Jiaqi Wang¹, Jie Zhang², Genlin Ji^2,*, Bo Sheng³

Intelligent Automation & Soft Computing, Vol.34, No.3, pp. 1629-1642, 2022, DOI:10.32604/iasc.2022.029535

Abstract The surveillance applications generate enormous video data and present challenges to video analysis for huge human labor cost. Reconstruction-based convolutional autoencoders have achieved great success in video anomaly detection for their ability of automatically detecting abnormal event. The approaches learn normal patterns only with the normal data in an unsupervised way due to the difficulty of collecting anomaly samples and obtaining anomaly annotations. But convolutional autoencoders have limitations in global feature extraction for the local receptive field of convolutional kernels. What is more, 2-dimensional convolution lacks the capability of capturing temporal information while videos change over time. In this paper,… More >

Chenxi Yu, Xin Li^*

Intelligent Automation & Soft Computing, Vol.34, No.3, pp. 2023-2034, 2022, DOI:10.32604/iasc.2022.029447

Abstract Machine reading comprehension (MRC) is a task in natural language comprehension. It assesses machine reading comprehension based on text reading and answering questions. Traditional attention methods typically focus on one of syntax or semantics, or integrate syntax and semantics through a manual method, leaving the model unable to fully utilize syntax and semantics for MRC tasks. In order to better understand syntactic and semantic information and improve machine reading comprehension, our study uses syntactic and semantic attention to conduct text modeling for tasks. Based on the BERT model of Transformer encoder, we separate a text into two branches: syntax part… More >

Daqing Wu^1,2, Jiye Cui^1,*, Dan Li³, Romany Fouad Mansour⁴

Intelligent Automation & Soft Computing, Vol.34, No.3, pp. 1553-1569, 2022, DOI:10.32604/iasc.2022.028780

Abstract Under the fierce market competition and the demand of low-carbon economy, the freshness of fresh products directly determines the degree of customer satisfaction. Cold chain logistics companies must pay attention to the freshness and carbon emissions of fresh products to obtain better service development. In the cold chain logistics path optimization problem, considering the cost, product freshness and carbon emission environmental factors at the same time, based on the cost-benefit idea, a comprehensive cold chain vehicle routing problem optimization model is proposed to minimize the unit cost of product freshness and the carbon trading mechanism for calculating the cost of… More >

Jianquan Ouyang^1,*, Jing Zhang¹, Tianming Liu²

Intelligent Automation & Soft Computing, Vol.34, No.3, pp. 1707-1723, 2022, DOI:10.32604/iasc.2022.028352

Abstract Joint entity and relation extraction (JERE) is an important foundation for unstructured knowledge extraction in natural language processing (NLP). Thus, designing efficient algorithms for it has become a vital task. Although existing methods can efficiently extract entities and relations, their performance should be improved. In this paper, we propose a novel model called Attention and Span-based Entity and Relation Transformer (ASpERT) for JERE. First, differing from the traditional approach that only considers the last hidden layer as the feature embedding, ASpERT concatenates the attention head information of each layer with the information of the last hidden layer by using an… More >

Ashit Kumar Dutta^1,*, Basit Qureshi², Yasser Albagory³, Majed Alsanea⁴, Anas Waleed AbulFaraj⁵, Abdul Rahaman Wahab Sait⁶

Intelligent Automation & Soft Computing, Vol.34, No.3, pp. 2097-2110, 2022, DOI:10.32604/iasc.2022.027500

Abstract Recently, the exponential utilization of Internet has posed several cybersecurity issues in social networks. Particularly, cyberbulling becomes a common threat to users in real time environment. Automated detection and classification of cyberbullying in social networks become an essential task, which can be derived by the use of machine learning (ML) and deep learning (DL) approaches. Since the hyperparameters of the DL model are important for optimal outcomes, appropriate tuning strategy becomes important by the use of metaheuristic optimization algorithms. In this study, an effective glowworm swarm optimization (GSO) with deep neural network (DNN) model named EGSO-DNN is derived for cybersecurity… More >

Kavitha Chinniyan^*, Thamil Vani Samiyappan, Aishvarya Gopu, Narmatha Ramasamy

Intelligent Automation & Soft Computing, Vol.34, No.3, pp. 1877-1891, 2022, DOI:10.32604/iasc.2022.027274

Abstract Steganography is the technique of hiding secret data within ordinary data by modifying pixel values which appear normal to a casual observer. Steganography which is similar to cryptography helps in secret communication. The cryptography method focuses on the authenticity and integrity of the messages by hiding the contents of the messages. Sometimes, it is not only just enough to encrypt the message but also essential to hide the existence of the message itself. As this avoids misuse of data, this kind of encryption is less suspicious and does not catch attention. To achieve this, Stacked Autoencoder model is developed which… More >

Sakorn Mekruksavanich¹, Anuchit Jitpattanakul^2,*

Intelligent Automation & Soft Computing, Vol.34, No.3, pp. 1907-1925, 2022, DOI:10.32604/iasc.2022.027233

Abstract Numerous learning-based techniques for effective human activity recognition (HAR) have recently been developed. Wearable inertial sensors are critical for HAR studies to characterize sport-related activities. Smart wearables are now ubiquitous and can benefit people of all ages. HAR investigations typically involve sensor-based evaluation. Sport-related activities are unpredictable and have historically been classified as complex, with conventional machine learning (ML) algorithms applied to resolve HAR issues. The efficiency of machine learning techniques in categorizing data is limited by the human-crafted feature extraction procedure. A deep learning model named MBiGRU (multimodal bidirectional gated recurrent unit) neural network was proposed to recognize everyday… More >

Vijaya Krishna Sonthi^1,*, S. Nagarajan¹, N. Krishnaraj²

Intelligent Automation & Soft Computing, Vol.34, No.3, pp. 1725-1736, 2022, DOI:10.32604/iasc.2022.026940

Abstract In India, Telugu is one of the official languages and it is a native language in the Andhra Pradesh and Telangana states. Although research on Telugu optical character recognition (OCR) began in the early 1970s, it is still necessary to develop effective printed character recognition for the Telugu language. OCR is a technique that aids machines in identifying text. The main intention in the classifier design of the OCR systems is supervised learning where the training process takes place on the labeled dataset with numerous characters. The existing OCR makes use of patterns and correlations to differentiate words from other… More >

Wen-Tsai Sung¹, Ching-Hao Weng¹, Sung-Jung Hsiao^2,*

Intelligent Automation & Soft Computing, Vol.34, No.3, pp. 1971-1988, 2022, DOI:10.32604/iasc.2022.026927

Abstract The Internet of Things (IoT) has flourished in recent years, which brings convenience to people’s lives, improves the quality of life, allows more effectively managing and maximizing benefits in industry, and improves weather predictions as the impact of global warming has complicated traditional methods to infer the weather. To this end, agriculture has also given more attention to greenhouse cultivation. In the early days of industrial research, Wi-Fi and ZigBee were used as short-or medium-distance communication technologies for transmissions in the network layer of the IoT architecture. Instead of long-distance communication technologies, such as LoRa and NB-IoT, the features of… More >

B. Gomathi¹, S. T. Suganthi^2,*, T. N. Prabhu³, Andriy Kovalenko⁴

Intelligent Automation & Soft Computing, Vol.34, No.3, pp. 1851-1860, 2022, DOI:10.32604/iasc.2022.026779

Abstract On the Internet of Vehicle (IoV) devices, offloading data is the major problem because massive amounts of data generate energy consumption, and the execution cost is high. At present, accidents traffic management is highly prominent due to increased vehicles among the population. IoV is the only technology to help the transport system effectively. This data outreach the memory also has high energy consumption, and the storage cost is high. To overcome these issues, a Mobility aware Offloading scheme with Multi-Objective Immune Optimization algorithm (MOS-MOIO) is used in the cloud storage. The data is generated from the online sensor system. The… More >