IoT Application of Transfer Learning in Hybrid Artificial Intelligence Systems for Acute Lymphoblastic Leukemia Classification

Pałczyński, Krzysztof; Śmigiel, Sandra; Gackowska, Marta; Ledziński, Damian; Bujnowski, Sławomir; Lutowski, Zbigniew

doi:10.3390/s21238025

Cited by 17 publications

(7 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This work is a continuation of the research described in [ 35 ] (Pałczyński et al). This article aims to establish the informativeness of a lymphocyte’s surroundings for leukemia classification.…”

Section: Introductionmentioning

confidence: 64%

“…A comparison of the most promising models obtained in this research with other works is presented in Table 5 . The results were compared against the outcomes of our previous work and work of Rodrigues et al [ 33 , 35 ], which according to our literature review obtained the best results on the ALL-IDB2 dataset.…”

Section: Resultsmentioning

confidence: 97%

“…In our previous work [ 35 ], the best combination of artificial neural networks for raw image encoding, classification heads, and image augmentation resulted in an average classification quality of 94.8%. The neural network used for this task was MobileNet v2, the state-of-the-art neural network for numerous image-processing tasks containing 3.4 million parameters.…”

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Entropy Measurements for Leukocytes’ Surrounding Informativeness Evaluation for Acute Lymphoblastic Leukemia Classification

Pałczyński

Ledziński

Andrysiak

2022

Entropy

View full text Add to dashboard Cite

The study of leukemia classification using deep learning techniques has been conducted by multiple research teams worldwide. Although deep convolutional neural networks achieved high quality of sick vs. healthy patient discrimination, their inherent lack of human interpretability of the decision-making process hinders the adoption of deep learning techniques in medicine. Research involving deep learning proved that distinguishing between healthy and sick patients using microscopic images of lymphocytes is possible. However, it could not provide information on the intermediate steps in the diagnosis process. As a result, despite numerous examinations, it is still unclear whether the lymphocyte is the only object in the microscopic picture containing leukemia-related information or if the leukocyte’s surroundings also contain the desired information. In this work, entropy measures and machine learning models were applied to study the informativeness of both whole images and lymphocytes’ surroundings alone for Leukemia classification. This work aims to provide human-interpretable features marking the probability of sickness occurrence. The research stated that the hue distribution of images with lymphocytes obfuscated alone is informative enough to facilitate 93.0% accuracy in healthy vs. sick classification. The research was conducted on the ALL-IDB2 dataset.

show abstract

Section: Introductionmentioning

confidence: 64%

Section: Resultsmentioning

confidence: 97%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Entropy Measurements for Leukocytes’ Surrounding Informativeness Evaluation for Acute Lymphoblastic Leukemia Classification

Pałczyński

Ledziński

Andrysiak

2022

Entropy

View full text Add to dashboard Cite

show abstract

“…Models were evaluated using the metrics described below [45]. For simplicity of equations, specific acronyms have been created: TP-True Positive, TN-True Negative, FP-False Positive, and FN-False Negative.…”

Section: Metricsmentioning

confidence: 99%

ECG Classification Using Orthogonal Matching Pursuit and Machine Learning

Śmigiel

2022

Sensors

Self Cite

View full text Add to dashboard Cite

Health monitoring and related technologies are a rapidly growing area of research. To date, the electrocardiogram (ECG) remains a popular measurement tool in the evaluation and diagnosis of heart disease. The number of solutions involving ECG signal monitoring systems is growing exponentially in the literature. In this article, underestimated Orthogonal Matching Pursuit (OMP) algorithms are used, demonstrating the significant effect of concise representation parameters on improving the performance of the classification process. Cardiovascular disease classification models based on classical Machine Learning classifiers were defined and investigated. The study was undertaken on the recently published PTB-XL database, whose ECG signals were previously subjected to detailed analysis. The classification was realized for class 2, class 5, and class 15 cardiac diseases. A new method of detecting R-waves and, based on them, determining the location of QRS complexes was presented. Novel aggregation methods of ECG signal fragments containing QRS segments, necessary for tests for classical classifiers, were developed. As a result, it was proved that ECG signal subjected to algorithms of R wave detection, QRS complexes extraction, and resampling performs very well in classification using Decision Trees. The reason can be found in structuring the signal due to the actions mentioned above. The implementation of classification issues achieved the highest Accuracy of 90.4% in recognition of 2 classes, as compared to less than 78% for 5 classes and 71% for 15 classes.

show abstract

“…Wireless communications and networks became very important in our daily life services and applications including mobile, satellite, radar, sonar, and recent wireless networks such as the Internet-of-Things (IoT) and medical networks [1][2][3][4][5][6]. Therefore, it is essential to improve the performance of wireless communications, which requires enabling technologies and techniques to accommodate the large number of users and devices both in the current fifth generation (5G) and beyond systems and networks as well.…”

Section: Introduction 1background and Motivationsmentioning

confidence: 99%

Optimum Extrapolation Techniques for Two-Dimensional Antenna Array Tapered Beamforming

Albagory

Alraddady

2022

Electronics

View full text Add to dashboard Cite

Optimizing antenna arrays is essential for achieving efficient beamforming with very low sidelobe level (SLL) where adopting tapered window functions is one of the straightforward efficient techniques for achieving this goal. Recently, two-dimensional (2D) beamforming has been extensively required for many applications; therefore, this paper proposes two extrapolation techniques applied to one-dimensional (1D) tapered functions to efficiently feed 2D antenna arrays using cross-linear and adaptive radial tapering techniques. The first proposed 2D cross-linear tapering technique determines the 2D tapering coefficients by Hadamard multiplication of two right-angled grids of repeated 1D functions, while the second proposed adaptive radial tapering technique locates the antenna element in the 2D array in terms of its radial distance with respect to the array center, then converts this distance to an element index in a virtual 1D tapering window to determine the element weighting value. The adaptive radial tapering technique is optimized for achieving the minimum SLLs. The two proposed techniques are analyzed and discussed, where it is found that the adaptive radial tapering provides deeper SLLs compared to the cross-linear tapering technique. The two extrapolation techniques are examined for four window functions including triangular (Bartlett), Hamming, cosine-square, and Blackman windows, and the simulation results show that for extrapolating the Blackman window using adaptive radial tapering, a –50 dB SLL can be achieved which is independent on the array size, while cross-linear tapering provides –35 dB and –41 dB SLLs for and antenna arrays, respectively.

show abstract

IoT Application of Transfer Learning in Hybrid Artificial Intelligence Systems for Acute Lymphoblastic Leukemia Classification

Cited by 17 publications

References 29 publications

Entropy Measurements for Leukocytes’ Surrounding Informativeness Evaluation for Acute Lymphoblastic Leukemia Classification

Entropy Measurements for Leukocytes’ Surrounding Informativeness Evaluation for Acute Lymphoblastic Leukemia Classification

ECG Classification Using Orthogonal Matching Pursuit and Machine Learning

Optimum Extrapolation Techniques for Two-Dimensional Antenna Array Tapered Beamforming

Contact Info

Product

Resources

About