Authors: Ramasamy, Mekala | Elangovan, Mohanraj

Article Type: Research Article

Abstract: The recent development of communication technologies made it possible for people to share opinions on various social media platforms. The opinion of the people is converted into small-sized textual data. Aspect Based Sentiment Analysis (ABSA) is a process used by businesses and other organizations to assess these textual data in order to comprehend people’s opinions about the services or products offered by them. The majority of earlier Sentiment Analysis (SA) research uses lexicons, word frequencies, or black box techniques to obtain the sentiment in the text. It should be highlighted that these methods disregard the relationships and interdependence between words …in terms of semantics. Hence, an efficient ABSA framework to determine the sentiment from the textual reviews of the customers is developed in this work. Initially, the raw text review data is collected from the standard benchmark datasets. The gathered text reviews undergo text pre-processing to neglect the unwanted words and characters from the input text document. The pre-processed data is directly provided to the feature extraction phase in which the seq2seq network and transformer network are employed. Further, the optimal features from the two resultant features are chosen by utilizing the proposed Modified Bird Swarm-Ladybug Beetle Optimization (MBS-LBO). After obtaining optimal features, these features are fused together and given to the final detection model. Consequently, the Optimized Cascaded Long Short Term Memory (OCas-LSTM) is proposed for predicting the sentiments from the given review by the users. Here, the parameters are tuned optimally by the MBS-LBO algorithm, and also it is utilized for enhancing the performance rate. The experimental evaluation is made to reveal the excellent performance of the developed SA model by contrasting it with conventional models. Show more

Keywords: Aspect-based sentiment analysis, optimized cascaded long short term memory, Modified Bird Swarm-Ladybug Beetle Optimization, optimal aspect feature selection, sequence-to-sequence network, transformer network

DOI: 10.3233/WEB-230096

Citation: Web Intelligence, vol. Pre-press, no. Pre-press, pp. 1-26, 2024

Authors: Sasirekha, K. | Asha, D. | Sivaganga, P. | Harini, R.

Article Type: Research Article

Abstract: The integrated system has generated numerous features for the users, like as identifying heart disease by its symptoms, forwarding the information to the doctors regarding the phase of the probability of disease as well as aiding to fix it. When an emergency situation exists, the system forwards the emergency alert to the respective doctor. Moreover, the automatic system is needed to diagnose heart disease but, the larger data is not sufficient to train the model. Thus, the Internet of Things (IoT) is employed to manage the huge amount of data. Therefore, a novel prediction of heart diseases is implemented with …the aid of IoT-based deep learning approaches. Here, the collected data is collected from the three standard databases and then perform preprocessed over the gathered data. Here, the IoT assisted deep learning model is performed to predict heart related diseases accurately. Further, the acquired features of heart diseases are selected using the developed Hybrid Chameleon Electric Fish Swarm Optimization (HCEFSO) via Chameleon Swarm Algorithm (CSA) and Electric Fish Optimization (EFO). Then, the optimally selected features are fed to the training process, where the Trans-Bi-directional Long Short-Term Memory with Gated Recurrent Unit (Trans-Bi-LSTM-GRU) is adopted for predicting heart diseases. Here, the weights are updated with the developed HCEFSO while validating the training phase. The trained Trans-Bi-LSTM-GRU network is used in the testing phase for predicting heart diseases. Show more

Keywords: Hybrid Chameleon Electric Fish Swarm Optimization, IoT-based heart disease prediction, Gated Recurrent Unit, Weight Updated Trans-Bidirectional Long Short Term Memory

DOI: 10.3233/WEB-230063

Citation: Web Intelligence, vol. Pre-press, no. Pre-press, pp. 1-28, 2024

Authors: Anastasios, Vazakas

Article Type: Research Article

Abstract: Creative ideas are introduced to the market by business owners, and inventiveness creates new demands that cause existing markets to be disrupted and new ones to be created, which are then destroyed by even more innovative goods or services. In this rsesearch work, an empirical study is undertaken to gather information about business model innovation and creativity as well as Entrepreneurship development in Greek SMEs. Using the stratum sample size determination formula, a valid sample of 257 people influenced the study. SEM and the F-test were used in the research’s data analysis. The findings of the study demonstrate that entrepreneurship …has a significant connection between business model innovation & creativity and digital capabilities. The test results also indicate that digital capabilities have a favorable impact on the business model innovation & creativity. They also found that the creativity and innovation of business models have a favorable impact on entrepreneurs’ business survival. However, the creativity and innovation of business models have no favorable impact on entrepreneurs’ business performance and reputation. Show more

Keywords: Entrepreneurship Development, business Model, innovation, digital capability, creativity

DOI: 10.3233/WEB-230006

Citation: Web Intelligence, vol. Pre-press, no. Pre-press, pp. 1-15, 2024

Authors: Peng, Ningkang | Guo, Shengjie | Yuan, Shuai | Kitsuregawa, Masaru | Gu, Yanhui

Article Type: Research Article

Abstract: With the rapid advancement of deep learning technologies, self-supervised learning utilizing large-scale unlabeled datasets has emerged as a dominant learning paradigm across multiple fields. This paradigm aligns well with the nature of medical imaging data, which has led to significant research efforts in applying self-supervised learning methods to this domain. However, many of these approaches fail to fully consider the unique characteristics of medical imaging, particularly the critical role that texture information plays in the diagnosis of thorax diseases. To address this gap, we propose a novel texture-aware self-supervised learning framework that leverages the Gray-Level Co-occurrence Matrix (GLCM) as an …auxiliary signal to strengthen the model’s capacity to extract disease-relevant texture features. Additionally, we integrate curriculum learning into our approach, which gradually emphasizes texture information throughout the training process. This method enables the model to more effectively capture the inherent characteristics of medical imaging data. Our qualitative and quantitative experimental results show that our approach surpasses the current state-of-the-art methods on both the NIH CXR and Stanford CheXpert datasets. Show more

Keywords: Self-supervised learning, medical image analysis, thorax disease diagnosis

DOI: 10.3233/WEB-240279

Citation: Web Intelligence, vol. Pre-press, no. Pre-press, pp. 1-13, 2024

Authors: Almadhoun, Mohamed D. | Malim, Nurul Hashimah Ahamed Hassain

Article Type: Research Article

Abstract: It is essential to use search engines to get the needed information. A search engine uses result matching to match the user’s query with appropriate web pages. Users see the search results in a certain order based on how they are ranked. A website or web page may be made better using search engine optimization (SEO), which will increase the amount of organic traffic it receives from search engines. If we can’t manage efficient SEO techniques to rank at the top of organic search results, a lot of money will be spent on sponsored adverts for certain keywords. The process …of building rank estimate algorithms for search engine results pages (SERP) or applying data analysis to find the best SEO tactics has been employed in several research projects. The datasets of existing studies were undiversified since they only included web pages from one or a small number of categories. This research will improve rank estimation algorithms by using multi-category web pages in the training datasets and will provide demonstrations of improvement on SERP rank estimation algorithms for English web pages. Since Google receives more than 90% of all internet search submissions, scraping will be used there. For the chosen web pages, a collection of on-page SEO variables will be retrieved. The methodology starts with choosing a set of search terms and scraping search engines, then crawling SERP web pages to extract certain SEO criteria from the contents of web pages, and lastly getting to data preprocessing. Various machine learning techniques were used to compare performance and choose the optimal approach. The main finding of research is the enhancement of SERP rank estimation by more than 25% on performance with the proposed dataset improvements for building models. Show more

Keywords: Search engine optimization, search engine results page, rank estimation, scrape search engine, machine learning, digital marketing

DOI: 10.3233/WEB-230239

Citation: Web Intelligence, vol. Pre-press, no. Pre-press, pp. 1-17, 2024

Authors: Liu, Changyu | Huang, Hao | Gao, Zhankai | Pei, Jiawei | Huang, Ziling | He, Yicong

Article Type: Review Article

Abstract: In this paper, the development of action and event detectors over the past three decades is summarized. The detectors are divided into 2D detectors, 3D detectors and deep learning detectors according to whether they contain spatial information and whether they use deep learning. This paper briefly introduces the typical detectors of the different types mentioned above, and explains the advantages, disadvantages and characteristics respectively, and compares them. Comparing traditional feature detection methods with ones based on deep learning, we found that the method of first detecting microscopic details such as point, line, surface angle, etc., and then performing action and …event recognition is no longer the mainstream of current research. Due to the strong generalization ability, end-to-end action and event recognition methods based on deep learning perform better than traditional methods. Finally, this paper proposes three research directions for action recognition and event recognition based on feature detectors. Show more

Keywords: Action recognition, detector, detection, deep learning

DOI: 10.3233/WEB-220084

Citation: Web Intelligence, vol. Pre-press, no. Pre-press, pp. 1-19, 2024

Authors: Sonawane, Sunil | Gulwani, Reshma | Sharma, Pooja

Article Type: Research Article

Abstract: Malicious traffic segregation and attack detection caused major financial loss and became one of the most serious security hazards. Moreover, cyber security attack is the major issue, which impacts network security. The network attack methods are constantly being upgraded by the technology development and it remains a major issue for detection and protection against network attacks. For this, it is required to present an effective strategy for detecting and maintaining network security. The work provides timely and accurate congestion attack detection and identification. In the Internet of Things (IoT) cloud system malicious traffic segregation and attack detection based on a …hybrid optimization-enabled deep learning (DL) network is developed in this research. At first, the input log files are gathered from the simulation of IoT sensors and the superior route is selected by the proposed Fractional Hunger Jellyfish Search Optimization (FHGJO) algorithm. The FHGJO is the integration of Hunger Game Jelly Fish Optimization (HGJO) and Fractional Calculus (FC). Furthermore, the HGJO is the combination of Hunger Game Search Optimization (HGS) with Jellyfish Optimization (JSO). Then, the segregation is done based on the fitness measures and for preprocessing; the input data is fed using quantile normalization. The feature selection process is employed using the weighted Euclidian distance (WED). With the SpinalNet, the malicious segregation is categorized as malicious and non-malicious and the proposed FHJGO is used to tune the SpinalNet. Furthermore, the proposed FHGJO-trained Deep Quantum Neural Network (DQNN) is utilized to detect the attack and classifies it into a Denial-of-Service (DOS) attack, Distributed Denial of Service (DDoS) attack, and buffer overflow attack. Moreover, the proposed model is evaluated using the NSL-KDD dataset and BoT-IoT dataset. The proposed method ensures network security with 0.931 accuracy, 0.923 sensitivity, and 0.936 specificity. Show more

Keywords: Deep Quantum Neural Network, weighted Euclidian distance, Hunger Game Search Optimization, Jelly Fish Optimization, Fractional Calculus

DOI: 10.3233/WEB-230214

Citation: Web Intelligence, vol. Pre-press, no. Pre-press, pp. 1-23, 2024

Authors: Kaulgud, Rama Vaibhav | Patil, Arun

Article Type: Research Article

Abstract: Lung cancer patients’ chances of survival can increase with early detection. For the diagnosis of lung cancer, precise lung nodule identification in computed tomography (CT) images is crucial. The variety of the lung nodules and the complexity of the surroundings, however, have made robust nodule identification a challenging problem. To address this challenge, the Extensible Hunt Optimization-based deep Convolutional Neural Network classifier (EHO-deep CNN), is developed in this research for detecting the lung nodules present in the CT images. The proposed model in which the preprocessing is performed through the median filter to eliminate the artifacts in the image. Specifically, …the images are segmented by adopting the centralized superpixels segmentation-based iterative clustering (CSSBIC) technique that enhances the accuracy of segmentation. The proposed approach relies on the GLCM and the VGG16-based feature extraction to explicate the discrimination of the lung nodule features. In addition, the retrieved features are combined and fed forwarded to the Deep CNN classifier that is optimally tuned via the EHO algorithm. The EHO algorithm is developed by fusing the fitness function of Border collie dogs with the hunting characteristics of Dingo to enhance convergence rate and performance. The proposed EHO-deep CNN is reported in terms of accuracy, sensitivity, and specificity values as 98.13%, 98.98%, and 97.28% when measuring TP 80 for the LIDC-IDRI dataset and 96.09%, 96.70%, and 95.48% for measuring k-fold 10. Further, implementing the suggested model obtains the values of 95.34%, 92.88%, and 97.80% for the LUNA 16 dataset when measuring TP 80 and 98.21%, 98.06%, 98.35% when measuring k-fold 10, which outperforms other existing techniques in effectiveness. Show more

Keywords: Extensible hunt optimization, CSSBIC algorithm, Convolutional Neural Network, computed tomography, lung nodule detection

DOI: 10.3233/WEB-230008A

Citation: Web Intelligence, vol. Pre-press, no. Pre-press, pp. 1-20, 2024

Authors: Bhowate, Vikas Gajananrao | Reddy, T. Hanumantha

Article Type: Research Article

Abstract: Imbalanced data classification (IDC) presents a significant challenge in data mining (DM), as it frequently occurs in various real-world areas with profound implications for highly skewed databases. IDC revolves around the task of learning from data characterized by a substantial imbalance in the number of samples across its different classes. Hence the Polar-CanisFel (PCF) Optimization-deep ensemble model is designed to address imbalanced big data issues, incorporating the SMOTE technique for rebalancing the dataset. This ensemble classifier leverages a deep convolutional neural network (DCNN), Long Short-Term Memory (LSTM), and Gated Recurrent Neural Network (GRNN) architectures for effective data classification. For the …Heart Failure Prediction Dataset, the model reaches an accuracy of 96.35%, sensitivity of 94.54%, and specificity of 96.11%. Further, the accuracy of 95.91%, sensitivity of 95.87%, and specificity of 94.79% are obtained concerning the Stroke Prediction dataset. Finally, when applied to the Hepatitis-C prediction dataset, the model attains an accuracy of 92.79%, sensitivity of 92.90%, and specificity of 92.63% during 90% of training. Show more

Keywords: Imbalanced data classification, SMOTE, Data balancing, Polar-CanisFel optimization, Deep ensemble classifier

DOI: 10.3233/WEB-230248

Citation: Web Intelligence, vol. Pre-press, no. Pre-press, pp. 1-22, 2024

Authors: Karpe, Sharmila Patil | SH, Brahmananda

Article Type: Research Article

Abstract: With the rapid proliferation of IoT devices, the volume of data generated has reached unprecedented levels, necessitating efficient management strategies. Fog computing, complemented by 5G technologies, offers promising solutions to reduce service latency and enhance Quality of Service (QoS). However, allocating resources effectively remains challenging due to factors such as uncertainty, mobility, heterogeneity, and limited resources in fog computing environments. Traditional resource allocation (RA) algorithms often fall short of addressing these complexities. This study proposes a novel approach to RA in fog computing, utilizing a non-linear function to optimize resource allocation. An objective function is introduced, incorporating multi constraints such …as resource utilization, service response rate, makespan, migration cost, and communication cost. The methodology emphasizes efficient resource allocation in crucial scenarios, facilitating rapid resource distribution where needed. The novel Coati Integrated Beluga Whale Optimization (CI-BWO) strategy is proposed to achieve optimal resource allocation in fog computing environments. By leveraging CI-BWO, this research aims to overcome the limitations of traditional RA methods and enhance the performance and scalability of fog computing applications. Finally, the superiority of the suggested strategy is assessed by comparison with many existing methods. When the task count is 200, the developed CI-BWO attained less migration cost of around 1.287, while existing models have acquired higher migration costs. Show more

Keywords: Heterogeneity inFog computing, optimal resource allocation, migration cost, resource prioritization, hybrid optimization algorithm

DOI: 10.3233/WEB-230332

Citation: Web Intelligence, vol. Pre-press, no. Pre-press, pp. 1-22, 2024