Journal of Intelligent & Fuzzy Systems - Volume 46, issue 4

Authors: Tomy, Navin | Johnson, T.P.

Article Type: Research Article

Abstract: This paper deals with lattice isomorphic L -topological spaces. We are concerned with a question: Under what conditions will a lattice isomorphic L -topological spaces be L -homeomorphic. We give contributions to this question in three different ways.

Keywords: L-homeomorphism, quasi L-homeomorphism, lattice isomorphism, pL-homeomorphism

DOI: 10.3233/JIFS-234375

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 4, pp. 9069-9082, 2024

Authors: Liu, Gan | Qi, Guirong | Wan, Sanyu

Article Type: Research Article

Abstract: Imbalanced data is a serious binary classification difficulty in forecasting the well-being of the elderly. This paper improves the Smote algorithm from the algorithm and sample dimensions to tackle the issue of imbalanced distribution of questionnaire data. The k-means Smote is combined with RBFNN as K-RBFNN Smote in the algorithm dimension and add FCM link to resample the minority set in the sample dimension as FCM K-RBFNN Smote. In order to improve the generalization of models, the RUS module is added to the algorithm. Experiments are carried out on four improved Smote technologies and two existing Smote technologies combined with …XGBoost, which is superior than the other five conventional classification models. The experimental results indicate that the performance order is RUS FCM K-RBFNN Smote > K-RBFNN Smote > FCM K-RBFNN Smote > RUS K-RBFNN Smote > K-Means Smote > FCM Smote. The RUS FCM K-RBFNN method has been identified as the optimal approach for enhancing performance, resulting in a 98.58% accuracy rate. In conclusion, Smote algorithm undergoes the implementation of K-RBFNN shows greater performance and the enhancement of FCM and RUS relies on the structure of sampling. Show more

Keywords: RUS FCM K-RBFNN Smote, XGBoost, imbalanced data, elderly well-being classification

DOI: 10.3233/JIFS-235213

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 4, pp. 9083-9102, 2024

Authors: Abraham, Asha | Kayalvizhi, R. | Mohideen, Habeeb Shaik

Article Type: Research Article

Abstract: This article has been retracted. A retraction notice can be found at https://doi.org/10.3233/JIFS-219433 .

DOI: 10.3233/JIFS-236197

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 4, pp. 9103-9117, 2024

Authors: Jumde, Amol | Keskar, Ravindra

Article Type: Research Article

Abstract: With tremendous evolution in the internet world, the internet has become a household thing. Internet users use search engines or personal assistants to request information from the internet. Search results are greatly dependent on the entered keywords. Casual users may enter a vague query due to lack of knowledge of the domain-specific words. We propose a query reformulation system that determines the context of the query, decides on keywords to be replaced and outputs a better-modified query. We propose strategies for keyword replacements and metrics for query betterment checks. We have found that if we project keywords into the vector …space of word projection using word embedding techniques and if the keyword replacement is correct, clusters of a new set of keywords become more cohesive. This assumption forms the basis of our proposed work. To prove the effectiveness of the proposed system, we applied it to the ad-hoc retrieval tasks over two benchmark corpora viz TREC-CDS 2014 and OHSUMED corpus. We indexed Whoosh search engine on these corpora and evaluated based on the given queries provided along with the corpus. Experimental results show that the proposed techniques achieved 9 to 11% improvement in precision and recall scores. Using Google’s popularity index, we also prove that the reformulated queries are not only more accurate but also more popular. The proposed system also applies to Conversational AI chatbots like ChatGPT, where users must rephrase their queries to obtain better results. Show more

Keywords: Query reformulation, WordNet, word embedding, whoosh, TREC

DOI: 10.3233/JIFS-236296

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 4, pp. 9119-9137, 2024

Authors: Selvakumar, B. | Abinaya, P. | Lakshmanan, B. | Sheron, S. | Smitha Rajini, T.

Article Type: Research Article

Abstract: Security and privacy are major concerns in this modern world. Medical documentation of patient data needs to be transmitted between hospitals for medical experts opinions on critical cases which may cause threats to the data. Nowadays most of the hospitals use electronic methods to store and transmit data with basic security measures, but these methods are still vulnerable. There is no perfect solution that solves the security problems in any industry, especially healthcare. So, to cope with the arising need to increase the security of the data from being manipulated the proposed method uses a hybrid image encryption technique to …hide the data in an image so it becomes difficult to sense the presence of data in the image while transmission. It combines Least Significant Bit (LSB) Algorithm using Arithmetic Division Operation along with Canny edge detection to embed the patient data in medical images. The image is subsequently encrypted using keys of six different chaotic maps sequentially to increase the integrity and robustness of the system. Finally, an encrypted image is converted into DNA sequence using DNA encoding rule to improve reliability. The experimentation is done on the Chest XRay image, Knee Magnetic Resonance Imaging (MRI) image, Neck MRI image, Lungs Computed Tomography (CT) Scan image datasets and patient medical data with 500 characters, 1000 characters and 1500 characters. And, it is evaluated based on time coefficient of encryption and decryption, histogram, entropy, similarity score (Mean Square Error), quality score (peak signal-to-noise ratio), motion activity index (number of changing pixel rate), unified average changing intensity, image similarity score (structure similarity index measurement) between original and encrypted images. Also, the proposed technique is compared with other recent state of arts methods for 500 characters embedding and performed better than those techniques. The proposed method is more stable and embeds comparatively more data than other recent works with lower Mean Square Error value of 4748.12 which is the main factor used to determine how well the data is hidden and cannot be interpreted easily. Also, it achieved a Peak Signal-Noise Ratio (PSNR) value of 71.34 dB, which is superior than other recent works, verifying that the image quality remains uncompromising even after being encrypted. Show more

Keywords: Hybrid image encryption, least significant bit algorithm, arithmetic division operation, canny edge detection algorithm, chaotic maps, DNA encoding

DOI: 10.3233/JIFS-236637

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 4, pp. 9139-9153, 2024

Authors: Zhong, Yu | Shen, Bo | Wang, Tao

Article Type: Research Article

Abstract: Document-level relation extraction aims to uncover relations between entities by harnessing the intricate information spread throughout a document. Previous research involved constructing discrete syntactic matrices to capture syntactic relationships within documents. However, these methods are significantly influenced by dependency parsing errors, leaving much of the latent syntactic information untapped. Moreover, prior research has mainly focused on modeling two-hop reasoning between entity pairs, which has limited applicability in scenarios requiring multi-hop reasoning. To tackle these challenges, a syntax-enhanced multi-hop reasoning network (SEMHRN) is proposed. Specifically, the approach begins by using a dependency probability matrix that incorporates richer grammatical information instead of …a sparse syntactic parsing matrix to build the syntactic graph. This effectively reduces syntactic parsing errors and enhances the model’s robustness. To fully leverage dependency information, dependency-type-aware attention is introduced to refine edge weights based on connecting edge types. Additionally, a part-of-speech prediction task is included to regularize word embeddings. Unrelated entity pairs can disrupt the model’s focus, reducing its efficiency. To concentrate the model’s attention on related entity pairs, these related pairs are extracted, and a multi-hop reasoning graph attention network is employed to capture the multi-hop dependencies among them. Experimental results on three public document-level relation extraction datasets validate that SEMHRN achieves a competitive F1 score compared to the current state-of-the-art methods. Show more

Keywords: Attention mechanism, document-level relation extraction, syntactic information, multi-hop reasoning

DOI: 10.3233/JIFS-237167

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 4, pp. 9155-9171, 2024

Authors: Amiri-Bideshki, M. | Hoskova-Mayerova, S. | Ameri, R.

Article Type: Research Article

Abstract: This article has been retracted. A retraction notice can be found at https://doi.org/10.3233/JIFS-219433 .

DOI: 10.3233/JIFS-237912

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 4, pp. 9173-9178, 2024

Authors: Khan, Younas | Ashraf, Shahzaib | Farman, Muhammad | Abdallah, Suhad Ali Osman

Article Type: Research Article

Abstract: Achieving household food security is the tumbling issue of the century. This article explores the factors affecting household food security and solutions by utilizing a synergy of statistical and mathematical models. The methodology section is divided into two portions namely sociological and mathematical methods. Sociologically, 379 household heads were interviewed through structured questions and further analyzed in terms of descriptive and binary logistic regression. The study found that 4 independent variables (poverty, poor governance, militancy, and social stratification) showed a significant association (P  = 0.000) to explain variations in the dependent variable (household FS). The Omnibus test value (χ2 = 102.386; P … = 0.000) demonstrated that the test for the entire model against constant was statistically significant. Therefore, the set of predictor variables could better distinguish the variation in household FS. The Nagelkerke’s R Square (R2  = .333) helps to interpret that the prediction variable and the group variables had a strong relationship. Moreover, 23% to 33% variation in FS was explained by the grouping variables (Cox and Snell R2  = 0.237 and Nagelkerke’s R2  = 0.333). The significant value of Wald test results for each variable confirmed that the grouping variables (poor governance P  = 0.004, militancy P  = 0.000, social stratification P  = 0.021 and poverty P  = 0.000) significantly predicted FS at the household level. Mathematically, all the statistics were validated further through the application of spherical fuzzy mathematics (TOPIS and MADM) to explore what factors are affecting household FS. Thus, the study found that F 3  (poverty ) > F 2  (militancy) > F 4  (social stratification) > F 1 (poor governance) respectively. Thus, it could be concluded from these findings that the prevalence of poverty dysfunctional all the channels of household FS at the macro and micro levels. Therefore, a sound and workable model to eradicate poverty in the study area by ensuring social safety nets for the locals was put forward some of the policy implications for the government are the order of the day. Show more

Keywords: Food security, militancy, poor governance, social stratification, poverty, logistic regression, TOPIS, MADM, spherical fuzzy set

DOI: 10.3233/JIFS-237938

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 4, pp. 9179-9195, 2024

Authors: Seethappan, K. | Premalatha, K.

Article Type: Research Article

Abstract: Even though various features have been investigated in the detection of figurative language, oxymoron features have not been considered in the classification of sarcastic content. The main objective of this work is to present a system that can automatically classify sarcastic phrases in multi-domain data. This multi-domain dataset consisting of 67850 sarcastic and non-sarcastic data is collected from various websites to identify sarcastic or non-sarcastic utterances. Multiple approaches are examined in this work to improve sarcasm identification: 1. A Combination of fasttext embedding, syntactic, semantic, lexical n-gram, and oxymoron features 2. TF-IDF feature weighting scheme 3. Three machine learning algorithms …(SVM, Multinomial Naïve Bayes, and Random Forest), three deep learning algorithms (CNN, LSTM, MLP), and one ensemble model (CNN + LSTM) The CNN + LSTM model achieves a Precision of 91.32%, Recall of 92.85%, F-Score of 92.08%, accuracy of 92.01%, and Kappa of 0.84 by combining the fasttext embedding, bigram, syntactic, semantic, and oxymoron features with TF-IDF method. These experimental results show CNN + LSTM with a combination of all features outperforms the other algorithms in classifying the sarcasm in both datasets. The sarcasm classification performance of our dataset and another sarcasm news dataset was compared while applying the above model. Show more

Keywords: Natural language processing, sarcasm, figurative language, deep learning, CNN, oxymoron

DOI: 10.3233/JIFS-224110

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 4, pp. 9197-9207, 2024

Authors: Sangeetha, R. | Kuriakose, Bessy M. | Naveen, V. Edward | Jenefa, A. | Lincy, A.

Article Type: Research Article

Abstract: This article has been retracted. A retraction notice can be found at https://doi.org/10.3233/JIFS-219433 .

DOI: 10.3233/JIFS-231113

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 4, pp. 9209-9223, 2024