Article
Computer Science, Information Systems
Ranjita Das, Dipanwita Debnath, Partha Pakray, Naga Chaitanya Kumar
Summary: This paper proposes a Binary Gray Wolf Optimization (BGWO)-based text summarization approach that tackles the sentence selection problem and generates an optimal summary using the BGWO algorithm.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Yi Wang, Tao Li, Xiaojie Liu, Jian Yao
Summary: This study develops an improved adaptive clonal selection algorithm with multiple differential evolution strategies. The algorithm introduces an adaptive mutation strategy pool, an adaptive population resizing method, and detection methods for premature convergence and stagnation. Experimental results demonstrate that the proposed method outperforms state-of-the-art clonal selection algorithms and differential evolution algorithms.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Information Systems
Zuling Wang, Ze Chen, Zidong Wang, Jing Wei, Xin Chen, Qi Li, Yujun Zheng, Weiguo Sheng
Summary: This paper proposes an adaptive memetic differential evolution algorithm with multi-niche sampling and neighborhood crossover strategies for global optimization. Experimental results show that the algorithm achieves superior performance on CEC'2015 benchmark functions and confirms the significance of the devised strategies.
INFORMATION SCIENCES
(2022)
Article
Multidisciplinary Sciences
Wu Su, Jin Jiang, Kaihui Huang
Summary: The crucial aspect of extractive document summarization lies in understanding the interrelations between sentences. A model utilizing heterogeneous graph neural networks and topic models is proposed to capture the semantic connections and topic-specific information in documents. Experimental evidence demonstrates the superior performance of the proposed model compared to existing methods, even without pre-trained language models.
Article
Operations Research & Management Science
Richard L. Church, Zvi Drezner, Pawel Kalczynski
Summary: This paper proposes three models for locating multiple facilities in the plane. The models consider the demand points and the available sources of raw material for the facilities. The optimal locations are determined based on minimizing total transport cost. A special algorithm is designed to solve these models, which performed better compared to non-linear solvers in most instances.
ANNALS OF OPERATIONS RESEARCH
(2023)
Article
Automation & Control Systems
Shailendra S. Aote, Anjusha Pimpalshende, Archana Potnurwar, Shantanu Lohi
Summary: Automatic text summarization is important for text retrieval. This study proposes a hybrid approach using swarm intelligence and evolutionary algorithm (BPSO-IGA) to achieve better results in Hindi text summarization. The proposed method combines multiple features and outperforms other well-known techniques in terms of precision, recall, f-measure, cohesion, and non-redundancy.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Environmental Sciences
Peipei Zhang, Mingzhen Yin, Xinjun Zhang, Qitong Wang, Ruihong Wang, Huajun Yin
Summary: This study investigated the effects of nitrogen deposition on phosphorus limitation in alpine coniferous plantations. The results showed that nitrogen addition exacerbated phosphorus deficiency in both plantations, but the plant strategies in addressing the deficiency differed depending on soil nitrogen availability. Alpine coniferous plantations with high soil nitrogen availability adopted a synergistic strategy of aboveground phosphorus conservation and belowground phosphorus mining, while plantations with low soil nitrogen availability showed a decoupling relationship between aboveground phosphorus conservation and belowground phosphorus acquisition.
SCIENCE OF THE TOTAL ENVIRONMENT
(2022)
Article
Management
Cristian Duran-Mateluna, Zacharie Ales, Sourour Elloumi
Summary: The p-median problem is a classic discrete location problem that focuses on minimizing the sum of distances to the nearest open site for a given number of sites to be opened. A Benders decomposition algorithm is used to efficiently solve the problem, and it is shown that the Benders cuts can be separated in linear time. The algorithm outperforms previous methods by a significant margin, allowing for the exact solution of large TSP and BIRCH instances.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2023)
Article
Computer Science, Interdisciplinary Applications
Harsha Gwalani, Chetan Tiwari, Armin R. Mikler
Summary: The study evaluates the solutions to the p-median problem, investigates the impact of destination location spatial distribution, and the number of sources and destinations on algorithm performance. The results show that exchange algorithms perform well in terms of solution quality and stability.
COMPUTERS ENVIRONMENT AND URBAN SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Shijie Xiong, Wenyin Gong, Kai Wang
Summary: This paper proposes an enhanced adaptive neighborhood-based speciation differential evolution (EANSDE) algorithm to solve multimodal optimization problems (MMOPs). The algorithm adaptively controls parameters to alleviate the fine-tuning process by users. It introduces an external archive to store inferior solutions and merges them with the current population in the following search. Additionally, a crowding relieving mechanism is proposed to remove extremely similar individuals from the population. Experimental results demonstrate the superiority of EANSDE on the 20 benchmark MMOPs in CEC-2013.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Xu Chen, Anning Shen
Summary: In this study, an improved differential evolution algorithm called SDEGCM is proposed to tackle large-scale CHPED problems. The algorithm incorporates Gaussian-Cauchy mutation, parameter self-adaptation, and constraint repair techniques, demonstrating advantages in solution accuracy and stability compared to existing methods.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Operations Research & Management Science
Huseyin Guden
Summary: The study shows that some easy classical problems become NP-hard when the linearity of the cost functions is lost, and transportation mode and flow dependent cost structures affect the p-hub median problem.
ANNALS OF OPERATIONS RESEARCH
(2021)
Article
Computer Science, Interdisciplinary Applications
Zvi Drezner, Jack Brimberg, Anita Schoebel
Summary: This paper proposes a novel method for solving the planar ������-median problem. By identifying a sub-class of the distributed ������-median problem, a continuous trajectory of local optima can be constructed as a parameter ������ decreases from 1 to 0. The trajectory converges to a local optimum of the planar ������-median problem as ������ approaches 0. Computational results show promising outcomes, with the proposed trajectory method finding better solutions in a fraction of the time taken by a conventional multi-start local search for larger instances. The methodology can be extended to continuous ������-median problems in higher dimensional spaces.
COMPUTERS & OPERATIONS RESEARCH
(2023)
Article
Computer Science, Interdisciplinary Applications
Davide Croci, Ola Jabali, Federico Malucelli
Summary: This study focuses on a variant of the p-median problem that considers two objectives: minimizing average travel distance and balancing the number of customers per facility. A bi-objective mixed-integer linear program is formulated, and a weighted sum method is used to generate a set of representative Pareto optimal solutions. A primal-dual algorithm is developed to handle large-scale instances, and a tailored minimum cost flow problem solution is utilized. The proposed formulation and algorithm are evaluated on test instances and applied to real-world districting for last-mile delivery, showing effectiveness and quality of solutions compared to alternative measures of inequity.
COMPUTERS & OPERATIONS RESEARCH
(2023)
Article
Computer Science, Artificial Intelligence
Lianzheng Cheng, Jia-Xi Zhou, Xing Hu, Ali Wagdy Mohamed, Yun Liu
Summary: Differential evolution (DE) is an efficient algorithm for global optimization problems. This paper introduces a novel crossover rate (CR) generation scheme called fcr, adjusts control parameters using unused bimodal settings based on individual evolution status, and updates the mean value of crossover rate and scale factor using L1 norm distance. These modifications are integrated with JADE mutation strategy to propose JADEfcr and LJADEfcr. Experimental results show that JADEfcr outperforms twelve state-of-the-art algorithms in terms of robustness, stability and solution quality, while LJADEfcr is statistically competitive with nine powerful algorithms in the competition.
COMPLEX & INTELLIGENT SYSTEMS
(2023)
Article
Computer Science, Interdisciplinary Applications
Rasim M. Alguliyev, Ramiz M. Aliguliyev, Lyudmila Sukhostat
Summary: This article introduces a new parallel batch clustering algorithm based on the k-means algorithm, which reduces computation complexity by splitting the dataset into multiple partitions and proposes a method to determine the optimal batch size. Experimental results show the practical applicability of this method for handling Big Data.
COMPUTERS & INDUSTRIAL ENGINEERING
(2021)
Article
Computer Science, Artificial Intelligence
Rasim Alguliyev, Yadigar Imamverdiyev, Lyudmila Sukhostat
Summary: The urgency of ensuring the security of cyber-physical systems lies in their correct functioning, which has a significant impact on various industrial sectors. This paper proposes a deep hybrid model based on three parallel neural architectures and experiments show its superiority over recent works using machine learning techniques.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Rasim Alguliyev, Yadigar Imamverdiyev, Lyudmila Sukhostat, Ruslan Bayramov
Summary: This paper proposes a deep learning based model for identifying and diagnosing plant leaf diseases, which provides a high-accuracy solution. Experimental results demonstrate that the proposed model excels in diagnosing plant diseases, and the addition of gated recurrent unit neural network further improves accuracy.
Article
Computer Science, Information Systems
Rasim M. Alguliyev, Fargana J. Abdullayeva, Sabira S. Ojagverdiyeva
Summary: This research presents a model called ChildNet for filtering harmful image content. The model uses pixels of digital images as the data source and employs a multi-layer deep neural network to study the color patterns of undesirable image pixels. By reducing the size of the filters, the accuracy of pixel recognition is improved. The proposed method achieves superior results compared to classical CNN when tested on real datasets.
JOURNAL OF INFORMATION SECURITY AND APPLICATIONS
(2022)
Article
Environmental Sciences
Rasim Alguliyev, Yadigar Imamverdiyev, Lyudmila Sukhostat
Summary: This study proposes a proxy-model for reservoir history matching using extreme learning machines, which calculates the mismatch between observed and simulated data. The experimental results demonstrate the high accuracy of the model in reservoir testing and its superiority over other proxy-models.
ENVIRONMENTAL MODELING & ASSESSMENT
(2022)
Article
Energy & Fuels
Rasim Alguliyev, Yadigar Imamverdiyev, Lyudmila Sukhostat
Summary: This paper proposes a machine learning method for automatically detecting and identifying facies from digital images of the oil well core. The proposed HOG + LBP + DenseNet model combined with a random forest shows better performance in facies recognition from core photographs.
PETROLEUM SCIENCE AND TECHNOLOGY
(2023)
Article
Computer Science, Cybernetics
Rasim M. Alguliyev, Ramiz M. Aliguliyev, Rashid G. Alakbarov
Summary: With the increasing number of mobile devices connected to the Internet, network load has been on the rise, leading to delays in delivering cloud resources to mobile users. Edge computing technologies have been widely used to eliminate these delays by allocating cloud resources to nearby cloudlets. This article proposes a clustering-based model for optimal allocation of cloud resources among cloudlets. The proposed model takes into account user activity, resource usage frequency, physical distance, and storage capacity of cloudlets for efficient allocation. The model is formalized as a constrained k-means method and an algorithm is developed and evaluated using the MATLAB 2022a toolkit, showing promising results.
Article
Computer Science, Artificial Intelligence
Adil M. Bagirov, Ramiz M. Aliguliyev, Nargiz Sultanova
Summary: Finding compact and well-separated clusters in data sets is a challenging task. Traditional clustering algorithms often only consider minimizing clustering objective functions without considering the compactness and separability of clusters. Therefore, this paper proposes a new clustering optimization model with the clustering function as the objective and introduces the silhouette coefficients as constraints to estimate the true number of clusters. Experimental results demonstrate that compared to other algorithms, this method can obtain more compact and well-separated clusters.
PATTERN RECOGNITION
(2023)
Article
Mathematical & Computational Biology
Rasim Alguliyev, Ramiz Aliguliyev, Farhad Yusifov
Summary: The article explores graph-based modelling of the COVID-19 infection spread, analyzing factors like social distance, duration of contact, and demographic characteristics. By visualizing the spread process from the first confirmed case to human transmission, the graph model allows for considering multiple factors and conducting numerical experiments effectively. This approach enables a reverse analysis of the spread, identifying undetected cases based on social distance and contact duration, reducing uncertainty in the process.
INFECTIOUS DISEASE MODELLING
(2021)
Article
Computer Science, Information Systems
Rasim M. Alguliyev, Yadigar N. Imamverdiyev, Rasim Sh. Mahmudov, Ramiz M. Aliguliyev
Summary: The article examines the essence and different approaches to national security, interpreting its objectives and provision methods. It classifies different areas and vital interests that are the objects of national security, as well as different components of national security such as socio-political, military, information, food, energy, education system, scientific and technological, health system, transport system, environmental, mass media, and cultural-moral security. Additionally, it describes the development of ICT and the growing role of the information society in connection with information security, as well as the relationship between information security and other components of national security.
INFORMATION SECURITY JOURNAL
(2021)
Article
Multidisciplinary Sciences
Rasim Alguliyev, Yadigar Imamverdiyev, Lyudmila Sukhostat
SN APPLIED SCIENCES
(2020)
Article
Computer Science, Artificial Intelligence
Hao Yang, Min Wang, Zhengfei Yu, Hang Zhang, Jinshen Jiang, Yun Zhou
Summary: In this paper, a novel method called CSTTA is proposed for test time adaptation (TTA), which utilizes confidence-based optimization and sample reweighting to better utilize sample information. Extensive experiments demonstrate the effectiveness of the proposed method.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Jin Liu, Ju-Sheng Mi, Dong-Yun Niu
Summary: This article focuses on a novel method for generating a canonical basis for decision implications based on object-induced operators (OE operators). The logic of decision implication based on OE operators is described, and a method for obtaining the canonical basis for decision implications is given. The completeness, nonredundancy, and optimality of the canonical basis are proven. Additionally, a method for generating true premises based on OE operators is proposed.
KNOWLEDGE-BASED SYSTEMS
(2024)
Review
Computer Science, Artificial Intelligence
Kun Bu, Yuanchao Liu, Xiaolong Ju
Summary: This paper discusses the importance of sentiment analysis and pre-trained models in natural language processing, and explores the application of prompt learning. The research shows that prompt learning is more suitable for sentiment analysis tasks and can achieve good performance.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Xiangjun Cai, Dagang Li
Summary: This paper presents a new decomposition mechanism based on learned decomposition mapping. By using a neural network to learn the relationship between original time series and decomposed results, the repetitive computation overhead during rolling decomposition is relieved. Additionally, extended mapping and partial decomposition methods are proposed to alleviate boundary effects on prediction performance. Comparative studies demonstrate that the proposed method outperforms existing RDEMs in terms of operation speed and prediction accuracy.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Xu Wu, Yang Liu, Jie Tian, Yuanpeng Li
Summary: This paper proposes a blockchain-based privacy-preserving trust management architecture, which adopts federated learning to train task-specific trust models and utilizes differential privacy to protect device privacy. In addition, a game theory-based incentive mechanism and a parallel consensus protocol are proposed to improve the accuracy of trust computing and the efficiency of consensus.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Zaiyang Yu, Prayag Tiwari, Luyang Hou, Lusi Li, Weijun Li, Limin Jiang, Xin Ning
Summary: This study introduces a 3D view-based approach that effectively handles occlusions and leverages the geometric information of 3D objects. The proposed method achieves state-of-the-art results on occluded ReID tasks and exhibits competitive performance on holistic ReID tasks.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Yongliang Shi, Runyi Yang, Zirui Wu, Pengfei Li, Caiyun Liu, Hao Zhao, Guyue Zhou
Summary: Neural implicit representations have gained attention due to their expressive, continuous, and compact properties. However, there is still a lack of research on city-scale continual implicit dense mapping based on sparse LiDAR input. In this study, a city-scale continual neural mapping system with a panoptic representation is developed, incorporating environment-level and instance-level modeling. A tailored three-layer sampling strategy and category-specific prior are proposed to address the challenges of representing geometric information in city-scale space and achieving high fidelity mapping of instances under incomplete observation.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Ruihan Hu, Zhi-Ri Tang, Rui Yang, Zhongjie Wang
Summary: Mesh data is crucial for 3D computer vision applications worldwide, but traditional deep learning frameworks have struggled with handling meshes. This paper proposes MDSSN, a simple mesh computation framework that models triangle meshes and represents their shape using face-based and edge-based Riemannian graphs. The framework incorporates end-to-end operators inspired by traditional deep learning frameworks, and includes dedicated modules for addressing challenges in mesh classification and segmentation tasks. Experimental results demonstrate that MDSSN outperforms other state-of-the-art approaches.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Buliao Huang, Yunhui Zhu, Muhammad Usman, Huanhuan Chen
Summary: This paper proposes a novel semi-supervised conditional normalizing flow (SSCFlow) algorithm that combines unsupervised imputation and supervised classification. By estimating the conditional distribution of incomplete instances, SSCFlow facilitates imputation and classification simultaneously, addressing the issue of separated tasks ignoring data distribution and label information in traditional methods.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Deeksha Varshney, Asif Ekbal, Erik Cambria
Summary: This paper focuses on the neural-based interactive dialogue system that aims to engage and retain humans in long-lasting conversations. It proposes a new neural generative model that combines step-wise co-attention, self-attention-based transformer network, and an emotion classifier to control emotion and knowledge transfer during response generation. The results from quantitative, qualitative, and human evaluation show that the proposed models can generate natural and coherent sentences, capturing essential facts with significant improvement over emotional content.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Junchen Ye, Weimiao Li, Zhixin Zhang, Tongyu Zhu, Leilei Sun, Bowen Du
Summary: Modeling multivariate time series has long been a topic of interest for scholars in various fields. This paper introduces MvTS, an open library based on Pytorch, which provides a unified framework for implementing and evaluating these models. Extensive experiments on public datasets demonstrate the effectiveness and universality of the models reproduced by MvTS.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Reham R. Mostafa, Ahmed M. Khedr, Zaher Al Aghbari, Imad Afyouni, Ibrahim Kamel, Naveed Ahmed
Summary: Feature selection is crucial in classification procedures, but it faces challenges in high-dimensional datasets. To overcome these challenges, this study proposes an Adaptive Hybrid-Mutated Differential Evolution method that incorporates the mechanics of the Spider Wasp Optimization algorithm and the concept of Enhanced Solution Quality. Experimental results demonstrate the effectiveness of the method in terms of accuracy and convergence speed, and it outperforms contemporary cutting-edge algorithms.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Ti Xiang, Pin Lv, Liguo Sun, Yipu Yang, Jiuwu Hao
Summary: This paper introduces a Track Classification Model (TCM) based on marine radar, which can effectively recognize and classify shipping tracks. By using a feature extraction network with multi-feature fusion and a dataset production method to address missing labels, the classification accuracy is improved, resulting in successful engineering application in real scenarios.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Zhihao Zhang, Yuan Zuo, Chenghua Lin, Junjie Wu
Summary: This paper proposes a novel unsupervised context-aware quality phrase mining framework called LMPhrase, which is built upon large pre-trained language models. The framework mines quality phrases as silver labels using a parameter-free probing technique on the pre-trained language model BERT, and formalizes the phrase tagging task as a sequence generation problem by fine-tuning on the Sequence to-Sequence pre-trained language model BART. The results of extensive experiments show that LMPhrase consistently outperforms existing competitors in two different granularity phrase mining tasks.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Kemal Buyukkaya, M. Ozan Karsavuran, Cevdet Aykanat
Summary: The study aims to investigate the hybrid parallelization of the Stochastic Gradient Descent (SGD) algorithm for solving the matrix completion problem on a high-performance computing platform. A hybrid parallel decentralized SGD framework with asynchronous inter-process communication and a novel flexible partitioning scheme is proposed to achieve scalability up to hundreds of processors. Experimental results on real-world benchmark datasets show that the proposed algorithm achieves 6x higher throughput on sparse datasets compared to the state-of-the-art, while achieving comparable throughput on relatively dense datasets.
KNOWLEDGE-BASED SYSTEMS
(2024)
