Skip to main content
Fachgebiete
Automobil + Motoren Bauwesen + Immobilien Business IT + Informatik Elektrotechnik + Elektronik Energie + Nachhaltigkeit Finance + Banking Management + Führung Marketing + Vertrieb Maschinenbau + Werkstoffe Versicherung + Risiko
DE
EN
Bücher
Zeitschriften
Themenseiten
Organisationspsychologie Projektmanagement Marketing Smart Manufacturing
Weitere Formate
Podcasts Webinare Technik Webinare Wirtschaft Kongresse Veranstaltungskalender Awards
Jetzt Einzelzugang starten
Zugang für Unternehmen
Referenzkunden
SLX-Digitalkonferenz: Zukunftswerkstatt 2024

Mehr Umsatz mit Top-Kontakten

Am 7. Mai erfahren Sie, wie Vertriebsteams Leadgenerierung, Leadnurturing und Leadstrategien effizient steuern können.
Erweiterte Suche
Anmelden
nach oben

2021 | Buch

Chaotic Ions Motion Optimization (CIMO) for Biological Sequences Local Alignment: COVID-19 as a Case Study Kapitel lesen Erstes Kapitel lesen

Recent Trends in Signal and Image Processing

ISSIP 2020

herausgegeben von: Dr. Siddhartha Bhattacharyya, Dr. Leo Mršić, Dr. Maja Brkljačić, Dr. Joseph Varghese Kureethara, Prof. Dr. Mario Koeppen

Verlag: Springer Nature Singapore

Buchreihe : Advances in Intelligent Systems and Computing

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten
insite
SUCHEN

Über dieses Buch

This book gathers selected papers presented at the Third International Symposium on Signal and Image Processing (ISSIP 2020), organized by the Department of Information Technology, RCC Institute of Information Technology, Kolkata, during March 18–19, 2020. It presents fascinating, state-of-the-art research findings in the field of signal and image processing. It includes conference papers covering a wide range of signal processing applications involving filtering, encoding, classification, segmentation, clustering, feature extraction, denoising, watermarking, object recognition, reconstruction and fractal analysis. It addresses various types of signals, such as image, video, speech, non-speech audio, handwritten text, geometric diagram, ECG and EMG signals; MRI, PET and CT scan images; THz signals; solar wind speed signals (SWS); and photoplethysmogram (PPG) signals, and demonstrates how new paradigms of intelligent computing, like quantum computing, can be applied to process and analyze signals precisely and effectively.

Inhaltsverzeichnis

Frontmatter
Chaotic Ions Motion Optimization (CIMO) for Biological Sequences Local Alignment: COVID-19 as a Case Study
Abstract
COVID-19 is a pandemic that broke out throughout the world and has a high mobility to transfer between humans. Developing intelligent bioinformatics tools is a mandatory to aid in the analysis of the disease. One of these tools is local aligner which aims to find the longest common subsequence between two biological sequences. Fragmented local aligner technique (FLAT) was developed based on meta-heuristic algorithms to accelerating the alignment process, especially for sequences with huge length. In this paper, the performance of ions motion optimization (IMO) algorithm for implementing FLAT was measured. The performance was poor, and a chaotic parameter was added in the exploration equations of IMO to enhance its performance for FLAT. A set of real proteins having a product length which ranges from 250,000 to 9,000,000 were used as a dataset to test the performance of IMO and its developed version. Besides, COVID-19 virus was aligned using FLAT according to IMO and chaotic IMO to verify the enhancement of IMO. All results were compared to the results founded by Smith–Waterman approach. The tests prove the superiority of chaotic IMO over IMO for implementing FLAT on all datasets.
Mohamed Issa, A. M. Helmi, Mohamed Abd Elaziz, Siddhartha Bhattacharyya
Differential Evolution-Based Shot Boundary Detection Algorithm for Content-Based Video Retrieval
Abstract
With the increase of multimedia devices on internet, enormous number of videos are being added as part of digital content. There is a huge challenge in retrieval of these videos as mostly the videos are kept in unstructured form. Intended users try to retrieve video content as per the relevancy and need. Shot boundary detection is a significant and critical approach in the domain of digital video processing. It is the foremost critical job of content-based video retrieval and indexing. In this paper, a novel approach for shot boundary detection algorithm based on Differential evolution algorithm (DE) with SVM classifier is proposed. In this method we first calculate the curves difference of U-component histograms as the feature of difference between video frames. In the next step, Slide-Window Mean Filter to filter difference curves and SVM Classifier applying DE to detect and classify the shot transitions. The well-known TRECVID 2005, 2006, and 2007 datasets are used to test the performance of our proposed approach. The result shows the superior performance of our proposed approach, and this method can achieve high recall, precision rate, accuracy, and better computation time.
Abhishek Dixit, Ashish Mani, Rohit Bansal
Qutrit-Based Genetic Algorithm for Hyperspectral Image Thresholding
Abstract
Thresholding of hyperspectral images is a tedious task. The interactive information value between three bands is used to reduce the redundant bands in the pre-processing stage. A qutrit-inspired genetic algorithm is proposed for thresholding the minimized hyperspectral images with improved quantum genetic operators. In this paper, a quantum disaster operation is implemented to rescue the qutrit-inspired genetic algorithm from getting stuck into local optima. The proposed algorithm produces better results than classical genetic algorithm and qubit-inspired genetic algorithm in most of the cases.
Tulika Dutta, Sandip Dey, Siddhartha Bhattacharyya, Somnath Mukhopadhyay
Employing Parallel Hardware Architectures to Diagnose Sickle Cell Anemia in Real-Time Basis
Abstract
Among the solid components of the human blood, the type that has the largest number of them is well known as red blood cells (RBCs). These cells have flat-round shapes, where their centers are depressed like a doughnut missing its hole. When the cell shape is changed from circular to sickle, then this case is a blood disease named sickle cell anemia (SCA). Based on its number, the dangerous level is obtained. This paper employs parallel hardware architectures to detect the sickle cells and its dangerous level in a real-time basis. These parallel architectures include the field programmable gated array (FPGA) and the graphical processing unit (GPU). In addition, the central processing unit (CPU) as the common serial architecture is also employed for comparison basis in terms of time consuming and power consumption. The circular Hough Transform (CHT) method is employed for detecting the sickle cells. To determine the dangerous level, the number of sickle cells and the number of normal ones are counted. The detection, counting, and classification algorithms are all coded in the Verilog language (for the FPGA) and in the MATLAB software (for the GPU and CPU). The findings have achieved well-behaved performances and acceptable results are obtained.
Mohammed A. Fadhel, Omran Al-Shamma
Implementing a Hardware Accelerator to Enhance the Recognition Performance of the Fruit Mature
Abstract
For recognizing vegetable and fruit maturing, various techniques have been released in the last two decades. These techniques have different accuracies and are generally time consuming. To speed up the recognition performance to be suitable for real-time basis, a hardware accelerator is needed to implement. This paper introduced a field programmable gate array (FPGA), as a parallel hardware architecture, to solve the problem of time-consuming. Moreover, color-threshold and k-means clustering are two techniques utilized for recognition purposes and for comparison principles. The findings showed that the color-threshold technique required 16% of the total logic elements and performed the recognition task in 10.25 ms. In contrast, the k-means clustering technique required 62% of the logic elements and performed the recognition task in 64.88 ms. Thus, color-threshold technique is more efficient and much faster than the k-means technique.
Mohammed A. Fadhel, Omran Al-Shamma
Time Series Modelling and Forecasting of Patient Arrivals at an Emergency Department of a Select Hospital
Abstract
Managing overcrowding with fluctuating patient arrivals in emergency department (ED) of hospitals requires a quantitative approach to make decisions related to resource planning and deployment by hospital administrators. In this context, analysing patient flow and predicting demand will enable better decision making. In this study, 7748 ED arrivals were recorded from a multi-specialty hospital in Bengaluru. The patient flow in each of the working shifts of the ED was analysed separately. Time series modelling techniques have shown to be useful in generating short-term forecasts. Shift-wise modelling approach has been used since hospital resources were planned according to the shifts. Exponential smoothing techniques proposed by Hyndman were used in this study. Model validation was further carried out along with residual analysis. The prediction intervals shift-wise have been obtained with an average confidence level of 90% which will help hospital management to redeploy resources and handle demand with increased operational efficiency.
V. Rema, K. Sikdar
Deep Convolutional Neural Network-Based Diagnosis of Invasive Ductal Carcinoma
Abstract
The morbidity rate of breast cancer is among the highest exhibited by all forms of known cancer. It accounts for a high mortality rate in women. Detection in the early stages and corresponding attempts to treatment can help avert the fatality. The most common method used for the screening of breast cancer is mammography. However, the isolation of the breast lesion using this method is quite difficult and requires highly skilled radiologists. The most cardinal form of breast cancer is invasive ductile carcinoma (IDC) where the malignant growth spreads over to the breast fatty tissue after originating from the ducts. The difficulty in the analysis of images for invasive ductile carcinoma, and the time spent on the diagnosis gives rise to the urgent need for an accurate computer-aided diagnosis system. In this effort, we use a deep convolutional neural networks (DCNN) for the automating the detection of invasive ductal carcinoma in the early stages. This would serve as an efficient tool for assisting radiologists in the decision-making process and further save more lives in the long term.
Smaranjit Ghose, Suhrid Datta, C. Malathy, M. Gayathri
Speaker Identification in Spoken Language Mismatch Condition: An Experimental Study
Abstract
This paper describes the impact of spoken language variation in a multilingual speaker identification (SID) system. The development of speech technology applications in low resource languages (LRL) is challenging due to the unavailability of proper speech corpus. This paper illustrates an experimental study of SID on Eastern and Northeastern (E&NE) Indian languages in language mismatch conditions. For this purpose, several experiments are carried out using the LRL data to build speaker identification models. Here, spectral features are explored for investigating the presence of speaker-specific information. Mel frequency cepstral coefficients (MFCCs) and shifted delta cepstral (SDC) are used for representing the spectral information. Gaussian mixture model (GMM) and support vector machine (SVM)-based models are developed to represent the speaker-specific information captured through the spectral features. Apart from that, to build the modern SID i-vectors, time delay neural networks (TDNN), and recurrent neural network with long short-term memory (LSTM-RNN) have been considered. For the evaluation, equal error rate (EER) has been used as a performance matrix of the SID system. Performances of the developed systems are analyzed with native and non-native corpus in terms of speaker identification (SID) accuracy. The best SID performances are observed to be EER 10.52% after the corpus fusion mechanism.
Joyanta Basu, Swanirbhar Majumder
Ultrasound Image Classification Using ACGAN with Small Training Dataset
Abstract
B-mode ultrasound imaging is a popular medical imaging technique. Like other image processing tasks, deep learning has been used for analysis of B-mode ultrasound images in the last few years. However, training deep learning models require large labeled datasets, which is often unavailable for ultrasound images. The lack of large labeled data is a bottleneck for the use of deep learning in ultrasound image analysis. To overcome this challenge, in this work, we exploit auxiliary classifier generative adversarial network (ACGAN) that combines the benefits of data augmentation and transfer learning in the same framework. We conduct experiment on a dataset of breast ultrasound images that shows the effectiveness of the proposed approach.
Sudipan Saha, Nasrullah Sheikh
Assessment of Eyeball Movement and Head Movement Detection Based on Reading
Abstract
The present age is the age of technology. People are increasingly using technology in their daily activities. That is why when we go to consider people’s attention to something, our head detection comes first. Detecting the head is not the only thing that ends here; the thing that is directly related to it is the eyeball movement. For example, when a student is studying, the level of attention means his concentration deeply. And the depth of this attention depends not only on the head movement but also on how many times his eyes are moving from left to right or from right to left. Because it is seen that looking at the same object at a glance does not mean that he is not paying attention, maybe he is thinking of something else or is immersed in another thought. And by using this motivation, eyeball and head movements play a vital role in the study. The system’s goal is to read the video frames and determine the number of eyeballs and head movements in real time. Eyeball and head movements from left to right and right to left are counted per minute. After one minute, the previous data will be refreshed, and new data will be recorded for the next minute. Thus, the system will give us the result of each minute movement numbers, and very nicely, our system can detect eyeballs and head movements in case of reading.
Saadman Sayeed, Farjana Sultana, Partha Chakraborty, Mohammad Abu Yousuf
Using Hadoop Ecosystem and Python to Explore Climate Change
Abstract
In this article, the data storing and processing capabilities of Apache Hadoop ecosystem and its components: Hive, Impala and Sqoop are demonstrated. Also, it demonstrates Python programming language’s capabilities in data analysis, plotting and statistical computing. It does so by exploring climate change problem, one of today’s most relevant and detrimental problems. Apache Sqoop was employed to migrate data from RDBMS system and store it into Hive database, where Hive and Impala were used for data processing and ELT. Finally, data was analyzed using Python, showing strong evidence for global warming presence, as well as exploring relationship between carbon dioxide (CO2) emissions and climate change.
Ivan Ksaver Šušnjara, Tomislav Hlupić
A Brief Review of Intelligent Rule Extraction Techniques
Abstract
Rule extraction is a process of extracting rules which helps in building domain knowledge. Rules plays an important role in reconciling financial transactions. This paper presents a brief study of intelligent methods for rule extraction. The paper touches upon heuristic, regression, fuzzy-based, evolutionary, and dynamic adaptive techniques for rule extraction. This paper also presents the state-of-the-art techniques used in dealing with numerical and linguistic data for rule extraction. The objective of the paper is to provide directional guidance to researchers working on rule extraction.
Abhishek Gunjan, Siddhartha Bhattacharyya
The Effect of Different Feature Selection Methods for Classification of Melanoma
Abstract
Features of skin cancer have a certain impact on computer-aided diagnosis (CAD) systems. Researchers had used different techniques to experience with patterns. The melanoma lesion could also be identified with a different texture, shape, and clinical features. The proposed study has used 22 features of texture, 12 features of shape. The study has exposed three feature selection (FS) techniques like gradient boosting (GB), particle swarm optimization (PSO), and statistical approach. The features are evaluated with these methods and highlighted the effectiveness of each feature for the classification of melanoma. Selected key features have less than the cost of computation. The reduced feature set can make classification better than per the selection of the model. The random forest has the highest performance based on accuracy as it got the highest accuracy of 97.1% on GB feature sets. Decision tree and K-nearest neighbors have shown a decent accuracy of 96.8 and 93.3% on GB feature sets. The study rewards upcoming explorations to select an effective subset of features for machine learning and deep learning techniques.
Ananjan Maiti, Biswajoy Chatterjee
Intelligent Hybrid Technique to Secure Bluetooth Communications
Abstract
E0 algorithm is the most popular which used for data transmission Bluetooth communication among devices. E0 is having a 128-bit of symmetric stream cipher key length. Many types of attacks at Bluetooth protocol and cryptanalysis of E0 has proved that it would be broken by using 264 operations. In this work, we have proposed hybrid encryption based on blowfish and md5 algorithms to im-prove the security of transferring data between two computers connected using Bluetooth technique. Because of the advantages of key management of the MD5 algorithm, we used it to encrypt the secret key of Blowfish algorithm which used for encryption of plaintext. Therefore, the proposed hybrid encryption (Blowfish and MD5) will positively improve the data security during communication in Bluetooth media.
Alaa Ahmed Abbood, Qahtan Makki Shallal, Haider Khalaf Jabbar
Parallel Algorithm to find Integer k where a given Well-Distributed Graph is k-Metric Dimensional
Abstract
Networks are very important in the world. In signal processing, the towers are modeled as nodes (vertices) and if two towers communicate, then they have an arc (edge) between them or precisely, they are adjacent. The least number of nodes in a network that can uniquely locate every node in the network is known in the network theory as the resolving set of a network. One of the properties that is used in determining the resolving set is the distance between the nodes. Two nodes are at a distance one if there is a single arc can link them whereas the distance between any two random nodes in the network is the least number of distinct arcs that can link them. We propose two algorithms in this paper with the proofs of correctness. The first one is in lines with the BFS that find distance between a designated node to every other node in the network. This algorithm runs in O(log n). The second algorithm is to identify the integer k, such that the given graph is k-metric dimensional. This can be implemented in O(log n) time with O(n2) processors in a CRCW PRAM.
Xavier Chelladurai, Joseph Varghese Kureethara
A Fog-Based Retrieval of Real-Time Data for Health Applications
Abstract
Fog computing is an emerging technology that offers high-quality cloud services by providing high bandwidth, low latency, and efficient computational power and storage capacity. Although cloud computing is an efficient solution so far to store and retrieve the huge data of IoT devices, it is expected to limit its performance due to low latency and storage capacity. Fog computing addresses these limitations by extending its services to the cloud at the edge of the network. In this paper, we use a fog computing network approach for efficiently retrieving the real-time patient data. The performance of our proposed approach has been compared with the cloud computing approach in terms of retrieval time of real-time data.
I. Diana Jeba Jingle, P. Mano Paul
Metadaten
Titel
Recent Trends in Signal and Image Processing
herausgegeben von
Dr. Siddhartha Bhattacharyya
Dr. Leo Mršić
Dr. Maja Brkljačić
Dr. Joseph Varghese Kureethara
Prof. Dr. Mario Koeppen
Copyright-Jahr
2021
Verlag
Springer Nature Singapore
Electronic ISBN
978-981-336-966-5
Print ISBN
978-981-336-965-8
DOI
https://doi.org/10.1007/978-981-33-6966-5

Neuer Inhalt

    Bildnachweise