Dynamic Threshold Algorithm Research Articles

Abnormal lower limb posture recognition based on spatial gait feature dynamic threshold detection

Lower limb rehabilitation training often involves the use of assistive standing devices. However, elderly individuals frequently experience reduced exercise effectiveness or suffer muscle injuries when utilizing these devices. The ability to recognize abnormal lower limb postures can significantly enhance training efficiency and minimize the risk of injury. To address this, we propose a model based on dynamic threshold detection of spatial gait features to identify such abnormal postures. A human-assisted standing rehabilitation device platform was developed to build a lower limb gait depth dataset. RGB data is employed for keypoint detection, enabling the establishment of a 3D lower limb posture recognition model that extracts gait, time, spatial features, and keypoints. The predicted joint angles, stride length, and step frequency demonstrate errors of 4 %, 8 %, and 1.3 %, respectively, with an average confidence of 0.95 for 3D key points. We employed the WOA-BP neural network to develop a dynamic threshold algorithm based on gait features and propose a model for recognizing abnormal postures. Compared to other models, our model achieves a 96 % accuracy rate in recognizing abnormal postures, with a recall rate of 83 % and an F1 score of 90 %. ROC curve analysis and AUC values reveal that the WOA-BP algorithm performs farthest from the pure chance line, with the highest AUC value of 0.89, indicating its superior performance over other models. Experimental results demonstrate that this model possesses a strong capability in recognizing abnormal lower limb postures, encouraging patients to correct these postures, thereby reducing muscle injuries and improving exercise effectiveness.

Exploring the Diversified Development of Vocal Music Teaching Methods in Colleges and Universities Combined with Multi-Priority Dynamic Threshold Algorithm

Abstract Enhancing the integration of modern information technology with educational practices, particularly in the vocal classroom, is crucial for improving academic quality. This paper presents an optimization method aimed at addressing the limitations of the existing multi-priority dynamic threshold algorithm. The specific performance is as follows: first, on the original basis of the PDT-RED algorithm, the expected cache utilization is set to ensure the utilization of the buffer. The optimized OPDT-RED algorithm should be used to ensure that the data frame is received with a high probability. Then, according to the channel environment, the dynamic fullness threshold was adjusted, which improved the performance of the highest priority queue with a high transmission success rate. Lastly, the measurements of vocal characteristic parameters like pitch, rhythm, beat, melody, and others. The goal was to create a complete evaluation network model for vocal teaching, which was applied to actual cases. The model’s performance and its effectiveness were evaluated. After testing, the subjects’ vocal rhythmic tempo was below 60, while the range of the sample repertoire was between 60 and 90, presenting two different forms of expression. The model proposed in this paper has the optimal effect on the enhancement of expressive movements while singing; 15.33% of the students improved by two notches, and the vocal teaching model designed in this paper has a very good effect on vocal enhancement.

Analysis of the change path of news dissemination under the trend of short-video convergence - Based on multi-priority dynamic thresholding algorithm

Abstract This paper proposes a multi-priority dynamic threshold algorithm for short video news transmission. The average queue threshold is dynamically adjusted according to the packet priority and unused cache space, and the data frames of short video news nodes are processed into multiple pulse data segments after the encoding process. The success rate and confidentiality of data transmission are improved by scrambling each segment of pulse data. Finally, after updating the thresholds at all levels, the overall thresholds of short video news are kept full to meet the performance requirements of the highest priority queue of short video news. The results show that 95.03% of the short video news with a high dissemination degree has a file size of less than 5 MB, and its video length is most popular among users in the range of 8~15 seconds. Compared to the traditional news dissemination mode, short video news is not limited by time and space, which greatly improves the efficiency of information dissemination.

Dynamic self-correcting key performance indicator anomaly detection algorithm

ABSTRACT The operation and maintenance of the background system is always an important link to ensure the system’s high availability. With the increasing number of background systems, their operation, and maintenance have to develop from the initial huge-crowd strategy to the direction of intelligence. The key to intelligent operation and maintenance is the abnormal detection of key performance indicators (KPI), such as CPU utilisation. However, the existing KPI anomaly detection algorithms not only cannot select the dynamic threshold under the non-parametric methods but also have no false-positive correction mechanism to correct the false alarms. In order to overcome the above shortcomings, this work proposes a dynamic self-correcting Key Performance Indicator (KPI) anomaly detection algorithm, hereafter referred to as DSCAD. To the best of our knowledge, in the field of KPI anomaly detection, the DSCAD algorithm is the first dynamic threshold algorithm that does not rely on the assumption of normal distribution. Compared with the existing KPI anomaly detection methods, the F-score of the DSCAD algorithm increased by 3% and had the best performance.

Evaluation of the accuracy of cone-beam computed tomography image segmentation of isolated tooth roots based on the dynamic threshold method

ObjectiveAccurate quantification of the root surface area (RSA) plays a decisive role in the advancement of periodontal, orthodontic, and restorative treatment modalities. In this study, we aimed to develop a dynamic threshold-based computer-aided system for segmentation and calculation of the RSA of isolated teeth on cone-beam computed tomography (CBCT) and to assess the accuracy of the measured data.MethodWe selected 24 teeth to be extracted, including single-rooted and multi-rooted teeth, from 22 patients who required tooth extraction. In the experimental group, we scanned 24 isolated teeth using CBCT with a voxel size of 0.3 mm. We designed a computer-aided system based on a personalized dynamic threshold algorithm to automatically segment the roots of 24 isolated teeth in CBCT images and calculate the RSA. In the control group, we employed digital intraoral scanner devices to perform optical scanning on 24 isolated teeth and subsequently manually segmented the roots using 3-matic software to calculate the RSA. We used the paired t-test (P < 0.05) and Bland-Altman plots to analyze the consistency of the two measurement methods.ResultsThe results of the paired t-test showed that there was no significant difference in the RSAs obtained using the dynamic threshold method and the optical scanning image reconstruction (t = 1.005, P = 0.325 > 0.05). As per the Bland-Altman plot, the results were evenly distributed within the region of ± 1.96 standard deviations of the mean, with no increasing or decreasing trends and good consistency.ConclusionIn this study, we designed a computer-aided root segmentation system based on a personalized dynamic threshold algorithm to automatically segment the roots of isolated teeth in CBCT images with a voxel size of 0.3 mm. We found that the RSA calculated using this approach was highly accurate, and a voxel of 0.3 mm in size could accurately display the surface area data in CBCT images. Overall, our findings in this study provide a foundation for future work on accurate automatic segmentation of tooth roots in full-mouth CBCT images and the computation of RSA.

Physics-informed interpretable wavelet weight initialization and balanced dynamic adaptive threshold for intelligent fault diagnosis of rolling bearings

Intelligent fault diagnosis of rolling bearings using deep learning-based methods has made unprecedented progress. However, there is still little research on weight initialization and the threshold setting for noise reduction. An innovative deep triple-stream network called EWSNet is proposed, which presents a wavelet weight initialization method and a balanced dynamic adaptive threshold algorithm. Initially, an enhanced wavelet basis function is designed, in which a scale smoothing factor is defined to acquire more rational wavelet scales. Next, a plug-and-play wavelet weight initialization for deep neural networks is proposed, which utilizes physics-informed wavelet prior knowledge and showcases stronger applicability. Furthermore, a balanced dynamic adaptive threshold is established to enhance the noise-resistant robustness of the model. Finally, normalization activation mapping is devised to reveal the effectiveness of Z-score from a visual perspective rather than experimental results. The validity and reliability of EWSNet are demonstrated through four data sets under the conditions of constant and fluctuating speeds. Source code is available at:https://github.com/liguge/EWSNet.

Online fault detection for temperature sensors based on orthogonal-complement-structure observer and dynamic threshold algorithm

In this paper, a novel fault detection observer structure for aero-engine temperature sensor faults is proposed. The observer structure overcomes the difficulty that the measured input cannot be obtained and has the advantages of the reduced-order observers. The performance index in the finite frequency domain is used to solve a set of observer gain matrices offline, which greatly reduces the computational burden of online applications, ensures the availability of the algorithm on board, and makes the observer robust to noises and sensitive to faults. A dynamic threshold (DT) method based on the isolated forest (IF) algorithm and a box-plot sliding window mechanism is proposed to realise early fault detection, which updates the threshold depending on the current state and reduces false and missed alarm rates. Finally, two traditional fault detection methods are presented as comparative examples to verify the effectiveness of the proposed method.

A Novel Joint Time-Frequency Spectrum Resources Sustainable Risk Prediction Algorithm Based on TFBRL Network for the Electromagnetic Environment

To protect the electromagnetic environment and understand its current state in a timely manner, monitoring the electromagnetic environment has great practical significance, while massive amounts of data are generated. It is crucial to utilize data mining technology to extract valuable information from these massive amounts of data for effective spectrum management. Traditional spectrum prediction methods do not integrate the prior information of spectrum resource occupancy, so that the prediction of the channel state of a single frequency point is of limited significance. To address these issues, the paper describes a dynamic threshold algorithm which mines bottom noise and spectrum resource occupancy from massive electromagnetic environment data. Moreover, the paper describes a joint time-frequency spectrum resource prediction algorithm based on the time-frequency block residual LSTM (TFBRL) network, which utilizes hourly time closeness, daily period, and annual trend as prior knowledge of spectrum resources. The TFBRL network comprises three main parts: (1) a residual convolution network with a squeeze-and-excitation (SE) attention mechanism, (2) a long short term memory (LSTM) model with memory ability to capture sequence latent information, and (3) a feature fusion module based on a matrix to combine time closeness, daily period, and annual trend feature components. Experimental results demonstrate that the TFBRL network outperforms the baseline networks, improving by 31.37%, 16.00% and 13.06% compared with the best baseline for MSE, RMSE and MAE, respectively. Thus, the TFBRL network has good risk prediction performance and lays the foundation for subsequent frequency scheduling.

Renyi Joint Entropy-Based Dynamic Threshold Approach to Detect DDoS Attacks against SDN Controller with Various Traffic Rates

The increasing incidence of distributed denial-of-service (DDoS) attacks has made software-defined networking (SDN) more vulnerable to the depletion of controller resources. DDoS attacks prevent the SDN controller from processing all incoming data efficiently, potentially disrupting a network or denying legitimate users access to network services. Thus, the protection of the SDN controller is crucial, especially from the ones that exploit the SDN characteristics. In this paper, the authors propose an efficient detection approach for low- and high-rate DDoS attacks on the controller with a high detection rate and a low false positive rate by adapting a dynamic threshold algorithm rather than a static one and proposing a new rule-based detection mechanism. In addition, the proposed approach was evaluated using eight simulation scenarios representing all potential attacks against the SDN controller in terms of attack traffic rates (low or high), sources (either single or multiple hosts), and targets (single or multiple victims). The experiment results show that the proposed approach is more effective than the existing approaches based on attack detection and false positive rates.

An Online Entropy-Based DDoS Flooding Attack Detection System With Dynamic Threshold

Distributed denial of service attacks are cyber-attacks that target the availability of servers. As a result, legitimate users no longer have access to the service. This can have a negative impact on an organization, such as lack of reputation and economic losses. Therefore, it is important to design defense mechanisms against these attacks. There are systems for detecting distributed denial of service attacks in the literature, which still have various shortcomings. Some of these systems detect the presence of attack traffic without identifying the attack packets or flows. Others use static thresholds and therefore cannot adapt to changes in legitimate traffic. In this paper, we propose an online system that aims to detect flooding attacks in a short timeframe and a client–server environment. The proposed detection system consists of five modules, namely features extraction and connections construction, suspicious activity detection, attack connections detection, alert generation and threshold update. The suspicious activity detection module calculates the normalized Shannon entropy by considering the source Internet Protocol address as a random variable. Suspicious activity is detected when the computed entropy is below a threshold. The threshold calculation is based on Chebyshev’s theorem. We propose a dynamic threshold algorithm to track changes in legitimate traffic. We evaluate the proposed system through simulations and using a publicly available dataset. Compared to other similar works, the proposed detection system has a better performance in terms of detection rate, false positive rate, precision and overall accuracy.

A BPR-CNN Based Hand Motion Classifier Using Electric Field Sensors

In this paper, we propose a BPR-CNN (Biometric Pattern Recognition-Convolution Neural Network) classifier for hand motion classification as well as a dynamic threshold algorithm for motion signal detection and extraction by EF (Electric Field) sensors. Currently, an EF sensor or EPS (Electric Potential Sensor) system is attracting attention as a next-generation motion sensing technology due to low computation and price, high sensitivity and recognition speed compared to other sensor systems. However, it remains as a challenging problem to accurately detect and locate the authentic motion signal frame automatically in real-time when sensing body-motions such as hand motion, due to the variance of the electric-charge state by heterogeneous surroundings and operational conditions. This hinders the further utilization of the EF sensing; thus, it is critical to design the robust and credible methodology for detecting and extracting signals derived from the motion movement in order to make use and apply the EF sensor technology to electric consumer products such as mobile devices. In this study, we propose a motion detection algorithm using a dynamic offset-threshold method to overcome uncertainty in the initial electrostatic charge state of the sensor affected by a user and the surrounding environment of the subject. This method is designed to detect hand motions and extract its genuine motion signal frame successfully with high accuracy. After setting motion frames, we normalize the signals and then apply them to our proposed BPR-CNN motion classifier to recognize their motion types. Conducted experiment and analysis show that our proposed dynamic threshold method combined with a BPR-CNN classifier can detect the hand motions and extract the actual frames effectively with 97.1% accuracy, 99.25% detection rate, 98.4% motion frame matching rate and 97.7% detection & extraction success rate.

Internal Damage Analysis of Braided Composites Embedded in Carbon Nanotube Yarn

Carbon nanotube (CNT) yarn sensors were embedded in 3D braided composites in the form of arrays to detect the internal damage of specimens and study the internal damage monitoring of the 3D braided composites. The signals collected by the sensor array of CNT yarn were preprocessed using the dynamic wavelet threshold algorithm. The exact position of the damage was calculated based on the main features of the resistance signal matrix, which was calculated using the quadratic matrix singular value. The results show that the internal damage localization of the specimens was consistent with the actual damage. The localizations in this study can provide a basis for enhancing the structural health monitoring of smart 3D braided composites.

A systematic method for spatio-temporal phenology estimation of paddy rice using time series Sentinel-1 images

Spatio-temporal phenological information is essential for regional crop monitoring and accurate management. This study aimed to obtain the spatio-temporal distribution of rice phenology using time series Sentinel-1A images. In this study, a systematic method for spatial and temporal phenological estimation was developed based on multi-temporal Sentinel data. This method consisted of: (1) the Spectral Similarity Measures (SSM) approach for rice mapping, and (2) the DTHT-PF approach, which includes a dynamic threshold algorithm (DT), a hierarchical tree (HT), and a particle filter (PF) used for phenology estimation. Thereinto, a dynamic threshold algorithm for transplanting date retrieval and a hierarchical tree for obtaining an initial phenology, which is then run through a PF, are proposed based on the SAR backscatter time series. In brief, we found that the VH backscatter has the potential to provide accurate phenological estimations for paddy rice. Furthermore, rice mapping at a high accuracy level of 92.97%, transplanting date retrieval, and initial phenology estimations lay a good foundation for understanding the spatio-temporal distribution of rice phenology. A determination factor (R2) and a root mean square error (RMSE) obtained using the DTHT-PF method were much higher (approximately 0.52 in the difference) and lower (approximately 14.67 in the difference), respectively, than those obtained using the PF approach with uniform initialization. R2 and RMSE values obtained using the real-time DTHT-PF method are slightly different from those obtained using the non-real-time DTHT-PF method. Map analysis revealed that the transplanting dates and the spatial distribution phenology were larger in the west and north of the study area near the South China Sea because of higher temperatures and earlier transplanting. Altogether, our results suggest that the DTHT-PF method and the VH backscatter obtained from the Sentinel-1A images have great potential for furthering our understanding of the spatio-temporal distribution of phenology estimation. This information can greatly contribute to the improvement of precision agriculture, including crop monitoring and yield predictions.

A Forecasting Approach to Improve Control and Management for 5G Networks

In 5G networks, time-series data will be omnipresent for the monitoring and management of network performance metrics. With the increase in the number of Internet of Things (IoT) devices, it is expected that the number of real-time time-series data streams will increase at a fast pace, making forecasting essential for the proactive successful management of the network. In this article, we discuss to use both linear and non-linear forecasting methods, including machine learning, deep learning, and neural networks to improve 5G networks’ management. For this purpose, we design and implement a real-time distributed forecasting framework, used to make simultaneous predictions of different network performance metrics, and with different learning algorithms. By using our framework, we compare the use of forecasting methods in two network scenarios, in a real vehicular network and in a 4G network, representing two different slices in a 5G network. We also integrate our framework in a 5G architecture. Using the best forecasting models assessed previously, we propose a dynamic threshold algorithm for multi-slice management, to ensure that the resources of each slice are updated according to the slices’ needs, while avoiding congestion and saving resources for other slices. The experimental results show that it is possible to forecast the slices’ needs and congestion probability, selecting the best forecasting approach or an ensemble of the best ones, and act accordingly in the network to optimize its management.

Cooperative Spectrum Sensing Algorithm to Overcome Noise Fluctuations Based on Energy Detection in Sensing Systems

In sensing systems, nodes must be able to rapidly detect whether a signal from a primary transmitter is present in a certain spectrum. However, traditional energy‐detection algorithms are poorly adapted to treating noisy signals. In this paper, we investigate how rapid energy detection and detection sensitivity are related to detection duration and average power fluctuation in noise. The results indicate that detection performance and detection sensitivity decrease quickly with increasing average power fluctuation in noise and are worse in situations with low signal‐to‐noise ratio. First, we present a dynamic threshold algorithm based on energy detection to suppress the influence of noise fluctuation and improve the sensing sensitivity. Then, we present a new energy‐detection algorithm based on cooperation between nodes. Simulations show that the proposed scheme improves the resistance to average power fluctuation in noise for short detection timescales and provides sensitive detection that improves with increasing numbers of cooperative detectors. In other words, the proposed scheme enhances the ability to overcome noise and improves spectrum sensing performance.

HDT: A Heuristic Dynamic Threshold Algorithm to Avoid Reprioritization of LEDBAT

HDT: A Heuristic Dynamic Threshold Algorithm to Avoid Reprioritization of LEDBAT

SEA FOG DETECTION BASED ON DYNAMIC THRESHOLD ALGORITHM AT DAWN AND DUSK TIME

Abstract. Dawn and dusk time is the high frequency period of sea fog occurrence, which is very important for all-day sea fog remote sensing detection. Most polar orbit satellites are limited by time resolution and transit time, and can not detect sea fog at dawn and dusk. Based on the Himawari-8 geostationary satellite data and the analysis of the spectral characteristics of sea fog at dawn and dusk, this paper determines the variation law of the reflectivity and brightness temperature of sea fog at dawn and dusk, chooses sensitive bands, sets the detection index of sea fog and its corresponding dynamic threshold, and realizes the detection of sea fog at dawn and dusk. The case study results indicate that our dynamic threshold algorithm can effectively detect the sea fog at dawn and dusk.

ENHANCED DYNAMIC THRESHOLD ALGORITHM OF QRS COMPLEX DETECTION

The dynamic threshold algorithm (DTA) presented by Pan Tompkins is a popular QRS detection method, and it has high sensitivity and specificity. However, the accuracy of this algorithm would be compromised if its sensitivity is increased. In this study, an enhanced dynamic threshold algorithm (EDTA) based on dynamic threshold rules is proposed, which add a compensation scheme to reduce the rate of misdetection and missed detection of R wave in low signal-to-noise ratio condition, sensitivity and detection error rate are calculated on simulated and clinical data to compare the performance between EDTA and DTA, and EDTA yields a competitive results. For the clinical data, the average accuracy rate of EDTA is 99.24%, which is higher than that of DTA at 95.98%. Further compared experiments among EDTA and the two other popular algorithms are conducted and the results of their validation over a public database are given and discussed, which prove our superiority.

Sentiment analysis via semi-supervised learning: a model based on dynamic threshold and multi-classifiers

Sentiment analysis has become a very popular research topic, especially for retrieving valuable information from various online environments. Most existing sentiment studies are based on supervised learning, which requires sufficient amount of labeled data. However, sentiment analysis often faces insufficient labeled data in practice, as it is very expensive and time-consuming to label large amount of data. To handle the scenario of insufficient initial labeled data, we propose a novel semi-supervised model based on dynamic threshold and multi-classifiers. In particular, the training data are auto-labeled in an iterative way based on the proposed dynamic threshold algorithm, where a dynamic threshold function is proposed to set thresholds for selecting the auto-labeled data. It considers both the quality and quantity of the auto-labeled data. In addition, the proposed weighted voting strategy combines multiple support vector machine classifiers by considering performance gap among different classifiers. The performance of the proposed model is validated through experiments on real datasets. Compared with two other existing models, the proposed model achieves the highest sentiment analysis accuracy across datasets with different sizes of initial labeled training data.

Dynamic ECN marking threshold algorithm for TCP congestion control in data center networks

Recent years have witnessed the rapid development in data center, which hosts a wide variety of applications and services with diverse requirements for network performance. Data center networks (DCNs) have the characteristics of high bandwidth and low latency and TCP incast usually happens when multiple senders simultaneously communicate with a single receiver. In this paper, we first investigate the DCTCP, which is widely deployed in DCNs and uses Explicit Congestion Notification (ECN) as a congestion signal when queue length is larger than a fixed threshold. We demonstrate that the queuing delay may be high or the bottleneck link utilization can be insufficient due to inappropriate fixed threshold. Then we propose a dynamic ECN marking threshold algorithm based on the number of concurrent flows, referred to as DEMT, to improve the network performance. After that, an enhanced DEMT algorithm, referred to as EDEMT, is proposed by using the ratio of the queue length over the marking threshold to perceive the degree of network congestion. We also integrate DEMT with DCTCP to observe its behavior and theoretically analyze the throughput. Finally, simulation results demonstrate that the DEMT and EDEMT algorithms can effectively improve the network throughput while they can maintain a small queue length as well as the short flow completion time.