Application Of Automatic Detection Research Articles

Intrinsic peroxidase activity of carbon dots derived from expired drugs and its application in automatic detection of total antioxidant capacity

In the post-COVID-19 pandemic, the stockpiling of medicines by most households could pose a pollution risk as they may expire over time. In this study, an expired amoxicillin act as carbon source to prepare peroxide-like functional carbon dots nanozymes doped Fe (Fe-CDs). Importantly, a high-value treatment technique for expired drugs was proposed. To obtain outstanding catalytic performance, compared with other commonly doped metals, Fe-CDs catalyzed the oxidation of TMB by H2O2 with the highest efficiency. In particular, the oxidation product of TMB (oxTMB) would be alleviated in the presence of antioxidants. Significantly, antioxidants could briefly cause the fading of oxTMB and the fading level was correlated with various concentrations of antioxidants. Importantly, a sequential injection strategy was introduced to control the fading process caused by antioxidants to improve the accuracy. Under the optimum condition, the limit of detection (LOD) was 0.13 mg/L (for ascorbic acid) with the linear concentration range from 0.5 to 15 mg·L−1. Finally, the total antioxidant capacity (TAC) in human serum samples were evaluated successfully.

Mis-mappings between a producer's quantitative test codes and LOINC codes and an algorithm for correcting them.

To access the accuracy of the Logical Observation Identifiers Names and Codes (LOINC) mapping to local laboratory test codes that is crucial to data integration across time and healthcare systems. We used software tools and manual reviews to estimate the rate of LOINC mapping errors among 179 million mapped test results from 2 DataMarts in PCORnet. We separately reported unweighted and weighted mapping error rates, overall and by parts of the LOINC term. Of included 179537986 mapped results for 3029 quantitative tests, 95.4% were mapped correctly implying an 4.6% mapping error rate. Error rates were less than 5% for the more common tests with at least 100000 mapped test results. Mapping errors varied across different LOINC classes. Error rates in chemistry and hematology classes, which together accounted for 92.0% of the mapped test results, were 0.4% and 7.5%, respectively. About 50% of mapping errors were due to errors in the property part of the LOINC name. Mapping errors could be detected automatically through inconsistencies in (1) qualifiers of the analyte, (2) specimen type, (3) property, and (4) method. Among quantitative test results, which are the large majority of reported tests, application of automatic error detection and correction algorithm could reduce the mapping errors further. Overall, the mapping error rate within the PCORnet data was 4.6%. This is nontrivial but less than other published error rates of 20%-40%. Such error rate decreased substantially to 0.1% after the application of automatic detection and correction algorithm.

Multi-modal voice pathology detection architecture based on deep and handcrafted feature fusion

Automatic voice pathology detection systems can effectively help clinicians by enabling objective assessment and diagnosis in early stage of voice pathologies. This paper suggests a novel multi-modal architecture utilizing speech and electroglottography (EGG) signals and investigates their effectiveness in automatic detection of voice pathology. The proposed multi-modal framework combines two parallel Convolutional Neural Networks (CNNs), one for voice signals and the other for EGG signals, to obtain deep features. Classical handcrafted features are also obtained in the same manner. These features are then concatenated to obtain a more prominent feature set. In addition, a feature selection method is applied to remove redundant features. Finally, a SVM classifier is utilized to detect the voice pathology. In order to measure the performance of the proposed pathology detection system, various experiments are conducted on Saarbruecken Voice Database (SVD) without excluding any available pathology or sample. The experimental results show that the proposed voice pathology detection method achieves accuracy up to 90.10% using all speech and EGG samples. Also, sensitivity, specificity and F1-score results of 92.9%, 84.6% and 92.57% are obtained, respectively. The proposed method provides better performance than those given in the literature using all SVD samples through cross-validation testing. Hence, it is promising for automatic detection applications of voice pathology.

Research and application of automatic detection of rail fastener damage

Research and application of automatic detection of rail fastener damage

Application of YOLOv4 for Detection and Motion Monitoring of Red Foxes.

Simple SummaryThe use of surveillance videos of animals is an important method for monitoring them, as animals often behave differently in the presence of humans. Moreover, the presence of humans can be a source of stress for the animals and can lead to changes in behavior. Extensive video material of red foxes has been recorded as part of a vaccine study. Since manual analysis of videos is both time-consuming and costly, we performed an analysis using a computer vision application in the present study. This made it possible to automatically analyze the videos and monitor animal activity and residency patterns without human interference. In this study, we used the computer vision architecture ‘you only look once’ version 4 (YOLOv4) to detect foxes and monitor their movement and, thus, their activity. Computer vision thereby outperforms manual and sensor-based exhaustive monitoring of the animals.Animal activity is an indicator for its welfare and manual observation is time and cost intensive. To this end, automatic detection and monitoring of live captive animals is of major importance for assessing animal activity, and, thereby, allowing for early recognition of changes indicative for diseases and animal welfare issues. We demonstrate that machine learning methods can provide a gap-less monitoring of red foxes in an experimental lab-setting, including a classification into activity patterns. Therefore, bounding boxes are used to measure fox movements, and, thus, the activity level of the animals. We use computer vision, being a non-invasive method for the automatic monitoring of foxes. More specifically, we train the existing algorithm ‘you only look once’ version 4 (YOLOv4) to detect foxes, and the trained classifier is applied to video data of an experiment involving foxes. As we show, computer evaluation outperforms other evaluation methods. Application of automatic detection of foxes can be used for detecting different movement patterns. These, in turn, can be used for animal behavioral analysis and, thus, animal welfare monitoring. Once established for a specific animal species, such systems could be used for animal monitoring in real-time under experimental conditions, or other areas of animal husbandry.

Application of automatic detection based on overnight airflow and blood oxygen in patients with sleep disordered breathing.

To explore the feasibility of automatic detection based on air flow and blood oxygen in patients with sleep disordered breathing. This study proposes a new automated detection method for sleep disordered breathing based on overnight airflow and blood oxygen saturation (SaO2). In this regard, local range (LR) of the airflow was adopted to detect apnea events and the SaO2 sudden drops were used to help determine hypopnea events. Pearson correlation index was used to evaluate the relationship between the two automated methods (this study vs. Remlogic software) and the manual reports. Error and mean absolute error (MAE) were used to assess the two automated methods. For all patients, the apnea-hypopnea index (AHI), apnea index (AI) and hypopnea index (HI) for our automated scoring and manual reports were highly correlated (the Pearson correlation index were 0.996, 0.995 and 0.928, respectively, P < 0.001). However, HI for Remlogic automated scoring and clinical manual reports was poorly correlated (r = 0.316, P < 0.001). Compared with the manual reports, mean absolute error of AHI, AI and HI between the two automated methods (this study vs. Remlogic software) were statistically significant (P < 0.0001). Furthermore, among the three subgroups (group 1, AHI < 15/h, group 2, 15/h ≤ AHI < 30/h and group 3, AHI ≥ 30/h), the mean error and MAE of AHI between the two automated methods were also statistically significant (P < 0.01). Generally, good agreements were shown between our automated detection and clinical reports. This procedure is robust and effective, which would significantly shorten the analysis time.

Automatic pest detection on bean and potato crops by applying neural classifiers

Instrumentation and Artificial Intelligence (AI) recognition techniques were developed for automatic pest detection. This system is based on pest detection and monitoring, and it improves the efficiency of vegetable and fruit farming and food production. This paper presents an automatic pest detection system that applies artificial neural networks. The system automatically detects two defoliating pests on potato and bean crops: Mexican Bean Beetle (MBB) and Colorado Potato Beetle (CPB) in the adult stage. The neural classifiers utilized for the beetle detection are RSC (Random Subspace Classifier) and LIRA (Limited Receptive Area). The MBB images that were employed as inputs to the classifiers were obtained on Mexican plantations. The CPB images were collected from various Internet sources. We compared the results obtained with both classifiers on image databases. The RSC classifier demonstrates the better result for recognition, which is 89%, while LIRA presents a recognition rate of 88%. These results are good for pest detection and can be used for the diagnosis of pest locations in crops. The purpose was to contribute to the development of automatic detection applications based on images of potato and bean plantations. In Mexico and other countries, it is of great importance to solve pest problems in agriculture. We chose insect recognition due to the importance of potato and bean crop production and consumption. Pest detection in the adult phase is of high priority because of the high rate of crop defoliation and destruction. Our automatic pest-detection system can be employed in pest recognition in monitoring activities.

Automated Detection of High Frequency Oscillations in Human Scalp Electroencephalogram.

High frequency oscillations (HFOs) > 80 Hz are a promising biomarker of epileptic tissue. Recent evidence has shown that spontaneous HFOs can be recorded from the scalp, but detection of these electrographic events remains a challenge. Here, we modified a simple automatic detector, used originally for intracranial EEG (iEEG) recordings, to detect ripples and fast ripples in scalp EEG. We analyzed scalp EEG recordings of seven subjects and validated our detector and artifact rejection algorithm via visual review. Of the candidate events marked by the detector, 40% and 60% were confirmed to be ripples and fast ripples, respectively, by human visual review, making this algorithm suitable for supervised detection. Detected HFOs occurred at a rate of <1/min in most channels, and the average duration was 47 and 24 ms for ripples and fast ripples, respectively. The simplicity of the algorithm, with only a single parameter, enables the consistent application of automatic detection across recording modalities, and it could therefore be a tool for the assessment and localization of epileptic activity.

Comparative assessment of the modeling and discrimination power of two pattern recognition methods applied to detect designer drugs

We are presenting a comparative assessment of the modeling and discrimination power of two pattern recognition methods, i.e. Hierarchical Cluster Analysis (HCA) and the Naive Bayes Classifier (NBC), from the point of view of their efficiency in detecting illicit amphetamines, based on their GC-IRAS laser spectra recorded between 1405 and 1150 cm-1. A special attention was also given to the detection of their main precursors, the ephedrines. The spectra were first preprocessed with a discriminating feature weight wTE. The performances of two automatic detection applications, based on HCA and on NBC, are compared from the point of view of their capacity to correctly recognize illicit amphetamines and ephedrines and distinguish among them according to the Schedules of the United Nations Convention on Psychotropic Substances.

A Simple Statistical Method for the Automatic Detection of Ripples in Human Intracranial EEG.

High frequency oscillations (HFOs) are a promising biomarker of epileptic tissue, but detection of these electrographic events remains a challenge. Automatic detectors show encouraging results, but they typically require optimization of multiple parameters, which is a barrier to good performance and broad applicability. We therefore propose a new automatic HFO detection algorithm, focusing on simplicity and ease of implementation. It requires tuning of only an amplitude threshold, which can be determined by an iterative process or directly calculated from statistics of the rectified filtered data (i.e. mean plus standard deviation). The iterative approach uses an estimate of the amplitude probability distribution of the background activity to calculate the optimum threshold for identification of transient high amplitude events. We tested both the iterative and non-iterative approaches using a dataset of visually marked HFOs, and we compared the performance to a commonly used detector based on the root-mean-square. When the threshold was optimized for individual channels via ROC curve, all three methods were comparable. The iterative detector achieved a sensitivity of 99.6%, false positive rate (FPR) of 1.1%, and false detection rate (FDR) of 37.3%. However, in an eight-fold cross-validation test, the iterative method had better sensitivity than the other two methods (80.0% compared to 64.4 and 65.8%), with FPR and FDR of 1.3, and 49.4%, respectively. The simplicity of this algorithm, with only a single parameter, will enable consistent application of automatic detection across research centers and recording modalities, and it may therefore be a powerful tool for the assessment and localization of epileptic activity.

Automatic classification of magnetic tiles internal defects based on acoustic resonance analysis

A novel signal processing method using wavelet packet transform (WPT), linear discriminant analysis (LDA) and support vector machine (SVM) is presented for detecting internal defects in magnetic tile. In this methodology, the acoustic signal obtained by a mechanical system based on acoustic resonance is analyzed. WPT is applied to extract the normalized features of the signal. The internal defects are identified by SVM based on the extracted features optimized by LDA and a constraint algorithm. The experimental results demonstrate that the presented approach can be employed for a promising application of automatic detection of internal defects in magnetic tile.

Russian

This article examines the clustering of the parameters of rhythmographic analysis of the events of the corporate network traffic of the Cisco MARS system. The author dwells upon classifying clustering methods and illustrates a conceptual clustering algorithm. The author infers that, firstly, the results of processing experimental data derived from network traffic logs substantiate the applicability of the methodology of rhythmographic analysis, which is accepted in cardiology, in the analysis of the rhythm of appearance of events in the Cisco MARS system; secondly, the results of clustering the fragments of the rhythm of events substantiate the effectiveness of the approach proposed; thirdly, the practical application of automatic detection of anomalies in network traffic events requires further research.

Cardiac Cycle Phase Estimation in 2-D Echocardiographic Images Using an Artificial Neural Network

This paper proposes a new hybrid approach to estimate the cardiac cycle phases in 2-D echocardiographic images as a first step in cardiac volume estimation. We focused on analyzing the atrial systole and diastole events by using the geometrical position of the mitral valve and a set of three image features. The proposed algorithm is based on a tandem of image processing methods and artificial neural networks as a classifier to robustly extract anatomical information. An original set of image features is proposed and derived to recognize the cardiac phases. The aforementioned approach is performed in two denoising scenarios. In the first scenario, the images are corrupted with Gaussian noise, and in the second one with Rayleigh noise distribution. Our hybrid algorithm does not involve any manual tracing of the boundaries for segmentation process. The algorithm is implemented as computer-aided diagnosis (CADi) software. A dataset of 150 images that include both normal and infarct cardiac pathologies was used. We reported an accuracy of 90 % and a 2 ± 0.3s in terms of execution time of CADi application in a cardiac cycle estimation task. The main contribution of this paper is to propose this hybrid method and a set of image features that can be helpful for automatic detection applications without any user intervention. The results of the employed methods are qualitatively and quantitatively compared in terms of efficiency for both scenarios.

Wrapper feature selection for small sample size data driven by complete error estimates

This paper focuses on wrapper-based feature selection for a 1-nearest neighbor classifier. We consider in particular the case of a small sample size with a few hundred instances, which is common in biomedical applications. We propose a technique for calculating the complete bootstrap for a 1-nearest-neighbor classifier (i.e., averaging over all desired test/train partitions of the data). The complete bootstrap and the complete cross-validation error estimate with lower variance are applied as novel selection criteria and are compared with the standard bootstrap and cross-validation in combination with three optimization techniques – sequential forward selection (SFS), binary particle swarm optimization (BPSO) and simplified social impact theory based optimization (SSITO). The experimental comparison based on ten datasets draws the following conclusions: for all three search methods examined here, the complete criteria are a significantly better choice than standard 2-fold cross-validation, 10-fold cross-validation and bootstrap with 50 trials irrespective of the selected output number of iterations. All the complete criterion-based 1NN wrappers with SFS search performed better than the widely-used FILTER and SIMBA methods. We also demonstrate the benefits and properties of our approaches on an important and novel real-world application of automatic detection of the subthalamic nucleus.

Top-Hat Transform Sequence Analysis and Application in Automatic Detection of Products Defects

Defects in parts bring great harms.To implement automatic monitoring of parts quality,images of parts are processed and analyzed.A method of Top-Hat transform sequence analysis is proposed.Firstly,iterative open operation and Top-Hat transformation of the signal are computed by using size driven structure elements and the O-TH(Open-TopHat) decomposition tree is obtained.Objects analysis spectrum is established whose amplitude is the energy of the O-TH tree leaf nodes.Then,the optimum size of the structure element and the optimum segmentation threshold are obtained by analyzing the behavior of each object of the signal in the spectrum.Thus,all the targets in the signal are located accurately.On this basis,the preliminary segment result is patched by comparing the elements in the TH sequence with the Top-Hat transform result which uses the optimum structure element,and the targets in the signal are detected completely.Finally,object extraction algorithm based on Top-Hat transform sequence analysis is designed.The method is verified by experiments including several kinds of parts and different defects.The results prove that the method has good generality and strong immunity and anti-background interference abililty,high accuracy in defect extraction and good robustness.

Traffic-Incident Detection-Algorithm Based on Nonparametric Regression

This paper proposes an improved nonparametric regression (INPR) algorithm for forecasting traffic flows and its application in automatic detection of traffic incidents. The INPRA is constructed based on the searching method of nearest neighbors for a traffic-state vector and its main advantage lies in forecasting through possible trends of traffic flows, instead of just current traffic states, as commonly used in previous forecasting algorithms. Various simulation results have indicated the viability and effectiveness of the proposed new algorithm. Several performance tests have been conducted using actual traffic data sets and results demonstrate that INPRs average absolute forecast errors, average relative forecast errors, and average computing times are the smallest comparing with other forecasting algorithms.