorten the first feeding time,and reduce the complication rate of patients.Therefore,it is worthy of clinical promotion.展开更多
基金funded by the National Natural Science Foundation of China under Grant No.62371187the Open Program of Hunan Intelligent Rehabilitation Robot and Auxiliary Equipment Engineering Technology Research Center under Grant No.2024JS101.
文摘The ubiquity of mobile devices has driven advancements in mobile object detection.However,challenges in multi-scale object detection in open,complex environments persist due to limited computational resources.Traditional approaches like network compression,quantization,and lightweight design often sacrifice accuracy or feature representation robustness.This article introduces the Fast Multi-scale Channel Shuffling Network(FMCSNet),a novel lightweight detection model optimized for mobile devices.FMCSNet integrates a fully convolutional Multilayer Perceptron(MLP)module,offering global perception without significantly increasing parameters,effectively bridging the gap between CNNs and Vision Transformers.FMCSNet achieves a delicate balance between computation and accuracy mainly by two key modules:the ShiftMLP module,including a shift operation and an MLP module,and a Partial group Convolutional(PGConv)module,reducing computation while enhancing information exchange between channels.With a computational complexity of 1.4G FLOPs and 1.3M parameters,FMCSNet outperforms CNN-based and DWConv-based ShuffleNetv2 by 1%and 4.5%mAP on the Pascal VOC 2007 dataset,respectively.Additionally,FMCSNet achieves a mAP of 30.0(0.5:0.95 IoU threshold)with only 2.5G FLOPs and 2.0M parameters.It achieves 32 FPS on low-performance i5-series CPUs,meeting real-time detection requirements.The versatility of the PGConv module’s adaptability across scenarios further highlights FMCSNet as a promising solution for real-time mobile object detection.
基金supported by the National Natural Science Foundation of China(NSFC)under grant No.62371187the Hunan Provincial Natural Science Foundation of China under Grant Nos.2024JJ8309 and 2023JJ50495.
文摘The integration of cloud computing into traditional industrial control systems is accelerating the evolution of Industrial Cyber-Physical System(ICPS),enhancing intelligence and autonomy.However,this transition also expands the attack surface,introducing critical security vulnerabilities.To address these challenges,this article proposes a hybrid intrusion detection scheme for securing ICPSs that combines system state anomaly and network traffic anomaly detection.Specifically,an improved variation-Bayesian-based noise covariance-adaptive nonlinear Kalman filtering(IVB-NCA-NLKF)method is developed to model nonlinear system dynamics,enabling optimal state estimation in multi-sensor ICPS environments.Intrusions within the physical sensing system are identified by analyzing residual discrepancies between predicted and observed system states.Simultaneously,an adaptive network traffic anomaly detection mechanism is introduced,leveraging learned traffic patterns to detect node-and network-level anomalies through pattern matching.Extensive experiments on a simulated network control system demonstrate that the proposed framework achieves higher detection accuracy(92.14%)with a reduced false alarm rate(0.81%).Moreover,it not only detects known attacks and vulnerabilities but also uncovers stealthy attacks that induce system state deviations,providing a robust and comprehensive security solution for the safety protection of ICPS.
文摘Objective:To explore the situation of patients and the compare the effect between two methods,which are preserving spontaneous breathing without intubation and endotracheal intubation with one lung ventilation in the single-hole thoracoscopic bulla suture.Method:42 patients who received single-hole thoracoscopic pulmonary bullae suture in our hospital from January 2020 to December 2021 were selected as the study subjects,including 19 patients who underwent endotracheal intubation and one lung ventilation as the control group and 23 patients who underwent single-hole thoracoscopic pulmonary bullae suture without intubation as the study group.The relevant indexes,postoperative general conditions,complications and pneumothorax recurrence of the two groups were analyzed and observed.Results:In the control group,the scores of anesthesia time(points),resuscitation time(points),surgical visual field score(points),surgical time(points),and surgical bleeding volume(points)were 20.8±4.6,19.9±7.9,1.7±0.5,44.9±7.9,and 11.4±2.4 respectively.In the study group,the scores of anesthesia time(points),resuscitation time(points),surgical visual field score(points),surgical time(points),and scores of surgical bleeding(points)were 17.9±4.3,15.4±3.4,1.9±0.4,48.4±7.1,10.9±2.2,respectively.There was no statistical difference in surgical visual field score,surgical time and surgical bleeding whereas there was a statistical difference between anesthesia time and resuscitation time.In the control group after operation,VAS score at 6 hours after operation,SaO_(2)(%)after operation,PaCO_(2)(mmHg)after operation,drainage volume(ML)after operation,feeding time(H)after operation,retention time of thoracic tube after operation(H),WBC(109)on the first day after operation,hospitalization time(d),and total hospitalization cost(RMB 1000)were 2.1±0.7,98.2±1.4,42.4±4.9,139.1±23.1,6.9±1.6,37.1±5.4,7.9±2.1,6.6±1.3,and 2.6±0.3 respectively.As for the study group,the VAS score at 6 hours after operation,SaO_(2)(%)after operation,PaCO_(2)(mmHg)after operation,drainage volume(ML)after operation,feeding time(H)after operation,retention time of thoracic tube after operation(H),WBC(109)on the first day after operation,hospitalization time(d),and total hospitalization cost(RMB 1000)were 1.9±0.4,97.9±1.2,42.8±5.1,151.8±21.9,4.3±1.4,15.3±2.6,5.2±2.3,4.2±1.2,and 1.8±0.4 respectively.Among them,there were no significant differences in visual analog scale(VAS)score at 6 hours after operation,SaO_(2) after operation and PaCO_(2) after operation between the two groups,but there were significant differences in other factors.The complication rate of the control group was 36.84%,which was significantly higher than that of the study group(4.35%),with statistical difference.The recurrence rate of the control group was 21.05%,which was not significantly different from that of the study group(4.35%).Conclusion:The single-hole thoracoscopic bullae suture without intubation can reduce the anesthesia time and resuscitation time of patients,reduce the hospitalization cost of patients,reduce the treatment burden,shorten the first feeding time,and reduce the complication rate of patients.Therefore,it is worthy of clinical promotion.
