The Role of Artificial Intelligence in Managing Emergencies and Crises within Smart Cities

Haghshenas, Sami Shaffiee; Guido, Giuseppe; Haghshenas, Sina Shaffiee; Astarita, Vittorio

doi:10.1109/ict-dm58371.2023.10286925

Cited by 5 publications

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

A fuzzy model for generalized transportation problems in China

Aljanabi,

Borna,

Ghanbari

2024

Concurrency and Computation

View full text Add to dashboard Cite

SummaryThis study underscores the growing significance of multimodal transportation within the cargo sector and its consequential environmental impacts. We present a novel mathematical model for operation scheduling, incorporating variables such as resource availability, customer service benchmarks, and environmental considerations. Our objective is to mitigate transportation expenses and reduce delivery delays. The proposed approach advocates LU decomposition with a pivot strategy for rapid model resolution, adherence to convergence criteria, optimization of cost strategies, and efficient resource utilization. Leveraging the adaptive neural fuzzy inference system (ANFIS) and genetic algorithm (GA), our methodology facilitates learning from past decisions to enhance solutions, aligning supply, and demand efficiently. We evaluate financial and environmental implications across four scenarios, offering insights into the economic and environmental advantages of various transportation modes—trains, ships, airplanes—compared to truck transportation, with a specific focus on CO2 emission impacts. Implementing the ANFIS+GA model in multimodal scenarios yield impressive results: minimal MAPE transportation cost of 0.17%, R2 transportation cost of 0.996, MAPE CO2 emissions of 0.13%, and R2 CO2 emissions of 0.996. By identifying cost‐efficient routes and optimizing resource allocations, our approach enables informed decisions regarding vehicle distribution, supplier selection, and contract negotiations. Additionally, we use LU decomposition to establish the supplier risk threshold, crucial for comparing emission trade variances. Multimodal scenarios typically yield lower emissions, favoring buying emission allowances low and selling them high. Notably, the risk threshold affects low‐emission provider utilization, impacting transportation emissions. With a risk threshold of 0.12 and an emission price of 1.2, our ANFIS+GA‐based multimodal approach achieves a significant −20% deviation in CO2 emissions.

show abstract

A fuzzy model for generalized transportation problems in China

Aljanabi,

Borna,

Ghanbari

2024

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

Planned and Implemented Actions by Exercises

Russo,

Rindone

2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

On a global scale, natural and man-made disasters cause significant losses. For this reason, disaster risk reduction is a priority. This paper focuses on the exposure risk component during the occurrence and evacuation planning. There is a gap between the planned actions and their implementation during real emergency conditions. From the proposed reviewed literature different lacks emerge, including the evaluation of the risk reduction produced by each exercise or training actions. To build a bridge above this gap, it is necessary to design and experiment with training and exercises for putting into practice the planned evacuation procedures. A method is proposed to evaluate the exposure reduction by means of these actions. The literature distinguishes two main classes of actions: discussion-based, aimed at reviewing evacuation plans and procedures; and operation-based, aimed at simulating real experimentations with decision-making and people involved in a potential emergency situation. The expected outcome is to increase awareness of managers and users about the evacuation procedures for pursuing the final goal of exposure and therefore risk reduction. With increasing complexity and capabilities, exercises and training contribute to increasing the effectiveness of the planned actions. The paper is useful for risk managers and public decision-takers involved in the evacuation planning process to increase preparedness before an emergency event.

show abstract

A Framework for LLM-Assisted Smart Policing System

Sarzaeim,

Mahmoud,

Azim

2024

IEEE Access

View full text Add to dashboard Cite

In the face of rapidly increasing crime rates, the evolving complexity of crime data processing, and public safety challenges, the need for more advanced policing solutions has increased leading to the emergence of smart policing systems and predictive policing techniques. This urgency and shift toward smart policing incorporates artificial intelligence (AI), with a specific focus on machine learning (ML) as an essential tool for data analysis, pattern recognition, and proactive crime forecasting. Among these, the flexibility and power of AI techniques including large language models (LLMs), as a subset of generative AI, have increased the interest in applying them in real-world applications, such as financial, medical, legal, and agricultural applications. However, the abilities and possibilities of adopting LLMs in applications including crime prediction remain unexplored. This paper focuses on bridging this gap by developing a framework based on the transformative potential of BART, GPT-3, and GPT-4, three state-of-the-art LLMs, in the domain of smart policing, specifically, crime prediction. As a prototype, diverse methods such as zeroshot prompting, few-shot prompting, and fine-tuning are used to comprehensively assess the performance of these models in crime prediction based on state-of-the-art datasets from two major cities: San Francisco and Los Angeles. The main objective is to illuminate the adaptability of LLMs and their capacity to revolutionize crime analysis practices. Additionally, a comparative analysis of the aforementioned methods on the GPT series model and BART with ML techniques is provided which shows that the GPT models are more suitable than the traditional ML models for crime classification in most experimental scenarios.INDEX TERMS Crime prediction, fine-tuning, few-shot prompting, Large language models, LLM, zeroshot prompting.

show abstract

The Role of Artificial Intelligence in Managing Emergencies and Crises within Smart Cities

Cited by 5 publications

References 50 publications

A fuzzy model for generalized transportation problems in China

A fuzzy model for generalized transportation problems in China

Planned and Implemented Actions by Exercises

A Framework for LLM-Assisted Smart Policing System

Contact Info

Product

Resources

About