Improving Naïve Bayes performance in single image pap smear using weighted principal component analysis (WPCA)

Dewi, Yumi Novita; Riana, Dwiza; Mantoro, Teddy

doi:10.1109/ced.2017.8308130

Cited by 14 publications

(13 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…With this method, solutions are found that are almost unintelligible to the errors that arise due to the effects of interference. Obviously, with increasing k this rule goes over to the Bayes' rule [19].…”

Section: Let the Given Imagementioning

confidence: 99%

See 1 more Smart Citation

Обробка Інформації Оптичним Датчиком Робота За Умови Неповної Вхідної Інформації

Parkhomey

Batrak

Tsopa

et al. 2019

«Адаптивні Системи Автоматичного Управління Міжвідомчий науково

View full text Add to dashboard Cite

The range of tasks, solved by the properties of classification and generalization, is quite broad. However, the quality of solving to the problem, for one reason or another, is not always the same. Some tasks cannot be solved at once, but a detailed study of phenomenon allows us to make the necessary classification. For instance, the task is to divide the objects, with the same geometric dimensions and objects, by visual observation into two classes. Moreover, the part is madeof steel, and another one -of gypsum. In principle, such task cannot be solved.To classify these subjects, a more detailed study of them is required. It is sufficiently to get data on the weight of objects, so that the task of classification has become trivial. The difficulty is to find such a description of phenomenon, in which the image (phenomenon), within each class, would have defined similar properties. Therefore, in order to eliminate the effect of interference on the recognition process, it is proposed to introduce a special decisive rule based on the fact that the decision to attach the image to the image is made on the basis of an analysis of images that have fallen into a definite close space that is classified.

show abstract

Section: Let the Given Imagementioning

confidence: 99%

“…Fig. 2 shows the qualitative dependences of the probability of error from the noise level [16], [17], [18], [19], [20]. In the event that the decision rule will be optimal for each noise level, then the error probability increases with increasing noise and reaches the limit at the value of 0.5 (dotted curve).…”

Section: Let the Given Imagementioning

confidence: 99%

Обробка Інформації Оптичним Датчиком Робота За Умови Неповної Вхідної Інформації

Parkhomey

Batrak

Tsopa

et al. 2019

«Адаптивні Системи Автоматичного Управління Міжвідомчий науково

View full text Add to dashboard Cite

show abstract

“…In this case, the optimal solution, obtained during the learning process, will no longer be optimal for the recognition process, and hence the probability of error increases. Figure 2 shows the qualitative dependences of the probability of error from the noise level [25]- [29]. In the event that the decision rule will be optimal for each noise level, then the error probability increases with increasing noise and reaches the limit at the value of 0.5 (dotted curve).…”

Section: Let the Given Imagementioning

confidence: 99%

Section: Let the Given Imagementioning

confidence: 99%

Identification information sensors of robot systems

Parkhomey

Boiko

Eromenko

2019

IJEECS

View full text Add to dashboard Cite

At the present time, the complexity of identification is to find such a description, in which the image (information) of each class would have identified similar properties. The task is to make the transformed description includes the whole set of input images, united by the similarity class by the given ratio.Using the ordinates of an autocorrelation function is an inseparable shift in the center of gravity of an image, which leads to a change of such description.Nicest, the concept of an invariant description of information arises, this is an autocorrelation function, which is invariant to the description of any displacements of the image in the vertical and horizontal directions.The problem of finding an optimal decision rule arises, which, in a number of cases, can be constructed on the basis of a method, based on the definition of the maximum incomplete coefficient of similarity.Using this method, the solutions, that are almost unintelligible to the errors that arise due to the effects of interference, are found. Therefore, in increments k, this rule passes into the Bayes’ rule.

show abstract

“…Untuk pengklasifikasian dengan dataset sel citra tunggal Pap Smear, perlu adanya model algoritma Sample Bootstrapping, dimana telah diketahui bahwa dataset sel citra tunggal Pap Smear dikategorikan dalam dataset dengan dimensi skala besar, dan perlu adanya teknik untuk mengurangi jumlah data training untuk diproses dan mengurangi atribut sehingga mampu meningkatkan akurasi [3]. Metode Sample Bootstrapping digunakan untuk mengurangi jumlah data training yang akan diproses [4] (Olive DJ, 2017). Untuk dapat mengatasi persoalan dengan dataset dengan dimensi besar, maka perlu perlu adanya sampel data (sampling) secara acak agar data yang akan diproses menjadi lebih kecil [5] Kondisi normal akan berubah ketika terdapat sel-sel pra-kanker pada leher rahim atau yang disebut dengan sel-sel dysplastic, informasi genetis dari sel-sel tersebut akan berubah, sehingga sel-sel tersebut tidak lagi terbagi ke dalam lapisan-lapisan perkembangan seperti seharusnya [5].…”

Section: Pendahuluanunclassified

Metode Sample Bootstrapping Untuk Meningkatkan Performa Algoritma Naive Bayes Pada Citra Tunggal Pap Smear

Dewi¹,

Sariasih²

2019

J. Teknik Informatika

Self Cite

View full text Add to dashboard Cite

Research on cell classification of single pap smear images is an interesting thing to discuss, where the value of consent is very important to determine whether the cells are normal or not. An example of this study is to determine whether using the bootstraping sample method can improve the performance of the Bayes naive algorithm to classify single pap smear images that are on the herlev dataset. Approval values will be given for two classes and seven classes. The method used consists of several stages, namely preprocessing, knowledge rules, evaluation, and performance reports. The results of this study prove that the bootstrap sample method can increase the accuracy of seven classes to 85.24% and 93.24% for accuracy values with two classes.Keywords: Sample Bootstrapping; Naive Bayes; Pap Smear. ABSTRAK Penelitian mengenai klasifikasi sel citra tunggal pap smear menjadi hal yang menarik untuk dibahas, dimana nilai akurasi tersebut sangat penting untuk menetukan apakah sel-sel tersebut normal atau tidak. Penelitian ini bertujuan untuk menentukan apakah penggunaan metode sample bootstrapping dapat meningkatkan kinerja algoritma naive bayes untuk mengklasifikasikan citra tunggal pap smear yang ada pada dataset herlev. Nilai akurasi akan diperiksa untuk dua kelas dan tujuh kelas. Metode yang digunakan terdiri dari beberapa tahapan yaitu preprocessing, knowledge rule, evaluation, dan performance report. Hasil penelitian ini menunjukkan bahwa metode sample bootstrapping dapat meningkatkan nilai akurasi tujuh kelas menjadi 85,24% dan 93,24% untuk nilai akurasi dengan dua kelas.

show abstract

Improving Naïve Bayes performance in single image pap smear using weighted principal component analysis (WPCA)

Cited by 14 publications

References 6 publications

Обробка Інформації Оптичним Датчиком Робота За Умови Неповної Вхідної Інформації

Обробка Інформації Оптичним Датчиком Робота За Умови Неповної Вхідної Інформації

Identification information sensors of robot systems

Metode Sample Bootstrapping Untuk Meningkatkan Performa Algoritma Naive Bayes Pada Citra Tunggal Pap Smear

Contact Info

Product

Resources

About