To see the other types of publications on this topic, follow the link: AI control safety.
Journal articles on the topic 'AI control safety'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'AI control safety.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Abu, N. S., W. M. Bukhari, M. H. Adli, Hari Maghfiroh, and Alfian Ma’arif. "Advancements, Challenges and Safety Implications of AI in Autonomous Vehicles: A Comparative Analysis of Urban vs. Highway Environments." Journal of Robotics and Control (JRC) 5, no. 3 (2024): 613–35. https://doi.org/10.18196/jrc.v5i3.21114.
Full textAbstract:
This research reviews AI integration in AVs, evaluating its effectiveness in urban and highway settings. Analyzing over 161 studies, it explores advancements like machine learning perception, sensor technology, V2X communication, and adaptive cruise control. It also examines challenges like traffic congestion, pedestrian and cyclist safety, regulations, and technology limitations. Safety considerations include human-AI interaction, cybersecurity, and liability/ethics. The study contributes valuable insights into the latest developments and challenges of AI in AVs, specifically in urban and highway contexts, which will guide future transportation research and decision-making. In urban settings, AI-powered sensor fusion technology helps AVs navigate dynamic traffic safely. On highways, adaptive cruise control systems maintain safe distances, reducing accidents. These findings suggest AI facilitates safer navigation in urban areas and enhances safety and efficiency on highways. While AI integration in AVs holds immense potential, innovative solutions like advanced perception systems and optimized long-range communication are needed to create safer and more sustainable transportation systems.
2
Jonsson, Roberth. "Avoiding AI Accidents." Industrial Vehicle Technology International 28, no. 1 (2020): 10. http://dx.doi.org/10.12968/s1471-115x(23)70471-6.
Full text
3
Sharma,, Siddharth. "Revolutionizing Sports Bikes with Artificial Intelligence: Safety, Performance, and Design Innovations." INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 08, no. 04 (2024): 1–5. http://dx.doi.org/10.55041/ijsrem30618.
Full textAbstract:
This study examines how artificial intelligence (AI) is incorporated into sports bikes and examines the significant impacts this has on ride quality, user experience, and safety. Adaptive cruise control and collision avoidance systems, two AI-driven technologies that improve rider safety, and engine performance improvements and predictive maintenance algorithms that improve overall bike performance and dependability. Furthermore, bike design processes are revolutionized by AI-driven design techniques, which allow for quick iterations and customisation. This study offers insights into how artificial intelligence (AI) can revolutionize sports bike technology in the future. Keywords: Artificial Intelligence (AI), Sports Bikes, Ride Quality, User Experience, Safety, Adaptive Cruise Control, Collision Avoidance Systems, Rider Safety, Engine Performance Improvements, Predictive Maintenance Algorithms, Bike Performance, Dependability, AI Driven Design Techniques.
4
Krainiuk, O., Yu Buts, N. Didenko, V. Barbashyn, and O. Trishyna. "METROLOGICAL CONTROL OF SENSORS FOR MONITORING WORKING CONDITIONS USING ARTIFICIAL INTELLIGENCE." Municipal economy of cities 3, no. 184 (2024): 216–22. http://dx.doi.org/10.33042/2522-1809-2024-3-184-216-222.
Full textAbstract:
Metrological control plays a vital role in ensuring the accuracy and reliability of the data collected as part of the working conditions monitoring. It helps to prevent potential errors and guarantee the quality of the results, which is critical for the efficient assessment and management of occupational health and safety. The article aims to investigate and analyse the role and importance of metrological control of sensors in the system for monitoring working conditions at production facilities using artificial intelligence. The article examines the possibilities of using artificial intelligence (AI) to optimise metrological control and analysis of sensor data. The authors provide specific applications of AI to improve the metrological control of sensors and identify the advantages and challenges of introducing AI into the metrological control system at production facilities. These tasks will help to reveal the essence and potential of using AI in the metrological control of sensors for monitoring working conditions and emphasise its significance in improving the safety of workers. Using artificial intelligence to improve the accuracy of sensor measurements in monitoring working conditions helps to increase the efficiency and safety of production processes and reduce health risks for employees. The metrological control methodology is essential for ensuring the reliability of sensor and measuring device measurements. Applying machine learning algorithms to develop sensor calibration models can automate and optimise the processes of measuring working conditions, improving the accuracy and reliability of data. The proposed flowchart demonstrates an innovative approach to calibrating a sound level meter using artificial intelligence (AI). The results show that integrating AI into the occupational health and safety management system contributes to monitoring process automation, predicting risks and hazards to employee health, and optimising safety processes. These approaches can enhance the production processes’ efficiency, safety, and productivity. Keywords: measuring instruments, production environment, hazards, inspection, calibration.
5
Duarte, Ana Beatriz. "THE CASE FOR CONVERGENCE IN AI SAFETY." IA Policy Brief Series 11, no. 1 (2024): 1–8. https://doi.org/10.5281/zenodo.15073811.
Full textAbstract:
This policy brief emphasizes the need for a unified, evidence-based approach to AI safety. Given the inability to fully explain AI decisions, the global community has a growing consensus about the need to prioritize AI safety. However, discussions about AI safety often focus on different topics. While some scholars are alert to the dangers of cyberattacks and even the possibility of AI taking over, civil society experts claim for now-and-here issues such as the military use of autonomous weapons and other present-day risks. Common to the discourse of both groups is the concern with control, diverging in what and how.
6
Kamala Aliyeva, Rashid Jafarov, Kamala Aliyeva, Rashid Jafarov. "SAFETY CONTROL SYSTEMS FOR ETHYLENE PRODUCTION." PAHTEI-Procedings of Azerbaijan High Technical Educational Institutions 35, no. 12 (2023): 206–13. http://dx.doi.org/10.36962/pahtei35122023-206.
Full textAbstract:
Ethylene production is a cornerstone of the petrochemical industry, with a global demand that continues to rise. Ensuring efficient, safe, and environmentally responsible ethylene production processes is paramount. Ethylene production control systems, encompassing a range of technologies and strategies, play a pivotal role in achieving these objectives. This abstract provides a concise overview of key aspects of ethylene production control systems, their challenges, and their critical importance. Ethylene production control systems serve as the backbone of modern ethylene plants, orchestrating complex operations to meet production targets while maintaining product quality. These systems integrate advanced technologies such as distributed control systems (DCS), safety instrumented systems (SIS), and process optimization tools to manage variables like temperature, pressure, flow rates, and feedstock composition. Efficiency and yield optimization are central objectives in ethylene production control. Control strategies are designed to maximize product output while minimizing energy consumption and raw material wastage. Additionally, safety control systems are a crucial component, mitigating risks associated with the highly flammable nature of ethylene and ensuring the well-being of personnel and environmental protection. Challenges in ethylene production control systems include managing the variability in feedstock quality, adapting to changing market demands, and adhering to stringent environmental regulations. As feedstock composition can fluctuate, control systems must continually adjust to maintain product quality and consistency. The emergence of Artificial Intelligence (AI) has brought new dimensions to ethylene production control. AI-driven predictive maintenance, anomaly detection, and process optimization are being explored to enhance operational efficiency and reduce downtime. In summary, ethylene production control systems are pivotal in sustaining the global supply of ethylene, a vital chemical compound. Their roles extend beyond production to safety and environmental compliance, making them indispensable components in the petrochemical industry's pursuit of efficiency and sustainability. To meet growing demands and address evolving challenges, the integration of advanced technologies, such as AI, holds promise for the future of ethylene production control systems. A strong safety culture is the backbone of safety control in ethylene production. This involves fostering a work environment where safety is paramount, and all personnel are equipped with the knowledge, awareness, and commitment to safety objectives. Clear communication and continuous training ensure that safety becomes an integral part of the organizational DNA. These systems represent a synergy of hardware, software, and operational protocols meticulously designed to monitor, detect, and respond to anomalous conditions, with a primary objective of averting incidents that could culminate in equipment damage, environmental harm, or harm to personnel. Keywords: Ethylene Production, Control Systems, Petrochemical Industry, Efficiency, Safety, Environmental Responsibility.
7
Ourzik, Victoria Yousra. "Security and safety concerns in the age of AI." International Conference on AI Research 4, no. 1 (2024): 329–37. https://doi.org/10.34190/icair.4.1.3142.
Full textAbstract:
Artificial Intelligence (AI) is transforming industries at an astonishing rate, reshaping how we live, work, and interact with technology. Yet, as AI becomes more pervasive, it brings urgent questions about security and safety. This article explores these critical issues, drawing a clear distinction between AI security and AI safety—two concepts that are often misunderstood but are crucial for responsible AI deployment. AI security focuses on protecting systems from external threats like data breaches, adversarial attacks, and unauthorized access. As AI systems increasingly handle sensitive data and control critical operations, securing them against such risks is essential. A breach or failure could compromise not only privacy but also the integrity of critical infrastructures. On the other hand, AI safety extends beyond technical defenses to the broader societal implications of AI. Issues like algorithmic bias, ethical decision-making, and unintended consequences of AI systems highlight the risks to human well-being. As AI becomes more autonomous, its alignment with human values and societal norms becomes paramount. Furthermore, the existential risks posed by advanced AI—such as loss of control or unintended outcomes—raise profound questions about the future of human-AI coexistence. This article delves into real-world case studies of AI failures and near-misses, offering tangible insights into the potential consequences of unchecked AI growth. It also explores strategies for mitigating these risks, balancing the pursuit of innovation with the need for transparency, accountability, and ethical oversight. As we look to the future, international cooperation and robust regulatory frameworks are essential to managing AI’s growing influence. By examining both technical and ethical dimensions, this article equips readers with a comprehensive understanding of AI security and safety, urging a proactive approach to managing the risks and harnessing the potential of this powerful technology.
8
Vishal Goyal, Kamal Sharma, Amit Jain,. "A Comprehensive Analysis of AI/ML-enabled Predictive Maintenance Modelling for Advanced Driver-Assistance Systems." Journal of Electrical Systems 20, no. 4s (2024): 486–507. http://dx.doi.org/10.52783/jes.2060.
Full textAbstract:
Advanced Driver-Assistance Systems (ADAS) are changing driver-vehicle interactions to improve road safety and reduce distractions. Technological advances like ADAS and AI in cars present societal challenges and opportunities. It shows how AI aids human-machine communication by improving motor skills. The auto industry is interested in ADAS because it can increase energy efficiency, safety, and comfort. Numerous studies have shown its benefits. ADAS and vehicle networking show promise, but establishing a sound control system is challenging. Model Predictive Control (MPC) is one answer to these problems. To manage higher-level connectivity and automation, the paper analyses and implements key research. It also finds issues and recommends solutions. The latest driverless car ADAS improvements have dramatically increased passenger safety. These systems are safer and more automated using sensors and ECUs. Most ADAS have RADAR, cameras, ultrasonic, and LiDAR. This work uses AI/ML-enabled Predictive Maintenance modelling to improve ADAS safety and longevity. AI and ML in Advanced Driver Assistance Systems (ADAS) are significant vehicle safety and reliability advances. AI/ML-enabled predictive maintenance detects and fixes ADAS component faults. ADAS predictive maintenance using AI/ML can detect issues, improve driver safety, and boost vehicle efficiency. Advanced sensor arrays and control units are needed for adaptive cruise control, traffic sign recognition, and lane-keeping assistance. AI/ML algorithms discover issues and enable early interventions in predictive maintenance models. Predictive maintenance is examined utilizing classical machine learning, deep learning, and reinforcement learning. Integration of numerous AI/ML models, real-time data processing, customization based on vehicle usage patterns, scalability, and adaptability of predictive maintenance models to new ADAS technologies are research gaps.
9
Schöning, Julius, and Hans-Jürgen Pfisterer. "Safe and Trustful AI for Closed-Loop Control Systems." Electronics 12, no. 16 (2023): 3489. http://dx.doi.org/10.3390/electronics12163489.
Full textAbstract:
In modern times, closed-loop control systems (CLCSs) play a prominent role in a wide application range, from production machinery via automated vehicles to robots. CLCSs actively manipulate the actual values of a process to match predetermined setpoints, typically in real time and with remarkable precision. However, the development, modeling, tuning, and optimization of CLCSs barely exploit the potential of artificial intelligence (AI). This paper explores novel opportunities and research directions in CLCS engineering, presenting potential designs and methodologies incorporating AI. Combining these opportunities and directions makes it evident that employing AI in developing and implementing CLCSs is indeed feasible. Integrating AI into CLCS development or AI directly within CLCSs can lead to a significant improvement in stakeholder confidence. Integrating AI in CLCSs raises the question: How can AI in CLCSs be trusted so that its promising capabilities can be used safely? One does not trust AI in CLCSs due to its unknowable nature caused by its extensive set of parameters that defy complete testing. Consequently, developers working on AI-based CLCSs must be able to rate the impact of the trainable parameters on the system accurately. By following this path, this paper highlights two key aspects as essential research directions towards safe AI-based CLCSs: (I) the identification and elimination of unproductive layers in artificial neural networks (ANNs) for reducing the number of trainable parameters without influencing the overall outcome, and (II) the utilization of the solution space of an ANN to define the safety-critical scenarios of an AI-based CLCS.
10
Turchin, Alexey, David Denkenberger, and Brian Green. "Global Solutions vs. Local Solutions for the AI Safety Problem." Big Data and Cognitive Computing 3, no. 1 (2019): 16. http://dx.doi.org/10.3390/bdcc3010016.
Full textAbstract:
There are two types of artificial general intelligence (AGI) safety solutions: global and local. Most previously suggested solutions are local: they explain how to align or “box” a specific AI (Artificial Intelligence), but do not explain how to prevent the creation of dangerous AI in other places. Global solutions are those that ensure any AI on Earth is not dangerous. The number of suggested global solutions is much smaller than the number of proposed local solutions. Global solutions can be divided into four groups: 1. No AI: AGI technology is banned or its use is otherwise prevented; 2. One AI: the first superintelligent AI is used to prevent the creation of any others; 3. Net of AIs as AI police: a balance is created between many AIs, so they evolve as a net and can prevent any rogue AI from taking over the world; 4. Humans inside AI: humans are augmented or part of AI. We explore many ideas, both old and new, regarding global solutions for AI safety. They include changing the number of AI teams, different forms of “AI Nanny” (non-self-improving global control AI system able to prevent creation of dangerous AIs), selling AI safety solutions, and sending messages to future AI. Not every local solution scales to a global solution or does it ethically and safely. The choice of the best local solution should include understanding of the ways in which it will be scaled up. Human-AI teams or a superintelligent AI Service as suggested by Drexler may be examples of such ethically scalable local solutions, but the final choice depends on some unknown variables such as the speed of AI progress.
11
Rupnawar, Shivam, Puja Deokate, and Mohit Bhandari. "Advancements in Bicycle Safety: Integrating Control Sensors and Artificial Intelligence for Enhanced Airbag Innovation." International Journal for Research in Applied Science and Engineering Technology 12, no. 4 (2024): 5053–74. http://dx.doi.org/10.22214/ijraset.2024.61181.
Full textAbstract:
Abstract: Motorcycle safety is a critical concern in traffic systems worldwide. This paper introduces a novel approach to enhancing rider safety through the integration of airless tires and advanced airbag systems, underpinned by artificial intelligence (AI) and control sensors. Airless tires contribute to vehicle stability by eliminating the risk of sudden deflation, while AI-driven airbag systems promise dynamic protection for riders during collisions. The study begins with an analysis of airless tire technology, emphasizing its impact on motorcycle stability and safety. It then transitions to the development of motorcyclespecific airbag systems, which utilize AI to process sensor data and make real-time decisions regarding airbag deployment. The effectiveness of these systems is validated through crash simulation tests and impact force measurements, demonstrating a substantial reduction in injury severity. Challenges such as cost, user acceptance, and technical constraints are thoroughly examined. The paper concludes with a discussion on future trends, including the potential for AI to predict and prevent accidents before they occur, thereby setting a new standard for motorcycle safety.
12
Silva Neto, Antonio V., Henrique L. Silva, João B. Camargo, Jorge R. Almeida, and Paulo S. Cugnasca. "Design and Assurance of Safety-Critical Systems with Artificial Intelligence in FPGAs: The Safety ArtISt Method and a Case Study of an FPGA-Based Autonomous Vehicle Braking Control System." Electronics 12, no. 24 (2023): 4903. http://dx.doi.org/10.3390/electronics12244903.
Full textAbstract:
With the advancements in utilizing Artificial Intelligence (AI) in embedded safety-critical systems based on Field-Programmable Gate Arrays (FPGAs), assuring that these systems meet their safety requirements is of paramount importance for their revenue service. Based on this context, this paper has two main objectives. The first of them is to present the Safety ArtISt method, developed by the authors to guide the lifecycle of AI-based safety-critical systems, and emphasize its FPGA-oriented tasks and recommended practice towards safety assurance. The second one is to illustrate the application of Safety ArtISt with an FPGA-based braking control system for autonomous vehicles relying on explainable AI generated with High-Level Synthesis. The results indicate that Safety ArtISt played four main roles in the safety lifecycle of AI-based systems for FPGAs. Firstly, it provided guidance in identifying the safety-critical role of activities such as sensitivity analyses for numeric representation and FPGA dimensioning to achieve safety. Furthermore, it allowed building qualitative and quantitative safety arguments from analyses and physical experimentation with actual FPGAs. It also allowed the early detection of safety issues—thus reducing project costs—and, ultimately, it uncovered relevant challenges not discussed in detail when designing safety-critical, explainable AI for FPGAs.
13
Davahli, Mohammad Reza, Waldemar Karwowski, Krzysztof Fiok, Thomas Wan, and Hamid R. Parsaei. "Controlling Safety of Artificial Intelligence-Based Systems in Healthcare." Symmetry 13, no. 1 (2021): 102. http://dx.doi.org/10.3390/sym13010102.
Full textAbstract:
In response to the need to address the safety challenges in the use of artificial intelligence (AI), this research aimed to develop a framework for a safety controlling system (SCS) to address the AI black-box mystery in the healthcare industry. The main objective was to propose safety guidelines for implementing AI black-box models to reduce the risk of potential healthcare-related incidents and accidents. The system was developed by adopting the multi-attribute value model approach (MAVT), which comprises four symmetrical parts: extracting attributes, generating weights for the attributes, developing a rating scale, and finalizing the system. On the basis of the MAVT approach, three layers of attributes were created. The first level contained six key dimensions, the second level included 14 attributes, and the third level comprised 78 attributes. The key first level dimensions of the SCS included safety policies, incentives for clinicians, clinician and patient training, communication and interaction, planning of actions, and control of such actions. The proposed system may provide a basis for detecting AI utilization risks, preventing incidents from occurring, and developing emergency plans for AI-related risks. This approach could also guide and control the implementation of AI systems in the healthcare industry.
14
Ukandu, Chidiebere Promise, O. Blessing Emoghene, and E. Thomas Boye. "Occupational Hazards Identification, Risk Evaluation and Mitigation in Contemporary Nigeria Society: The Application of Artificial Intelligence (AI)." International Journal of Research and Innovation in Social Science VII, no. XI (2023): 1344–56. http://dx.doi.org/10.47772/ijriss.2023.7011104.
Full textAbstract:
This paper examines the current state and potential future developments of Artificial Intelligence (AI) applications in Occupational Health and Safety (OHS) in Nigeria. OHS is a critical concern in the world and particularly in Nigeria, as workplace hazards pose risks to the health, safety, and well-being of workers. AI offers promising solutions to enhance hazard identification, risk evaluation, and control measures in OHS practices. The paper begins by providing an overview of AI, its subfields, and techniques commonly used in OHS. It then explores the real-time applications of AI in hazard identification, risk evaluation, and control measures, highlighting the benefits it brings to OHS practices. Furthermore, the paper discusses the challenges and considerations in adopting AI in Nigeria, including infrastructure limitations, skill gaps, and ethical concerns. Based on the analysis, four suggestion were proposed for Nigeria’s OHS context. These suggestions include investment in AI infrastructure and research, capacity building programs to develop AI expertise; collaboration between stakeholders, and the establishment of regulatory frameworks to ensure responsible AI deployment. By embracing AI in OHS, Nigeria can improve workplace safety, mitigate risks, and protect the health and well-being of its workforce.
15
Ravi, Aravind, and Chirag Vinalbhai Shah. "Innovations in Electronic Control Units: Enhancing Performance and Reliability with AI (Revision-1)." International Journal of Engineering and Computer Science 13, no. 01 (2024): 26033–50. http://dx.doi.org/10.18535/ijecs/v13i01.4796.
Full textAbstract:
As the automobile industry moves toward greater efficiency, safety, and autonomous operation, the demand for Electronic Control Units (ECUs) - the microprocessors controlling everything from engine functions to infotainment systems - has exploded globally. Currently, there are more than 200 million ECUs in the world, and that number is expected to rise to 700 million by 2030, necessitating enhanced ECU performance, reliability, and safety. However, the growing complexity of ECUs has ironically led to increased false alarms and failures, which in some cases have endangered user safety and privacy, causing heavy penalties for manufacturers. Although artificial intelligence (AI) and machine learning (ML) are showing promise in addressing ECU-related issues, existing methods remain insufficient. Manufacturers need to employ AI-driven, end-to-end, standardized solutions that help design, train, test, and deploy models without deep AI expertise and allow real-time runtime monitoring and retraining of the ECUs.Drawing on decades of experience in the electronics and automotive industries, as well as a track record of successfully deploying AI-based solutions in safety-critical systems like avionics and diesel engine control, a comprehensive method is proposed. It includes an array of novel functionalities that increase transparency, reliability, and safety while keeping development times low. Central to the method is a feature that creates an environment-sensitive digital twin of the ECU by assimilating data from ECUs and the vehicle, thus improving model fidelity and monitoring for unforeseen edge cases. The proposal is based on co-design and training of AI-based perception and prediction models, which can monitor the relevant environmental parameters both on-board and in the cloud. The on-board model is lightweight yet deterministic and can trigger warnings in case of model uncertainty and prediction errors, while the corrective action is taken by the re-licensed cloud-based model. A dataset of more than 33 million kilometers of driving from passenger vehicles in Northern Europe with SaaStronic and Focus models has been provided, using compute-efficient methods for interpretation and simplification of AI-based models.
16
Pompi., R. Boro. "Artificial Intelligence in Meat Industry." Science world a Monthly e magazine 5, no. 4 (2025): 6700–6702. https://doi.org/10.5281/zenodo.15166754.
Full textAbstract:
The growing global demand for animal-derived food products has sparked significant concerns regarding the hygiene and overall quality of these products. In the animal food production industry, conventional methods of monitoring, inspection, and quality control are often labour-intensive, time-consuming, and prone to human error. In this context, Artificial Intelligence (AI) has emerged as a transformative technology, offering innovative approaches to enhance the safety and quality of animal food products. This review presents an overview of AI applications within the animal food sector, emphasizing its crucial role in ensuring food quality and safety. We examine various facets of AI implementation, such as computer vision, biosensors, machine vision, ultrasonic sensing, the Internet of Things, and electronic methods. The review investigates the use of AI in quality control, disease detection, feed optimization, and supply chain management within the animal food industry. By harnessing the capabilities of AI, the animal food sector can improve food safety, elevate product quality, and satisfy the growing demands of a global consumer base that prioritizes the source and safety of their food. This review seeks to illuminate the diverse applications of AI in the animal food industry, underscoring its potential to transform quality and safety standards while fostering innovation and sustainability in an increasingly interconnected world. <strong> </strong>
17
Yin, Binfeng, Gang Tan, Rashid Muhammad, Jun Liu, and Junjie Bi. "AI-Powered Innovations in Food Safety from Farm to Fork." Foods 14, no. 11 (2025): 1973. https://doi.org/10.3390/foods14111973.
Full textAbstract:
Artificial intelligence is comprehensively transforming the food safety governance system by integrating modern technologies and building intelligent control systems that provide rapid solutions for the entire food supply chain from farm to fork. This article systematically reviews the core applications of AI in the orbit of food safety. First, in the production and quality control of primary food sources, the integration of spectral data with AI efficiently identifies pest and disease, food spoilage, and pesticide and veterinary drug residues. Secondly, during food processing, sensors combined with machine learning algorithms are utilized to ensure regulatory compliance and monitor production parameters. AI also works together with blockchain to build an immutable and end-point traceability system. Furthermore, multi-source data fusion can provide personalized nutrition and dietary recommendations. The integration of AI technologies with traditional food detection methods has significantly improved the accuracy and sensitivity of food analytical methods. Finally, in the future, to address the increasing food safety issues, Food Industry 4.0 will expand the application of AI with lightweight edge computing, multi-modal large models, and global data sharing to create a more intelligent, adaptive and flexible food safety system.
18
Joel Frenette. "Ensuring human oversight in high-performance AI systems: A framework for control and accountability"." World Journal of Advanced Research and Reviews 20, no. 2 (2023): 1507–16. https://doi.org/10.30574/wjarr.2023.20.2.2194.
Full textAbstract:
As AI systems increasingly outperform humans in specialized tasks such as medical diagnosis, financial analysis, and strategic decision-making, ensuring human oversight becomes a critical challenge. This paper explores frameworks and mechanisms that allow humans to maintain control over AI-driven agents without hindering their efficiency. We examine case studies where AI has demonstrated superior performance, analyze the risks of over-reliance, and propose governance strategies to ensure AI remains a tool for augmentation rather than replacement. The findings suggest that maintaining a balance between AI autonomy and human oversight is essential for trust, safety, and ethical AI deployment.
19
Sahoo, Sushil Kumar, and Bibhuti Bhusan CHOUDHURY. "AI ADVANCES IN WHEELCHAIR NAVIGATION AND CONTROL: A COMPREHENSIVE REVIEW." Journal of process management and new technologies 11, no. 3-4 (2023): 115–32. http://dx.doi.org/10.5937/jpmnt11-45181.
Full textAbstract:
This paper presents a systematic review of the literature on integrating artificial intelligence (AI) to improve wheelchair navigation and control for people with mobility impairments. The review covers a range of AI-based approaches including computer vision, machine learning, and path planning algorithms. The paper highlights the potential benefits of integrating AI into wheelchair technology, including increased safety, autonomy, and personalized control. The review discusses the limitations and challenges of current wheelchair navigation and control systems, and how AI can address these limitations. The paper identifies common themes and trends in the literature and summarizes the strengths and weaknesses of existing AI-based wheelchair navigation and control systems. Finally, the paper concludes by discussing the potential future directions for research and development of AI-based wheelchair navigation and control systems. This review paper provides a valuable resource for researchers and engineers interested in developing and improving AI-based wheelchair technology.
20
Kirwan, Barry. "Human Factors Requirements for Human-AI Teaming in Aviation." Future Transportation 5, no. 2 (2025): 42. https://doi.org/10.3390/futuretransp5020042.
Full textAbstract:
The advent of Artificial Intelligence in the cockpit and the air traffic control centre in the coming decade could mark a step-change improvement in aviation safety, or else could usher in a flush of ‘AI-induced’ accidents. Given that contemporary AI has well-known weaknesses, from data biases and edge or corner effects, to outright ‘hallucinations’, in the mid-term AI will almost certainly be partnered with human expertise, its outputs monitored and tempered by human judgement. This is already enshrined in the EU Act on AI, with adherence to principles of human agency and oversight required in safety-critical domains such as aviation. However, such sound policies and principles are unlikely to be enough. Human interactions with current automation in the cockpit or air traffic control tower require extensive requirements, methods, and validations to ensure a robust (accident-free) partnership. Since AI will inevitably push the boundaries of traditional human-automation interaction, there is a need to revisit Human Factors to meet the challenges of future human-AI interaction design. This paper briefly reviews the types of AI and ‘Intelligent Agents’ along with their associated levels of AI autonomy being considered for future aviation applications. It then reviews the evolution of Human Factors to identify the critical areas where Human Factors can aid future human-AI teaming performance and safety, to generate a detailed requirements set organised for Human AI Teaming design. The resultant requirements set comprises eight Human Factors areas, from Human-Centred Design to Organisational Readiness, and 165 detailed requirements, and has been applied to three AI-based Intelligent Agent prototypes (two cockpit, one air traffic control tower). These early applications suggest that the new requirements set is scalable to different design maturity levels and different levels of AI autonomy, and acceptable as an approach to Human-AI Teaming design teams.
21
Temilade Abass, Esther Oleiye Itua, Tabat Bature, and Michael Alurame Eruaga. "Concept paper: Innovative approaches to food quality control: AI and machine learning for predictive analysis." World Journal of Advanced Research and Reviews 21, no. 3 (2024): 823–28. http://dx.doi.org/10.30574/wjarr.2024.21.3.0719.
Full textAbstract:
The concept paper explores the potential of artificial intelligence (AI) and machine learning (ML) in revolutionizing food quality control processes. In response to the growing challenges faced by the food industry in ensuring consistent quality and safety standards, this paper proposes leveraging advanced technologies to enhance predictive analysis. The traditional methods of food quality control are often reactive and time-consuming, leading to inefficiencies and increased risks of contamination or spoilage. By harnessing AI and ML algorithms, businesses can shift towards proactive strategies, predicting potential issues before they arise and implementing preventive measures accordingly. Key components of the proposed approach include data collection from various sources such as sensors, supply chain records, and historical quality data. Through sophisticated data analysis techniques, AI systems can identify patterns, anomalies, and correlations that might indicate deviations from expected quality standards. Moreover, ML models can continuously learn and adapt based on new data, improving prediction accuracy over time. Implementation of AI-driven predictive analysis in food quality control offers several benefits. Automation of quality control processes reduces manual effort and enables real-time monitoring, enabling timely interventions to maintain product quality. By minimizing the likelihood of product recalls, waste, and rework, businesses can achieve significant cost savings associated with quality control measures. Consistently delivering high-quality products strengthens consumer trust and loyalty, leading to increased market competitiveness and brand reputation. AI-powered systems can assist in ensuring compliance with stringent food safety regulations by providing comprehensive documentation of quality control measures and outcomes. However, successful adoption of AI and ML technologies in food quality control requires overcoming various challenges, including data privacy concerns, integration with existing systems, and ensuring the reliability and interpretability of AI-driven insights. the integration of AI and ML for predictive analysis represents a transformative opportunity for the food industry to modernize quality control practices and uphold the highest standards of safety and excellence. Embracing innovation in this domain is essential for staying competitive in a rapidly evolving market landscape and meeting the evolving expectations of consumers and regulatory bodies alike.
22
Temilade, Abass, Oleiye Itua Esther, Bature Tabat, and Alurame Eruaga Michael. "Concept paper: Innovative approaches to food quality control: AI and machine learning for predictive analysis." World Journal of Advanced Research and Reviews 21, no. 3 (2024): 823–28. https://doi.org/10.5281/zenodo.14060627.
Full textAbstract:
The concept paper explores the potential of artificial intelligence (AI) and machine learning (ML) in revolutionizing food quality control processes. In response to the growing challenges faced by the food industry in ensuring consistent quality and safety standards, this paper proposes leveraging advanced technologies to enhance predictive analysis. The traditional methods of food quality control are often reactive and time-consuming, leading to inefficiencies and increased risks of contamination or spoilage. By harnessing AI and ML algorithms, businesses can shift towards proactive strategies, predicting potential issues before they arise and implementing preventive measures accordingly. Key components of the proposed approach include data collection from various sources such as sensors, supply chain records, and historical quality data. Through sophisticated data analysis techniques, AI systems can identify patterns, anomalies, and correlations that might indicate deviations from expected quality standards. Moreover, ML models can continuously learn and adapt based on new data, improving prediction accuracy over time. Implementation of AI-driven predictive analysis in food quality control offers several benefits. Automation of quality control processes reduces manual effort and enables real-time monitoring, enabling timely interventions to maintain product quality. By minimizing the likelihood of product recalls, waste, and rework, businesses can achieve significant cost savings associated with quality control measures. Consistently delivering high-quality products strengthens consumer trust and loyalty, leading to increased market competitiveness and brand reputation. AI-powered systems can assist in ensuring compliance with stringent food safety regulations by providing comprehensive documentation of quality control measures and outcomes. However, successful adoption of AI and ML technologies in food quality control requires overcoming various challenges, including data privacy concerns, integration with existing systems, and ensuring the reliability and interpretability of AI-driven insights. the integration of AI and ML for predictive analysis represents a transformative opportunity for the food industry to modernize quality control practices and uphold the highest standards of safety and excellence. Embracing innovation in this domain is essential for staying competitive in a rapidly evolving market landscape and meeting the evolving expectations of consumers and regulatory bodies alike.
23
Thirunagalingam, Arun kumar. "Generative AI Ethics: a Comprehensive Safety and Regulation Framework." International Journal of Security, Privacy and Trust Management 13, no. 4 (2024): 01–13. https://doi.org/10.5121/ijsptm.2024.13401.
Full textAbstract:
The quick development of generative AI technology has brought about revolutionary new possibilities for decision-making, design, and content production. But these developments have also raised serious ethical questions, emphasizing the need for an all-encompassing framework to guarantee the security and control of generative AI systems. To address the ethical issues raised by generative AI, this study puts forth a paradigm that centers on the concepts of accountability, transparency, and governance. Strategies for reducing the dangers associated with AI-generated content are provided by this paper through an analysis of the present regulatory frameworks and the identification of gaps. The framework that is being suggested supports a multi-stakeholder approach that incorporates technical, legal, and ethical viewpoints to establish a well-rounded and efficient regulatory framework. The discussion of research directions for the future and the significance of continuing discourse to maintain AI technologies in line with social ideals finishes the article.
24
Mahajan, Gulshan, and Bhagirath S. Chauhan. "Screening of Herbicides for Rice Seedling Safety and Echinochloa colona Management under Australian Conditions." Agronomy 12, no. 6 (2022): 1273. http://dx.doi.org/10.3390/agronomy12061273.
Full textAbstract:
Different herbicides are currently required for sustainable weed management in aerobic rice. Three pot experiments were conducted using different herbicides to evaluate rice safety and for the control of Echinochloa colona, a major weed of aerobic rice. Among the pre-emergence (PRE) herbicides, it was found that pendimethalin (594 g ai ha−1) and flumioxazin (60 g ai ha−1) were relatively safe herbicides for rice and provided 100% control of E. colona. All other PRE herbicides, such as atrazine, cinmethylin, clomazone, dimethenamid-P, isoxaflutole, metribuzin, prosulfocarb + S-metolachlor, pyroxasulfone, trifluralin, and S-metolachlor reduced the biomass of rice compared with the non-treated control. Dose-response studies revealed that flumioxazin and pendimethalin even at low doses (30 g ai ha−1 for flumioxazin and 294 g ai ha−1 for pendimethalin) provided excellent control (>95%) of E. colona. Post-emergence (POST) application of paraquat (360 g ai ha−1) at the time of rice emergence caused toxicity in the crop, but also provided excellent control of E. colona. When applied just after crop emergence (11 days after sowing), Pendimethalin was found to be safe for rice (2% mortality) and reduced the biomass of E. colona by 88% compared with the non-treated control. It is quite possible that the rice variety Reiziq used in this study may have a tolerance to flumioxazin, which needs further investigation involving more rice varieties. This study suggests that flumioxazin can be used as an alternative to pendimethalin for the sustainable management of E. colona in aerobic rice.
25
Shah, Chirag Vinalbhai. "Vehicle Control Systems: Integrating Edge AI and ML for Enhanced Safety and Performance." International Journal of Scientific Research and Management (IJSRM) 10, no. 04 (2022): 871–86. http://dx.doi.org/10.18535/ijsrm/v10i4.ec10.
Full textAbstract:
AI-driven dynamic trajectory planning and control systems are the keys to enhancing safety and performance for the next generation of autonomous vehicles. The growing demand for autonomous vehicles is pushing relevant companies to deploy the latest AI/ML methods to build better, more reliable, and versatile control systems. Current software architectures supporting the deployment and execution of AI in vehicles rely on centralized or decentralized control. Centralized approaches optimize performance over specific tasks, but they are poorly scalable. Decentralized approaches target scalability but struggle to maximize global efficiency and safety, especially when handling the variability and unpredictability associated with real-world scenarios. In this talk, we bring on the discussion that modular software architectures offer a more appealing way to organize the three core functions of future autonomous vehicles, i.e., sensing, planning, and control.Moreover, fostering the debate and collaboration between companies, academic institutions, and community-driven open-source foundations is a key priority to increase the number of potential solutions from a vast array of currently applicable technologies such as Deep Reinforcement Learning, Model Predictive Control, and Motion Planning Field, to name a few. The scale needed for a production-worthy solution is not achievable by any single company. Finally, an increasing level of democratization and standardization has a desirable side effect for the community itself: making the final user confident in the performance and safety of AI-driven products is the key to unlocking the adoption of fully autonomous vehicles.
26
Srivastava, Siddharth. "Unifying Principles and Metrics for Safe and Assistive AI." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 17 (2021): 15064–68. http://dx.doi.org/10.1609/aaai.v35i17.17769.
Full textAbstract:
The prevalence and success of AI applications have been tempered by concerns about the controllability of AI systems about AI's impact on the future of work. These concerns reflect two aspects of a central question: how would humans work with AI systems? While research on AI safety focuses on designing AI systems that allow humans to safely instruct and control AI systems, research on AI and the future of work focuses on the impact of AI on humans who may be unable to do so. This Blue Sky Ideas paper proposes a unifying set of declarative principles that enable a more uniform evaluation of arbitrary AI systems along multiple dimensions of the extent to which they are suitable for use by specific classes of human operators. It leverages recent AI research and the unique strengths of the field to develop human-centric principles for AI systems that address the concerns noted above.
27
Zhou, Zhiyu. "Technological Control Tool of Everyday life? Six Questions on the Design Ethics of Artificial Intelligence." Journal of Design Service and Social Innovation 1, no. 1 (2023): 36–43. http://dx.doi.org/10.59528/ms.jdssi2023.0614a5.
Full textAbstract:
Artificial intelligence (AI) continues to expand into different areas of social life, bringing design ethics and public rights under challenge. Instead of stopping the research application of AI, it is better to urgently study some of the practical problems that AI technology may bring about and promptly formulate corresponding laws to regulate them. This paper discusses the following issues: 1. Security and privacy of face recognition; 2. Political and economic applications of AI; 3. Emotional learning of AI; 3. Human-computer development of brain-computer interface; 5. Ethical supervision of AI; 6. Automatic design of AI etc. It analyses design ethics basic principles, such as security, privacy, fairness, trustworthiness, honesty, etc., and calls for strengthening the institutional construction of design ethics and public safety for AI technology products.
28
Noviati, Nuraini Diah, Fengki Eka Putra, Sadan Sadan, Ridhuan Ahsanitaqwim, Nanda Septiani, and Nuke Puji Lestari Santoso. "Artificial Intelligence in Autonomous Vehicles: Current Innovations and Future Trends." International Journal of Cyber and IT Service Management 4, no. 2 (2024): 97–104. https://doi.org/10.34306/ijcitsm.v4i2.161.
Full textAbstract:
Artificial Intelligence (AI) has become a cornerstone in advancing autonomous vehicles, enabling realtime decision making, object detection, and automation in driving systems. This study aims to explore key AI innovations, including Machine Learning (ML) algorithms, computer vision, and reinforcement learning, that contribute to the development of autonomous vehicles. A qualitative approach} was adopted to analyze both current applications and future innovations of AI in autonomous vehicles. The study highlights various current AI applications in autonomous vehicles, such as automated safety features, advanced navigation systems, and adaptive cruise control. These technologies demonstrate how AI enhances vehicle functionality and improves safety in today driving environment. Looking ahead, AI is expected to enable full autonomy in vehicles, foster integration with smart city infrastructures, and drive innovations in fleet management. These advancements are anticipated to significantly improve vehicle safety, operational efficiency, and the overall user experience, solidifying AI as the fundamental technology for the future of intelligent transportation systems.
29
Xie, Aoyu. "Intelligent technologies in traffic flow control: a review." Applied and Computational Engineering 126, no. 1 (2025): 16–21. https://doi.org/10.54254/2755-2721/2025.20047.
Full textAbstract:
With the acceleration of global urbanization, traffic congestion has become a major bottleneck in the development of modern cities, leading to serious economic losses and a decline in the quality of life. To address this challenge, traffic flow prediction techniques have received much attention. This paper reviews the application of three key technologies, including 5G, artificial intelligence (AI), and vehicular networking (V2X) in intelligent traffic management. 5G technology provides a communication foundation with high speed rates, low latency, and large-scale device connectivity, which effectively supports real-time data transmission and communication needs. AI technology, on the other hand, with its powerful data processing capability, is able to make high-precision traffic predictions in dynamic traffic environments. However, the effectiveness of AI models is highly dependent on the support of high-quality data.V2X technology greatly improves road safety and traffic mobility by realizing real-time information exchange between vehicles and infrastructure. However, relying on a single technology alone cannot comprehensively solve complex transportation problems. For this reason, this paper proposes a technology fusion scheme of 5G, AI, and V2X, aiming to optimize the intelligence level of the traffic management system through the complementary advantages of each technology. The study shows that the synergistic application of the technologies can not only effectively alleviate traffic congestion but also improve the overall safety of roads, providing a feasible solution for the future intelligent transportation system in cities.
30
Zhang, Xuanning. "Artificial Intelligence in Intelligent Traffic Signal Control." Applied and Computational Engineering 118, no. 1 (2025): 113–20. https://doi.org/10.54254/2755-2721/2025.20846.
Full textAbstract:
With the rapid urbanization and the increasing traffic demand in cities, traffic congestion and accidents have become significant challenges for urban transportation systems. Traditional traffic signal control systems, which rely on fixed signal cycles, often fail to adapt to real-time traffic conditions, leading to inefficiencies and resource waste. This paper explores the application of Artificial Intelligence (AI) in intelligent traffic signal control systems. Specifically, it focuses on the use of Deep Reinforcement Learning (DRL), particularly the Deep Q-Network (DQN) model, for optimizing signal timing based on real-time traffic data. The system dynamically adjusts the signal cycles based on traffic flow, reducing congestion, improving traffic efficiency, and enhancing safety. The study also discusses the challenges AI-based systems face, such as algorithm complexity, data quality, and system integration, as well as the potential benefits of AI in managing traffic during peak hours and at complex intersections. Through simulation and real-world testing, the study demonstrates the advantages of AI-based signal control systems in improving urban traffic management. The findings suggest that AI can significantly enhance traffic flow, reduce waiting times, and optimize traffic resource allocation, offering a promising approach to solving urban traffic problems.
31
Ashrafi, Negin, Sahar Yousefi, Guy Roger Aby, et al. "AI-driven solutions to improve safety and health: Application of the REDECA framework for agricultural tractor drivers." PLOS Global Public Health 5, no. 6 (2025): e0003543. https://doi.org/10.1371/journal.pgph.0003543.
Full textAbstract:
Introduction Despite tremendous efforts, including research, teaching, and extension, toward improving the safety of agricultural tractor drivers, the number of incidents related to agricultural tractor drivers has not declined. This evidence points out an urgent need to explore artificial intelligence (AI) solutions to improve the safety of tractor drivers. Methods This paper uses 171 Fatality Assessment and Control Evaluation (FACE) reports related to tractor drivers and a new framework called Risk Evolution, Detection, Evaluation, and Control of Accidents (REDECA) to identify existing AI solutions, such as machine learning models for predictive maintenance, sensor-based monitoring, computer vision, and automated safety interventions, and specific areas where AI solutions are missed and can be developed to reduce incidents and recovery time. Fatality reports of tractor drivers were categorized into six main categories, including run over, pinned by/ Crushed and entanglement, fall, fire, roll over, and overturn. Each category was then subcategorized based on similarities of incident causes in the reports. Results The application of the REDECA framework, which categorizes risk states into R1 (safe), R2 (hazard exposure), and R3 (incident), revealed potential AI solutions that could improve the safety of tractor drivers. In all categories, the REDECA framework lacks AI solutions for three elements, including the probability of reducing recovery time in R3, detecting changes between R2 and R3, and intervention to send workers to R2. Most of the categories were missing AI solutions for interventions to prevent entry to the R3 element of the REDECA. In addition, the fall, roll over, and overturn categories lacked AI intervention that minimized damage and recovery in R3. Conclusions The outcome of this study shows an urgent need to develop AI solutions to improve tractor driver safety.
32
Yu, Pan, Hui Wan, Bozhi Zhang, et al. "Review on System Identification, Control, and Optimization Based on Artificial Intelligence." Mathematics 13, no. 6 (2025): 952. https://doi.org/10.3390/math13060952.
Full textAbstract:
Control engineering plays an indispensable role in enhancing safety, improving comfort, and reducing fuel consumption and emissions for various industries, for which system identification, control, and optimization are primary topics. Alternatively, artificial intelligence (AI) is a leading, multi-disciplinary technology, which tries to incorporate human learning and reasoning into machines or systems. AI exploits data to improve accuracy, efficiency, and intelligence, which is beneficial, especially in complex and challenging cases. The rapid progress of AI facilitates major changes in control engineering and is helping advance the next generation of system identification, control, and optimization methods. In this study, we review the developments, key technologies, and recent advancements of AI-based system identification, control, and optimization methods, as well as present potential future research directions.
33
Sathian, Brijesh, Edwin van Teijlingen, Israel Junior Borges Do Nascimento, et al. "Urgent need for better quality control, standards and regulation for the Large Language Models used in healthcare domain." Nepal Journal of Epidemiology 14, no. 2 (2024): 1310–12. http://dx.doi.org/10.3126/nje.v14i2.69361.
Full textAbstract:
Current methodologies for ensuring AI technology safety and efficacy may be adequate for earlier AI iterations predating generative artificial intelligence (GAI). However, governing clinical GAI may necessitate the development of novel regulatory frameworks. As AI technology advances, researchers, academic institutions, funding bodies, and publishers should continue to examine its impact on scientific inquiry and revise their understanding, ethical guidelines, and regulations accordingly.
34
Vasileiou, Marios, Leonidas Sotirios Kyrgiakos, Christina Kleisiari, et al. "Transforming weed management in sustainable agriculture with artificial intelligence: a systematic literature review towards weed identification and deep learning." Crop Protection 176 (February 1, 2024): 106522. https://doi.org/10.1016/j.cropro.2023.106522.
Full textAbstract:
In the face of increasing agricultural demands and environmental concerns, the effective management of weeds presents a pressing challenge in modern agriculture. Weeds not only compete with crops for resources but also pose threats to food safety and agricultural sustainability through the indiscriminate use of herbicides, which can lead to environmental contamination and herbicide-resistant weed populations. Artificial Intelligence (AI) has ushered in a paradigm shift in agriculture, particularly in the domain of weed management. AI's utilization in this domain extends beyond mere innovation, offering precise and eco-friendly solutions for the identification and control of weeds, thereby addressing critical agricultural challenges. This article aims to examine the application of AI in weed management in the context of weed detection and the increasing impact of deep learning techniques in the agricultural sector. Through an assessment of research articles, this study identifies critical factors influencing the adoption and implementation of AI in weed management. These criteria encompass factors of AI adoption (food safety, increased effectiveness, and eco-friendliness through herbicides reduction), AI implementation factors (capture technology, training datasets, AI models, and outcomes and accuracy), ancillary technologies (IoT, UAV, field robots, and herbicides), and the related impact of AI methods adoption (economic, social, technological, and environmental). Of the 5821 documents found, 99 full-text articles were assessed, and 68 were included in this study. The review highlights AI's role in enhancing food safety by reducing herbicide residues, increasing effectiveness in weed control strategies, and promoting eco-friendliness through judicious herbicide use. It underscores the importance of capture technology, training datasets, AI models, and accuracy metrics in AI implementation, emphasizing their synergy in revolutionizing weed management practices. Ancillary technologies, such as IoT, UAVs, field robots, and AI-enhanced herbicides, complement AI's capabilities, offering holistic and data-driven approaches to weed control. Additionally, the adoption of AI methods influences economic, social, technological, and environmental dimensions of agriculture. Last but not least, digital literacy emerges as a crucial enabler, empowering stakeholders to navigate AI technologies effectively and contribute to the sustainable transformation of weed management practices in agriculture.
35
Durlik, Irmina, Tymoteusz Miller, Ewelina Kostecka, Polina Kozlovska, and Wojciech Ślączka. "Enhancing Safety in Autonomous Maritime Transportation Systems with Real-Time AI Agents." Applied Sciences 15, no. 9 (2025): 4986. https://doi.org/10.3390/app15094986.
Full textAbstract:
The maritime transportation sector is undergoing a profound shift with the emergence of autonomous vessels powered by real-time artificial intelligence (AI) agents. This article investigates the pivotal role of these agents in enhancing the safety, efficiency, and sustainability of autonomous maritime systems. Following a structured literature review, we examine the architecture of real-time AI agents, including sensor integration, communication systems, and computational infrastructure. We distinguish maritime AI agents from conventional systems by emphasizing their specialized functions, real-time processing demands, and resilience in dynamic environments. Key safety mechanisms—such as collision avoidance, anomaly detection, emergency coordination, and fail-safe operations—are analyzed to demonstrate how AI agents contribute to operational reliability. The study also explores regulatory compliance, focusing on emission control, real-time monitoring, and data governance. Implementation challenges, including limited onboard computational power, legal and ethical constraints, and interoperability issues, are addressed with practical solutions such as edge AI and modular architectures. Finally, the article outlines future research directions involving smart port integration, scalable AI models, and emerging technologies like federated and explainable AI. This work highlights the transformative potential of AI agents in advancing autonomous maritime transportation.
36
SKRABACZ, Aleksandra, Magdalena BSOUL-KOPOWSKA, and Bartosz KOZICKI. "THE APPLICATION OF ARTIFICIAL INTELLIGENCE IN ROAD TRAFFIC MANAGEMENT AND ITS SAFETY IMPROVEMENT." Transport Problems 19, no. 4 (2024): 5–16. https://doi.org/10.20858/tp.2024.19.4.01.
Full textAbstract:
Artificial intelligence (AI) is used in many aspects of life, from personal voice assistants to product recommendations in online stores to advanced diagnostic systems in medicine. All these applications show how AI technology is becoming an increasingly integral part of everyday life. Understanding the basics of AI is key to recognizing its role in traffic management. AI can be used to monitor and control road traffic, prevent traffic jams and road crashes, support vehicle diagnostics, and optimize response times for emergency services and roadside assistance. Particular attention should be paid to reducing the number of fatal road crashes. This goal is to be achieved by integrating AI with autonomous vehicle technology, which should improve or even reduce the number of road accident victims to 0.
37
Izquierdo-Bueno, Inmaculada, Javier Moraga, Jesús M. Cantoral, María Carbú, Carlos Garrido, and Victoria E. González-Rodríguez. "Smart Viniculture: Applying Artificial Intelligence for Improved Winemaking and Risk Management." Applied Sciences 14, no. 22 (2024): 10277. http://dx.doi.org/10.3390/app142210277.
Full textAbstract:
This review explores the transformative role of artificial intelligence (AI) in the entire winemaking process, from viticulture to bottling, with a particular focus on enhancing food safety and traceability. It discusses AI’s applications in optimizing grape cultivation, fermentation, bottling, and quality control, while emphasizing its critical role in managing microbiological risks such as mycotoxins. The review aims to show how AI technologies not only refine operational efficiencies but also raise safety standards and ensure traceability from vineyard to consumer. Challenges in AI implementation and future directions for integrating more advanced AI solutions into the winemaking industry will also be discussed, providing a comprehensive overview of AI’s potential to revolutionize traditional practices.
38
Yao, Keyu. "AI-driven innovations in automation and urban management." Applied and Computational Engineering 57, no. 1 (2024): 160–65. http://dx.doi.org/10.54254/2755-2721/57/20241327.
Full textAbstract:
This paper examines the transformative impact of Artificial Intelligence (AI) across diverse sectors, particularly focusing on industrial automation, smart homes, and intelligent cities. It delves into how AI-driven technologies enhance predictive maintenance, quality control, and supply chain optimization in industrial settings, contribute to energy management, security enhancement, and health monitoring in smart homes, and improve traffic management, waste management, and public safety in intelligent cities. Through detailed analyses and quantitative assessments, the study showcases the efficiency gains, cost reductions, and quality of life improvements facilitated by AI integration. It highlights the pivotal role of AI in addressing contemporary challenges and setting new standards for operational excellence, sustainability, and safety.
39
Alvarado Contreras, Rocio E., Lizbeth Escobedo, and Jessica Beltrán. "AI Companions in Ride-Hailing: Enhancing Sense of Safety with Voice Chatbots." Avances en Interacción Humano-Computadora 9, no. 1 (2024): 11–15. https://doi.org/10.47756/aihc.y9i1.138.
Full textAbstract:
In this paper, we present the development and formative evaluation of AI Companion, a voice chatbot based on Artificial Intelligence Large Language Models designed to enhance users' perception of safety and control during transportation using ride-hailing apps or similar services. We conducted a study with 10 participants to understand their travel experiences and evaluate the AI Companion's ability to maintain coherent conversations, simulating a phone call. Our findings indicate that participants generally liked the system. However, we provide several recommendations for significant improvements to the AI Companion.
40
Nanban, Desiya, Jennifer Selvan, A. T. Ashmi Christus, and Muhammad Al Amin. "Enhancing Air Traffic Management: The Transformative Role of Artificial Intelligence in Modern Air Traffic Control." FMDB Transactions on Sustainable Intelligent Networks 1, no. 2 (2024): 72–84. http://dx.doi.org/10.69888/ftsin.2024.000210.
Full textAbstract:
Since the Wright brothers' December 17, 1903 flight, the aviation business has grown quickly alongside IT. Growth is concentrated in aircraft development, airport infrastructure, and air traffic control. AI will revolutionize each of these fields. AI optimizes fuel usage, structural designs, and avionics in aircraft development, making them more efficient and modern. AI streamlines airport check-in, luggage processing, and airport security, improving efficiency and passenger experience. The heart of aviation, ATC, coordinates take-offs, landings, and en-route traffic through Aerodrome Control, Approach Control, and Area Control. ATC may use AI to optimize air traffic management, automate mundane jobs, analyze data for decision-making, and predict traffic flow to avoid congestion and delays. Due to the complexity of air traffic and the requirement for quick human judgment, replacing human ATC operators with AI is difficult. However, AI can be gradually introduced into particular operations to improve efficiency and safety. AI will support these functions as technology advances, making air travel safer and more efficient.
41
Pishgar, Maryam, Salah Fuad Issa, Margaret Sietsema, Preethi Pratap, and Houshang Darabi. "REDECA: A Novel Framework to Review Artificial Intelligence and Its Applications in Occupational Safety and Health." International Journal of Environmental Research and Public Health 18, no. 13 (2021): 6705. http://dx.doi.org/10.3390/ijerph18136705.
Full textAbstract:
Introduction: The field of artificial intelligence (AI) is rapidly expanding, with many applications seen routinely in health care, industry, and education, and increasingly in workplaces. Although there is growing evidence of applications of AI in workplaces across all industries to simplify and/or automate tasks there is a limited understanding of the role that AI contributes in addressing occupational safety and health (OSH) concerns. Methods: This paper introduces a new framework called Risk Evolution, Detection, Evaluation, and Control of Accidents (REDECA) that highlights the role that AI plays in the anticipation and control of exposure risks in a worker’s immediate environment. Two hundred and sixty AI papers across five sectors (oil and gas, mining, transportation, construction, and agriculture) were reviewed using the REDECA framework to highlight current applications and gaps in OSH and AI fields. Results: The REDECA framework highlighted the unique attributes and research focus of each of the five industrial sectors. The majority of evidence of AI in OSH research within the oil/gas and transportation sectors focused on the development of sensors to detect hazardous situations. In construction the focus was on the use of sensors to detect incidents. The research in the agriculture sector focused on sensors and actuators that removed workers from hazardous conditions. Application of the REDECA framework highlighted AI/OSH strengths and opportunities in various industries and potential areas for collaboration. Conclusions: As AI applications across industries continue to increase, further exploration of the benefits and challenges of AI applications in OSH is needed to optimally protect worker health, safety and well-being.
42
Jadhav, N. R., Sunil Bhutada, S. R. Sagavkar, Rohit Pawar, Archana Bajirao Kanwade, and Purva Mange. "AI-driven pharmaceutical manufacturing : Revolutionizing quality control and process optimization." Journal of Statistics and Management Systems 27, no. 2 (2024): 405–16. http://dx.doi.org/10.47974/jsms-1265.
Full textAbstract:
The Integrating AI into pharmaceutical production processes represents a paradigm change for the pharmaceutical sector. This article examines the role of AI in pharmaceutical production, focusing on its potential to improve productivity, cut costs, and guarantee the highest standards of product quality and safety in quality control and process optimization. AI technologies, including machine learning, computer vision, and natural language processing, are increasingly being employed to analyze large volumes of data generated throughout the pharmaceutical manufacturing lifecycle. Risks related to production anomalies can be reduced and regulatory compliance can be ensured with the help of these smart systems’ real-time monitoring, early identification of deviations, and predictive maintenance. AI-driven technologies are revolutionizing quality control processes by allowing for the automated screening of pharmaceutical items at lightning speeds and with pinpoint accuracy. Better product quality and fewer cases of batch rejection are the results of AI systems’ superiority over conventional approaches for detecting tiny faults, ensuring uniformity, and identifying potential contamination. In addition, AI is improving manufacturing processes by analyzing large data sets for trends, tweaking settings, and maximizing output. Pharmaceutical companies save money as a result of streamlined production processes, shorter cycle times, and better resource utilization.
43
Revelou, Panagiota-Kyriaki, Efstathia Tsakali, Anthimia Batrinou, and Irini F. Strati. "Applications of Machine Learning in Food Safety and HACCP Monitoring of Animal-Source Foods." Foods 14, no. 6 (2025): 922. https://doi.org/10.3390/foods14060922.
Full textAbstract:
Integrating advanced computing techniques into food safety management has attracted significant attention recently. Machine learning (ML) algorithms offer innovative solutions for Hazard Analysis Critical Control Point (HACCP) monitoring by providing advanced data analysis capabilities and have proven to be powerful tools for assessing the safety of Animal-Source Foods (ASFs). Studies that link ML with HACCP monitoring in ASFs are limited. The present review provides an overview of ML, feature extraction, and selection algorithms employed for food safety. Several non-destructive techniques are presented, including spectroscopic methods, smartphone-based sensors, paper chromogenic arrays, machine vision, and hyperspectral imaging combined with ML algorithms. Prospects include enhancing predictive models for food safety with the development of hybrid Artificial Intelligence (AI) models and the automation of quality control processes using AI-driven computer vision, which could revolutionize food safety inspections. However, handling conceivable inclinations in AI models is vital to guaranteeing reasonable and exact hazard assessments in an assortment of nourishment generation settings. Moreover, moving forward, the interpretability of ML models will make them more straightforward and dependable. Conclusively, applying ML algorithms allows real-time monitoring and predictive analytics and can significantly reduce the risks associated with ASF consumption.
44
Abbas, Zaigham, Fouzia Amin, and Muhammad Mashhood Khan. "Integration of Artificial Intelligence in Nuclear Command and Control Systems (NC2): Assessing Cold- War Paradigm." Journal of Social Sciences Review 5, no. 1 (2025): 180–88. https://doi.org/10.62843/jssr.v5i1.476.
Full textAbstract:
Artificial Intelligence (AI) is increasingly permeating critical decision-making domains, including nuclear command and control (NC2) systems. This study examines the strategic and ethical dimensions of AI integration into NC2 structures, emphasizing its potential to enhance decision-making speed, accuracy, and resilience while mitigating human cognitive limitations. The research introduces the concept of "Intelligentization Syndrome," a theoretical framework explaining resistance to AI adoption in high-risk environments. By contextualizing historical technological resistance and contemporary AI-related anxieties, the study identifies key psychological and structural barriers to AI symbiosis with NC2 systems. Furthermore, it evaluates different AI integration models—human-in-the-loop, human-on-the-loop, and human-out-of-the-loop—highlighting the advantages of a human-on-the-loop configuration as a balanced approach that leverages AI’s computational strengths while preserving human oversight. The study concludes that a phased and regulated AI integration strategy, complemented by robust ethical frameworks and safety measures, is essential to harness AI’s potential without compromising strategic stability.
45
Adebayo, Abiodun Sunday, Olanrewaju Oluwaseun Ajayi, and Naomi Chukwurah. "AI-Driven Control Systems for Autonomous Vehicles: A Review of Techniques and Future Innovations." International Journal of Future Engineering Innovations 1, no. 1 (2024): 22–28. https://doi.org/10.54660/ijfei.2024.1.1.22-28.
Full textAbstract:
This review paper explores the current state of AI-driven control systems in autonomous vehicles (AVs), focusing on key techniques such as reinforcement learning (RL), Proportional-Integral-Derivative (PID) control, and hybrid approaches that combine traditional and AI-driven methods. While these techniques have enabled significant AV technology advancements, safety, reliability, scalability, and real-time decision-making challenges persist. The paper proposes several future innovations, including advanced RL techniques, integration of machine learning with traditional control systems, Model Predictive Control (MPC) and AI fusion, enhanced sensor fusion, and human-AI collaboration. These innovations address existing limitations and enhance AV control systems' adaptability, decision-making, and overall performance. The review concludes by discussing the broader implications of these innovations for the future of autonomous vehicles. It offers recommendations for future research to advance the field further.
46
Anupama A, Ramya S Yamikar, and Renuka K M. "AI-driven gesture control for industrial robots: A vision-based approach for enhancing human-robot collaboration." World Journal of Advanced Research and Reviews 20, no. 2 (2023): 1498–506. https://doi.org/10.30574/wjarr.2023.20.2.2254.
Full textAbstract:
The integration of artificial intelligence (AI) with vision-based gesture control systems has significantly transformed human-robot interaction in industrial environments. This paper explores recent advancements in AI-driven gesture recognition for industrial robots, focusing on its role in improving human-robot collaboration, efficiency, and safety. AI-powered gesture control enables intuitive and contactless operation, reducing the need for physical controllers and enhancing ergonomics in industrial workflows. The study examines key components of AI-driven gesture recognition, including deep learning models, convolutional neural networks (CNNs), and recurrent neural networks (RNNs) for real-time gesture classification. Additionally, various sensor technologies such as RGB cameras, depth sensors, and LiDAR are analyzed for their effectiveness in detecting and interpreting human gestures with high precision. Real-time data processing techniques, including edge computing and cloud-based AI inference, are discussed to highlight their impact on reducing latency and improving system responsiveness. Despite its potential, AI-based gesture control systems face challenges related to accuracy, adaptability, and security. Variability in gesture execution, environmental conditions, and user differences can affect recognition accuracy. Adaptability concerns arise when deploying these systems across diverse industrial applications, requiring robust training datasets and adaptive learning models. Furthermore, security risks such as unauthorized access and potential cyber threats necessitate strong encryption and authentication measures. To validate the effectiveness of AI-driven gesture control, experimental results are presented, supported by figures, tables, and bar charts. These results demonstrate improvements in operational efficiency, accuracy, and safety compared to conventional control methods such as manual operation and joystick-based interfaces. The findings highlight the transformative potential of AI-powered gesture recognition in industrial robotics and provide insights into future research directions for optimizing human-robot collaboration.
47
FAHMI, C. "Rescue Vision: AI Insight for Emergencies." INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 09, no. 05 (2025): 1–9. https://doi.org/10.55041/ijsrem48934.
Full textAbstract:
Abstract— To improve safety procedures in a variety of locations, such as workplaces, public areas, and industrial sites, the project aims to create a comprehensive visual surveillance system that integrates fire detection with density counts of people. The system uses computer vision, deep learning, and artificial intelligence (AI) to analyze surveillance camera footage in order to identify fire dangers and count people in real time. It also provides dual alarms to increase fire safety and security. Even under difficult circumstances with congestion or obstacles, the system recognizes human figures using convolutional neural networks (CNNs) and sophisticated object detection models like YOLO and Faster R-CNN. In order to differentiate human bodies from other things in the scene, these models are trained. Even in complex surroundings, the counting functionality en- sures that people are precisely monitored across camera frames, avoiding duplicate counts. The number of people in a place, the movement trajectories, and the density estimation are among the real-time outputs produced by the system. In addition, it may identify odd behavior of the crowd, such as congestion or abnormal movements, which can set alarms to help operational monitoring and security personnel. Furthermore, automatic crowd control solutions are made possible by the technology’s seamless integration with the current monitoring infrastructure. Rapid and precise detection is crucial because fire occurrences pose serious risks to people, property, and the environment. The efficacy of traditional fire monitoring systems is limited since they frequently rely on manual observation or simple sensors. A more sophisticated approach is provided by the suggested AI- powered fire monitoring system, which uses computer vision, Internet of Things sensors, and AI algorithms to identify fire outbreaks in real time, forecast their spread, and start automated reactions. These devices have the ability to detect fires, predict their path, and initiate emergency responses, including notifying emergency personnel, directing evacuations, and initiating fire suppression techniques. Artificial intelligence (AI) technologies are highly effective in analyzing visual and sensor data to quickly identify fire dangers in complex contexts such as metropolitan regions, industrial zones, and forests. Faster reaction times are ensured by the system’s integration with crisis response protocols, which may prevent harm and save lives. The technology offers a strong tool to improve safety in both public and private areas by merging human density monitoring with fire detection. All things considered, our AI- powered surveillance system provides reliable real-time fire detection and crowd monitoring, improving the effectiveness of emergency response, security control, and general safety in a variety of settings. Keywords: Dual Alarms, Congestion Detection, Automated Crowd Control, Fire Spread Prediction, Crisis Response Pro- tocol, Emergency Evacuation
48
Zhong, Bingzhuo, Hongpeng Cao, Majid Zamani, and Marco Caccamo. "Towards Safe AI: Sandboxing DNNs-Based Controllers in Stochastic Games." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 12 (2023): 15340–49. http://dx.doi.org/10.1609/aaai.v37i12.26789.
Full textAbstract:
Nowadays, AI-based techniques, such as deep neural networks (DNNs), are widely deployed in autonomous systems for complex mission requirements (e.g., motion planning in robotics). However, DNNs-based controllers are typically very complex, and it is very hard to formally verify their correctness, potentially causing severe risks for safety-critical autonomous systems. In this paper, we propose a construction scheme for a so-called Safe-visor architecture to sandbox DNNs-based controllers. Particularly, we consider the construction under a stochastic game framework to provide a system-level safety guarantee which is robust to noises and disturbances. A supervisor is built to check the control inputs provided by a DNNs-based controller and decide whether to accept them. Meanwhile, a safety advisor is running in parallel to provide fallback control inputs in case the DNN-based controller is rejected. We demonstrate the proposed approaches on a quadrotor employing an unverified DNNs-based controller.
49
Hutchinson, Pamela J. S., Charlotte V. Eberlein, and Dennis J. Tonks. "Broadleaf Weed Control and Potato Crop Safety with Postemergence Rimsulfuron, Metribuzin, and Adjuvant Combinations." Weed Technology 18, no. 3 (2004): 750–56. http://dx.doi.org/10.1614/wt-03-172r1.
Full textAbstract:
The effects of postemergence rimsulfuron, metribuzin, and adjuvant combinations on potato crop safety and weed control were evaluated in field studies conducted at the University of Idaho Aberdeen Research and Extension Center in 1999 and 2000. Rimsulfuron at 26 g ai/ha plus metribuzin at 0, 140, or 280 g ai/ha was combined with nonionic surfactant (NIS), crop oil concentrate (COC), or methylated seed oil (MSO) in a 3 by 3 factorial with two controls. Under cool, cloudy conditions in 1999, initial ‘Russet Burbank’ potato injury was greater when metribuzin was included in the tank mixture than when rimsulfuron was applied alone, regardless of adjuvant. Under warmer conditions in 2000, however, adding MSO or COC to the tank mixture caused more injury than adding NIS. Rimsulfuron did not provide acceptable season-long common lambsquarters control in 1999 (76%) or in 2000 (88%), regardless of adjuvant. Rimsulfuron combined with metribuzin at 140 or 280 g/ha provided ≥95% common lambsquarters control both years, regardless of adjuvant. Among adjuvants, using MSO (1999 and 2000) or COC (2000) in the spray mixture improved common lambsquarters control compared with using NIS. Tuber yield and quality were not reduced as a result of metribuzin rate or adjuvant treatments either year compared with the weed-free control.
50
Adama Gaye, Barnabas Narteh Paflo, and Derrick Atuobi Oware. "Assessing the reliability of AI-driven predictive models in food safety risk management." Computer Science & IT Research Journal 6, no. 2 (2025): 49–58. https://doi.org/10.51594/csitrj.v6i2.1832.
Full textAbstract:
Sustaining food safety in a world that has undergone globalization with complex supply chains makes it very challenging. Conventional risk management methodologies are sometimes inadequate in addressing emerging risks, making the use of AI and predictive modeling invaluable tools in enhancing food safety evaluation and decision making. AI-based models have the prospects of identifying contamination risks at an early stage, enhancing the optimization of hazardous control measures, and increasing the effectiveness of compliance monitoring. Nevertheless, the reliability of their predictions is still questionable due to factors such as data integrity, model interpretability, and regulatory compliance that influence their applicability in practice. Despite AI's potential, challenges such as inconsistent data sources, varying regulatory standards, and adaptability across diverse food production environments limit its efficacy. Addressing these issues is crucial for AI-driven models to be fully integrated into food safety management systems. This paper provides a critical review of the current AI-based predictive models for food safety risk management synthesizing insights from existing literature, industry studies and regulatory reports. Through an evaluation of the strengths, drawbacks and limitations of these models, this research emphasizes the importance of developing standardized validation frameworks and improved strategies for integrating data across models. Overall, this research enriches the current discourse regarding the use of AI in food safety and offers key recommendations for improving model reliability and performance in protecting consumers and safeguarding public health Keywords: Artificial Intelligence (AI), Predictive Modeling, Food Safety Risk Management, Data-Driven Decision Making.