Umamaheswari Ramalingam^1,*, Senthil Kumar Murugesan², Karthikeyan Lakshmanan², Chidhambararajan Balasubramaniyan³

Intelligent Automation & Soft Computing, Vol.36, No.2, pp. 1733-1744, 2023, DOI:10.32604/iasc.2023.032108

Abstract A Deep Neural Sentiment Classification Network (DNSCN) is developed in this work to classify the Twitter data unambiguously. It attempts to extract the negative and positive sentiments in the Twitter database. The main goal of the system is to find the sentiment behavior of tweets with minimum ambiguity. A well-defined neural network extracts deep features from the tweets automatically. Before extracting features deeper and deeper, the text in each tweet is represented by Bag-of-Words (BoW) and Word Embeddings (WE) models. The effectiveness of DNSCN architecture is analyzed using Twitter-Sanders-Apple2 (TSA2), Twitter-Sanders-Apple3 (TSA3), and Twitter-DataSet (TDS). TSA2 and TDS consist of… More >

E. Bharath^1,*, T. Rajagopalan²

Intelligent Automation & Soft Computing, Vol.36, No.2, pp. 1417-1433, 2023, DOI:10.32604/iasc.2023.032102

Abstract Parkinson’s disease (PD) is a neurodegenerative disease cause by a deficiency of dopamine. Investigators have identified the voice as the underlying symptom of PD. Advanced vocal disorder studies provide adequate treatment and support for accurate PD detection. Machine learning (ML) models have recently helped to solve problems in the classification of chronic diseases. This work aims to analyze the effect of selecting features on ML efficiency on a voice-based PD detection system. It includes PD classification models of Random forest, decision Tree, neural network, logistic regression and support vector machine. The feature selection is made by RF mean-decrease in accuracy… More >

G. Murugesan^1,*, J. Jeyapriya², M. Hemalatha³, S. Rajeshkannan⁴

Intelligent Automation & Soft Computing, Vol.36, No.2, pp. 2099-2109, 2023, DOI:10.32604/iasc.2023.032068

Abstract The diagnostic interpretation of dermoscopic images is a complex task as it is very difficult to identify the skin lesions from the normal. Thus the accurate detection of potential abnormalities is required for patient monitoring and effective treatment. In this work, a Two-Tier Segmentation (TTS) system is designed, which combines the unsupervised and supervised techniques for skin lesion segmentation. It comprises preprocessing by the median filter, TTS by Colour K-Means Clustering (CKMC) for initial segmentation and Faster Region based Convolutional Neural Network (FR-CNN) for refined segmentation. The CKMC approach is evaluated using the different number of clusters (k = 3,… More >

P. S. Ramapraba^1,*, P. Epsiba², K. Umapathy³, E. Sivanantham⁴

Intelligent Automation & Soft Computing, Vol.36, No.2, pp. 2177-2189, 2023, DOI:10.32604/iasc.2023.032040

Abstract The classification of lung nodules is a challenging problem as the visual analysis of the nodules and non-nodules revealed homogenous textural patterns. In this work, an Auxiliary Classifier (AC)-Generative Adversarial Network (GAN) based Lung Cancer Classification (LCC) system is developed. The proposed AC-GAN-LCC system consists of three modules; preprocessing, Lungs Region Detection (LRD), and AC-GAN classification. A Wiener filter is employed in the preprocessing module to remove the Gaussian noise. In the LRD module, only the lung regions (left and right lungs) are detected using iterative thresholding and morphological operations. In order to extract the lung region only, flood filling… More >

V. Nandagopal^1,*, T. S. Balaji Damodhar², P. Vijayapriya³, A. Thamilmaran³

Intelligent Automation & Soft Computing, Vol.36, No.2, pp. 1315-1329, 2023, DOI:10.32604/iasc.2023.032039

Abstract

The development of non-linear loads at consumers has significantly impacted power supply systems. Since, the poor power quality has been found in the three-phase distribution system due to unbalanced loads, harmonic current, undesired voltage regulation, and extreme reactive power demand. To overcome this issue, Distributed STATicCOMpensator (DSTATCOM) is implemented. DSTATCOM is a shunt-connected Voltage Source Converter (VSC) that has been utilized in distribution networks to balance the bus voltage in terms of enhancing reactive power control and power factor. DSTATCOM can provide both rapid and continuous capacitive and inductive mode compensation. A rectified resistive and inductive load eliminates current harmonics… More >

Anju Shukla¹, Mohammad Zubair Khan², Shishir Kumar^3,*, Abdulrahman Alahmadi², Reem Ibrahim A. Altamimi², Ahmed H. Alahmadi²

Intelligent Automation & Soft Computing, Vol.36, No.2, pp. 2281-2297, 2023, DOI:10.32604/iasc.2023.031931

Abstract Integrated CloudIoT is an emerging field of study that integrates the Cloud and the Internet of Things (IoT) to make machines smarter and deal with real-world objects in a distributed manner. It collects data from various devices and analyses it to increase efficiency and productivity. Because Cloud and IoT are complementary technologies with distinct areas of application, integrating them is difficult. This paper identifies various CloudIoT issues and analyzes them to make a relational model. The Interpretive Structural Modeling (ISM) approach establishes the interrelationship among the problems identified. The issues are categorised based on driving and dependent power, and a… More >

Nabilah Abughazalah¹, Iqra Ishaque², Majid Khan^2,*, Ammar S. Alanazi³, Iqtadar Hussain^4,5

Intelligent Automation & Soft Computing, Vol.36, No.2, pp. 1451-1463, 2023, DOI:10.32604/iasc.2023.031855

Abstract In today’s digital world, the most inevitable challenge is the protection of digital information. Due to the weak confidentiality preserving techniques, the existing world is facing several digital information breaches. To make our digital data indecipherable to the unauthorized person, a technique for finding a cryptographically strong Substitution box (S-box) have presented. An S-box with sound cryptographic assets such as nonlinearity (NL), strict avalanche criterion (SAC), bit independence criteria (BIC), bit independence criteria of nonlinearity (BIC-NL), Bit independence criteria of Strict avalanche criteria (BIC-SAC), and Input/output XOR is considered as the robust S-box. The Decision-Making Trial and Evaluation Laboratory (DEMATEL)… More >

R. Ann Caroline Jenifer^*, M. A. Bhagyaveni, V. Saroj Malini, M. Shanmugapriya

Intelligent Automation & Soft Computing, Vol.36, No.2, pp. 2165-2176, 2023, DOI:10.32604/iasc.2023.031840

Abstract Fifth generation (5G) wireless networks must meet the needs of emerging technologies like the Internet of Things (IoT), Vehicle-to-everything (V2X), Video on Demand (VoD) services, Device to Device communication (D2D) and many other bandwidth-hungry multimedia applications that connect a huge number of devices. 5G wireless networks demand better bandwidth efficiency, high data rates, low latency, and reduced spectral leakage. To meet these requirements, a suitable 5G waveform must be designed. In this work, a waveform namely Shaped Offset Quadrature Phase Shift Keying based Orthogonal Frequency Division Multiplexing (SOQPSK-OFDM) is proposed for 5G to provide bandwidth efficiency, reduced spectral leakage, and… More >

Amira Tarek Mahmoud^1,*, Wael A. Awad², Gamal Behery², Mohamed Abouhawwash^3,4, Mehedi Masud⁵, Hanan Aljuaid⁶, Ahmed Ismail Ebada⁷

Intelligent Automation & Soft Computing, Vol.36, No.2, pp. 2007-2023, 2023, DOI:10.32604/iasc.2023.031692

Abstract The accuracy of fingerprint recognition model is extremely important due to its usage in forensic and security fields. Any fingerprint recognition system has particular network architecture whereas many other networks achieve higher accuracy. To solve this problem in a unified model, this paper proposes a model that can automatically specify itself. So, it is called an automatic deep neural network (ADNN). Our algorithm can specify the appropriate architecture of the neural network used and some significant parameters of this network. These parameters are the number of filters, epochs, and iterations. It guarantees the highest accuracy by updating itself until achieving… More >

B. Divya^*, M. Santhi

Intelligent Automation & Soft Computing, Vol.36, No.2, pp. 1881-1898, 2023, DOI:10.32604/iasc.2023.031573

Abstract Pest detection in agricultural crop fields is the most challenging task, so an effective pest detection technique is required to detect insects automatically. Image processing techniques are widely preferred in agricultural science because they offer multiple advantages like maximal crop protection, improved crop management and productivity. On the other hand, developing the automatic pest monitoring system dramatically reduces the workforce and errors. Existing image processing approaches are limited due to the disadvantages like poor efficiency and less accuracy. Therefore, a successful image processing technique based on FF-GWO-CNN classification algorithm is introduced for effective pest monitoring and detection. The four-step image… More >