Deep learning based automatic vertical height adjustment of incorrectly fastened seat belts for driver and passenger safety in fleet vehicles

2021 ◽  
pp. 095440702110253
Author(s):  
Arif Şenol Şener ◽  
Ibrahim Furkan Ince ◽  
Husnu Baris Baydargil ◽  
Ilhan Garip ◽  
Oktay Ozturk
Keyword(s):  
Seat Belt ◽  
False Positive Rate ◽  
False Negative ◽  
False Negative Rate ◽  
The Body ◽  
Seat Belts ◽  
Data Program ◽  
Reliable Solution ◽  
Sensitivity Specificity ◽  
Vertical Height

The recognition of incorrect fastening of seat belts is significant in passenger and driver safety for the automotive industry and public health. It should be made sure that the passenger’s seat belt is not only fastened but also correctly fastened across the body so that the passenger is adequately protected in the event of an accident. Current technology employs the buckle effect sensor, which merely solves the buckling detection problem, but there is no reliable solution for the correct positioning of the seat belt. Additionally, computer vision-based systems are still incapable of recognizing the incorrect positioning of seat belts when the training is performed by employing the subjects out of the fleet. Considering this fact, in this study, we propose a novel solution that employs a vision-based incorrect fastening seat belt detector to perform automatic vertical height adjustment independent from drivers and passengers for the fleet vehicles. We recognize the incorrect positioning of the seat belt inside the car by the acceptable distance of the seat belt from the neck of drivers or passengers to avoid neck injuries and the deaths caused by neck cuts. An extensive benchmarking is performed by comparing the three CNN architectures such as; DenseNet121, GoogLeNet (Inception-v3), ResNet50 with respect to sensitivity, specificity, precision, false-positive rate, false-negative rate, F1 score, and accuracy. Additionally, training and validation loss curves and accuracy curves are plotted for all the models. Later, the three models are evaluated with a precision-recall (PR) curve at the end. According to the results, the DenseNet121 achieved the highest classification accuracy among the tested models with 99.95%. This paper includes information about the proposed system elements, registration of data, elaboration of data, program algorithm, testing the system in the lab, and on the vehicle.

Liquid-Based Cytology in Diagnosing Nasopharyngeal Carcinoma

2009 ◽  
Vol 23 (4) ◽  
pp. 422-425 ◽  
Author(s):  
Yee-Jee Jan ◽  
Su-Ju Chen ◽  
John Wang ◽  
Rong-San Jiang
Keyword(s):  
Nasopharyngeal Carcinoma ◽  
False Positive Rate ◽  
False Negative ◽  
False Negative Rate ◽  
Sampling Technique ◽  
Punch Biopsy ◽  
Great Success ◽  
Nasopharyngeal Biopsy ◽  
Liquid Based Cytology ◽  
Sensitivity Specificity

Background Liquid-based cytology (LBC) has achieved great success in cytological diagnosis of various cancers when compared with conventional smear methods. However, its application in diagnosing nasopharyngeal carcinoma (NPC) has never been studied. Methods Eighty-four consecutive patients who underwent nasopharyngeal biopsy for suspicious NPC or a nasopharyngeal mass under nasopharyngoscopy were enrolled in this prospective study. Brush samples were taken from the same site before punch biopsy and processed with the Thin Prep test. Results The adequacy, accuracy, sensitivity, specificity, false-negative rate, and false-positive rate of LBC in diagnosing NPC were 92.9% (78 of 84), 93.6% (73 of 78), 84.2% (16 of 19), 96.6% (57 of 59), 15.8% (three of 19), and 3.4% (two of 25), respectively. There were four inadequate specimens from patients with NPC and two inadequate ones from those without NPC. Conclusions Our study showed that the adequacy, accuracy, sensitivity, specificity, and diagnostic rate of LBC were equivalent to those using conventional smear methods. Although the diagnostic rate of NPC was lower using brush cytology than by punch biopsy, further improvements in the sampling technique could make brushing cytology a potential tool for NPC screening.

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.

scholarly journals Sensitivity, Specificity and Accuracy of Color Doppler Ultrasonography for Diagnosis of Retinal Detachment

2020 ◽  
Author(s):  
Mohammadreza Akhlaghi ◽  
Masoomeh Zarei ◽  
Majid Ziaei ◽  
Mohsen Pourazizi
Keyword(s):  
Retinal Detachment ◽  
Diagnostic Accuracy ◽  
Doppler Ultrasonography ◽  
Color Doppler ◽  
False Positive Rate ◽  
False Negative ◽  
False Negative Rate ◽  
Color Doppler Ultrasonography ◽  
Promising Tool ◽  
Sensitivity Specificity

Purpose: This study evaluated the sensitivity, specificity, and diagnostic accuracy of Color Doppler Ultrasonography (CDUS) in patients with suspected retinal detachment (RD) who underwent surgery. Methods: In this prospective, observational clinical study, 65 eyes of 65 consecutive patients with suspected RD with opaque media were included. Following a standardized protocol, CDUS of the retina of the affected eye was performed. The sensitivity, specificity, and diagnostic accuracy of CDUS were determined and compared to the findings during surgery. Results: The mean age of patients (18 men and 47 women) was 52.36 years (range: 8–77 years). The sensitivity, specificity, and overall accuracy of ocular CDUS were 91.3%, 88.1%, and 89.2%, respectively. The false-negative rate (negative CDUS images but presence of RD at operation) was 3.1% (2/65) and the false-positive rate (positive CDUS images but absence of RD at operation) was 7.7% (5/65). Conclusion: CDUS of the retina could be considered as a promising tool in the diagnosis of RD in patients with opaque media.

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 Detection of Single Umbilical Artery in the First Trimester Ultrasound: Its Value as a Marker of Fetal Malformation

2014 ◽  
Vol 2014 ◽  
pp. 1-6 ◽  
Author(s):  
Cristina Martínez-Payo ◽  
Elena Cabezas ◽  
Yolanda Nieto ◽  
Miguel Ruiz de Azúa ◽  
Fátima García-Benasach ◽  
...  
Keyword(s):  
Umbilical Artery ◽  
False Positive Rate ◽  
False Negative ◽  
False Negative Rate ◽  
First Trimester ◽  
University Hospital ◽  
Fetal Malformation ◽  
Single Umbilical Artery ◽  
Sensitivity Specificity ◽  
First Trimester Ultrasound

Introduction. The value of a single umbilical artery (SUA) in first trimester ultrasound is not well established. The aim of our study was to determinate the relevance of diagnosis of single umbilical artery in first trimester ultrasound as an early marker suggesting the presence of malformations or associated chromosomopathies.Material and Methods. Retrospective study of clinical cases of SUA diagnosed at the University Hospital Puerta de Hierro in Madrid (Spain) during the first trimester ultrasound between September 2008 and September 2012.Results. Prevalence of SUA was 1.1% in single pregnancies and 3.3% in twin pregnancies. Sensitivity, specificity, false positive rate, and false negative rate for the finding in the first trimester were 84.2, 99.8, 0.2, and 15.7%, respectively. 17.6% of cases had associated malformations. With an ultrasound in the 16th week most of the cases with significant fetal malformation were diagnosed.Discussion. SUA is a useful marker in the first trimester for fetal malformation pathology, as it will allow detecting a large number of cases with malformations before 20 weeks of gestation.

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.

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.

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.

Sign in / Sign up

Export Citation Format

Share Document