EAI Endorsed Transactions on Industrial Networks and Intelligent Systems

Bi-objective model for community detection in weighted complex networks

2024-08-02T19:56:29+00:00

In this study, we introduce an innovative approach that utilizes complex networks and the k_core method to address community detection in weighted networks. Our proposed bi-objective model aims to simultaneously discover non-overlapping communities while ensuring that the degree of similarity remains below a critical threshold to prevent network degradation. We leverage the k_core structure to detect tightly interconnected node groups, a concept particularly valuable in edge-weighted networks where different edge weights indicate the strength or importance of node relationships. Beyond maximizing the count of k_core communities, our model seeks a homogeneous weight distribution across edges within these communities, promoting stronger cohesion. To tackle this challenge, we implement two multi-target algorithms: Non-dominated Sorting Genetic Algorithm II (NSGAII) and a Multi-Objective Simulated Annealing (MOSA) algorithm. Both algorithms efficiently identify non-overlapping communities with a specified degree 'k'. The results of our experiments reveal a trade-off between maximizing the number of k_core communities and enhancing the homogeneity of these communities in terms of their minimum weighted interconnections. Notably, the MOSA algorithm outperforms NSGAII in both small and large instances, demonstrating its effectiveness in achieving this balance. This approach sheds light on effective strategies for resolving conflicting goals in community detection within weighted networks.

Emotional Inference from Speech Signals Informed by Multiple Stream DNNs Based Non-Local Attention Mechanism

2024-08-02T20:20:22+00:00

It is difficult to determine whether a person is depressed due to the symptoms of depression not being apparent. However, the voice can be one of the ways in which we can acknowledge signs of depression. Understanding human emotions in natural language plays a crucial role for intelligent and sophisticated applications. This study proposes deep learning architecture to recognize the emotions of the speaker via audio signals, which can help diagnose patients who are depressed or prone to depression, so that treatment and prevention can be started as soon as possible. Specifically, Mel-frequency cepstral coefficients (MFCC) and Short Time Fourier Transform (STFT) are adopted to extract features from the audio signal. The multiple streams of the proposed DNNs model, including CNN-LSTM based on an attention mechanism, are discussed within this research. Leveraging a pretrained model, the proposed experimental results yield an accuracy rate of 93.2% on the EmoDB dataset. Further optimization remains a potential avenue for future development. It is hoped that this research will contribute to potential application in the fields of medical treatment and personal well-being.

ViMedNER: A Medical Named Entity Recognition Dataset for Vietnamese

2024-07-11T14:39:06+00:00

Named entity recognition (NER) is one of the most important tasks in natural language processing, which identifies entity boundaries and classifies them into pre-defined categories. In literature, NER systems have been developed for various languages but limited works have been conducted for Vietnamese. This mainly comes from the limitation of available and high-quality annotated data, especially for specific domains such as medicine and healthcare. In this paper, we introduce a new medical NER dataset, named ViMedNER, for recognizing Vietnamese medical entities. Unlike existing works designed for common or too-specific entities, we focus on entity types that can be used in common diagnostic and treatment scenarios, including disease names, the symptoms of the diseases, the cause of the diseases, the diagnostic, and the treatment. These entities facilitate the diagnosis and treatment of doctors for common diseases. Our dataset is collected from four well-known Vietnamese websites that are professional in terms of drag selling and disease diagnostics and annotated by domain experts with high agreement scores. To create benchmark results, strong NER baselines based on pre-trained language models including PhoBERT, XLM-R, ViDeBERTa, ViPubMedDeBERTa, and ViHealthBERT are implemented and evaluated on the dataset. Experiment results show that the performance of XLM-R is consistently better than that of the other pre-trained language models. Furthermore, additional experiments are conducted to explore the behavior of the baselines and the characteristics of our dataset.

Efficient LDPC Code Design based on Genetic Algorithm for IoT Applications

2024-08-01T15:24:03+00:00

In this paper, we propose a low-density parity check (LDPC) code design scheme that improves the performance of the existing genetic algorithm-based LDPC scheme. In particular, we enhance the performance of the LDPC code by removing the girth-4 property of the parity check matrix and utilizing the min-sum decoding algorithm instead of the belief propagation decoding algorithm. In addition, we consider different short block-length scenarios, including 64-bit and 128-bit block length. Then, we evaluate the block error rate (BLER) of the LDPC code over the binary input additive white Gaussian noise (BI-AWGN) channel. Finally, extensive simulation results indicate that our proposed approach achieves more than 11% gain in terms of BLER compared with the benchmarked schemes.

A Secure Cooperative Image Super-Resolution Transmission with Decode-and-Forward Relaying over Rayleigh Fading Channels

2024-09-02T14:58:30+00:00

In addition to susceptibility to performance degradation due to hardware malfunctions and environmental influences, wireless image transmission poses risks of information exposure to eavesdroppers. This paper delves into the image communications within wireless relay networks (WRNs) and proposes a secure cooperative relaying (SCR) protocol over Rayleigh fading channels. In this protocol, a source node (referred to as Alice) transmits superior-resolution (SR) images to a destination node (referred to as Bob) with the assistance of a mediating node (referred to as Relay) operating in decode-and-forward mode, all while contending with the presence of an eavesdropper (referred to as Eve). In order to conserve transmission bandwidth, Alice firstly reduces the size of the original SR images before transmitting them to Relay and Bob. Subsequently, random linear network coding (RLNC) is employed by both Alice and Relay on the downscaled poor-resolution (PR) images to obscure the original images from Eve, thereby bolstering the security of the image communications. Simulation results demonstrate that the proposed SCR protocol surpasses both secure relaying transmission without a direct link and secure direct transmission without relaying links.

Additionally, a slight reduction in image quality can be achieved by increasing the scaling factor for saving transmission bandwidth. Furthermore, the results highlight the SCR protocol’s superior effectiveness at Bob’s end when compared to Eve’s, which is due to Eve’s lack of access to the RLNC coefficient matrices and reference images utilised by Alice and Relay in the RLNC process. Finally, the evaluation of reference images, relay allocations and diversity reception over Rayleigh fading channels confirms the effectiveness of the SCR protocol for secure image communications in the WRNs.