scholarly journals Impact of Classification Algorithms on Census Dataset

2020 ◽  
Vol 8 (5) ◽  
pp. 2666-2670
Keyword(s):  
Neural Network ◽  
Error Rate ◽  
False Negative ◽  
The Other ◽  
Algorithm Analysis ◽  
Classification Algorithms ◽  
True Positive ◽  
Target Groups ◽  
True Negative ◽  
Large Databases

Data mining is a method by which valuable information can be obtained from large databases. A supervised method of classification assigns data samples to target groups. In this system, it uses various classification algorithms namely decision trees, SVM, random forest and neural network. This system will classify and analyses the best suited algorithm which gives maximum accuracy among the other algorithms. The accuracy in these algorithms has been calculated by sensitivity and specificity. Evaluation of these models has been calculated by the error rate with respect to the classes. It uses census dataset and finds whether the income above 50k or below 50k. Matrix of error consists of true positive, neutral, true negative and false negative values. Based on true positive and false negative values, specificity is determined. Based on true negative and false positive values, sensitivity is determined. The algorithm analysis which finds the better algorithm with respect to the accuracy, error rate and efficiency

scholarly journals Classification of Melanoma and Nevus for Diagnosis of Skin Cancer by Using Optimized Convolution Neural Network

2021 ◽  
Vol 9 (12) ◽  
pp. 1984-1989
Author(s):  
Neha Maheshwari
Keyword(s):  
Neural Network ◽  
Median Filter ◽  
Confusion Matrix ◽  
False Negative ◽  
Convolution Neural Network ◽  
True Positive ◽  
True Negative ◽  
Index Terms ◽  
Risk Of Cancer

Abstract: Melanoma is taken into account a fatal sort of carcinoma .Differentiating melanoma from nevus is difficult task. Nevus is a common pigmented skin lesion, usually developing during adulthood, which is harmless. Since they look similar it has to be identified and reduce the risk of cancer. The death rate thanks to this disease is in particular other skin-related consolidated malignancies. In this work, we have used convolution neural networks to classify the image into melanoma and nevus. The images are pre-processed using median filter, top-bottom hat filter and are passed through layers of CNN. We have achieved an accuracy of 97.56%, sensitivity of 95.23%.The F1_socre is 97.56. Index terms: Melanoma, Nevus, True Positive, True Negative, False Negative, False Positive, Confusion Matrix, Epoch, Convolution Neural Network.

scholarly journals Coupling Uncertainties with Accuracy Assessment in Object-based Slum Detections, Case Study: Jakarta, Indonesia

2017 ◽  
Author(s):  
Jati Pratomo ◽  
Monika Kuffer ◽  
Javier Martinez ◽  
Divyani Kohli
Keyword(s):  
Land Tenure ◽  
Classification Accuracy ◽  
Accuracy Assessment ◽  
False Negative ◽  
National Policy ◽  
True Positive ◽  
True Negative ◽  
Object Based ◽  
The Impact

Object-Based Image Analysis (OBIA) has been successfully used to map slums. In general, the occurrence of uncertainties in producing geographic data is inevitable. However, most studies concentrated solely on assessing the classification accuracy and neglecting the inherent uncertainties. Our research analyses the impact of uncertainties in measuring the accuracy of OBIA-based slum detection. We selected Jakarta as our case study area, because of a national policy of slum eradication, which is causing rapid changes in slum areas. Our research comprises of four parts: slum conceptualization, ruleset development, implementation, and accuracy and uncertainty measurements. Existential and extensional uncertainty arise when producing reference data. The comparison of a manual expert delineations of slums with OBIA slum classification results into four combinations: True Positive, False Positive, True Negative and False Negative. However, the higher the True Positive (which lead to a better accuracy), the lower the certainty of the results. This demonstrates the impact of extensional uncertainties. Our study also demonstrates the role of non-observable indicators (i.e., land tenure), to assist slum detection, particularly in areas where uncertainties exist. In conclusion, uncertainties are increasing when aiming to achieve a higher classification accuracy by matching manual delineation and OBIA classification.

scholarly journals Comparison Study Between Local TSH IRMA Kit (CRRT) and Imported TSH IRMA Kit (Riakey, Korea)

2019 ◽  
Vol 4 (2) ◽  
pp. 77
Author(s):  
Gina Mondrida ◽  
Triningsih Triningsih ◽  
Kristina Dwi Purwanti ◽  
Sutari Sutari ◽  
Sri Setyowati ◽  
...  
Keyword(s):  
False Negative ◽  
Thyroid Stimulating Hormone ◽  
The Body ◽  
True Positive ◽  
Comparison Study ◽  
Complex Matrix ◽  
Normal Range ◽  
True Negative ◽  
Immunoassay Technique ◽  
Tsh Levels

<p><em>Thyroid Stimulating Hormone</em> (TSH) is one of hormones that our body need for growth of brains, bones and other tissues and regulate the metabolism in the body. Normal range of TSH for adult is from 0.3 to 5.5 µIU/ml, whereas for baby ranged from 3 to 18 µIU/ml. An Immunoradiometricassay (IRMA) is one of immunoassay technique using radionuclide as the tracer to detect low quantity of analyte. This technique is suitable for determine TSH levels in human blood serum which has complex matrix and various concentration. The Center for Radioisotope and Radiopharmaceutical Technology (CRRT)-BATAN has developed a reagent of TSH IRMA kit. The aim of this research is to compare between local TSH IRMA kit (CRRT-BATAN) and imported TSH IRMA kit (Riakey, Korea) toward 110 adult samples obtained from PTKMR - BATAN. The results showed 97 samples as true negative, 5 samples as true positive, 1 sample as false negative and 7 samples false positive. The comparison study gave diagnostic sensitivity as much as 83.33 %, diagnostic spesificity as much as 93.27 % and accuracy as much as 92.72 %.</p>

scholarly journals Multiple Compounds Recognition from The Tandem Mass Spectral Data Using Convolutional Neural Network

Molecules ◽  
2019 ◽  
Vol 24 (24) ◽  
pp. 4590
Author(s):  
Jiali Lv ◽  
Jian Wei ◽  
Zhenyu Wang ◽  
Jin Cao
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Spectral Data ◽  
Test Data ◽  
False Positive ◽  
Tandem Mass ◽  
True Positive ◽  
Mass Spectral Data ◽  
True Negative ◽  
Mass Spectral

Mixtures analysis can provide more information than individual components. It is important to detect the different compounds in the real complex samples. However, mixtures are often disturbed by impurities and noise to influence the accuracy. Purification and denoising will cost a lot of algorithm time. In this paper, we propose a model based on convolutional neural network (CNN) which can analyze the chemical peak information in the tandem mass spectrometry (MS/MS) data. Compared with traditional analyzing methods, CNN can reduce steps in data preprocessing. This model can extract features of different compounds and classify multi-label mass spectral data. When dealing with MS data of mixtures based on the Human Metabolome Database (HMDB), the accuracy can reach at 98%. In 600 MS test data, 451 MS data were fully detected (true positive), 142 MS data were partially found (false positive), and 7 MS data were falsely predicted (true negative). In comparison, the number of true positive test data for support vector machine (SVM) with principal component analysis (PCA), deep neural network (DNN), long short-term memory (LSTM), and XGBoost respectively are 282, 293, 270, and 402; the number of false positive test data for four models are 318, 284, 198, and 168; the number of true negative test data for four models are 0, 23, 7, 132, and 30. Compared with the model proposed in other literature, the accuracy and model performance of CNN improved considerably by separating the different compounds independent MS/MS data through three-channel architecture input. By inputting MS data from different instruments, adding more offset MS data will make CNN models have stronger universality in the future.

scholarly journals Discordance between fine-needle aspiration cytology and histopathology in patients with mucoepidermoid carcinoma of parotid gland

2020 ◽  
Vol 102 (5) ◽  
pp. 340-342
Author(s):  
H Iftikhar ◽  
M Sohail Awan ◽  
M Usman ◽  
A Khoja ◽  
W Khan
Keyword(s):  
Fine Needle Aspiration ◽  
Fine Needle Aspiration Cytology ◽  
Mucoepidermoid Carcinoma ◽  
False Negative ◽  
Needle Aspiration ◽  
True Positive ◽  
Aspiration Cytology ◽  
True Negative ◽  
Fine Needle ◽  
Needle Aspiration Cytology

Introduction Fine-needle aspiration cytology (FNAC) is an important diagnostic tool used preoperatively for the diagnosis of parotid lump. Mucoepidermoid carcinoma comprises 5–10% of all salivary gland tumours. It poses a diagnostic challenge on FNAC with high false negative rate. The objective of this study was to evaluate the discordance between cytology/FNAC and histopathology in patients with mucoepidermoid carcinoma. Material and methods A cross-sectional study was conducted from 1 January 2010 to 31 December 2014. Patients aged 18 years and above with FNAC or histopathology suggestive of mucoepidermoid carcinoma were identified. FNAC when compared with histology (gold standard) was classified into true positive (presence of mucoepidermoid carcinoma correctly diagnosed on FNAC), true negative (absence of mucoepidermoid carcinoma correctly diagnosed on FNAC), false positive (FNAC incorrectly diagnosed mucoepidermoid carcinoma), false negative (FNAC failed to diagnose mucoepidermoid carcinoma). Results A total of 16 patients fulfilled our eligibility criteria. Seven cytological samples were true positive (ie correctly diagnosed mucoepidermoid carcinoma by FNAC), eight cytological specimens were false negative (ie could not pick up mucoepidermoid carcinoma on FNAC). One case was false positive on cytology (ie diagnosed mucoepidermoid carcinoma on FNAC but was reported to be Warthin’s tumour on histopathology) and none were true negative. Conclusion FNAC is not reliable for diagnosis of mucoepidermoid carcinoma. More than 50% of our patients had discordant results between cytology and histology. We recommend a high index of suspicion for mucoepidermoid carcinoma given the poor yield of cytology.

Serum Levels of Carcinoembryonic Antigen, Gastrointestinal Cancer-Associated Antigen and Alphafetoprotein in Staging and Management of Patients with Advanced Carcinoma of the Stomach

1987 ◽  
Vol 2 (1) ◽  
pp. 19-24 ◽  
Author(s):  
Janusz J. Szymendera ◽  
Andrzej W. Szawlowski ◽  
Marek P. Nowacki ◽  
Malgorzata Kowalska ◽  
Janina A. Kaminska ◽  
...  
Keyword(s):  
Carcinoembryonic Antigen ◽  
Gastrointestinal Cancer ◽  
False Negative ◽  
Serum Levels ◽  
True Positive ◽  
True Negative ◽  
Carcinoma Of The Stomach ◽  
Joint Application ◽  
Serum Cea

Serum levels of carcinoembryonic antigen (CEA), gastrointestinal cancer-associated antigen (GICA or CA 19-9), and alphafetoprotein (AFP) were concurrently determined in patients with carcinoma of the stomach: in 84 preoperatively, and in 67 serially postoperatively. Before surgery, serum CEA gave information about the tumor load analogous to serum GICA in 69% of the patients: true-positive in 25% and false-negative in 43%; less information in 18% and more in 14%. The sensitivity of the test tended to be better in the more advanced stages, and was higher for CEA with GICA than for CEA alone or GICA alone. During follow-up, serum CEA gave information about the presence or absence of active disease analogous to serum GIC A in 78% of the patients: true-positive in 30%, true-negative in 36% and false-negative in 12%; less information in 9% and more in 13%. Neither test gave any false-positive indications. Sensitivity of the test rose from 67% for CEA alone and 60% for GICA alone to 81% for CEA with GICA. Serum AFP was elevated only preoperatively in 2% of patients. We conclude that joint application of CEA and GICA tests gave only slightly better preoperative sensitivity than CEA alone or GICA alone but proved fairly sensitive for postoperative follow-up of the patients. AFP was of little value for either purpose.

scholarly journals Fluoroscopy Guided Percutaneous Transpedicular Biopsy for Thoracic and Lumbar Vertebral Body Lesion: Technique and Safety in 23 Consecutive Cases

2017 ◽  
Vol 13 (3) ◽  
pp. 256-260
Author(s):  
D. Shrestha ◽  
R. Shrestha ◽  
D Dhoju
Keyword(s):  
Vertebral Body ◽  
False Negative ◽  
Invasive Technique ◽  
Safe Procedure ◽  
Microbiological Diagnosis ◽  
True Positive ◽  
True Negative ◽  
Lumbar Vertebral Body ◽  
Vertebral Biopsy ◽  
Fluoroscopy Guidance

Background Though some vertebral lesions have typical imaging findings, histological/ microbiological evidence are required for definitive diagnosis and management, specially for tumor and infective lesions so that wrong diagnosis and wrong treatment can be avoided. Conventionally, open biopsy methods are used. With availability of CT scan, MRI, percutaneous transpedicular vertebral biopsy has now become popular as a minimally invasive technique for biopsy of vertebral lesion.Objective To describes technique and to analyzes safety and feasibility of percutaneous transpedicular vertebral biopsy with fluoroscopy guidance for thoracic and lumbar vertebral body lesions.Method Twenty three patients who underwent percutaneous transpedicular vertebral biopsy under fluoroscopy guidance were retrospectively evaluated for demographic data, indication for biopsy, anatomical locations, histological/microbiological diagnosis, complications and final outcome of treatment. True positive, true negative, false positive and false negative cases were defined.Result There were 17 males and 6 female patients of mean age 47 (range 22-73 years). Biopsies were performed in 17 dorsal and six lumbar vertebral bodies. Adequate sample were obtained in all cases. Seventeen patients (12: tubercular pathology, 1: primary tumor, 3: metastasis, 1: osteoporotic fracture) had definitive histological/ microbiological diagnosis. Four patients had no granuloma and tumor. Two had histological features of chronic non specific inflammation. True positive cases were 17, true negative were four and false negative case were two. Overall accuracy was 92%. One patient developed small hematoma at biopsy site.Conclusion Fluoroscopy guided percutaneous transpedicular biopsy of is a safe procedure with high adequacy and accuracy and low complication rate for thoracic and lumbar vertebral body lesion.

Parotid Tumors: Fine-Needle Aspiration and/or Frozen Section

2008 ◽  
Vol 139 (2_suppl) ◽  
pp. P42-P43
Author(s):  
Peter Zbaren ◽  
Heinz Loosli ◽  
Edouard Stauffer
Keyword(s):  
Sensitivity And Specificity ◽  
Fine Needle Aspiration ◽  
False Positive ◽  
Frozen Section ◽  
False Negative ◽  
Needle Aspiration ◽  
True Positive ◽  
True Negative ◽  
Fine Needle ◽  
Parotid Neoplasms

Objective Assess the difficulties of preoperative and intraoperative tumor typing of parotid neoplasms. Know the advantages and pitfalls of fine-needle-aspiration cytology (FNAC) and frozen section (FS) analysis in primary parotid neoplasms. Methods In 113 parotid neoplasms (70 malignancies and 43 benign tumors) preoperative FNAC as well as intraoperative FS analysis were performed. FNAC and FS findings were analyzed and compared with the final histopathologic diagnosis. Results The FNAC smear was non-diagnostic in 6 tumors. In 2 FS specimens, it was not possible to determine the tumor dignity. FNAC findings and FS findings were both available in 105 neoplasMS The FNAC findings were true positive for malignancy in 54, true negative in 36, false positive in 4, and false negative in 11 tumors. The accuracy, sensitivity, and specificity were 86%, 83%, and 90% respectively. The FS findings were true positive in 60, true negative in 38, false positive in 2, and false negative in 5 tumors. The accuracy, sensitivity, and specificity were 93%, 92% and 95% respectively. The exact histologic tumor typing by FNAC was correct, false or not mentioned in 58%, 20% and 22% true positive or true negative evaluated tumors, and by FS in 83%, 5% and 12% true positive or true negative evaluated tumors. Conclusions The current analysis showed a superiority of FS compared with FNAC regarding the diagnosis of malignancy and especially of tumor typing. FNAC alone is not prone in many cases to determine the surgical management of primary parotid carcinomas.

scholarly journals Comparison of Various Classification Techniques for Prediction of the Agriculture Production Based on Different Parameters Rainfall, Temperature

2021 ◽  
Vol 23 (04) ◽  
pp. 356-372
Author(s):  
Manpreet Kaur ◽  
◽  
Dr. Dinesh Kumar ◽  
Keyword(s):  
Naive Bayes ◽  
Confusion Matrix ◽  
Big Data Analysis ◽  
Naïve Bayes ◽  
The Other ◽  
Machine Learning Techniques ◽  
True Positive ◽  
True Negative ◽  
Classification Techniques ◽  
Learning Techniques

The classification techniques based on various machine learning techniques are having use for the Big data analysis. This will be useful in identifying the classification and then finally the prediction which will be useful for the decision managers for having quality decisions. There are various types of supervised and unsupervised learning techniques which are having capabilities in the terms of driving the analysis. This analysis will be useful for having identification of relationship between the various attributes which is required to device the analysis. There are various supervised learning techniques which are useful to drive the analysis. These techniques are SVM, Logistic regression, KNN, Naïve Bayes, Tree, Neural network. The relative comparison of this technique is done in the terms of various parameters for example AUC, CA, F1, Recall and precision. The accuracy in the terms of AUC, CA is highest for the Naïve Bayes. This shows the Naïve Bayes is having higher true positives, true negative ratio. The proposed technique is having higher accuracy of 81% which is far above than all the remaining techniques. The confusion matrix for the Naïve Bayes is having true positive count as 729, true negative at 103. This shows that the true positive and true negative count is far above for this technique compared to the other techniques.

scholarly journals SPK Penentuan Lokasi ATM Menggunakan Metode AHP dan SAW

2019 ◽  
Vol 5 (1) ◽  
pp. 49-56
Author(s):  
Gede Surya Mahendra ◽  
Kadek Yota Ernanda Aryanto
Keyword(s):  
False Positive ◽  
Confusion Matrix ◽  
False Negative ◽  
True Positive ◽  
True Negative

Persaingan industri perbankan saat ini semakin meningkat, baik dalam hal penyediaan inovasi produk serta peningkatan kualitas transaksi dan pelayanan. Untuk mengatasi masalah tersebut diciptakan sebuah terminal yang dikenal dengan ATM. Namun fungsionalitas dan efektifitas ATM tersebut belum memenuhi kebutuhan nasabah dikarenakan pengambilan keputusan penentuan lokasi ATM belum menggunakan SPK sehingga banyak kriteria yang terlupakan dalam penentuan lokasi ATM terbaik. Metode AHP yang merupakan sebuah hierarki fungsional dengan input utamanya adalah persepsi manusia sedangkan metode SAW dengan konsep dasar mencari penjumlahan terbobot dari rating kinerja pada setiap alternatif pada semua atribut. AHP digunakan untuk memberikan pembobotan pada masing-masing kriteria dan SAW untuk melakukan perangkingan dari masing-masing alternatif. Terdapat 7 kriteria dengan 11 sub kriteria pada pembobotan dan 76 data alternatif. Pengujian dilakukan dengan membandingkan hasil delpoyment ATM dengan hasil perhitungan sistem. Dari 76 data alternatif yang diujikan, terdapat 38 lokasi deployment ATM. Dari hasil pengujian yang ditampilkan dalam confusion matrix, pada kriteria yang tidak teruji signifikansi didapatkan 33 data True Positive, 38 True Negative, 5 False Negative dan 5 False Positive dengan akurasi sebesar 86,84%, dan pada kriteria yang teruji signifikansi didapatkan 35 data True Positive, 35 True Negative, 3 False Negative dan 3 False Positive memiliki akurasi 92,11%.

Sign in / Sign up

Export Citation Format

Share Document