The serious security threat for Wireless Sensor Network comes from compromised nodes. Node Compromise (NC) effects oftwo types: independent and dependent. In independent type, the NC effect is limited to that node only; whereas in dependent,it will spread to all the nodes across the network. In literature, there is an intelligent model which predicts the spread of nodecompromise. This model suffers from false positives as it trusts the communication from neighbouring nodes. To address thisissue, our Parameter Grouping (PG) † mechanism is used in association with the existing Intelligent Model (IM). This ExtendedIntelligent Model (E-IM) performs better than the IM. The E-IM has studied through NS-2 based simulation and its performanceis analyzed.
1 January 2024 in Journal of Discrete Mathematical Sciences and Cryptography
This study introduces an Ant Lion-based Advanced Encryption Standard with Blockchain (ALAESB) model to enhance security and privacy in healthcare data management. Utilizing cloud storage, Electronic Health Records (EHR) are encrypted using AES and authenticated via blockchain. The methodology integrates hash functions and Merkle trees for data validation and secure block storage. Key generation is optimized through antlion fitness updates, ensuring efficient encryption and decryption processes. The model aims to mitigate privacy risks and secure patient data access for healthcare providers, emphasizing reliability and integrity in medical data handling.
11 February 2026 in Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology
In text classification tasks with complex models and high-stakes domains the alignment between predictions and explanations tends to be weak because post-hoc explainability methods operate independent of model training. In this paper, we suggest ATM-AM - an approach based on the Gated Recurrent Unit (GRU) that combines Bahdanau attention with a training-time SHAP-backed alignment objective to offer real-time, context-aware interpretability without trade-off in predictive performance. The model is tested over three frequently-used sentiment analysis datasets (IMDbhttps://huggingface.co/datasets/imdb, Amazon Reviews https://www.kaggle.com/datasets/bittlingmayer/amazonreviews, and SST-2. https://huggingface.co/datasets/glue/viewer/sst2) yielding accuracy scores of 91.8%, 89.5%, and 90.0% with respective F1-scores of 0.899, 0.877, and 0.889 respectively, on each dataset. We also average our measurements over three runs for statistical soundness. The additional training latency added by ATM-AM is quite modest (13–18%), and the inference time remains short (3–4 ms per sample), rendering it feasible to be deployed in real-time. A user-centered interpretability study with 30 participants obtained an average rating of 4.6/5 showing that users trust the explanations produced by our proposed model. These observations posit ATM-AM as a feasible and interpretable solution Text Classification in contexts where model behavior needs to be accountable and reliable.