ECG signals in digital format are being used for gathering various vital information and for predicting diseases in patients using advanced artificial intelligence and digital signalprocessing technologies. It is imp...
详细信息
This paper proposes a gait recognition method based on the modified OVR-CSP fusion feature of plantar pressure and Long Short-Term Memory classification (referred to as the OVR-CSP-LSTM model). 10 subjects conducted 4...
详细信息
ISBN:
(数字)9798350361445
ISBN:
(纸本)9798350361452
This paper proposes a gait recognition method based on the modified OVR-CSP fusion feature of plantar pressure and Long Short-Term Memory classification (referred to as the OVR-CSP-LSTM model). 10 subjects conducted 4 type of gait experiments including normal speed walking, fast walking, slow walking, imitating stroke gait walking in this paper. Transfer the commonly used Common Spatial Pattern (CSP) feature extraction method for EEG to plantar pressure signals, and splice the OVR-CSP features of 2-class, 3-class and 4-class, adopting Long Short Term Memory Network (LSTM) for classification. In this paper, the Intra-patient mode and Inter-patient mode of 10 people are modeled and compared respectively, and the recognition effects under different sensor number and different position sensors' combination are also studied. The experimental results show that the proposed model has good performance for both modes. The method proposed in this article is expected to be applied to multi-sensor signalprocessing and classification with spatial characteristics.
This study explores customized medicine using the customized Treatment Optimization Framework (PTOF). advanced analytics and big data transform customized healthcare. The Genetic Variant Prioritization Algorithm (GVPA...
详细信息
ISBN:
(数字)9798350368949
ISBN:
(纸本)9798350368956
This study explores customized medicine using the customized Treatment Optimization Framework (PTOF). advanced analytics and big data transform customized healthcare. The Genetic Variant Prioritization Algorithm (GVPA), Dynamic Treatment Response Prediction Model (DTRP), and Optimal Treatment Adjustment Algorithm (OTAA) make personalized medicine more dynamic and adaptable. PTOF is compared against GenoOpti, PharmaSys, BioDecide, RxPro, MedAlign, and OmniCare in our study. The results reveal that PTOF excels at data combination, prediction, and ethics. PTOF's capacity to adjust treatment regimens based on real-time projections raises the bar for specialist medicine and enhances patient care.
As our world continues to embrace digital technology, cyber threats have become increasingly prevalent, especially botnet attacks. Ensuring cybersecurity is a significant concern, and to address this, we need Intrusio...
详细信息
ISBN:
(数字)9798331511890
ISBN:
(纸本)9798331511906
As our world continues to embrace digital technology, cyber threats have become increasingly prevalent, especially botnet attacks. Ensuring cybersecurity is a significant concern, and to address this, we need Intrusion Detection Systems (IDS) that can automatically adapt to new threats using advanced machine learning (ML) and deep learning (DL) techniques. Our project aims to develop an advanced anomaly detection and recognition system for IoT botnet attacks using hyper-dimensional models namely Random Forest, Decision Tree, Gradient Boosting, Multi-layer Perceptron (MLP), and K-Nearest Neighbor (KNN) and makes uses of hyperparameter tuning for performance optimization. By integrating an ensemble voting classifier that combines these five algorithms using a soft-voting mechanism, our results indicate an improved detection accuracy and adaptability. The proposed ensemble-based model is tested on a publicly available dataset which offers comprehensive coverage of botnet attack patterns and outperforms all individual classifiers, achieving an accuracy of 99.88% and an ROC AUC score of 0.999. The proposed approach highlights the advantages of combining hyper-dimensional classification models in effectively detecting IoT botnet attacks.
The need to accurately identify dog breeds is important due to their popularity and role as companions. With an increase in the variety of dog breeds worldwide, there is a pressing demand for better classification met...
详细信息
ISBN:
(数字)9798350353068
ISBN:
(纸本)9798350353075
The need to accurately identify dog breeds is important due to their popularity and role as companions. With an increase in the variety of dog breeds worldwide, there is a pressing demand for better classification methods. Advances in artificial intelligence have resulted in the creation of a new model that combines YOLOv7 with the Whale Optimization Algorithm (WOA) in a Convolutional Neural Network (CNN) setup, designed specifically for detecting dog breeds. This model uses the extensive Stanford Dogs dataset, which includes 120 unique breeds, and has been thoroughly tested. It has shown to be more accurate and precise than current methods. The effectiveness of this model in identifying dog breeds marks a significant improvement in the field and suggests its usefulness in various areas such as veterinary services, dog behavior studies, and improved pet management systems. Additionally, this method showcases the benefits of merging advanced machine learning techniques with nature-inspired algorithms to address complex identification challenges, making a significant contribution to the development of AI-based solutions in animal identification and related areas.
This paper proposes an automobile export prediction algorithm based on big data analysis, combined with advanced machine learning technology, to achieve accurate analysis and prediction of global automobile export dat...
详细信息
ISBN:
(数字)9798331528676
ISBN:
(纸本)9798331528683
This paper proposes an automobile export prediction algorithm based on big data analysis, combined with advanced machine learning technology, to achieve accurate analysis and prediction of global automobile export data. The core of the algorithm is to use a hierarchical clustering algorithm to classify and process automobile export data from different regions and markets, thereby improving the efficiency and accuracy of data processing. Through feature extraction and data preprocessing steps, the algorithm constructs a prediction model that can flexibly adapt to different market needs and can be optimized for different market conditions. The model is not only simulated and verified on multiple real-world automobile export data sets, but also combined with statistical methods to conduct a comprehensive and accurate analysis of the simulation results. The simulation data shows that the prediction algorithm proposed in this paper not only shows extremely high computational efficiency when processing large-scale data sets and complex market environments, but also significantly outperforms existing traditional algorithms in terms of prediction accuracy. Especially in the face of volatile demand in different economies, the algorithm demonstrates its strong adaptability and prediction capabilities.
The proposed work is an advanced machine learning techniques that aids in detecting epileptic zones using a combination of electroencephalography (EEG) and magnetic resonance imaging (MRI), emphasizing the integration...
详细信息
ISBN:
(数字)9798331537555
ISBN:
(纸本)9798331537562
The proposed work is an advanced machine learning techniques that aids in detecting epileptic zones using a combination of electroencephalography (EEG) and magnetic resonance imaging (MRI), emphasizing the integration of signalprocessingalgorithms for improved accuracy. Various methodologies, including Independent Component Analysis (ICA), Multiple signal Classification (MUSIC), and Adaptive Spatial Filters (beam formers), are evaluated to benchmark and enhance the detection of seizure onset zones within the brain. The research underscores the importance of robust data acquisition and preprocessing techniques to ensure high-quality signalprocessing, thereby improving the reliability of zonal detection. The proposed algorithm, demonstrates that EEG and MRI integration allow for better spatial and temporal localization of epileptic activities. The results indicate that techniques such as high-density EEG and adaptive spatial filtering provide detailed insights into brain function during seizure events, while ICA effectively isolates significant signal components, reducing artifacts and improving detection sensitivity to 95%.
Efficient management of growing urban parking demand would require smart parking systems. A dynamic approach will be presented: using IoT-enabled algorithms, predictive analytics, and processing real-time data to opti...
详细信息
ISBN:
(数字)9798331511890
ISBN:
(纸本)9798331511906
Efficient management of growing urban parking demand would require smart parking systems. A dynamic approach will be presented: using IoT-enabled algorithms, predictive analytics, and processing real-time data to optimize space utilization in the parking lot and provide convenience for users while allowing for the maximum possible operational revenue. The system achieves this by utilizing IoT sensors such as ultrasonic, infrared, and magnetic field sensors to accurately detect the occupancy of parking spaces. algorithms for sensor data aggregation preprocess and fuse the information so that it can be relied upon and, as a result, allows for real-time monitoring. Dynamic reservation and pricing algorithms are built into the system that balances parking fees according to real-time demand, applying techniques like surge pricing, time-based adjustments, and predictive forecasting to balance occupancy and maximize revenue. Predictive analytics further supports demand forecasting by using historical data, user behavior, and environmental factors, allowing for advanced resource allocation and proactive price adjustment during peak hours. Further enhancements are added to the system in the form of edge and corner detection techniques for better vehicle identification and reservation management. The dynamic capabilities of the proposed system enhance the efficiency of operation, improve the user experience by allowing real-time spot allocation and reservations, and reduce parking congestion.
The windowed fast Fourier transform (FFT) is the ubiquitous tool for spectral analysis because it is fast and easy to use. In this paper we will show how the polyphase channelizer can replace the FFT for spectral anal...
详细信息
ISBN:
(纸本)9781665459068
The windowed fast Fourier transform (FFT) is the ubiquitous tool for spectral analysis because it is fast and easy to use. In this paper we will show how the polyphase channelizer can replace the FFT for spectral analysis and produce estimates of the power spectral density (PSD) and the shorttime Fourier transform (STFT) spectrogram. We refer to the polyphase channelizer equivalents of these estimates respectively as the channelizer power spectral density (cPSD) and the channo-gram. It will be shown that the spectral resolution of the cPSD and channogram improves upon the well-established FFT-based estimators for a given FFT length while introducing minimal processing overhead. We will then discuss Parseval's theorem equivalent for the polyphase channelizer. Finally, we will show how the polyphase channelizer leads to straightforward signal segregation and inversion back to time domain when signals of random and unknown center frequencies and bandwidth are encountered. This is an important enabler for real-time radio frequency (RF) signal classification using machine learning algorithms.
Automotive frequency-modulated continuous wave (FMCW) radars, essential in advanced Driver Assistance Systems, encounter mutual interference issues that degrade their detection capabilities. Model-based algorithms, th...
详细信息
ISBN:
(数字)9798350368741
ISBN:
(纸本)9798350368758
Automotive frequency-modulated continuous wave (FMCW) radars, essential in advanced Driver Assistance Systems, encounter mutual interference issues that degrade their detection capabilities. Model-based algorithms, though widely used, rely heavily on predetermined assumptions about the statistical properties. General-purpose black-box deep learning approaches, while effective in their training distribution, often lack flexibility and generalizability in dynamic environments. We introduce a novel hybrid method that combines model-based techniques with deep learning, treating interference mitigation as a source separation problem. Specifically, our method employs score-based deep generative networks to accurately capture the structure of FMCW interference. Additionally, we employ deep unfolding to accelerate inference, critical for automotive radar applications. Empirical results from simulated data demonstrate that the proposed algorithm outperforms the baseline models by 3.26 dB in signal-to-interference-plus-noise ratio in the presence of aggressive interference, and also shows good generalizability with measured data.
暂无评论