
While automatic image captioning systems have made notable progress in the past few years, generating captions that fully convey sentiment remains a considerable challenge. Although existing models achieve strong performance in visual recognition and factual description, they often fail to account for the emotional context that is naturally present in human-generated captions. To address this gap, we propose the Sentiment-Driven Caption Generator (SDCG), which combines transformer-based visual and textual processing with multi-level fusion. RoBERTa is used for extracting sentiment from textual input, while visual features are handled by the Vision Transformer (ViT). These features are fused using several fusion approaches, including Concatenation, Attention, Visual-Sentiment Co-Attention (VSCA), and Cross-Attention. Our experiments demonstrate that SDCG significantly outperforms baseline models such as the Generalized Image Transformer (GIT), which achieves 82.01%, and Bootstrapping Language-Image Pre-training (BLIP), which achieves 83.07%, in sentiment accuracy. While SDCG achieves 94.52% sentiment accuracy and improves scores in BLEU and ROUGE-L, the model demonstrates clear advantages. More importantly, the captions are more natural, as they incorporate emotional cues and contextual awareness, making them resemble those written by a human.

Background: National and ethnic mutation frequency databases (NEMDBs) play a crucial role in documenting gene variations across populations, offering invaluable insights for gene mutation research and the advancement of precision medicine. These databases provide an essential resource for understanding genetic diversity and its implications for health and disease across different ethnic groups. Objective: The aim of this study is to systematically evaluate 42 NEMDBs to (1) quantify gaps in standardization (70% nonstandard formats, 50% outdated data), (2) propose artificial intelligence/linked open data solutions for interoperability, and (3) highlight clinical implications for precision medicine across NEMDBs. Methods: A systematic approach was used to assess the databases based on several criteria, including data collection methods, system design, and querying mechanisms. We analyzed the accessibility and user-centric features of each database, noting their ability to integrate with other systems and their role in advancing genetic disorder research. The review also addressed standardization and data quality challenges prevalent in current NEMDBs. Results: The analysis of 42 NEMDBs revealed significant issues, with 70% (29/42) lacking standardized data formats and 60% (25/42) having notable gaps in the cross-comparison of genetic variations, and 50% (21/42) of the databases contained incomplete or outdated data, limiting their clinical utility. However, databases developed on open-source platforms, such as LOVD, showed a 40% increase in usability for researchers, highlighting the benefits of using flexible, open-access systems. Conclusions: We propose cloud-based platforms and linked open data frameworks to address critical gaps in standardization (70% of databases) and outdated data (50%) alongside artificial intelligence–driven models for improved interoperability. These solutions prioritize user-centric design to effectively serve clinicians, researchers, and public stakeholders.
The exponential growth in the use of network services through the design of various network infrastructures, has led to increased complexities and challenges in the network. A major problem in computer networks is privacy and security breach. Cyber attackers exploit loopholes to infiltrate and disrupt the operation of the network through various attacks. Anomaly-based intrusion detection often employs Artificial Neural Network techniques like Multi-layer Perceptron (MLP) to classify malicious and legitimate traffic. Nevertheless, these techniques are vulnerable to overfitting and require extensive labeled data and computational resources. Consequently, this reduces the accuracy of intrusion detection systems and increases the error detection rate. To minimize the error detection rate of the intrusion detection system, it is necessary to optimize the connection parameters of the MLP neural network such as weights and biases. To this end, we proposed an optimized MLP-based Intrusion Detection using Gray Wolf Optimization (GWOMLP-IDS) to optimize the learning process of the MLP neural network by optimizing weights and biases. GWO aims to select an optimal connection parameter during the learning process to minimize the error rate of intrusion detection. Extensive simulations in Python reveal the effectiveness of the proposed approach in terms of designated performance metrics.

The presented paper is devoted to the development of a method for identifying and correcting spelling errors in Kazakh texts. In this paper, the study object is methods for more accurate correction of spelling errors in Kazakh texts. The aim of the study is to develop an augmented version of the Damerau-Levenshtein method for correcting spelling errors in Kazakh language texts. Automatic detection and correction of spelling errors have become a default feature in modern text editors for working with text data, in text messaging applications such as chatbots, messengers, etc. However, although this task is well solved in geographically widespread languages, it has not been fully solved in languages with a small audience, such as the Kazakh language. The methods developed so far cannot correct all spelling errors found in Kazakh texts. Therefore, the development of a method with specific algorithms for spelling error correction in Kazakh texts is considered. As a result of the research work, algorithms for correcting errors found in Kazakh language texts were developed, and the developed algorithms were included in the Damerau-Levenshtein method. The experimental testing results of the augmented Damerau-Levenshtein method showed 97.2 % accuracy in correcting specific errors found only in Kazakh words and 92.8 % accuracy in correcting common errors from letter symbols. The standard Damerau-Levenshtein method testing results showed 76.4 % accuracy in correcting specific errors found only in Kazakh words. The results of the tests in correcting common errors from letter symbols with the standard Damerau-Levenshtein were approximately the same with the augmented Damerau-Levenshtein method, the accuracy is 92.2 %. The extent and conditions of practical application of the results are implemented by including them in text editors, messengers, e-mails and similar applications that work with text data.

A hardware-software system has been implemented to monitor the environmental state (EnvState) at the site of railway (RY) accidents and disasters. The proposed hardware-software system consists of several main components. The first software component, based on the queueing theory (QT), simulates the workload of emergency response units at the RY accident site. It also interacts with a central data processing server and information collection devices. A transmitter for these devices was built on the ATmega328 microcontroller. The hardware part of the environmental monitoring system at the RY accident site is also based on the ATmega328 microcontroller. In the hardware-software system for monitoring the EnvState at the RY accident site, the data processing server receives information via the MQTT protocol from all devices about the state of each sensor and the device's location at the RY accident or disaster site, accompanied by EnvState contamination. All data is periodically recorded in a database on the server in the appropriate format with timestamps. The obtained information can then be used by specialists from the emergency response headquarters. © 2023 Polish Academy of Sciences. All rights reserved.

This paper presents a certificateless group signature scheme designed specifically for Unmanned Aerial Vehicle (UAV) communications in resource-constrained environments. The scheme leverages Physical Unclonable Functions (PUFs) and elliptic curve cryptography (ECC) to provide a lightweight security solution while maintaining essential security properties including anonymity, unforgeability, traceability, and unlikability. We describe the cryptographic protocols for system setup, key generation, signing, verification, and revocation mechanisms. The implementation shows promising results for UAV applications where computational resources are limited, while still providing robust security guarantees for group communications. Our approach eliminates the need for computationally expensive certificate management while ensuring that only legitimate group members can create signatures that cannot be linked to their identities except by authorized group managers.

The research introduces a dual deep learning system which predicts salary ranges by processing job descriptions through BERT-based contextual embeddings and structured metadata integration. The proposed method utilizes more than 124,000 LinkedIn job postings to merge BERT-based contextual embeddings with structured information about location and industry and experience level and compensation type. The model uses multi-head attention to identify essential salary-related terms in job descriptions which results in better model interpretability and improved prediction accuracy. The model combines semantic embeddings with tabular data to create a multimodal representation which serves as input for supervised learning with an ordinal-aware loss function. The model achieves stable performance in salary classification across three categories through F1-scores between 0.82 and 0.84. The proposed model achieves excellent generalization capabilities for different sectors and job types while providing precise predictions and clear decision-making processes for salary benchmarking and recruitment analytics applications.

Modern air compressors used in the mining industry have a high margin of safety when operating in difficult conditions: This includes uneven terrain, high temperature differences and work underground. Scientific research, complex of theoretical and experimental studies, is carried out in order to obtain sound initial data, to find principles and ways to create a new generation of compressors for use in a mining field. Air compressors are used in deep mines, including supplying clean air, since there may not be enough air in the mine. The compressor can take in outside air, compress and filter it, then feed it into the tunnel. It is necessary to choose compressor equipment for use in mines very carefully; there are many potential risks and limitations. The basic problem, its relevance – in this paper, the issues related to the device, operation and the possibility of optimizing the design of a screw compressor, gas compressor station in the mining industry are considered. The modeling of processes and the construction of flowcharts were carried out using programs MathCad, Drawio, MS PP. A simplified mathematical model of a screw compressor is obtained. Of the work carried out, the optimal regulator capable of controlling the system with minimal energy consumption has been determined. The relevance of the topic is explained by the fact that in Kazakhstan and other developing countries special attention is paid to the issue of energy conservation. This requires an increase in the efficiency of gas compressor equipment in general and compressor stations in particular. The practical value is an optimal regulator capable of controlling the system with minimal energy consumption.
Показано 361–368 из 1222