The COVID-19 pandemic,which was declared by the WHO,had created a global health crisis and disrupted people’s daily lives.A large number of people were affected by the COVID-19 pandemic.Therefore,a diagnostic model n...The COVID-19 pandemic,which was declared by the WHO,had created a global health crisis and disrupted people’s daily lives.A large number of people were affected by the COVID-19 pandemic.Therefore,a diagnostic model needs to be generated which can effectively classify the COVID and non-COVID cases.In this work,our aim is to develop a diagnostic model based on deep features using effectiveness of Chest X-ray(CXR)in distinguishing COVID from non-COVID cases.The proposed diagnostic framework utilizes CXR to diagnose COVID-19 and includes Grad-CAM visualizations for a visual interpretation of predicted images.The model’s performance was evaluated using various metrics,including accuracy,precision,recall,F1-score,and Gmean.Several machine learning models,such as random forest,dense neural network,SVM,twin SVM,extreme learning machine,random vector functional link,and kernel ridge regression,were selected to diagnose COVID-19 cases.Transfer learning was used to extract deep features.For feature extraction many CNN-based models such as Inception V3,MobileNet,ResNet50,VGG16 and Xception models are used.It was evident from the experiments that ResNet50 architecture outperformed all other CNN architectures based on AUC.The TWSVM classifier achieved the highest AUC score of 0.98 based on the ResNet50 feature vector.展开更多
Robotic manipulators increasingly operate in complex three-dimensional workspaces where accuracy and strict limits on position,velocity,and acceleration must be satisfied.Conventional geometric planners emphasize path...Robotic manipulators increasingly operate in complex three-dimensional workspaces where accuracy and strict limits on position,velocity,and acceleration must be satisfied.Conventional geometric planners emphasize path smoothness but often ignore dynamic feasibility,motivating control-aware trajectory generation.This study presents a novel model predictive control(MPC)framework for three-dimensional trajectory planning of robotic manipulators that integrates second-order dynamic modeling and multi-objective parameter optimization.Unlike conventional interpolation techniques such as cubic splines,B-splines,and linear interpolation,which neglect physical constraints and system dynamics,the proposed method generates dynamically feasible trajectories by directly optimizing over acceleration inputs while minimizing both tracking error and control effort.A key innovation lies in the use of Pareto front analysis for tuning prediction horizon and sampling time,enabling a systematic balance between accuracy and motion smoothness.Comparative evaluation using simulated experiments demonstrates that the proposed MPC approach achieves a minimum mean absolute error(MAE)of 0.170 and reduces maximum acceleration to 0.0217,compared to 0.0385 in classical linear methods.The maximum deviation error was also reduced by approximately 27.4%relative to MPC configurations without tuned parameters.All experiments were conducted in a simulation environment,with computational times per control cycle consistently remaining below 20 milliseconds,indicating practical feasibility for real-time applications.Thiswork advances the state-of-the-art inMPC-based trajectory planning by offering a scalable and interpretable control architecture that meets physical constraints while optimizing motion efficiency,thus making it suitable for deployment in safety-critical robotic applications.展开更多
Background:Skin cancer is a major cause of mortality,and early detection is vital for effective treatment.Diagnosis is challenging because of lesion variability.This study adapts VINCE-NET,a hybrid deep-learning model...Background:Skin cancer is a major cause of mortality,and early detection is vital for effective treatment.Diagnosis is challenging because of lesion variability.This study adapts VINCE-NET,a hybrid deep-learning model originally designed for stroke detection,to classify melanoma using dermoscopic images.Methods:VINCE-NET combines vision transformer layers for global context,convolutional neural networks for local features,and long short-term memory for spatial sequence modeling.During preprocessing,Gaussian blur,normalization,and augmentation were applied to reduce noise and handle class imbalance.During training,the public HAM10000 dataset was used in a central processing unit-only Google Colab environment(12.72 GB random access memory,107.7 GB disk)with an AdamW optimizer,a batch size of 12,learning-rate scheduling,and early stopping(patience=50).VINCE-NET's performance was compared with those of a convolutional neural networks,long short-term memory,residual network with 50 layers(ResNet-50),visual geometry group network with 16 and 19 layers(VGG-16/19),and densely connected convolutional network with 121 and 201 layers(DenseNet-121/201)under identical preprocessing conditions.Results:VINCE-NET achieved 94.1%accuracy,95.5% precision,90.4% recall,a 92.9% F1-score,and an area under the receiver operating characteristic curve of 0.98 at a training time of 34,308.42 s.Benchmarks showed that VINCE-NET outperformed baselines while being computationally efficient.Conclusion:VINCE-NET provides competitive performance for melanoma classification and feasibility in resource-limited settings.Although promising,VINCE-NET has not been clinically validated yet.Future work will address resolution,ablation studies,interpretability,and external validation.展开更多
文摘The COVID-19 pandemic,which was declared by the WHO,had created a global health crisis and disrupted people’s daily lives.A large number of people were affected by the COVID-19 pandemic.Therefore,a diagnostic model needs to be generated which can effectively classify the COVID and non-COVID cases.In this work,our aim is to develop a diagnostic model based on deep features using effectiveness of Chest X-ray(CXR)in distinguishing COVID from non-COVID cases.The proposed diagnostic framework utilizes CXR to diagnose COVID-19 and includes Grad-CAM visualizations for a visual interpretation of predicted images.The model’s performance was evaluated using various metrics,including accuracy,precision,recall,F1-score,and Gmean.Several machine learning models,such as random forest,dense neural network,SVM,twin SVM,extreme learning machine,random vector functional link,and kernel ridge regression,were selected to diagnose COVID-19 cases.Transfer learning was used to extract deep features.For feature extraction many CNN-based models such as Inception V3,MobileNet,ResNet50,VGG16 and Xception models are used.It was evident from the experiments that ResNet50 architecture outperformed all other CNN architectures based on AUC.The TWSVM classifier achieved the highest AUC score of 0.98 based on the ResNet50 feature vector.
基金funded by the research project“BR24992947—Development of Robots,Scientific,Technical,and Software for Flexible Robotization and Industrial Automation(RPA)in Automotive Industrial Enterprises in Kazakhstan Using Artificial Intelligence”.
文摘Robotic manipulators increasingly operate in complex three-dimensional workspaces where accuracy and strict limits on position,velocity,and acceleration must be satisfied.Conventional geometric planners emphasize path smoothness but often ignore dynamic feasibility,motivating control-aware trajectory generation.This study presents a novel model predictive control(MPC)framework for three-dimensional trajectory planning of robotic manipulators that integrates second-order dynamic modeling and multi-objective parameter optimization.Unlike conventional interpolation techniques such as cubic splines,B-splines,and linear interpolation,which neglect physical constraints and system dynamics,the proposed method generates dynamically feasible trajectories by directly optimizing over acceleration inputs while minimizing both tracking error and control effort.A key innovation lies in the use of Pareto front analysis for tuning prediction horizon and sampling time,enabling a systematic balance between accuracy and motion smoothness.Comparative evaluation using simulated experiments demonstrates that the proposed MPC approach achieves a minimum mean absolute error(MAE)of 0.170 and reduces maximum acceleration to 0.0217,compared to 0.0385 in classical linear methods.The maximum deviation error was also reduced by approximately 27.4%relative to MPC configurations without tuned parameters.All experiments were conducted in a simulation environment,with computational times per control cycle consistently remaining below 20 milliseconds,indicating practical feasibility for real-time applications.Thiswork advances the state-of-the-art inMPC-based trajectory planning by offering a scalable and interpretable control architecture that meets physical constraints while optimizing motion efficiency,thus making it suitable for deployment in safety-critical robotic applications.
文摘Background:Skin cancer is a major cause of mortality,and early detection is vital for effective treatment.Diagnosis is challenging because of lesion variability.This study adapts VINCE-NET,a hybrid deep-learning model originally designed for stroke detection,to classify melanoma using dermoscopic images.Methods:VINCE-NET combines vision transformer layers for global context,convolutional neural networks for local features,and long short-term memory for spatial sequence modeling.During preprocessing,Gaussian blur,normalization,and augmentation were applied to reduce noise and handle class imbalance.During training,the public HAM10000 dataset was used in a central processing unit-only Google Colab environment(12.72 GB random access memory,107.7 GB disk)with an AdamW optimizer,a batch size of 12,learning-rate scheduling,and early stopping(patience=50).VINCE-NET's performance was compared with those of a convolutional neural networks,long short-term memory,residual network with 50 layers(ResNet-50),visual geometry group network with 16 and 19 layers(VGG-16/19),and densely connected convolutional network with 121 and 201 layers(DenseNet-121/201)under identical preprocessing conditions.Results:VINCE-NET achieved 94.1%accuracy,95.5% precision,90.4% recall,a 92.9% F1-score,and an area under the receiver operating characteristic curve of 0.98 at a training time of 34,308.42 s.Benchmarks showed that VINCE-NET outperformed baselines while being computationally efficient.Conclusion:VINCE-NET provides competitive performance for melanoma classification and feasibility in resource-limited settings.Although promising,VINCE-NET has not been clinically validated yet.Future work will address resolution,ablation studies,interpretability,and external validation.
