Artificial Intelligence Review最新文献

Recommender systems are software mechanisms whose usage is to offer suggestions for different types of entities like products, services, or contacts that could be useful or interesting for a specific user. Other ways have been explored in the field to enhance the power of these systems by integrating the context as an additional attribute. This inclusion tries to extract the user preferences more accurately taking into account multiple components such as temporal, spatial, or social ones. Notwithstanding the magnitude of context-awareness in this area, the research community is in agreement with the lack of framework for context information and how to integrate it into recommender systems. Under this premise, this paper focuses on a comprehensive systematic literature review of the state-of-the-art recommendation techniques and their characteristics to benefit from contextual information. The following survey presents the following contributions as outcomes of our study: (i) determine a framework where multiple aspects are taken into account to have a clear definition of context representation, (ii) the techniques used to incorporate context, and (iii) the evaluation of these methods in terms of reproducibility and effectiveness. Our review also covers some crucial topics about context integration, classification of the contexts, application domains, and evaluation of the used datasets, metrics, and code implementations, where we observed clear shiftings in algorithmic and evaluation trends towards Neural Network approaches and ranking metrics, respectively. Just as importantly, future research opportunities and directions are exposed as final closure, standing out the exploitation of various data sources and the scalability and customization of existing solutions.

Federated learning is a multiple device collaboration setup designed to solve machine learning problems under framework for aggregation and knowledge transfer in distributed local data. This distributed model ensures the privacy of data at each local node. Owing to its relevance, there has been extensive research activities and outcomes in federated learning with expanded applicability to different areas by the research community. As such, there is a vast research archive made available by the community with research work and articles related to the various aspects of federated learning such as applications, challenges, privacy, functionalities, and design. With respect to the function and design of federated learning, client selection, aggregation, knowledge transfer, management of distributed data (Non-IID), Incentive of data and communication cost are of paramount importance. Any effective design of federated learning requires these aspects to be well considered. There are numerous survey articles found among the available literature that focus on its application and challenges, opportunities, data privacy and protection, as well as on federated learning on internet of things, federated learning on edge computing, etc. In this paper, a review of the available literature on the various elements of design and functionalities in federated learning has been carried out with an aim to lay emphasis on the important challenges and research opportunities. More specifically, this work has endeavored to understand and summarize the various functional methods available, along with their techniques and goals. Additionally, it has strived to get a bird’s eye view of how various functions and designs of federated learning have been used in applications, and how it has helped uncover challenges and promising research directions for the future.

Meta-heuristic algorithms, particularly those based on swarm intelligence, are highly effective for solving black-box optimization problems. However, maintaining a balance between exploration and exploitation within these algorithms remains a significant challenge. This paper introduces a useful algorithm, called Escape or Escape Algorithm (ESC), inspired by crowd evacuation behavior, to solve real-world cases and benchmark problems. The ESC algorithm simulates the behavior of crowds during the evacuation, where the population is divided into calm, herding, and panic groups during the exploration phase, reflecting different levels of decision-making and emotional states. Calm individuals guide the crowd toward safety, herding individuals imitate others in less secure areas, and panic individuals make volatile decisions in the most dangerous zones. As the algorithm transitions into the exploitation phase, the population converges toward optimal solutions, akin to finding the safest exit. The effectiveness of the ESC algorithm is validated on two adjustable problem size test suites, CEC 2017 and CEC 2022. ESC ranked first in the 10-dimensional, 30-dimensional tests of CEC 2017, and the 10-dimensional and 20-dimensional tests of CEC 2022, and second in the 50-dimensional and 100-dimensional tests of CEC 2017. Additionally, ESC performed exceptionally well, ranking first in the engineering problems of pressure vessel design, tension/compression spring design, and rolling element bearing design, as well as in two 3D UAV path planning problems, demonstrating its efficiency in solving real-world complex problems, particularly complex problems like 3D UAV path planning. Compared with 12 other high-performance, classical, and advanced algorithms, ESC exhibited superior performance in complex optimization problems. The source codes of ESC algorithm will be shared at https://aliasgharheidari.com/ESC.html and other websites.

The Bald Eagle Search (BES) algorithm is an innovative population-based method inspired by the intelligent hunting behavior of bald eagles. While BES shows promise, it faces challenges such as susceptibility to local optima and imbalances between exploration and exploitation phases. To address these limitations, this paper introduces the Multi-Strategy Boosted Bald Eagle Search (MBBES) algorithm. MBBES enhances the original BES by incorporating an adaptive parameter, two distinct mutation strategies, and replacing the swoop stage with a fall stage. We rigorously evaluate MBBES against classic and improved algorithms using the CEC2014 and CEC2017 test sets. The experimental results demonstrate that MBBES significantly improves the ability to escape local optima and achieves superior convergence accuracy. Moreover, MBBES ranks first according to the Friedman test, outperforming its counterparts in solving five practical engineering problems and three MLP classification problems, underscoring its effectiveness in real-world optimization scenarios. These findings indicate that MBBES not only surpasses BES but also sets a new benchmark in optimization performance.

The right methods for effective financing of electric vehicle charging infrastructure investments should be identified. However, in the literature, there is no consensus on which funding source would be right for these projects. There is a need for a new study to recommend the most appropriate financing strategy for these projects. Accordingly, the purpose of this study is to identify innovative solutions for financing electric vehicle charging infrastructure investments. A novel fuzzy decision-making model is introduced to reach this objective. Firstly, the weights of experts are calculated using dimension reduction. Secondly, Spherical fuzzy decision matrix is obtained. Thirdly, the criteria in charging infrastructure for electric vehicles are weighted using Spherical fuzzy criteria importance through intercriteria correlation (CRITIC). Fourthly, innovative solutions for financing electric vehicles charging infrastructure are ranked via Spherical fuzzy ranking technique by geometric mean of similarity ratio to optimal solution (RATGOS). The main contribution of this study is that effective strategies can be identified for financing electric vehicle charging infrastructure investments by establishing a novel decision-making model. Most of the existing models in the literature could not consider the weights of the experts. This condition is criticized by different scholar because these experts can have different qualifications. To satisfy this problem, in this study, dimension reduction algorithm with machine learning is taken into consideration to compute thee weights of the experts. The findings demonstrate that the most effective criterion in the innovative financial solution for the charging infrastructure of electric vehicles is determined as “potential income”. According to the ranking results, it is also defined that the most sustainable solution among the innovative strategies for financing the charging infrastructure of electric vehicles is “blockchain technology”.

This work tackles the challenge of ranking-based machine reading comprehension (MRC), where a question answering (QA) system generates a ranked list of relevant answers for each question instead of simply extracting a single answer. We highlight the limitations of traditional learning methods in this setting, particularly under limited training data. To address these issues, we propose a novel ranking-inspired learning method that focuses on ranking multiple answer spans instead of single answer extraction. This method leverages lexical overlap as weak supervision to guide the ranking process. We evaluate our approach on the Qur’an Reading Comprehension Dataset (QRCD), a low-resource Arabic dataset over the Holy Qur’an. We employ transfer learning with external resources to fine-tune various transformer-based models, mitigating the low-resource challenge. Experimental results demonstrate that our proposed method significantly outperforms standard mechanisms across different models. Furthermore, we show its better alignment with the ranking-based MRC task and the effectiveness of external resources for this low-resource dataset. Our best performing model achieves a state-of-the-art partial Reciprocal Rank (pRR) score of 63.82%, surpassing the previous best-known score of 58.60%. To foster further research, we release code [GitHub repository:github.com/mohammed-elkomy/weakly-supervised-mrc], trained models, and detailed experiments to the community.

In the realm of agribusiness, transformative shifts are underway, propelled by the growing demands and expanding scales of grain production. This evolution calls for a critical reevaluation of the existing paradigms in coffee production and marketing paradigms, with a specific focus on integrating Artificial Intelligence (AI). This work aims to review, synthesize, and summarize the available data regarding how Machine Learning (ML) has been used to detect and classify characteristics in coffee beans and leaves. For this purpose, a comprehensive literature review of the most significant research contributions describing the application of AI for advanced classification techniques in coffee agriculture has been carried out. Our analysis suggests that implementing AI technologies allows the classification of coffee, encompassing various attributes such as maturity, roast intensity, disease identification, flavor profiles, and overall quality. More largely, this technological advancement holds the potential to revolutionize coffee farming by providing producers and agricultural specialists with sophisticated tools to enhance production efficiency, minimize costs, and improve the accuracy and confidence of their decision-making processes. The motivation for the literature review is to address the increasing global demands and evolving scales of grain production, particularly in coffee farming, by critically reevaluating existing paradigms and integrating AI techniques. This review aims to synthesize and summarize how ML has been utilized to detect and classify various characteristics of coffee beans and leaves, thereby highlighting the potential of AI to revolutionize coffee farming by enhancing production efficiency, minimizing costs, and improving decision-making accuracy. This article presents the latest studies in ML in the coffee area, observes the methodology used, and allows researchers to develop new solutions that cover gaps in the literature, open problems, challenges, and future trends, bringing a real contribution to the scientific field. Finally, this article gathers and presents the databases used in many studies, which may be useful for future ML projects.

This study addresses the problem of coordination in cooperative multi-robot systems performing complex tasks. An analysis of cooperative behavior in mobile multi-robot systems in terms of task execution accuracy by heterogeneous robots is carried out. In addition, we evaluate the capacity and compatibility of tasks assigned to robots to optimize task execution without using direct communication with the robots or a central decision-making unit. A model for task selection in heterogeneous distributed multi-robot systems is proposed. It is based on two processes: the first decomposes complex tasks into elementary tasks, and the second assigns elementary tasks to mobile robots for real-time execution. The distribution of elementary tasks is NP-hard, which leads us to recommend approximate solutions. A fuzzy system called Fuzzy Decision Making in Task Selection is proposed, which uses fuzzy logic to solve this problem. This system allows robots to choose to perform any task in the future. An approach is presented that uses two cascading fuzzy systems. The first calculates the utility of the robot and then activates the second fuzzy system to calculate the utility of the task. By using the output of the fuzzy decision system in our model, each robot will be able to decide for itself which tasks to perform. The results of a simulation of mobile robots transporting goods demonstrate the effectiveness of this fuzzy decision-maker.

The current study investigates the robustness of deep learning models for accurate medical diagnosis systems with a specific focus on their ability to maintain performance in the presence of adversarial or noisy inputs. We examine factors that may influence model reliability, including model complexity, training data quality, and hyperparameters; we also examine security concerns related to adversarial attacks that aim to deceive models along with privacy attacks that seek to extract sensitive information. Researchers have discussed various defenses to these attacks to enhance model robustness, such as adversarial training and input preprocessing, along with mechanisms like data augmentation and uncertainty estimation. Tools and packages that extend the reliability features of deep learning frameworks such as TensorFlow and PyTorch are also being explored and evaluated. Existing evaluation metrics for robustness are additionally being discussed and evaluated. This paper concludes by discussing limitations in the existing literature and possible future research directions to continue enhancing the status of this research topic, particularly in the medical domain, with the aim of ensuring that AI systems are trustworthy, reliable, and stable.

Proposing an efficient meta-heuristic to improve the inputs of a trainer in deep neural network (DNNs) is significant. According to the Kaluza’s theory, there exists an extra dimension in the universe. This paper proposes a novel algorithm, extra dimension algorithm (EDA), which is simulated based on this theory. The proposed algorithm utilizes the extra dimension to evaluate the current region of solutions and determine the best direction to follow for the next step of the process. Finally, EDA is used to improve inputs of DNN in the process of solving optimization test problems. The same DNN with and without EDA is used to solve extensive optimization problems, including energy-related tasks. The efficiency of EDA in DNN is assessed by solving some test problems in references, the feasibility and efficiency of solutions, within a suitable number of iterations are demonstrated according to the results. The contributions of this paper are as follows: (1) Introduction of the EDA based on Kaluza’s theory. (2) Application of EDA to enhance the performance of DNNs. (3) Demonstration of EDA’s effectiveness in solving complex optimization problems. (4) Comprehensive evaluation of EDA’s impact on energy optimization problems and other test cases. (5) EDA achieved an average improvement of 15% in optimization accuracy and reduced convergence time compared to the best-performing alternatives.