Empirical mean curve decomposition with multiwavelet transformation for eye movements recognition using electrooculogram signals

2020 ◽  
Vol 234 (8) ◽  
pp. 794-811
Author(s):  
Harikrishna Mulam ◽  
Malini Mudigonda
Keyword(s):  
Neural Network ◽  
Eye Movements ◽  
False Positive Rate ◽  
False Negative ◽  
False Negative Rate ◽  
Principal Component ◽  
The Neural Network ◽  
Marquardt Algorithm ◽  
Positive Rate ◽  
Sensitivity Specificity

Many research works are in progress in classification of the eye movements using the electrooculography signals and employing them to control the human–computer interface systems. This article introduces a new model for recognizing various eye movements using electrooculography signals with the help of empirical mean curve decomposition and multiwavelet transformation. Furthermore, this article also adopts a principal component analysis algorithm to reduce the dimension of electrooculography signals. Accordingly, the dimensionally reduced decomposed signal is provided to the neural network classifier for classifying the electrooculography signals, along with this, the weight of the neural network is fine-tuned with the assistance of the Levenberg–Marquardt algorithm. Finally, the proposed method is compared with the existing methods and it is observed that the proposed methodology gives the better performance in correspondence with accuracy, sensitivity, specificity, precision, false positive rate, false negative rate, negative predictive value, false discovery rate, F1 score, and Mathews correlation coefficient.

EOG-based eye movement recognition using GWO-NN optimization

2020 ◽  
Vol 65 (1) ◽  
pp. 11-22
Author(s):  
Harikrishna Mulam ◽  
Malini Mudigonda
Keyword(s):  
Eye Movement ◽  
Recognition Performance ◽  
Error Function ◽  
False Positive Rate ◽  
False Negative ◽  
False Negative Rate ◽  
Movement Recognition ◽  
Positive Rate ◽  
Sensitivity Specificity ◽  
Novel Model

AbstractIn recent times, the control of human-computer interface (HCI) systems is triggered by electrooculography (EOG) signals. Eye movements recognized based on the EOG signal pattern are utilized to govern the HCI system and do a specific job based on the type of eye movement. With the knowledge of various related examinations, this paper intends a novel model for eye movement recognition based on EOG signals by utilizing Grey Wolf Optimization (GWO) with neural network (NN). Here, the GWO is used to minimize the error function from the classifier. The performance of the proposed methodology was investigated by comparing the developed model with conventional methods. The results reveal the loftier performance of the adopted method with the error minimization analysis and recognition performance analysis in correspondence with varied performance measures such as accuracy, sensitivity, specificity, precision, false-positive rate (FPR), false-negative rate (FNR), negative predictive value (NPV), false discovery rate (FDR) and the F1 score.

scholarly journals Role of complementary cytology, colposcopy and histopathology in detecting premalignant and malignant lesions of cervix

2016 ◽  
Author(s):  
Akanksha Mangla ◽  
Renuka Sinha
Keyword(s):  
Predictive Value ◽  
False Positive Rate ◽  
False Negative ◽  
False Negative Rate ◽  
Cross Sectional Study ◽  
High Grade ◽  
Cervical Lesions ◽  
Cross Sectional ◽  
Positive Rate ◽  
Sensitivity Specificity

Objective: Cervical cancer is the second most common gynecologic malignancy worldwide. India alone accounts for one fifth of total number of cases worldwide. The aim of our study was to calculate sensitivity, specificity, positive predictive value, negative predictive value, false positive rate and false negative rate of complementary cytology and colposcopy with histopathology as gold standard for detection of premalignant and malignant cervical lesions. Methods: A cross sectional study was conducted at Vardhman Mahavir Medical College and Safdarjung hospital, Delhi, India. 100 non pregnant females with complaint of post coital or irregular vaginal bleeding and those who had unhealthy cervix on visual inspection were included in study. Results: Colposcopy exhibited a high degree of accuracy in diagnosis of high grade lesions. Overall sensitivity of cytology was 50% whereas that of colposcopy was 83.3%. Cytology had specificity of 93.4% whereas colposcopy had specificity of 89.4%. 100% of high grade and invasive cancers on colposcopy were associated with similar findings on histology. The degree of agreement between cytology and colposcopy with histology was significant (p<0.001). Conclusion: Colposcopy is sensitive method as compared to cytology, especially in the higher grade lesions and combination of both methods appears to be of higher diagnostic importance.

scholarly journals Evaluating the usefulness of breast strain elastography for intraductal lesions

2021 ◽  
Author(s):  
Yumi Kokubu ◽  
Keiko Yamada ◽  
Masahiko Tanabe ◽  
Ayumi Izumori ◽  
Chieko Kato ◽  
...  
Keyword(s):  
False Positive ◽  
False Positive Rate ◽  
False Negative ◽  
False Negative Rate ◽  
Intraductal Papilloma ◽  
Breast Diseases ◽  
Strain Elastography ◽  
Negative Rate ◽  
Positive Rate ◽  
Sensitivity Specificity

Abstract Purpose Strain elastography for imaging lesion stiffness is being used as a diagnostic aid in the malignant/benign discrimination of breast diseases. While acquiring elastography in addition to B-mode images has been reported to help avoid performing unnecessary biopsies, intraductal lesions are difficult to discriminate whether they are malignant or benign using elastography. An objective evaluation of strain in lesions was performed in this study by measuring the elasticity index (E-index) and elasticity ratio (E-ratio) of lesions as semi-quantitative numerical indicators of the color distribution of strain. We examined whether ductal carcinoma in situ (DCIS) and intraductal papilloma could be distinguished using these semi-quantitative numerical indicators. Methods In this study, 170 ultrasonographically detected mass lesions in 162 cases (106 malignant lesions and 64 benign lesions)—in which tissue biopsy by core needle biopsy and vacuum-assisted biopsy, or surgically performed histopathological diagnosis, was performed—were selected as subjects from among 1978 consecutive cases (from January 2014 to December 2016) in which strain elastography images were acquired, in addition to standard B-mode breast ultrasonography, by measuring the E-index and E-ratio. Results The cut-off values for E-index and E-ratio in the malignant/benign discrimination of breast lesions were determined to be optimal values at 3.5 and 4.2, respectively, based on receiver operating characteristic (ROC) curve analysis. E-index sensitivity, specificity, accuracy, and AUC value (area under the curve) were 85%, 86%, 85%, and 0.860, respectively, while those for E-ratio were 78%, 74%, 74%, and 0.780, respectively. E-index yielded superior results in all aspects of sensitivity, specificity, accuracy, and AUC values, compared to those of E-ratio. The mean E-index values for malignant tumors and benign tumors were 4.46 and 2.63, respectively, indicating a significant difference (P < 0.001). E-index values of 24 DCIS lesions and 25 intraductal papillomas were 3.88 and 3.35, respectively, which showed a considerably close value, while the false-negative rate for DCIS was 29.2%, and the false-positive rate for intraductal papilloma was as high as 32.0%. Conclusion E-index in strain elastography yielded better results than E-ratio in the malignant/benign discrimination of breast diseases. On the other hand, E-index has a high false-negative rate and false-positive rate for intraductal lesions, a factor which should be taken into account when making ultrasound diagnoses.

scholarly journals Development of USI-Kit for Evaluation of Iodine Content in Iodized Salt

2020 ◽  
Vol 17 (10) ◽  
pp. 1149-1156
Author(s):  
Sakaewan OUNJAIJEAN ◽  
Kongsak BOONYAPRANAI ◽  
Kanokwan KULPRACHAKARN ◽  
Kittipan RERKASEM
Keyword(s):  
Spectrophotometric Method ◽  
False Positive ◽  
False Positive Rate ◽  
False Negative ◽  
False Negative Rate ◽  
Iodine Content ◽  
Kappa Coefficient ◽  
Test Kit ◽  
Positive Rate ◽  
Sensitivity Specificity

Iodine deficiency has been considered as a serious public health problem for the past decades. Universal salt iodization program is introduced and implemented to address such problem. To encourage this program in an effective and sustainable way, it is essential to regularly monitor whether salt is adequately iodized at various points along the supply chain. The traditional iodometric titration method has problems related to accessibility, cost, and time. Colorimetric test kits have been used extensively to measure coverage of iodized salt in household surveys due to its expediency and affordability. In Thailand, “I-KIT” is the most widely used. The visualization of intensive color, however, is inconvenient for untrained-user in determining the adequacy of iodine content. Thus, an improvement to make testing more precise and affordable is still required. In this respect, a new test kit namely USI-Kit was developed to assess iodine quality and semi-quantity in edible salt. The kit was tested to evaluate its performance, by comparing the result with the I-KIT and with the spectrophotometric method. Compared with I-Kit, the USI-Kit exerted the relative accuracy, sensitivity, specificity, false positive rate, false negative rate and Kappa coefficient value of 74.0, 76.3, 72.6, 27.4, 23.7 and 0.47, respectively. Compared to the spectrophotometric method, USI-Kit exerted the relative accuracy, sensitivity, specificity, false positive rate, false negative rate and Kappa coefficient value of 85.4, 80.1, 89.3, 10.7, 19.9 and 0.70, respectively. The finding suggested that a newly developed iodine test kit holds promise to be used in field inspection of iodine content in salt.

scholarly journals Advanced Principal Component Analysis for Analysis of Optimized Credit Card Fraud Detection

2019 ◽  
Vol 8 (11) ◽  
pp. 318-322
Keyword(s):  
Principal Component Analysis ◽  
Credit Card ◽  
Detection System ◽  
False Positive Rate ◽  
False Negative ◽  
False Negative Rate ◽  
Principal Component ◽  
Component Analysis ◽  
Security Systems ◽  
Positive Rate

The information has turned out to be increasingly more imperative to people, associations, and organizations, and thusly, shielding this delicate information in social databases has turned into a basic issue. In any case, in spite of customary security systems, assaults coordinated to databases still happen. In this way, an intrusion detection system (IDS) explicitly for the database that can give security from all conceivable malignant clients is important. In this paper, we present the Principal Component Analysis (PCA) technique with weighted voting in favor of the assignment of inconsistency location. PCA is a diagram based procedure reasonable for demonstrating bunching questions, and weighted casting a ballot improves its capacities by adjusting the casting a ballot effect of each tree. Trials demonstrate that RF with weighted casting a ballot shows a progressively predominant presentation consistency, just as better blunder rates with an expanding number of trees, contrasted with traditional grouping approaches. Besides, it outflanks all other best in class information mining calculations as far as false positive rate and false negative rate.

Deep Learning of Empirical Mean Curve Decomposition-Wavelet Decomposed EEG Signal for Emotion Recognition

2020 ◽  
Vol 28 (01) ◽  
pp. 153-177 ◽  
Author(s):  
Sujata Bhimrao Wankhade ◽  
Dharmpal Dronacharya Doye
Keyword(s):  
Emotion Recognition ◽  
False Positive Rate ◽  
False Negative ◽  
False Negative Rate ◽  
Emotional States ◽  
Eeg Signal ◽  
Significant Information ◽  
State Recognition ◽  
Positive Rate ◽  
Sensitivity Specificity

Recently, the emotional state recognition of humans via Electroencephalogram (EEG) is one of the emerging topics that grasp the attention of researchers too. This EEG based recognition is normally an effective model for many of the real-time applications, especially for disabled people. A number of researchers are in progress to make the recognition model more effective in terms of accurate emotion recognition. However, it is not so satisfactory in the precise accurate progressing. Hence this paper intends to recognize the human emotional states or affects through EEG signals by adopting advanced features and classifier models. In the first stage of recognition procedure, this paper exploits 2501 (EMCD) and Wavelet Transformation to represent the EEG signal in low dimension as well as descriptive. By EMCD, the EEG redundancy can be neglected, and the significant information can be extracted. The classification processes using the extracted features with the aid of a classifier named Deep Belief Network (DBN). The performance of the proposed Wavelet-EMCD (WE) approach is analyzed in terms of measures such as Accuracy, Sensitivity, Specificity, Precision, False positive rate (FPR), False negative rate (FNR), Negative Predictive Value (NPV), False Discovery Rate (FDR), F1Score and Mathews correlation coefficient (MCC) and proven the superiority of proposed work in recognizing the emotions more accurately.

Construction of subsystem determination of attacks in cyberphysical systems by neural network methods

2021 ◽  
Vol 26 (jai2021.26(2)) ◽  
pp. 15-25
Author(s):  
Belej O ◽  
◽  
Kolesnyk K ◽  
Nestor N ◽  
Fedirko Yu ◽  
...  
Keyword(s):  
Neural Network ◽  
High Reliability ◽  
False Positive Rate ◽  
Multivariate Time Series ◽  
False Negative ◽  
Research Work ◽  
False Negative Rate ◽  
Cyberphysical Systems ◽  
Network Layers ◽  
Positive Rate

In this research work analyzes and compares existing methods for describing data from cyberphysical systems, methods for detecting network attacks targeting cyberphysical systems, analyzes fundamental approaches and solutions in the field of cyberphysical systems security, and makes recommendations for supplementing existing approaches using new algorithms. The considered application of the neuroevolutionary algorithm of NeuroEvolution of Augmenting Topology using a hypercube for the analysis of multivariate time series describing the state of cyberphysical systems in order to identify abnormal conditions. After the modification, the algorithm allows almost completely configuring the target neural network without user intervention according to the specified parameters, including additionally creating intermediate network layers that were previously unavailable in the primary version of the algorithm. The method is verified on the TON_IOT DATASETS dataset. The system topology is the structure of the Internet of Things. The data are relevant, verified and correct, which allows them to be used for analysis and assessment of the accuracy of the approach under consideration. The obtained overall accuracy, proximity of solutions, values of False Positive Rate and False Negative Rate indicate the lack of retraining of the model and the high reliability of this method for detecting attacks in cyberphysical systems

Application of Musculoskeletal Ultrasound in Real-Time Dynamic Detection of Luschka Joint Hyperplasia of Cervical Vertebrae

2021 ◽  
Vol 11 (2) ◽  
pp. 321-331
Author(s):  
Chenwei Gao ◽  
Dakui Xu ◽  
Chenxi Sun
Keyword(s):  
Real Time ◽  
Cervical Vertebrae ◽  
False Positive Rate ◽  
False Negative ◽  
False Negative Rate ◽  
Musculoskeletal Ultrasound ◽  
Time Dynamic ◽  
Positive Rate ◽  
Dynamic Detection ◽  
Sensitivity Specificity

In order to explore the application of musculoskeletal ultrasound (MSKUS) in real-time dynamic detection of Luschka joint hyperplasia of cervical vertebrae, a total of 80 patients who were diagnosed as cervical spondylosis of vertebral artery type and underwent musculoskeletal ultrasound and three-dimensional computed tomography angiograph (3D-CTA) examination at a designated hospital by this study from December 2016 to December 2018 were selected as study subjects. Taking 3D-CTA as gold standard, the results of MSKUS and 3D-CTA were compared and their correlation and consistency analysis were performed; the sensitivity, specificity, false positive rate, false negative rate and diagnostic compliance rate of MSKUS were calculated for evaluating the lateral hyperplasia of Luschka joint; the Kappa values were used to compare the test results' consistency, which were divided into three categories of high consistency, general consistency, and poor consistency to evaluate the lateral hyperplasia of Luschka joint. The results show that the sensitivity, specificity, false positive rate, false negative rate, positive predictive value, negative predictive value and diagnostic coincidence rate of MSKUS in evaluating the lateral hyperplasia of Luschka joint were 87.34%, 95.78%, 2.49%, 12.45%, 93.02%, 92.18%, and 94.67%, respectively; there was no significantly statistical difference between the MSKUS and 3D-CTA evaluation results (χ2 = 0.34, P > 0.05) and they have higher correlation (K = 0.82) and excellent consistency (K = 0.769). Therefore, it is concluded that the MSKUS has a good validity in evaluating the lateral hyperplasia of cervical vertebrae joints. The study results of this paper provide a reference for further research on the application of MSKUS in real-time dynamic detection of Luschka joint hyperplasia of cervical vertebrae.

A Comparative Study of Different Relevant Features Hybrid Neural Networks Based Intrusion Detection Systems

2011 ◽  
Vol 403-408 ◽  
pp. 4703-4710
Author(s):  
Rashid Ali ◽  
Supriya Kamthania
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Intrusion Detection ◽  
False Positive Rate ◽  
False Negative ◽  
False Negative Rate ◽  
Intrusion Detection Systems ◽  
Detection Systems ◽  
The Neural Network ◽  
Hybrid Neural Networks

Intrusion detection is the task of detecting, preventing and possibly reacting to the attacks and intrusions in a network based computer system. The neural network algorithms are popular for their ability to ’learn’ the so called patterns in a given environment. This feature can be used for intrusion detection, where the neural network can be trained to detect intrusions by recognizing patterns of an intrusion. In this work, we propose and compare the three different Relevant Features Hybrid Neural Networks based intrusion detection systems, where in, we first recognize the most relevant features for a connection record from a benchmark dataset and use these features in training the hybrid neural networks for intrusion detection. Performance of these three systems are evaluated on a well structured KDD CUP 99 dataset using a number of evaluation parameters such as classification rate, false positive rate, false negative rate etc.

scholarly journals Evaluation of optimal urine screening and confirmation cut-off values for opiates, at a national reference laboratory

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Çiğdem Karakükcü ◽  
Mehmet Zahid Çıracı ◽  
Derya Kocer ◽  
Mine Yüce Faydalı ◽  
Muhittin Abdulkadir Serdar
Keyword(s):  
False Positive ◽  
False Positive Rate ◽  
False Negative ◽  
Urine Samples ◽  
Reference Laboratory ◽  
National Reference Laboratory ◽  
Urine Screening ◽  
National Reference ◽  
Positive Rate ◽  
Sensitivity Specificity

Abstract Objectives To obtain optimal immunoassay screening and LC-MS/MS confirmation cut-offs for opiate group tests to reduce false positive (FP) and false negative (FN) rates. Methods A total of 126 urine samples, −50 opiate screening negative, 76 positive according to the threshold of 300 ng/mL by CEDIA method – were confirmed by a full-validated in-house LC-MS/MS method. Sensitivity, specificity, FP, and FN rates were determined at cut-off concentrations of both 300 and 2,000 ng/mL for morphine and codeine, and 10 ng/mL for heroin metabolite 6-mono-acetyl-morphine (6-MAM). Results All CEDIA opiate negative urine samples were negative for morphine, codeine and 6-MAM. Although sensitivity was 100% for each cut-off; specificity was 54.9% at CEDIA cut-off 300 ng/mL vs. LC-MS/MS cut-off 300 ng/mL and, 75% at CEDIA cut-off 2,000 ng/mL vs. LC-MS/MS cut-off 2,000 ng/mL. False positive rate was highest (45.1%) at CEDIA cut-off 300 ng/mL. At CEDIA cut-off 2,000 ng/mL vs. LC-MS/MS cut-off 300 ng/mL, specificity increased to 82.4% and FP rate decreased to 17.6%. All 6-MAM positive samples had CEDIA concentration ≥2,000 ng/mL. Conclusions 2,000 ng/mL for screening and 300 ng/mL for confirmation cut-offs are the most efficient thresholds for the lowest rate of FP opiate results.

Sign in / Sign up

Export Citation Format

Share Document