BazTech - Yadda

1

Grey Wolf optimization based breast cancer detection using 1D Convolution LSTM classifier

Jebarani Esther P., Umadevi N.

Przegląd Elektrotechniczny

|

2023

|

R. 99, nr 1

1--9

EN

Women are particularly vulnerable to breast cancer. Breast cancer diagnosis has benefited greatly from the utilization of ultrasound imaging. Breast UltraSound (BUS) image segmentation remains a difficult challenge due to low image quality. Furthermore, BUS image segmentation, as well as classification, is an important stage in the analysis process. Initially, the image associated with breast cancer is gathered from MIAS database. The gathered image undergoes pre-processing operation using the adaptive median filtering technique. Subsequently, the segmentation is performed in the pre-processed images using the hybrid method consisting of GMM and K-Means. These segmented images undergo the feature extraction steps further where the features are extracted by utilizing the Gray Level Co-occurrence Matrix (GLCM). Grey Wolf Optimization (GWO) selects the optimal features for further classification using a novel 1D Convolution LSTM. Here, the pooling layer of 1D CNN is replaced by the LSTM. The objective function behind the optimal feature selection and classification is the accuracy maximization. Finally, the novel One Dimensional Convolution Long Short Term Memory (1 DCLSTM) classifies the outcome into normal, benign, and malignant, respectively. The proposed method is compared with the other state of art methods related to this research.

PL

Kobiety są szczególnie narażone na raka piersi. Diagnostyka raka piersi bardzo skorzystała na wykorzystaniu obrazowania ultrasonograficznego. Segmentacja obrazu UltraSound (BUS) piersi pozostaje trudnym wyzwaniem ze względu na niską jakość obrazu. Ponadto segmentacja obrazu BUS, a także klasyfikacja, jest ważnym etapem procesu analizy. Początkowo obraz związany z rakiem piersi pozyskiwany jest z bazy MIAS. Zgromadzony obraz jest poddawany wstępnemu przetwarzaniu przy użyciu techniki adaptacyjnego filtrowania medianowego. Następnie na wstępnie przetworzonych obrazach przeprowadzana jest segmentacja metodą hybrydową składającą się z GMM i K-Means. Te podzielone na segmenty obrazy przechodzą kolejne etapy ekstrakcji cech, w których cechy są wyodrębniane przy użyciu macierzy współwystępowania poziomu szarości (GLCM). Optymalizacja Gray Wolf (GWO) wybiera optymalne funkcje do dalszej klasyfikacji przy użyciu nowatorskiego rozwiązania 1D Convolution LSTM. W tym przypadku warstwa łączenia 1D CNN zostaje zastąpiona przez LSTM. Funkcją celu stojącą za optymalnym doborem i klasyfikacją cech jest maksymalizacja dokładności. Wreszcie, powieść jednowymiarowa pamięć krótkoterminowa z konwolucją jednowymiarową (1 DCLSTM) klasyfikuje wynik odpowiednio na normalny, łagodny i złośliwy. Proponowana metoda jest porównywana z innymi nowoczesnymi metodami związanymi z tymi badaniami.

2

Capsule network assisted electrocardiogram classification model for smart healthcare

Jiao Ying, Qi Huamei, Wu Jia

Biocybernetics and Biomedical Engineering

|

2022

|

Vol. 42, no. 2

543--555

EN

Improving the classification accuracy of electrocardiogram (ECG) signals is of great significance for diagnosing heart abnormalities and arrhythmias and preventing cardiovascular diseases (CVDs). The traditional classification method depends on medical experience to select and extract features artificially, lacks the generalization ability to deal with big medical data. The vital feature extraction ability of neural networks has become a hot topic to solve this problem. Based on this, the capsule network is applied to ECG signal classification in this paper. Based on the original network architecture, long short-term memory (LSTM) network and 1D convolutional neural network (CNN) are added as a parallel feature extraction layer to extract the spatial and temporal features of the ECG signal. In addition, the enhanced routing algorithm is proposed, which uses the prior probability of subcapsules as a weighting factor for routing algorithm classification to weaken the influence of noise capsules. The proposed model is superior to the existing state-of-the-art techniques when tested on the MIT-BIH arrhythmia database.

3

Sequence-to-sequence deep neural network with spatio-spectro and temporal features for motor imagery classification

Rammy Sadaqat Ali, Abbas Waseem, Mahmood Syed Shahid, Riaz Haider, Rehman Haseeb Ur, Abideen Rao Zain Ul, Aqeel Muhammad, Zhang Wu

Biocybernetics and Biomedical Engineering

|

2021

|

Vol. 41, no. 1

97--110

EN

Electroencephalography (EEG) is a method of the brain–computer interface (BCI) that measures brain activities. EEG is a method of (non-)invasive recording ofthe electrical activity ofthe brain. This can be used to build BCIs. From the last decade, EEG has grasped researchers' attention to distinguish human activities. However, temporal information has rarely been retained to incorporate temporal information for multi-class (more than two classes) motor imagery classification. This research proposes a long-short-term-memory-based deep learning model to learn the hidden sequential patterns. Two types of features are used to feed the proposed model, including Fourier Transform Energy Maps (FTEMs) and Common Spatial Patterns (CSPs) filters. Multiple experiments have been conducted on a publicly available dataset. Extraction of spatial and spectro-temporal features using CSP filters and FTEM allow the sequence-tosequence based proposed model to learn the hidden sequential features. The proposed method is trained, evaluated, and optimized for a publicly available benchmark data set and resulted in 0.81 mean kappa value. Obtained results depict the model robustness for the artifacts and suitable for real-life applications with comparable classification accuracy. The code and findings will be available at https://github.com/waseemabbaas/Motor-Imagery-Classification.git.

4

Blood glucose prediction with deep neural networks using weighted decision level fusion

Dudukcu Hatice Vildan, Taskiran Murat, Yildirim Tulay

Biocybernetics and Biomedical Engineering

|

2021

|

Vol. 41, no. 3

1208--1223

EN

Background and Objective: Diabetes mellitus is a chronic disease that requires regular monitoring of blood glucose in the circulatory system. If the amount of glucose in the blood is not regulated constantly, this may have vital consequences for the individual. For this reason, there are many studies in the literature that perform blood glucose (BG) prediction. Methods: Blood glucose prediction is generally performed by using many parameters. In this paper, it was attempted to predict the future blood glucose values of the patient by using only the blood glucose values of diabetes patients’ history. For this purpose, Long short term memory (LSTM), WaveNet and Gated Recurrent Units (GRU) and decision-level combinations of these architectures were used to predict blood glucose. First of all, hyper-parameters were selected for the most efficient operation of these network architectures and experimental studies were conducted using the extended OhioT1DM data set which has blood glucose history of 12 diabetes patients. Results: Experimental studies using 30, 45 and 60 min prediction horizon (PH), the average lowest RMSE value were obtained by the fusion of three networks as 21.90 mg/dl, 29.12 mg/dl, 35.10 mg/dl respectively. Conclusions: When the obtained RMSE value compared to state-of-art studies in the literature, the results show that the proposed method is quite successful for short-term blood glucose prediction. In addition, the proposed fusion method gives a new perspective for future studies in the literature for BG prediction.

5

An analysis of the effect between the heat index and Long Short-Term Memory model to electricity load forecasting

Anh Nguyen Thi Ngoc, Hoang Vu Viet, Chau Do Thi Thanh, Linh Bui Duy, Huy Nguyen Duc

Annals of Computer Science and Information Systems

|

2021

|

Vol. 27

1--6

EN

Accurate electricity load forecasting is essential for operating electrical systems. Most of the studies on electricity load forecasting are based on electricity load data or weather data, which is air temperature, but there are not consider the heat index. This paper proposes a short-term electricity load forecasting model using Long-Short Term Memory (LSTM) based on electricity load history and heat index data. In addition, the proposed model is applied to the data of IEVN NLDC (National Load Dispatching Center) in forecasting electricity load before 48 hours. This model is used to predict the electricity load of the Vietnamese nation and the power corporations of Vietnam. For a fair comparison, the LSTM network has fixed parameters, then compared the results when using temperature and the heat index. According to experimental results based on the Mean absolute percentage errors (MAPE) assessment, the proposed model has better accuracy than the model based on electricity load history and temperature.

6

The use of LSTM networks in the detection of outliers in IoTbased air quality monitoring systems

Rymarczyk Tomasz, Cieplak Tomasz, Kłosowski Grzegorz, Kozłowski Edward

Przegląd Elektrotechniczny

|

2020

|

R. 96, nr 5

91--94

EN

Recently, several attempts have been made to build social air quality monitoring systems. Systems of this kind are solutions in the creation of which it is necessary to solve many problems concerned with the collection and analysis of data. After all, such systems are complex, extensive and multidisciplinary IT solutions. Our work focuses on creating such a system which, in addition to being a distributed social system, additionally uses low-budget and available measuring devices. The system consists of the data acquisition subsystem, then the data collection and analysis subsystem, and the communication system with the end user. In this article, we focus on describing data acquisition subsystems and on one aspect related to data analysis, namely outliers prediction using recurrent neural networks in the form of their implementation as LSTM.

PL

W okresie kilku ostatnich kilku miesięcy podjęto działania budowy społecznościowych systemów monitorowania jakości powietrza. Systemy tego rodzaju są rozwiązaniami, przy tworzeniu których konieczne jest rozwiązanie różnorodnych problemów związanych z gromadzeniem i analizą danych. Systemy tego rodzaju to złożone, rozbudowane i multidyscyplinarne rozwiązania informatyczne. Opisywana praca koncentruje się na działaniach związanych z stworzeniem takiego systemu, który oprócz tego, że jest rozproszonym systemem społecznościowym, dodatkowo wykorzystuje niskobudżetowe i ogólnie dostępne urządzenia pomiarowe. System składa się z podsystemu gromadzenia danych, następnie podsystemu gromadzenia i analizy danych oraz systemu komunikacji z użytkownikiem końcowym. W tym artykule skupiamy się na opisie podsystemów akwizycji danych oraz na wybranym zagadnieniu związanym z analizą danych, a mianowicie przewidywaniu wartości odstających z wykorzystaniem rekurencyjnych sieci neuronowych w postaci ich implementacji jako sieci LSTM.

7

A segment-wise reconstruction method based on bidirectional long short term memory for Power Line Interference suppression

Qiu Y., Huang K., Xiao F., Shen H.

Biocybernetics and Biomedical Engineering

|

2018

|

Vol. 38, no. 2

217--227

EN

The overlap between the signal components of Power Line Interference (PLI) and biomedical signals in the frequency domain makes the filtered results prone to severe distortion. Electrocardiogram (ECG) is a type of biomedical electronic signal used for cardiac diagnosis. The objective of this work is to suppress the PLI components from biomedical signals with minimal distortion, and the object of study is mainly the ECG signals. In this study, we propose a novel segment-wise reconstruction method to suppress the PLI in biomedical signals based on the Bidirectional Recurrent Neural Networks with Long Short Term Memory (Bi-LSTM). Experiments are conducted on both synthetic and real signals, and quantitative comparisons are made with a traditional IIR notch filter and two state-of-the-art methods in the literature. The results show that by our method, the output Signal-to-Noise Ratio (SNR) is improved by more than 7 dB and the settling time for step response is reduced to 0.09 s on average. The results also demonstrate that our method has enough generalization ability for unforeseen signals without retraining.