STCGRU: A hybrid model based on CNN and BiGRU for mild cognitive impairment diagnosis

Computer Methods and Programs in Biomedicine, Journal Year: 2024, Volume and Issue: 248, P. 108123 - 108123

Published: March 8, 2024

Language: Английский

---

Factors influencing user experience in AI chat systems – a satisfaction study based on factor analysis and linear regression

Kybernetes, Journal Year: 2024, Volume and Issue: unknown

Published: May 7, 2024

Purpose Since the introduction of outstanding web AI chat system, ChatGPT, it has caused a significant impact in both academia and business world. Many studies have started to explore its potential applications various fields. However, there is lack research from perspective user experience. To fill this theoretical gap provide basis for operation design related services, study plans develop set evaluation scales system experience relationship between factors satisfaction. Design/methodology/approach This obtained 41 indicators through literature review research. Subsequently, these were used as questionnaire items, combined with satisfaction metrics. A total 515 questionnaires distributed, factor analysis linear regression employed determine specific elements influencing model. Findings found that are usefulness, accuracy, logical inference, interactivity, growth, anthropomorphism, convenience, credibility, ease use, creativity, security. Among factors, only security indirectly influence while rest direct positive on Originality/value provides constructive suggestions services serves reference future area.

Language: Английский

---

Feature selection using a sinusoidal sequence combined with mutual information

Engineering Applications of Artificial Intelligence, Journal Year: 2023, Volume and Issue: 126, P. 107168 - 107168

Published: Sept. 22, 2023

Language: Английский

---

NetTiSA: Extended IP flow with time-series features for universal bandwidth-constrained high-speed network traffic classification

Computer Networks, Journal Year: 2024, Volume and Issue: 240, P. 110147 - 110147

Published: Jan. 3, 2024

Network traffic monitoring based on IP Flows is a standard approach that can be deployed to various network infrastructures, even the large ISP networks connecting millions of people. Since flow records traditionally contain only limited information (addresses, transport ports, and amount exchanged data), they are also commonly extended by additional features enable analysis with high accuracy. These extensions are, however, often too or hard compute, which then allows offline limits their deployment smaller-sized networks. This paper proposes novel called NetTiSA (Network Time Series Analysed) flow, analysing time series packet sizes. By thoroughly testing 25 different classification tasks, we show broad applicability usability flow. For practical deployment, consider sizes flows evaluate performance impacts computation in exporter. The proved computationally inexpensive showed excellent discriminatory performance. trained machine learning classifiers proposed mostly outperformed state-of-the-art methods. finally bridges gap brings universal, small-sized, for scaled up extensive bringing 100 Gbps backbone lines.

Language: Английский

---

Data-Driven Innovations: Transforming Healthcare through Machine Learning Integration

Journal of Machine and Computing, Journal Year: 2025, Volume and Issue: unknown, P. 356 - 364

Published: Jan. 3, 2025

Today's healthcare sector generates an unprecedented amount of data, creating a promising junction between data mining and machine learning. This research aims to achieve two key goals. First, it effortlessly integrates AI into clinical decision-support systems improve treatment regimens. The emphasis is on individualizing medicines, increasing effectiveness, minimizing side effects. main goal optimize methods using AI. also examines how learning may hospital operations. objective involves improving logistical administration, planning, resource allocation boost operational efficiency, lower costs, enhance access high-quality care. study rigorously investigates data-driven approaches revolutionize system the synergy medicine, focusing current trends advances. medical applications that demonstrate learning's ability change delivery. illuminate approaches' potential advance patient-centeredness, financial sustainability, efficiency in healthcare.

Language: Английский

---

A New Feature Level‐Based Multi‐Biometric Identification System to Enable Secure and Reliable Communication Systems for Next‐Generation Smart Cities

Security and Privacy, Journal Year: 2025, Volume and Issue: 8(1)

Published: Jan. 1, 2025

ABSTRACT The concept of smart cities, which aims to improve urban lifestyles through innovative technologies and policies, has gained significant momentum over the last few years. As we transition into next‐generation city era, it is crucial review some fundamental driving this evolution. Among these, security‐related challenges necessitate implementation effective authentication systems. This paper introduces a novel feature‐based multi‐biometric identification system designed provide secure reliable communication frameworks for cities. use multi‐modal biometric twins long been fascinating valuable area research. Because its high reliability acceptance, approach significantly advances domain twins. unique characteristics are determined by variations in features extracted during process. However, many these superfluous, expanding search space complicating generalization Therefore, primary challenge lies isolating most salient capable accurately identifying biometrics. To address challenge, research proposes an improved twin framework. proposed method employs fusion Dis‐Eigen with SailFish optimization algorithm enhance both accuracy efficiency. In study, were simplified using process, after Sailfish was applied optimize model parameters accuracy. result, intra‐class similarity error decreased, while inter‐class increased, improving identification. Consequently, several classifier applications achieved rate exceeding 93%.

Language: Английский

---

Optimizing IoT network lifetime through an enhanced hybrid energy harvesting system

Sustainable Computing Informatics and Systems, Journal Year: 2025, Volume and Issue: unknown, P. 101081 - 101081

Published: Jan. 1, 2025

Language: Английский

---

Smart IoT-based snake trapping device for automated snake capture and identification

Environmental Monitoring and Assessment, Journal Year: 2025, Volume and Issue: 197(3)

Published: Feb. 10, 2025

Language: Английский

---

Towards Secure and Efficient Data Aggregation in Blockchain‐Driven IoT Environments: A Comprehensive and Systematic Study

Transactions on Emerging Telecommunications Technologies, Journal Year: 2025, Volume and Issue: 36(2)

Published: Feb. 1, 2025

ABSTRACT The rapid evolution of the Internet Things (IoT) has revolutionized various sectors, fostering seamless intercommunication and real‐time monitoring. Central to this transformation is integrating blockchain technology, which ensures data integrity security in IoT networks. This paper provides a meticulous exploration aggregation techniques within context blockchain‐based systems. study categorizes algorithms into Privacy‐Preserving, Machine Learning‐Based, Hierarchical, Real‐Time, Custom Aggregation Algorithms, each tailored specific requirements. Privacy‐Preserving Algorithms focus on safeguarding sensitive through encryption secure protocols. Learning‐Based adapts dynamically patterns, offering predictive insights adaptability. Hierarchical organizes devices structured hierarchy, optimizing processing. Real‐Time processes instantly, ensuring low latency for time‐sensitive applications. are bespoke solutions unique application demands, emphasizing efficiency security. Through comparative analysis these techniques, explores their advantages, disadvantages, applicability, addressing challenges suggesting future research directions. integration not only enhances network but also longevity modern technological infrastructures. builds upon prior field technology by extending implications SLR method been used investigate one terms influential properties such as main idea, strategies. results indicate most articles were published 2021 2022. Moreover, some important parameters privacy security, latency, processing, energy consumption, complexity, reliability involved investigations.

Language: Английский

---

The applications of machine learning mechanisms in the compositions of internet of things services: A systematic study, current progress, and future research agenda

Engineering Applications of Artificial Intelligence, Journal Year: 2025, Volume and Issue: 147, P. 110345 - 110345

Published: Feb. 26, 2025

Language: Английский

---