Development Of Intelligent System Research Articles

Delineating Mastitis Cases in Dairy Cows: Development of an IoT-Enabled Intelligent Decision Support System for Dairy Farms

Delineating Mastitis Cases in Dairy Cows: Development of an IoT-Enabled Intelligent Decision Support System for Dairy Farms

Modeling Autonomous Vehicle Responses to Novel Observations Using Hierarchical Cognitive Representations Inspired Active Inference

Equipping autonomous agents for dynamic interaction and navigation is a significant challenge in intelligent transportation systems. This study aims to address this by implementing a brain-inspired model for decision making in autonomous vehicles. We employ active inference, a Bayesian approach that models decision-making processes similar to the human brain, focusing on the agent’s preferences and the principle of free energy. This approach is combined with imitation learning to enhance the vehicle’s ability to adapt to new observations and make human-like decisions. The research involved developing a multi-modal self-awareness architecture for autonomous driving systems and testing this model in driving scenarios, including abnormal observations. The results demonstrated the model’s effectiveness in enabling the vehicle to make safe decisions, particularly in unobserved or dynamic environments. The study concludes that the integration of active inference with imitation learning significantly improves the performance of autonomous vehicles, offering a promising direction for future developments in intelligent transportation systems.

SURVEILLANCE CYBER-PHYSICAL SYSTEM AS A PART OF INTERNET OF VEHICLES

Integration of cyber-physical surveillance systems (CPSS) into the Internet of Vehicles (IoV) paradigm represents a transformative approach to enhancing transportation safety and efficiency. This article discusses the design, implementation, and application of CPSS as part of IoV ecosystems. Leveraging advancements in sensor technologies, communication protocols, and data analytics, CPSS within IoV enables real-time monitoring, analysis, and response to road conditions, incidents, and emergencies. Our research explores the architecture and functional capabilities of CPSS, including sensor deployment, data fusion, anomaly detection, and decision support mechanisms. We investigate the synergistic interaction between CPSS and IoV platforms, facilitating seamless data exchange, collaboration, and compatibility between automotive and infrastructural domains. Additionally, we discuss potential applications of CPSS in traffic management, law enforcement, emergency response, and urban planning, emphasizing its role in enhancing transportation safety, optimizing resource allocation, and preventing congestion and accidents. Through empirical evaluations and thematic studies, we demonstrate the effectiveness, scalability, and societal impact of integrating CPSS into IoV ecosystems. This research contributes to the development of intelligent transportation systems and underscores the transformative potential of CPSS within the IoV context.

Evaluating the Performance of ETSI-ITS Multi-Stack Protocols for V2V Communication in VANETs: A Simulation Study

The research evaluates various multi-stack protocols for Vehicular Ad-hoc Networks (VANETs), focusing on Vehicle-to-Vehicle (V2V) communication scenarios with Emergency Vehicle (EV) simulations. The study uses the ns-3 network and SUMO (Simulation of Urban MObility) traffic simulators to test these protocols in diverse scenarios, including fluctuating data rates and dense network conditions. By implementing the IEEE 802.11p protocol alongside vehicular message dissemination stacks compliant with ETSI (European Telecommunications Standards Institute) ITS (Intelligent Transport Systems) standards, the study performs simulation experiments with varying vehicle counts, ranging from 20 to 35. It employs two distinct data rate configurations while maintaining a constant transmission power of 23 dBm. The results indicate a decline in the average Packet Reception Ratio (PRR) as vehicle density increases, indicating heightened contention and interference. At the same time, there is an observed increase in average latency, contributing to increased message transmission and reception delays. The quantitative analysis demonstrates an inverse relationship between the average PRR and the total vehicle count when the SEND_CAM message is enabled. On the other hand, disabling SEND_CAM maintains a relatively consistent average PRR across scenarios. Additionally, a positive correlation between vehicle count and average latency underlines the impact of network congestion and interference on communication efficacy within VANETs. Despite suboptimal PRR values falling between 41% and 47%, latency performance remains satisfactory, with average latency durations ranging from 0.154 s to 0.187 s. Notably, the SEND_CAM parameter status shows negligible impact on protocol performance, suggesting that network density plays a more pivotal role. Finally, this study offers valuable insights into the trade-offs and challenges of multi-stack protocols in V2V communication within VANETs. Further optimization efforts are recommended to improve packet reception ratios, especially in high-vehicle-density environments, while maintaining acceptable latency levels. These findings contribute to the ongoing efforts to enhance the reliability and efficiency of communication protocols in VANETs, thus advancing the development of intelligent transportation systems. The study's quantitative protocol performance analysis under varying network conditions provides valuable guidance for optimizing V2V communication deployments in VANETs.

Core knowledge as a neuro-ethologist views it.

Innateness of core knowledge mechanisms (in the form of "cognitive priors") can be revealed by proper comparisons of altricial and precocial species. Cognitive priors and sensitive periods in their expression may also provide clues for the development of plausible artificial intelligence systems.

Edge computing and AI-driven intelligent traffic monitoring and optimization

Intelligent transportation system is a comprehensive system engineering, involving real-time data processing, security and privacy protection and other challenges. This paper discusses the key role of edge computing in intelligent transportation, especially its combination with SLAM technology. Edge computing enables faster data processing and response times by placing computing and data storage resources near the data source and end users, improving the efficiency and reliability of intelligent transportation systems. At the same time, edge computing can also enhance information security and privacy protection, and bring more possibilities for the future development of intelligent transportation systems. In the future, with the progress and development of technology, we can look forward to the deeper application of edge computing and SLAM technology in the field of intelligent transportation, bringing more innovation and development to smart city transportation.

Educational models for cognition: Methodology of modeling intellectual skills for intelligent tutoring systems

Automation of teaching people new skills requires modeling of human reasoning because human cognition involves active reasoning over the new subject domain to acquire skills that will later become automatic. The article presents Thought Process Trees — a language for modeling human reasoning that was created to facilitate the development of intelligent tutoring systems, which can perform the same reasoning that is expected of a student and find deficiencies in their line of thinking, providing explanatory messages and allowing them to learn from performance errors. The methodology of building trees which better reflect human learning is discussed, with examples of design choices during the modeling process and their consequences. The characteristics of educational modeling that impact building subject-domain models for intelligent tutoring systems are discussed. The trees were formalized and served as a basis for developing a framework for constructing intelligent tutoring systems. This significantly lowered the time required to build and debug a constraint-based subject-domain model. The framework has already been used to develop five intelligent tutoring systems and their prototypes and is being used to develop more of them.

Design, Fabrication, and Evaluation of 3D Biopotential Electrodes and Intelligent Garment System for Sports Monitoring.

This study presents the development and evaluation of an innovative intelligent garment system, incorporating 3D knitted silver biopotential electrodes, designed for long-term sports monitoring. By integrating advanced textile engineering with wearable monitoring technologies, we introduce a novel approach to real-time physiological signal acquisition, focusing on enhancing athletic performance analysis and fatigue detection. Utilizing low-resistance silver fibers, our electrodes demonstrate significantly reduced skin-to-electrode impedance, facilitating improved signal quality and reliability, especially during physical activities. The garment system, embedded with these electrodes, offers a non-invasive, comfortable solution for continuous ECG and EMG monitoring, addressing the limitations of traditional Ag/AgCl electrodes, such as skin irritation and signal degradation over time. Through various experimentation, including impedance measurements and biosignal acquisition during cycling activities, we validate the system's effectiveness in capturing high-quality physiological data. Our findings illustrate the electrodes' superior performance in both dry and wet conditions. This study not only advances the field of intelligent garments and biopotential monitoring, but also provides valuable insights for the application of intelligent sports wearables in the future.

How the EU AI Act Seeks to Establish an Epistemic Environment of Trust

With focus on the development and use of artificial intelligence (AI) systems in the digital health context, we consider the following questions: How does the European Union (EU) seek to facilitate the development and uptake of trustworthy AI systems through the AI Act? What does trustworthiness and trust mean in the AI Act, and how are they linked to some of the ongoing discussions of these terms in bioethics, law, and philosophy? What are the normative components of trustworthiness? And how do the requirements of the AI Act relate to these components? We first explain how the EU seeks to create an epistemic environment of trust through the AI Act to facilitate the development and uptake of trustworthy AI systems. The legislation establishes a governance regime that operates as a socio-epistemological infrastructure of trust which enables a performative framing of trust and trustworthiness. The degree of success that performative acts of trust and trustworthiness have achieved in realising the legislative goals may then be assessed in terms of statutorily defined proxies of trustworthiness. We show that to be trustworthy, these performative acts should be consistent with the ethical principles endorsed by the legislation; these principles are also manifested in at least four key features of the governance regime. However, specified proxies of trustworthiness are not expected to be adequate for applications of AI systems within a regulatory sandbox or in real-world testing. We explain why different proxies of trustworthiness for these applications may be regarded as ‘special’ trust domains and why the nature of trust should be understood as participatory.

Fake Currency Detection Using Machine Learning

The proliferation of counterfeit currency poses a significant threat to the global economy, necessitating the development of efficient and accurate detection methods. This paper presents a novel approach to fake currency detection using machine learning techniques. The proposed system leverages a combination of computer vision and machine learning algorithms to identify counterfeit banknotes with high accuracy. The system employs a convolutional neural network (CNN) to extract features from images of banknotes, which are then classified as genuine or fake using a support vector machine (SVM) classifier. The CNN is trained on a large dataset of images of genuine and fake banknotes, while the SVM is fine-tuned to optimize its performance. The Experimental results demonstrate that our proposed system achieves an accuracy of 98.5% in detecting fake currency, outperforming traditional methods based on manual inspection and rule-based systems. The system's performance has been evaluated using a comprehensive set of metrics, including precision, recall, F1-score, and receiver operating characteristic (ROC) curve analysis. The proposed system offers several advantages, including high accuracy, speed, and scalability, making it suitable for real-world applications in banking, finance, and law enforcement. Furthermore, the system's modular design enables easy integration with existing currency processing systems, facilitating seamless deployment. This research contributes to the development of intelligent systems for fake currency detection, providing a robust and reliable solution to combat counterfeiting.

Regulatory sandboxes for trustworthy artificial intelligence – global and Latin American experiences

ABSTRACT This paper explores how regulatory sandboxes can be used to promote the development of trustworthy artificial intelligence (AI) systems. The analysis focus on the experiences of Data Protection Authorities (DPAs) who have been experimenting with sandboxes to foster the implementation of privacy by design principles in AI systems. Throughout bibliographic research, this study (i) highlights privacy-related elements on international AI regulatory frameworks; (ii) explores the concept of privacy by design (PbD) and some of its strategies, patterns and techniques, such as Privacy Enhancing Technologies (PETs); (iii) reflects upon the impact of regulatory sandboxes; and (iv) analyses how regulatory sandboxes are being discussed in the context of AI regulatory frameworks. While this study brings global perspective on regulatory sandboxes, it also does relevant analysis in the Latin American context by presenting different stages of development of initiatives in the region. One of the main findings of this paper is that literature currently lacks an analysis of how privacy by design could be used in the context of AI systems design and governance. It also suggests that regulatory sandboxes may be able to integrate PbD principles to foster the development of trustworthy AI, although further research would be needed on that matter.

Air volume reconstruction and sensor optimization distribution in building intelligent ventilation network

Ensuring the accuracy and reliability of ventilation parameter monitoring is pivotal for the development of intelligent ventilation systems. To attain a visual representation of airflow, solving the challenge of airflow reconstruction necessitates the strategic use of a limited number of sensors. In addressing these concerns, this article introduces an optimization approach for ventilation airflow leveraging the Breadth-First Search (BFS) algorithm. Additionally, it proposes an optimization distribution method for mine ventilation sensors, grounded in the Independent Cut Set algorithm. Research has found that compared to the traditional PSO algorithm, the BFS algorithm produces a higher optimal air volume solution when optimizing the air volume; Comparatively, the proposed algorithm exhibits significantly shorter average running times than the Particle Swarm Optimization (PSO) algorithm. It boasts the highest average convergence rate, ensuring superior accuracy, and possesses a notable capability to escape local minima, facilitating the acquisition of optimal solutions. Leveraging the independent cut set algorithm optimizes the calculation process through matrix operations. Exploiting the properties of matrices allows for a more rapid and intuitive resolution of sensor localization problems.

Toward a nomenclature consensus for diverse intelligent systems: Call for collaboration

Disagreements about language use are common both between and within fields. Where interests require multidisciplinary collaboration or the field of research has the potential to impact society at large, it becomes critical to minimize these disagreements where possible. The development of diverse intelligent systems, regardless of the substrate (e.g., silicon vs. biology), is a case where both conditions are met. Significant advancements have occurred in the development of technology progressing toward these diverse intelligence systems. Whether progress is silicon based, such as the use of large language models, or through synthetic biology methods, such as the development of organoids, a clear need for a community-based approach to seeking consensus on nomenclature is now vital. Here, we welcome collaboration from the wider scientific community, proposing a pathway forward to achieving this intention, highlighting key terms and fields of relevance, and suggesting potential consensus-making methods to be applied.

Sentiment Analysis Based on Transformer

This article aims to explore the sentiment analysis of Transformer comments on Weibo to understand the attitudes and emotional tendencies of social media users regarding the movie The boy and the heron. This paper uses natural language processing technology and sentiment analysis model Transformer to crawl the Weibo comment data set, analyzes the anti-crawling mechanism of Weibo, adds HEADERS and REFERER directly in the code to bypass the inspection, and preprocesses it. Sentiment analysis was conducted on a large number of Weibo comments related to the boy and the heron. The results of the study showed that the vast majority of the comments expressed positive emotional attitudes and held positive and appreciative attitudes towards the boy and the heron. This study reveals that social media users have positive attitudes and emotional identification with the boy and the heron, and the audience really likes the film, which is of great help for the filmmakers to further understand the advantages and disadvantages of the film. Performing Weibo sentiment analysis based on advanced natural language processing technologies such as transformers can not only improve the accuracy and efficiency of sentiment analysis, but also help promote the progress and application of artificial intelligence technology. This is important for the development of more intelligent social media analysis tools and systems.

An “intelligent-sensing and targeted release” antimicrobial pickering emulsion for banana preservation

Conventional Pickering emulsions can kill microorganisms by slow release of active substances to prevent foodborne contamination; however, their low bactericidal efficiency due to the absence of bacterial inducibility is a problem that needs to be addressed. Inspired by the fact that the growth of bacteria depends on the consumption of proteins and polysaccharides by microbial enzymes, the present study prepared a novel Pickering emulsion capable of intelligent sensing and targeted release using chitosan (CS)-soy protein isolate (SPI) colloidal particles as stabilizers and plant essential oils as active substances. The Pickering emulsion demonstrated optimal performance in achieving these goals when prepared with a CS:SPI ratio of 1:4, an oil fraction of 40%, at a homogeneous speed of 25 000 rpm, and utilizing cinnamon oil as the plant essential oil. This was evidenced by the emulsion having the smallest droplet size and the greatest stability, which can increase the chances of coming into contact with microorganisms and avoid premature demulsification. Antibacterial experiments demonstrated that the emulsion could control the bacteria-mediated release of essential oils, realizing intelligent sterilization. Experiments on banana preservation showed that the released essential oils effectively delayed banana spoilage. These findings contribute to the development of intelligent food preservation systems.

Human feedback enhanced autonomous intelligent systems: a perspective from intelligent driving

Artificial intelligence empowers the rapid development of autonomous intelligent systems (AISs), but it still struggles to cope with open, complex, dynamic, and uncertain environments, limiting its large-scale industrial application. Reliable human feedback provides a mechanism for aligning machine behavior with human values and holds promise as a new paradigm for the evolution and enhancement of machine intelligence. This paper analyzes the engineering insights from ChatGPT and elaborates on the evolution from traditional feedback to human feedback. Then, a unified framework for self-evolving intelligent driving (ID) based on human feedback is proposed. Finally, an application in the congested ramp scenario illustrates the effectiveness of the proposed framework.

Design and Construction of a Multipole Electric Motor Using an Axial Flux Configuration

In the transportation industry, the use of renewable energies has been implemented in conjunction with the development of higher-power electric motors and, consequently, the development of intelligent control systems for torque and speed control. Currently, the coupling between both systems is being developed through mechanical systems, affecting the efficient transmission of energy and the useful life of the components. On the other hand, new configurations of electric motors are being developed, such as axial flux motors (AFM), because these can be coupled directly without a mechanical coupling, given their characteristics of high torque at low speeds. In the present work, an innovative design of a multipole axial flux motor (MAFM) is introduced. General criteria for the design and construction are presented considering the geometry in axial flux and permanent magnets. The performance of the system is evaluated through finite element magnetic simulations (FEMM) and compared with experimental measurements of the developed prototype; confirming the effectiveness of the design, obtaining torques of up to 1.784 Nm without extra mechanical couplings and maximum speed regulation errors of 8.43%. The motor was controlled by a digital pole switching system whit six control mode, applied to a permanent magnet MFA for speed and torque control at constant speed. This control can be extended to conventional radial flux electric motor configurations and intelligent traction applications, based on torque demand.

An explainable machine learning-based web attack detection system for industrial IoT web application security

ABSTRACT Within Industry 4.0, the integration of Industrial IoT (IIoT) marks a transformative phase for modern industries, fostering the development of smart factories and intelligent manufacturing systems. Despite the substantial growth of IIoT, a critical research gap persists in web security within IIoT environments. This paper addresses this gap by proposing an explainable and robust machine learning-based web attack detection system to ensure IIoT web application security using ToN-IoT and NF-ToN-IoTv2 datasets that accurately reflects IIoT traffic. Given eXplainable Artificial Intelligence’s (XAI) capability to instill trustworthiness and transparency in learning models, the authors opted for the SHAP technique for feature selection, leveraging its global insights to explain feature contributions to the system’s decision-making. Compared to the existing works, the system demonstrated strong performance across various metrics, including accuracy, recall, precision, specificity, F-value, FPR, FNR, AUC-ROC curve, MCE, training, and prediction times, in binary and multi-classification scenarios.

A new intelligent scheme for short-circuit detection, classification and location in power transmission lines with the PV generation presence

Transmission lines constitute critical energy infrastructure in an electrical installation, as they ensure a reliable and efficient energy transition. However, they are prone to breakdowns, due to their significant length and their continuous exposure to atmospheric conditions. In addition, the photovoltaic energy sources integration can modify their behavior, which contributes to a greater increase in the breakdowns probability. Short circuits are the most common and dangerous fault type, leading in the majority of cases to other fault types. This research describes the development of a new intelligent system that consists of three stages. The first stage aim is to identify whether there is a short circuit or not using a binary SVM. In the second stage, an innovative expert system is used to determine the short circuit type among 11 potential faults. The output of this system depends on the inputs obtained by four binary SVM, each of which determines the fault presence or absence in a phase. The third stage is responsible for estimating the exact fault position in a 100 km transmission line. This stage is made up of 11 universal regressors of type MLP. The proposed system was validated using signals, obtained from a modelled High-Voltage Line with a PV Energy Source (25 kV-50 Hz-100 Km) and processed by the Discrete Wavelet Transform. Statistical metrics (with all p-value < 0.001) validate the proposed system performance with: 100% sensitivity and specificity for the fault detector ; an average sensitivity, specificity, and false alarms of 99.38%, 99.94%, and 0.17%, respectively, for the fault discriminator ; and a 2.66% mean squared error and a 97.80% overall sensitivity for the fault location estimator. These results conclude the proposed approach reliability, demonstrating its potential effectiveness in real-world scenarios.

Construction of a large-scale maritime element semantic schema based on knowledge graph models for unmanned automated decision-making

In maritime logistics optimization, considerable research efforts are focused on the extraction of deep behavioral characteristics from comprehensive shipping data to discern patterns in maritime vessel behavior. The effective linkage of these characteristics with maritime infrastructure, such as berths, is critical for the enhancement of ship navigation systems. This endeavor is paramount not only as a research focus within maritime information science but also for the progression of intelligent maritime systems. Traditional methodologies have primarily emphasized the analysis of navigational paths of vessels without an extensive consideration of the geographical dynamics between ships and port infrastructure. However, the introduction of knowledge graphs has enabled the integration of disparate data sources, facilitating new insights that propel the development of intelligent maritime systems. This manuscript presents a novel framework using knowledge graph technology for profound analysis of maritime data. Utilizing automatic identification system (AIS) data alongside spatial information from port facilities, the framework forms semantic triplet connections among ships, anchorages, berths, and waterways. This enables the semantic modeling of maritime behaviors, offering precise identification of ships through their diverse semantic information. Moreover, by exploiting the semantic relations between ships and berths, a reverse semantic knowledge graph for berths is constructed, which is specifically tailored to ship type, size, and category. The manuscript critically evaluates a range of graph embedding techniques, dimensionality reduction methods, and classification strategies through experimental frameworks to determine the most efficacious methodologies. The findings reveal that the maritime knowledge graph significantly enhances the semantic understanding of unmanned maritime equipment, thereby improving decision-making capabilities. Additionally, it establishes a semantic foundation for the development of expansive maritime models, illustrating the potential of knowledge graph technology in advancing intelligent maritime systems.