Wyniki wyszukiwania - BazTech

1

Histopathology image classification using hybrid parallel structured DEEP-CNN models

Dsouza Kevin Joy, Ansari Zahid Ahmed

Applied Computer Science

|

2022

|

Vol. 18, no 1

20--36

EN

The healthcare industry is one of the many out there that could majorly benefit from advancement in the technology it utilizes. Artificial intelligence (AI) technologies are especially integral and specifically deep learning (DL); a highly useful data-driven technology. It is applied in a variety of different methods but it mainly depends on the structure of the available data. However, with varying applications, this technology produces data in different contexts with particular connotations. Reports which are the images of scans play a great role in identifying the existence of the disease in a patient. Further, the automation in processing these images using technology like CNN-based models makes it highly efficient in reducing human errors otherwise resulting in large data. Hence this study presents a hybrid deep learning architecture to classify the histopathology images to identify the presence of cancer in a patient. Further, the proposed models are parallelized using the TensorFlow-GPU framework to accelerate the training of these deep CNN (Convolution Neural Networks) archi-tectures. This study uses the transfer learning technique during training and early stopping criteria are used to avoid overfitting during the training phase. these models use LSTM parallel layer imposed in the model to experiment with four considered architectures such as MobileNet, VGG16, and ResNet with 101 and 152 layers. The experimental results produced by these hybrid models show that the capability of Hybrid ResNet101 and Hybrid ResNet152 architectures are highly suitable with an accuracy of 90% and 92%. Finally, this study concludes that the proposed Hybrid ResNet-152 architecture is highly efficient in classifying the histopathology images. The proposed study has conducted a well-focused and detailed experimental study which will further help researchers to understand the deep CNN architectures to be applied in application development.

2

An Accuracy Analysis Comparison of Supervised Classification Methods for Mapping Land Cover Using Sentinel 2 Images in the Al‑Hawizeh Marsh Area, Southern Iraq

Alwan Imzahim A., Aziz Nadia A.

Geomatics and Environmental Engineering

|

2021

|

Vol. 15, no. 1

5--21

EN

Land cover mapping of marshland areas from satellite images data is not a simple process, due to the similarity of the spectral characteristics of the land cover. This leads to challenges being encountered with some land covers classes, especially in wetlands classes. In this study, satellite images from the Sentinel 2B by ESA (European Space Agency) were used to classify the land cover of Al Hawizeh marsh/Iraq Iran border. Three classification methods were used aimed at comparing their accuracy, using multispectral satellite images with a spatial resolution of 10 m. The classification process was performed using three different algorithms, namely: Maximum Likelihood Classification (MLC), Artificial Neural Networks (ANN), and Support Vector Machine (SVM). The classification algorithms were carried out using ENVI 5.1 software to detect six land cover classes: deep water marsh, shallow water marsh, marsh vegetation (aquatic vegetation), urban area (built up area), agriculture area, and barren soil. The results showed that the MLC method applied to Sentinel 2B images provides a higher overall accuracy and the kappa coefficient compared to the ANN and SVM methods. Overall accuracy values for MLC, ANN, and SVM methods were 85.32%, 70.64%, and 77.01% respectively.

3

Spatiotemporal variability in spate irrigation systems in Khirthar National Range, Sindh, Pakistan (case study)

Soomro Abdul Ghani, Babar Muhammad Munir, Arshad Muhammad, Memon Anila, Naeem Babar, Ashraf Arshad

Acta Geophysica

|

2020

|

Vol. 68, no. 1

219--228

EN

Satellite remote sensing and geographical information system (GIS) have been used successfully to monitor and assess the land use and land cover (LULC) dynamics and their impacts on people and the environment. LULC change detection is essential for studying spatiotemporal conditions and for proposing better future planning and development options. The current research analyzes the detection of spatiotemporal variability of spate irrigation systems using remote sensing and GIS in the Khirthar National Range, Sindh Province of Pakistan. We use Landsat images to study the dynamics of LULC using ArcGIS software and categorize fve major LULC types. We obtain secondary data related to precipitation and crop yield from the provincial department of revenue. The maximum likelihood supervised classifcation (MLSC) procedure, augmented with secondary data, reveals a signifcant increase of 86.25% in settlements, 83.85% in spate irrigation systems, and 65% in vegetation, and a substantial negative trend of 39.50% in water bodies and 20% in barren land during the period from 2013 to 2018. Our study highlights an increase in settlements due to the infow of local population for better means of living and an increase in spate irrigation systems, which indicates the water conservation practices for land cultivation and human purpose lead to the shrinkage of water bodies. The confusion matrix using Google Earth data to rectify modeled (classifed) data, which showed an overall accuracy of 82.8%–92%, and the Kappa coefcient estimated at 0.80–0.90 shows the satisfactory results of the LULC classifcation. The study suggests the need to increase water storage potential with the appropriate water conservation techniques to enhance the spate irrigation system in the hilly tracts for sustainable develop‑ ments, which mitigates drought impact and reduces migration rate by providing more opportunities through agricultural activities in the study area.

4

Machine learning analysis of e-nose signal in early detection of mold contamination in buildings

Majerek D., Garbacz M., Duda S., Nabrdalik M.

Proceedings of ECOpole

|

2017

|

Vol. 11, No. 2

395--401

EN

Mould that develops on moistened building barriers is a major cause of the Sick Building Syndrome (SBS). Fungi emit Volatile Organic Compounds (VOC) that can be detected in the indoor air using several techniques of detection e.g. chromatography but also using gas sensors arrays. All array sensors generate particular electric signals that ought to be analysed using properly selected statistical methods of interpretation. This work is focused on the attempt to apply unsupervised and supervised statistical classifying models in the evaluation of signals from gas sensors matrix to analyse the air sampled from the headspace of various types of the building materials at the different level of contamination but also clean reference materials.

PL

Grzyb rozwijający się na ścianach budynków jest głównym powodem zjawiska, które nazwano Syndromem Chorego Budynku. Wolne związki organiczne emitowane przez grzyby mogą być wykryte różnymi metodami, m.in. na podstawie chromatografii, ale także za pomocą matryc czujników gazowych. Wszystkie tego typu narzędzia generują sygnały elektryczne, które można analizować za pomocą odpowiednich technik statystycznych. Praca skupia się na zastosowaniu nadzorowanych i nienadzorowanych technik uczenia maszynowego w ocenie sygnału pochodzącego z elektronicznego nosa.

5

A dynamic model of classifier competence based on the local fuzzy confusion matrix and the random reference classifier

Trajdos P., Kurzynski M.

International Journal of Applied Mathematics and Computer Science

|

2016

|

Vol. 26, no. 1

175--189

EN

Nowadays, multiclassifier systems (MCSs) are being widely applied in various machine learning problems and in many different domains. Over the last two decades, a variety of ensemble systems have been developed, but there is still room for improvement. This paper focuses on developing competence and interclass cross-competence measures which can be applied as a method for classifiers combination. The cross-competence measure allows an ensemble to harness pieces of information obtained from incompetent classifiers instead of removing them from the ensemble. The cross-competence measure originally determined on the basis of a validation set (static mode) can be further easily updated using additional feedback information on correct/incorrect classification during the recognition process (dynamic mode). The analysis of computational and storage complexity of the proposed method is presented. The performance of the MCS with the proposed cross-competence function was experimentally compared against five reference MCSs and one reference MCS for static and dynamic modes, respectively. Results for the static mode show that the proposed technique is comparable with the reference methods in terms of classification accuracy. For the dynamic mode, the system developed achieves the highest classification accuracy, demonstrating the potential of the MCS for practical applications when feedback information is available.

6

A study on the effectiveness of investment strategy based on the concept of pivot points levels using Matthews criterion

Wiliński A., Nyczaj T., Bera A., Błaszyński P.

Journal of Theoretical and Applied Computer Science

|

2013

|

Vol. 7, nr 4

42--55

EN

In this work, the possibility of assessing traditional investment strategy based on the pivot points for using with other than the commonly used criterion is examined. The authors attempted to apply the Matthews Correlation Coefficient (further reffered as MCC) criterion based on a confusion matrix when assessing the strategy to include more factors than the traditional criteria (such as profit, profit vs. Risk, Sharpe ratio, Calmar ratio) and to express these factors by one number. The criterion based on a confusion matrix is, in authors beliefs, unique in this application and gives a fairly valuable estimation of trading strategy. An example of several strategies tested on EURUSD 1h time series in selected intervals in the years 2012-2013 is considered. Among these strategies there is a simple strategy based on the concept of pivot points levels and more complex derivative strategies, based on the vector of optimized values of certain parameters. These strategies are evaluated using both traditional criteria and modification of MCC proposed by the authors.

7

Two template matching approaches to Arabic, Amharic and Latin isolated characters recognition

Cowell J., Hussain F.

Machine Graphics and Vision

|

2005

|

Vol. 14, No. 2

213-232

EN

With the establishment of commercial OCR systems for Latin text, recent research efforts have been directed at the design of recognition systems for non-Latin scripts, such as Japanese, Cyrillic, Chinese, Hindi, Tibetan, and in particular Arabic. The Unicode 4.0 standard supports 50 scripts that are used across the world, and many, such as Amharic (Ethiopic), have attracted virtually no attention from researchers. An extensive literature review reveals no papers which report on an OCR system for Amharic. This paper describes a normalised technique which can be used for recognition of isolated Arabic, Amharic and Latin characters. Two approaches are considered for identifying the characters by comparing them to a series of templates and using a signature template scheme. The degrees of similarity between pairs of Amharic, Arabic and typical Latin characters are presented in the confusion matrix, and the performance of the two approaches is compared for each of these three character sets.