How to search?
advanced search

Search results

Filters

  • Journals
  • Authors
  • Keywords
  • Date
  • Type

Search results

Number of results: 11
items per page: 25 50 75
Sort by:

The Role of Faster R-CNN Algorithm in the Internet of Things to Detect Mask Wearing: The Endemic Preparations

Marah Doly Nasution Al-Khowarizmi Romi Fadillah Rahmat Arif Ridho Lubis Muharman Lubis
International Journal of Electronics and Telecommunications | 2023 | vol. 69 | No 4 | 691-696 | DOI: 10.24425/ijet.2023.147689
Keywords Faster R-CNN IoT mask Endemic
Download PDF Download RIS Download Bibtex

Abstract

Faster R-CNN is an algorithm development that continuously starts from CNN then R-CNN and Faster R-CNN. The development of the algorithm is needed to test whether the heuristic algorithm has optimal provisions. Broadly speaking, faster R-CNN is included in algorithms that are able to solve neural network and machine learning problems to detect a moving object. One of the moving objects in the current phenomenon is the use of masks. Where various countries in the world have issued endemic orations after the Covid 19 pandemic occurred. Detection tool has been prepared that has been tested at the mandatory mask door, namely for mask users. In this paper, the role of the Faster R-CNN algorithm has been carried out to detect masks poured on Internet of Thinks (IoT) devices to automatically open doors for standard mask users. From the results received that testing on the detection of moving mask objects when used reaches 100% optimal at a distance of 0.5 to 1 meter and 95% at a distance of 1.5 to 2 meters so that the process of sending detection signals to IoT devices can be carried out at a distance of 1 meter at the position mask users to automatic doors.
Go to article

Authors and Affiliations

Marah Doly Nasution
1
Al-Khowarizmi
2
Romi Fadillah Rahmat
3
Arif Ridho Lubis
4
Muharman Lubis
5
  1. Department of Mathematics Education,Universitas Muhammadiyah Sumatera Utara, Indonesia
  2. Department of Information Technology, UniversitasMuhammadiyah Sumatera Utara, Indonesia
  3. Department of Information Technology,Universitas Sumatera Utara, Indonesia
  4. Department of Management Informatics, PoliteknikNegeri Medan, Indonesia
  5. Department of Information Systems, TelkomUniversity, Indonesia

Ensemble of classifiers based on CNN for increasing generalization ability in face image recognition

Robert Szmurło Stanislaw Osowski
Bulletin of the Polish Academy of Sciences Technical Sciences | 2022 | 70 | 3 | e141004 | DOI: 10.24425/bpasts.2022.141004
Keywords CNN ensemble of classifiers face recognition feature selection
Download PDF Download RIS Download Bibtex

Abstract

The paper considers the problem of increasing the generalization ability of classification systems by creating an ensemble of classifiers based on the CNN architecture. Different structures of the ensemble will be considered and compared. Deep learning fulfills an important role in the developed system. The numerical descriptors created in the last locally connected convolution layer of CNN flattened to the form of a vector, are subjected to a few different selection mechanisms. Each of them chooses the independent set of features, selected according to the applied assessment techniques. Their results are combined with three classifiers: softmax, support vector machine, and random forest of the decision tree. All of them do simultaneously the same classification task. Their results are integrated into the final verdict of the ensemble. Different forms of arrangement of the ensemble are considered and tested on the recognition of facial images. Two different databases are used in experiments. One was composed of 68 classes of greyscale images and the second of 276 classes of color images. The results of experiments have shown high improvement of class recognition resulting from the application of the properly designed ensemble.
Go to article

Authors and Affiliations

Robert Szmurło
1
ORCID: ORCID
Stanislaw Osowski
2
ORCID: ORCID
  1. Faculty of Electrical Engineering, Warsaw University of Technology, Koszykowa 75, 00-662 Warszawa, Poland
  2. Faculty of Electronic Engineering, Military University of Technology, gen. S. Kaliskiego 2, 00-908 Warszawa, Poland

A CNN based Hybrid approach towards automatic image registration

Pattathal V. Arun Sunil K. Katiyar
Geodesy and Cartography | 2013 | vol. 62 | No 1 | DOI: 10.2478/geocart-2013-0005
Keywords Cellular Neural Network (CNN) image analysis image registration resampling remote sensing
Download PDF Download RIS Download Bibtex

Abstract

Image registration is a key component of various image processing operations which involve the analysis of different image data sets. Automatic image registration domains have witnessed the application of many intelligent methodologies over the past decade; however inability to properly model object shape as well as contextual information had limited the attainable accuracy. In this paper, we propose a framework for accurate feature shape modeling and adaptive resampling using advanced techniques such as Vector Machines, Cellular Neural Network (CNN), SIFT, coreset, and Cellular Automata. CNN has found to be effective in improving feature matching as well as resampling stages of registration and complexity of the approach has been considerably reduced using corset optimization The salient features of this work are cellular neural network approach based SIFT feature point optimisation, adaptive resampling and intelligent object modelling. Developed methodology has been compared with contemporary methods using different statistical measures. Investigations over various satellite images revealed that considerable success was achieved with the approach. System has dynamically used spectral and spatial information for representing contextual knowledge using CNN-prolog approach. Methodology also illustrated to be effective in providing intelligent interpretation and adaptive resampling.
Go to article

Authors and Affiliations

Pattathal V. Arun
Sunil K. Katiyar

Recognition of Sign Language from High Resolution Images Using Adaptive Feature Extraction and Classification

Filip Csóka Jaroslav Polec Tibor Csóka Juraj Kačur
International Journal of Electronics and Telecommunications | 2019 | vol. 65 | No 2 | 303-308 | DOI: 10.24425/ijet.2019.126314
Keywords sign language gesture sign recognition CNN LoG real-time pattern recognition machine learning
Download PDF Download RIS Download Bibtex

Abstract

A variety of algorithms allows gesture recognition in video sequences. Alleviating the need for interpreters is of interest to hearing impaired people, since it allows a great degree of self-sufficiency in communicating their intent to the non-sign language speakers without the need for interpreters. State-of-theart in currently used algorithms in this domain is capable of either real-time recognition of sign language in low resolution videos or non-real-time recognition in high-resolution videos. This paper proposes a novel approach to real-time recognition of fingerspelling alphabet letters of American Sign Language (ASL) in ultra-high-resolution (UHD) video sequences. The proposed approach is based on adaptive Laplacian of Gaussian (LoG) filtering with local extrema detection using Features from Accelerated Segment Test (FAST) algorithm classified by a Convolutional Neural Network (CNN). The recognition rate of our algorithm was verified on real-life data.

Go to article

Authors and Affiliations

Filip Csóka
Jaroslav Polec
Tibor Csóka
Juraj Kačur

Ensemble of classifiers based on deep learning for medical image recognition

Fabian Gil Stanisław Osowski Bartosz Świderski Monika Słowińska
Metrology and Measurement Systems | 2023 | vol. 30 | No 1 | 139-156 | DOI: 10.24425/mms.2023.144400
Keywords breast cancer CNN deep learning ensemble of classifiers feature selection melanoma
Download PDF Download RIS Download Bibtex

Abstract

The paper presents special forms of an ensemble of classifiers for analysis of medical images based on application of deep learning. The study analyzes different structures of convolutional neural networks applied in the recognition of two types of medical images: dermoscopic images for melanoma and mammograms for breast cancer. Two approaches to ensemble creation are proposed. In the first approach, the images are processed by a convolutional neural network and the flattened vector of image descriptors is subjected to feature selection by applying different selection methods. As a result, different sets of a limited number of diagnostic features are generated. In the next stage, these sets of features represent input attributes for the classical classifiers: support vector machine, a random forest of decision trees, and softmax. By combining different selection methods with these classifiers an ensemble classification system is created and integrated by majority voting. In the second approach, different structures of convolutional neural networks are directly applied as the members of the ensemble. The efficiency of the proposed classification systems is investigated and compared to medical data representing dermoscopic images of melanoma and breast cancer mammogram images. Thanks to fusion of the results of many classifiers forming an ensemble, accuracy and all other quality measures have been significantly increased for both types of medical images.
Go to article

Authors and Affiliations

Fabian Gil
1
Stanisław Osowski
1 2
Bartosz Świderski
3
Monika Słowińska
4
  1. Military University of Technology, Faculty of Electronics, Institute of Electronic Systems, ul. gen. Sylwestra Kaliskiego 2, 00-908 Warsaw, Poland
  2. Warsaw University of Technology, Faculty of Electrical Engineering, pl. Politechniki 1, 00-661 Warsaw, Poland
  3. University of Life Sciences, ul. Nowoursynowska 166, 02-787 Warsaw
  4. Central Clinical Hospital Ministry of Defense, Military Institute of Medicine – National Research Institute, ul. Szaserów 128, 04-141 Warsaw, Poland

Performance Analysis of LEACH with Deep Learning in Wireless Sensor Networks

Hardik K Prajapati Rutvij Joshi
International Journal of Electronics and Telecommunications | 2022 | vol. 68 | No 4 | 799-805 | DOI: 10.24425/ijet.2022.143888
Keywords machine learning Deep learning Convolutional Neural Network (CNN) LEACH
Download PDF Download RIS Download Bibtex

Abstract

Thousands of low-power micro sensors make up Wireless Sensor Networks, and its principal role is to detect and report specified events to a base station. Due to bounded battery power these nodes are having very limited memory and processing capacity. Since battery replacement or recharge in sensor nodes is nearly impossible, power consumption becomes one of the most important design considerations in WSN. So one of the most important requirements in WSN is to increase battery life and network life time. Seeing as data transmission and reception consume the most energy, it’s critical to develop a routing protocol that addresses the WSN’s major problem. When it comes to sending aggregated data to the sink, hierarchical routing is critical. This research concentrates on a cluster head election system that rotates the cluster head role among nodes with greater energy levels than the others.We used a combination of LEACH and deep learning to extend the network life of the WSN in this study. In this proposed method, cluster head selection has been performed by Convolutional Neural Network (CNN). The comparison has been done between the proposed solution and LEACH, which shows the proposed solution increases the network lifetime and throughput.
Go to article

Authors and Affiliations

Hardik K Prajapati
1
Rutvij Joshi
2
  1. Gujarat Technological University, Ahmedabad, Gujarat, India
  2. Parul University, Vadodara, Gujarat, India

An enhanced performance evaluation of workflow computing and scheduling using hybrid classification approach in the cloud environment

P. Tharani A.M. Kalpana
Bulletin of the Polish Academy of Sciences Technical Sciences | 2021 | 69 | 4 | e137728 | DOI: 10.24425/bpasts.2021.137728
Keywords cloud workflow scheduling machine learning CNN AlexNet
Download PDF Download RIS Download Bibtex

Abstract

Workflow Scheduling is the major problem in Cloud Computing consists of a set of interdependent tasks which is used to solve the various scientific and healthcare issues. In this research work, the cloud based workflow scheduling between different tasks in medical imaging datasets using Machine Learning (ML) and Deep Learning (DL) methods (hybrid classification approach) is proposed for healthcare applications. The main objective of this research work is to develop a system which is used for both workflow computing and scheduling in order to minimize the makespan, execution cost and to segment the cancer region in the classified abnormal images. The workflow computing is performed using different Machine Learning classifiers and the workflow scheduling is carried out using Deep Learning algorithm. The conventional AlexNet Convolutional Neural Networks (CNN) architecture is modified and used for workflow scheduling between different tasks in order to improve the accuracy level. The AlexNet architecture is analyzed and tested on different cloud services Amazon Elastic Compute Cloud- EC2 and Amazon Lightsail with respect to Makespan (MS) and Execution Cost (EC).
Go to article

Bibliography

  1.  A.M. Manasrah and H. Ba Ali, “Workflow scheduling using hybrid GA-PSO algorithm in cloud computing,” Wireless Commun. Mob. Comput., vol. 15, no. 3, pp. 1–16, 2018, doi: 10.1155/2018/1934784.
  2.  S.G. Ahmad, C.S. Liew, E.U. Munir, A.T. Fong, and S.U. Khan, “A hybrid genetic algorithm for optimization of scheduling workflow applications in heterogeneous computing systems,” J. Parallel Distrib. Comput., vol. 87, no. 2, pp. 80–90, 2016, doi: 10.1016/j. jpdc.2015.10.001.
  3.  H. Alaskar, A. Hussain, N. Al-Aseem, P. Liatsis, and D. Al-Jumeily, “Application of convolutional neural networks for automated ulcer detection in wireless capsule endoscopy images,” Sensors., vol. 19, no. 6, pp. 1265–1281, 2019, doi: 10.3390/s19061265.
  4.  L. Teylo, L. Arantes, P. Sens, and L.M.A. Drummond, “A dynamic task scheduler tolerant to multiple hibernations in cloud environments,” J. Cluster Comput., vol. 21, no. 5, pp. 1–23, 2020, doi: 10.1007/s10586-020-03175-2.
  5.  M. Sardaraz and M. Tahir, “A parallel multi-objective genetic algorithm for scheduling scientific workflows in cloud computing,” Int. J. Distri. Sensor Net., vol. 16, no. 8, pp. 1–10, 2020, doi: 10.1177/1550147720949142.
  6.  M. Hosseinzadeh, M.Y. Ghafour, and H.K. Hama, “Multi-objective task and workflow scheduling approaches in cloud computing: a comprehensive review,” J. Grid Comput., vol. 18, no. 3, pp. 327–356, 2020, doi: 10.1007/s10723-020-09533-z.
  7.  C.L. Chen, M.L. Chiang, and C.B. Lin, “The high performance of a task scheduling algorithm using reference queues for cloud- computing data centers,” Electronics, . vol. 9, no. 1, pp. 371–379, 2020, doi: 10.3390/electronics9020371.
  8.  Y. Hu, H. Wang, and W. Ma, “Intelligent Cloud workflow management and scheduling method for big data applications,” J. Cloud Comp, vol. 9, no. 1, pp. 1–13, 2020, doi: 10.1186/s13677-020-00177-8.
  9.  M. Grochowski, A. Kwasigroch, and A. Mikołajczyk,” Selected technical issues of deep neural networks for image classification purposes,” Bull. Polish Acad. Sci. Tech. Sci., vol. 67, no. 2, pp. 363–376, 2019, doi: 10.24425/bpas.2019.128485.
  10.  A.A. Nasr, N.A. El-Bahnasawy, and G. Attiya, “Cost-effective algorithm for workflow scheduling in cloud computing under deadline constraint,” Arab. J. Sci. Eng., vol. 44, no. 4, pp. 3765–3780, 2019, doi: 10.1007/s13369-018-3664-6.
  11.  Z. Swiderska-Chadaj, T. Markiewicz, J. Gallego, G. Bueno, B. Grala, and M. Lorent, “Deep learning for damaged tissue detection and segmentation in Ki-67 brain tumor specimens based on the U-net model,” Bull. Polish Acad. Sci. Tech. Sci., vol. 66, no. 6, pp. 849–856, 2018, doi: 10.24425/bpas.2018.125932.
  12.  Y. Cui and Z. Xiaoqing, “Workflow tasks scheduling optimization based on genetic algorithm in Clouds,” in IEEE 3rd Int. Conf. on Cloud Computing and Big Data Analysis (ICCCBDA), Chengdu, 2018, pp. 6–10, doi: 10.1109/ICCCBDA.2018.8386458.
  13.  T. Wang, Z. Liu, Y. Chen, Y. Xu, and X. Dai, “Load balancing task scheduling based on Genetic algorithm in Cloud Computing,” in IEEE 12th Int. Conf. on Dependable, Autonomic and Secure Computing, Dalian, 2014, pp. 146–152, doi: 10.1109/DASC.2014.35.
  14.  X. Zhao, Y. Wu, G. Song, Z. Li, Y. Zhang, and Y. Fan, “A deep learning model integrating FCNNs and CRFs for brain tumor segmentation,” Med. Imag. Anal., vol. 43, no. 4, pp.  98–111, 2018, doi: 10.1016/j.media.2017.10.002.
  15.  C. Liu, R. Zhao, W. Xie, and M. Pang, “Pathological lung segmentation based on random forest combined with deep model and multi- scale superpixels,” Neu. Proc, Let., vol. 52, no. 2, pp. 1631–1649, 2020, doi: 10.1007/s11063-020-10330-8.
  16.  C. Zhang, J. Zhao, Ji. Niu, and D. Li, “New convolutional neural network model for screening and diagnosis of mammograms,” PLoS One., vol. 15, no. 8, pp. 67–80, 2020, doi: 10.1371/journal.pone.0237674.
  17.  L.D. Nicanor, H.R. Orozco Aguirre, and V.M. Landassuri Moreno, “An assessment model to establish the use of services resources in a cloud computing scenario,” J. High Perf. Vis. Int., vol. 12, no. 5, pp. 83–100, 2020, doi: 10.1007/978-981-15-6844-2_7.
  18.  V. Magudeeswaran and J. Fenshia Singh, “Contrast limited fuzzy adaptive histogram equalization for enhancement of brain images,” Int. J. Imag. Sys. and Tech., vol. 27, no. 1, pp. 98–103, 2017, doi: 10.1002/ima.22214.
  19.  S.P. Cleary and J.S. Prell, “Liberating native mass spectrometry from dependence on volatile salt buffers by use of Gábor transform,” Int. J. Imag. Syst. Tech., vol. 20, no. 4, pp. 519–523, 2019, doi: 10.1002/cphc.201900022.
  20.  V. Srivastava, R.K. Purwar, and A. Jain, “A dynamic threshold‐based local mesh ternary pattern technique for biomedical image retrieval,” Int. J. Imag. Sysy. Tech., vol. 29, no. 2, pp. 168–179, 2019, doi: 10.1002/ima.22296.
  21.  J.H. Johnpeter and T. Ponnuchamy, “Computer aided automated detection and classification of brain tumors using CANFIS classification method,” Int. J. Imag. Sysy. Tech., vol. 29, no. 4, pp. 431–438, 2019, doi: 10.1002/ima.22318.
  22.  N. Kumar and D. Kumar, “Classification using artificial neural network optimized with bat algorithm”, Int. J. Innovative Tech. Exploring Eng. (IJITEE), vol. 9, no. 3, pp.  696–700, 2020, doi: 10.35940/ijitee.C8378.019320.
  23.  A.S. Mahboob and S.H. Zahiri, “Automatic and heuristic complete design for ANFIS classifier, network: computation in neural systems,” J. Net. Comput. Neu. Syst., vol. 30, no. 4, pp. 31–57, 2019, doi: 10.1080/0954898X.2019.1637953.
  24.  C. Shorten and T.M. Khoshgoftaar, “A survey on image data augmentation for deep learning,” J. Big. Data., vol.  60, no. 6, pp. 1–48, 2019, doi: 10.1186/s40537-019-0197-0.
Go to article

Authors and Affiliations

P. Tharani
1
A.M. Kalpana
1
  1. Department of Computer Science and Engineering, Government College of Engineering, Salem-636011, Tamil Nadu, India

A few-shot fine-grained image recognition method

Jianwei Wang Deyun Chen
Bulletin of the Polish Academy of Sciences Technical Sciences | 2023 | 71 | 1 | e144584 | DOI: 10.24425/bpasts.2023.144584
Keywords few-shot learning attention metric CNN (convolutional neural network) feature expression
Download PDF Download RIS Download Bibtex

Authors and Affiliations

Jianwei Wang
1 2
ORCID: ORCID
Deyun Chen
1
  1. College of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, China
  2. College of Computer Science and Technology, Heilongjiang Institute of Technology, Harbin 150050, China

Grounding line positions of Amery Ice Shelf based on long interferometric Sentinel-1 time series

Michał Tympalski Marek Sompolski Anna Kopeć Wojciech Milczarek
Polish Polar Research | 2024 | vol. 45 | No 1 | 1-19 | DOI: 10.24425/ppr.2023.146738
Keywords Antarctic Prydz Bay ice shelf DInSAR CNN
Download PDF Download RIS Download Bibtex

Abstract

The paper presents the potential of combining satellite radar data and neural networks for quasi-automatic detection of glacier grounding lines. The conducted research covered five years and was carried out in the area of the Amery Ice Shelf. It has a very complex shoreline, so its grounding-line location is uncertain. Thus, it has always been the subject of much research. The main objective of our work was to find out if Synthetic Aperture Radar data combined with a deep learning implementation would enable rapid detection of ice shelf grounding lines over large areas. For this purpose, 290 radar images from the Sentinel-1 satellite covering 46 000 km2 were used. Processed by the Differential Interferometry of Synthetic Aperture Radar four-pass method, the images formed a time-consistent series between 2017 and 2021. As a result of performed calculations, a total length of 1280 km of grounding line was determined. They were validated by comparing with other independent data sources based on manual measurements. It has been demonstrated that the combination of satellite radar data and automated data processing allows for obtaining high-precision results continuously in a very short time. Such an approach allows monitoring of grounding line position in the long term with intervals of less than one week. It enables analysis of the dynamics changes with unprecedented frequency and the identification of patterns.
Go to article

Authors and Affiliations

Michał Tympalski
1
ORCID: ORCID
Marek Sompolski
1
ORCID: ORCID
Anna Kopeć
1
ORCID: ORCID
Wojciech Milczarek
1
ORCID: ORCID
  1. Faculty of Geoengineering, Mining and Geology, Wrocław University of Science and Technology, Na Grobli 15, 50-421 Wrocław, Poland

A Novel Intelligent Neural Network Techniques of UPQC with Integrated Solar PV System for Power Quality Enhancement

Ramesh Rudraram Sasi Chinnathambi Manikandan Mani
International Journal of Electronics and Telecommunications | 2023 | vol. 69 | No 3 | 605-613 | DOI: 10.24425/ijet.2023.146514
Keywords PV system Re-lift Luo DC-DC converter Cascaded ANN MPPT Adaptive PI controller CNN assisted dq theory
Download PDF Download RIS Download Bibtex

Abstract

A Novel Intelligent control of a Unified Power Quality Conditioner (UPQC) coupled with Photovoltaic (PV) system is proposed in this work. The utilization of a Re-lift Luo converter in conjunction with a Cascaded Artificial Neural Network (ANN) Maximum Power Point Tracking (MPPT) method facilitates the optimization of power extraction from PV sources. UPQC is made up of a series and shunt Active Power Filter (APF), where the former compensates source side voltage quality issues and the latter compensates the load side current quality issues. The PV along with a series and shunt APFs of the UPQC are linked to a common dc-bus and for regulating a dc-bus voltage a fuzzy tuned Adaptive PI controller is employed. Moreover, a harmonics free reference current is generated with the aid of CNN assisted dq theory in case of the shunt APF. The results obtained from MATLAB simulation.
Go to article

Authors and Affiliations

Ramesh Rudraram
1
Sasi Chinnathambi
1
Manikandan Mani
2
  1. Electrical Engineering Department, Annamalai University, Annamalainagar, India
  2. Electrical and Electronics Engineering Department, Jyothishmathi Institute of Technology and Science, Karimnagr, Telangana, India

A deep learning method for hard-hat-wearing detection based on head center localization

Bartosz Wójcik Mateusz Żarski Kamil Książek Jarosław A. Miszczak Mirosław J. Skibniewski
Bulletin of the Polish Academy of Sciences Technical Sciences | 2023 | 71 | 6 | e147340 | DOI: 10.24425/bpasts.2023.147340
Keywords hard hat personal protective equipment construction safety deep learning keypoint R-CNN
Download PDF Download RIS Download Bibtex

Abstract

In recent years, a lot of attention has been paid to deep learning methods in the context of vision-based construction site safety systems. However, there is still more to be done to establish the relationship between supervised construction workers and their essential personal protective equipment, like hard hats. A deep learning method combining object detection, head center localization, and simple rule-based reasoning is proposed in this article. In tests, this solution surpassed the previous methods based on the relative bounding box position of different instances and direct detection of hard hat wearers and non-wearers. Achieving MS COCO style overall AP of 67.5% compared to 66.4% and 66.3% achieved by the approaches mentioned above, with class-specific AP for hard hat non-wearers of 64.1% compared to 63.0% and 60.3%. The results show that using deep learning methods with a humanly interpretable rule-based algorithm is better suited for detecting hard hat non-wearers.
Go to article

Authors and Affiliations

Bartosz Wójcik
1
ORCID: ORCID
Mateusz Żarski
1
ORCID: ORCID
Kamil Książek
1
Jarosław A. Miszczak
1
Mirosław J. Skibniewski
1 2
  1. Institute of Theoretical and Applied Informatics, Polish Academy of Sciences, 44-100 Gliwice, Poland
  2. A. James Clark School of Engineering, University of Maryland, College Park, MD 20742-3021, USA

This page uses 'cookies'. Learn more