Article
Automation & Control Systems
Amit Kumar Kar, Amaresh Chandra Mishra, Sraban Kumar Mohanty
Summary: Clustering is an unsupervised learning technique that discovers intrinsic groups in data based on proximity. This paper proposes a new distance metric for computing dissimilarity between categorical data points. Experimental results show the efficacy of the proposed metric in handling complex real datasets.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Enrico De Santis, Francesco Arno, Antonello Rizzi
Summary: Machine Learning is a widely adopted approach for solving data-driven problems in predictive maintenance. This paper compares calibration techniques for fuzzy scoring values of a hybrid classifier and proposes new techniques that demonstrate comparable performance, computational efficiency, and flexibility.
Article
Computer Science, Artificial Intelligence
Fatih Saglam, Emre Yildirim, Mehmet Ali Cengiz
Summary: Bayesian classification is a frequently used approach in machine learning, but it may not perform well when attributes are concentrated in multiple regions. To address this issue, this study proposes a clustered Bayesian classification method that detects different concentrations within classes using clustering and improves prediction performance.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Hitesh Mohapatra, Amiya Kumar Rath
Summary: The wireless sensor network plays a significant role in smart city applications for data sensing, collecting, and transmitting. The advanced metering infrastructure is an automatic system for reading electricity consumption, with data communication over a wireless medium. Routing is a major attribute in the AMI network, with successful communication depending on the proper state of links and nodes.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2021)
Article
Engineering, Multidisciplinary
Rahman Dashti, Mohammad Daisy, Hamid Mirshekali, Hamid Reza Shaker, Mahmood Hosseini Aliabadi
Summary: The study highlights the importance of accurate fault prediction and location in distribution networks for maintaining reliability and customer satisfaction. It compares various methods and covers different network types and technical standards.
Article
Engineering, Chemical
Seul-Gi Kim, Donghyun Park, Jae-Yoon Jung
Summary: Real-time fault detection and predictive maintenance based on sensor data are being actively introduced in various industries. This study evaluates the effectiveness of Mahalanobis distance-based classifiers in detecting faults in rotating machinery, showing their superior performance compared to binary classifiers in cases with imbalanced data ratios.
Article
Engineering, Electrical & Electronic
Huishi Liang, Jin Ma
Summary: Load shape dictionary (LSD) is a useful tool for understanding customers' electricity consumption behaviors using smart meter data. A bilevel LSD generation framework is proposed to cluster and index residential load profiles, extracting useful information. Fast DDTW is introduced to speed up calculations, and the methodology is validated for clustering performance and computational efficiency.
IEEE TRANSACTIONS ON SMART GRID
(2021)
Article
Computer Science, Information Systems
Haomiao Yang, Shaopeng Liang, Xizhao Luo, Dianhua Tang, Hongwei Li, Xuemin Shen
Summary: This article proposes a secure K-means clustering scheme called PIPC, which aims to protect the privacy and integrity of load profiling. By using techniques such as encrypted distance measurement and integrity assurance, PIPC successfully protects the privacy of smart-meter data and maintains the integrity of outsourced clustering.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Computer Science, Information Systems
Moustapha Diaw, Agnes Delahaies, Jerome Landre, Florent Retraint, Frederic Morain-Nicolier
Summary: This study presents a new method for image pair comparison and classification based on the modeling of the Local Dissimilarity Map (LDM). The method uses a statistical model for the LDM and applies classifiers to compute the classification scores. It is capable of effectively differentiating and classifying similar and dissimilar image pairs, and is robust against geometric transformations such as translation.
Article
Physics, Multidisciplinary
Yunxiao Liu, Youfang Lin, Ziyu Jia, Jing Wang, Yan Ma
Summary: The paper proposes a novel dissimilarity measure based on the ordinal pattern representation of signals, which can analyze physiological signals in a simple, robust, and computationally efficient manner. Experimental results demonstrate the effectiveness of this method in distinguishing signals from different conditions.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2021)
Article
Engineering, Electrical & Electronic
Inam Ullah Khan, Nadeem Javaid, C. James Taylor, Xiandong Ma
Summary: The role of electricity theft detection is crucial in maintaining cost-efficiency in smart grids. Existing methods are limited by the large volume of data, missing values, and non-linearity. A novel framework is proposed that combines three modules to address these issues. The framework efficiently handles missing values, imbalanced datasets, and accurately predicts electricity theft cases using a hybrid classification approach and an improved artificial neural network.
IEEE TRANSACTIONS ON POWER SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Ryan S. Tulabing, Brian C. Mitchell, Grant A. Covic, John T. Boys
Summary: The increased adoption of electric vehicles is challenging the traditional electricity grid, especially at the local residential network level, due to higher peak demands, system overloads, and voltage violations. This study proposes a non-wire solution called Localized Demand Control, which enables the local grid to follow a preferred demand curve through coordinated actions of flexible loads. The system has been validated in a real-world microgrid facility and recommended rates for gradual technology adoption in the next 20 years have been created through simulations of a representative network.
IEEE TRANSACTIONS ON SMART GRID
(2023)
Article
Chemistry, Analytical
Loris Nanni, Giovanni Minchio, Sheryl Brahnam, Gianluca Maguolo, Alessandra Lumini
Summary: The image classification system proposed in this study utilizes Siamese Neural Networks to generate dissimilarity spaces, calculates centroids with k-means clustering, and classifies images using SVMs. The system performs competitively on medical and animal audio data sets, achieving state-of-the-art performance without ad-hoc optimization of clustering methods on tested data sets.
Article
Energy & Fuels
Daniel Istvan Nemeth, Kalman Tornai
Summary: The full utilization of renewable energy resources is challenging due to the changing load of the electrical grid. Demand-side management is a solution to this problem, which requires knowledge about the grid load composition and the ability to schedule individual loads. Existing Smart Plugs lack the ability to detect previously unseen electrical loads, causing problems in load estimation and scheduling. This paper evaluates the application of open-set recognition methods to address this issue, with promising results from a Support Vector Machine approach and a modified OpenMax-based algorithm.
Article
Construction & Building Technology
Elham Eskandarnia, Hesham M. Al-Ammal, Riadh Ksantini
Summary: This study proposes an unsupervised deep clustering framework for load profiling. The framework utilizes an autoencoder for data representation and combines dimensionality reduction with clustering, resulting in improved load profiling performance.
SUSTAINABLE CITIES AND SOCIETY
(2022)
Article
Computer Science, Artificial Intelligence
Luca Baldini, Alessio Martino, Antonello Rizzi
Summary: This paper proposes an evolutionary-based approach for learning multiple dissimilarity measures tailored on each problem-related class for classification. By learning class-specific metrics, high informative class prototypes can be synthesized using granular computing approach for graph classification with common pattern recognition techniques.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Alessio Martino, Luca Baldini, Antonello Rizzi
Summary: This paper compares different strategies for the automatic synthesis of information granules in the context of graph classification and finds that a class-aware granulation method can improve performance.
Article
Computer Science, Artificial Intelligence
Enrico De Santis, Francesco Arno, Antonello Rizzi
Summary: Machine Learning is a widely adopted approach for solving data-driven problems in predictive maintenance. This paper compares calibration techniques for fuzzy scoring values of a hybrid classifier and proposes new techniques that demonstrate comparable performance, computational efficiency, and flexibility.
Article
Computer Science, Artificial Intelligence
Enrico De Santis, Parisa Naraei, Alessio Martino, Alireza Sadeghian, Antonello Rizzi
Summary: In this paper, a multi-fractal analysis was conducted on a diastolic blood pressure signal. The signal exhibited interesting scaling properties and a pronounced multifractality. The study also demonstrated how the analyzed signal could be described by a concise multifractal model.
Article
Computer Science, Artificial Intelligence
Pietro Verzelli, Cesare Alippi, Lorenzo Livi, Peter Tino
Summary: Reservoir computing is a popular approach for designing recurrent neural networks due to its training simplicity and approximation performance. An analysis of the network dynamics using the controllability matrix can provide insights into the memory capacity of the network and the impact of its architecture.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Enrico De Santis, Alessio Martino, Antonello Rizzi
Summary: In pattern recognition techniques, it is crucial to automatically learn the appropriate dissimilarity measure for object comparison. This article discusses the use of component-wise dissimilarity measures in unconventional spaces and how they interact with the Euclidean behavior of dissimilarity matrices.
PEERJ COMPUTER SCIENCE
(2022)
Article
Computer Science, Artificial Intelligence
Enrico De Santis, Antonello Rizzi
Summary: This paper presents a novel framework for solving text categorization tasks using the Conceptual Space Theory, Granular Computing approach, and Machine Learning. The authors propose a concept-based representation of text and compare the performance of neural embedding techniques and LSA in knowledge discovery applications.
COGNITIVE COMPUTATION
(2023)
Article
Computer Science, Information Systems
Enrico De Santis, Alessio Martino, Francesca Ronci, Antonello Rizzi
Summary: On February 24, 2022, the Russian invasion of Ukraine initiated a dramatic conflict. The battlefield in this modern conflict exists both in the physical world and in the virtual realm, with social networks playing a significant role. Scholars have expressed concern about the spread of disinformation on these platforms. This study utilizes an unsupervised topic tracking system that combines Natural Language Processing and graph-based techniques to analyze the Italian social context, specifically focusing on Twitter data and metadata captured during the first month of the war. This improved system effectively highlights emerging topics, major events, and their interconnections.
Article
Computer Science, Artificial Intelligence
Enrico De Santis, Giovanni De Santis, Antonello Rizzi
Summary: This study applies an interdisciplinary approach to analyze the complexity underlying the morphological organization in various linguistic texts and investigates the predictive power of multifractal signatures through machine learning. The results demonstrate the presence of persistence in the analyzed texts, which plays a role in characterizing different linguistic families. The proposed approach is effective and can be used for further comparative studies and advancements in information retrieval and artificial intelligence.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Enrico De Santis, Alessio Martino, Francesca Ronci, Antonello Rizzi
Summary: In the era of generalist social media, finding users who share the same diseases and related experiences is crucial for patients. This study investigates different semantic text representation approaches, both traditional and advanced, using NLP techniques to classify Italian users in medical discussion groups. The classification and semantic evaluation experiments of the models are satisfactory, especially considering the unbalanced dataset.
2023 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Enrico De Santis, Francesco Arno, Alessio Martino, Antonello Rizzi
Summary: This paper introduces a system for anomaly detection in railway environments, with a focus on the pressurization systems of high-speed trains. The study utilizes statistical techniques and classification tasks to address the issue of unbalanced data.
2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Emanuele Ferrandino, Antonin Capillo, Enrico De Santis, Fabio Massimo Frattale Mascioli, Antonello Rizzi
Summary: This paper presents an autonomous driving system for boats in a simulated environment, aiming to help define a standard equivalent to those used in land vehicles. The system combines classical approaches and computational intelligence techniques, and has been tested in the mid-level control scenario. Results demonstrate that fuzzy controllers can achieve a lower probability of collision and stall, while maintaining the same performance as crisp controllers.
2022 IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS (FUZZ-IEEE)
(2022)
Article
Computer Science, Artificial Intelligence
Rui Lv, Dingheng Wang, Jiangbin Zheng, Zhao-Xu Yang
Summary: In this paper, the authors investigate tensor decomposition for neural network compression. They analyze the convergence and precision of tensor mapping theory, validate the rationality of tensor mapping and its superiority over traditional tensor approximation based on the Lottery Ticket Hypothesis. They propose an efficient method called 3D-KCPNet to compress 3D convolutional neural networks using the Kronecker canonical polyadic (KCP) tensor decomposition. Experimental results show that 3D-KCPNet achieves higher accuracy compared to the original baseline model and the corresponding tensor approximation model.
Article
Computer Science, Artificial Intelligence
Xiangkun He, Zhongxu Hu, Haohan Yang, Chen Lv
Summary: In this paper, a novel constrained multi-objective reinforcement learning algorithm is proposed for personalized end-to-end robotic control with continuous actions. The approach trains a single model using constraint design and a comprehensive index to achieve optimal policies based on user-specified preferences.
Article
Computer Science, Artificial Intelligence
Zhijian Zhuo, Bilian Chen, Shenbao Yu, Langcai Cao
Summary: In this paper, a novel method called Expansion with Contraction Method for Overlapping Community Detection (ECOCD) is proposed, which utilizes non-negative matrix factorization to obtain disjoint communities and applies expansion and contraction processes to adjust the degree of overlap. ECOCD is applicable to various networks with different properties and achieves high-quality overlapping community detection.
Article
Computer Science, Artificial Intelligence
Yizhe Zhu, Chunhui Zhang, Jialin Gao, Xin Sun, Zihan Rui, Xi Zhou
Summary: In this work, the authors propose a Contrastive Spatio-Temporal Distilling (CSTD) approach to improve the detection of high-compressed deepfake videos. The approach leverages spatial-frequency cues and temporal-contrastive alignment to fully exploit spatiotemporal inconsistency information.
Review
Computer Science, Artificial Intelligence
Laijin Meng, Xinghao Jiang, Tanfeng Sun
Summary: This paper provides a review of coverless steganographic algorithms, including the development process, known contributions, and general issues in image and video algorithms. It also discusses the security of coverless steganography from theoretical analysis to actual investigation for the first time.
Article
Computer Science, Artificial Intelligence
Yajie Bao, Tianwei Xing, Xun Chen
Summary: Visual question answering requires processing multi-modal information and effective reasoning. Neural-symbolic learning is a promising method, but current approaches lack uncertainty handling and can only provide a single answer. To address this, we propose a confidence based neural-symbolic approach that evaluates NN inferences and conducts reasoning based on confidence.
Article
Computer Science, Artificial Intelligence
Anh H. Vo, Bao T. Nguyen
Summary: Interior style classification is an interesting problem with potential applications in both commercial and academic domains. This project proposes a method named ISC-DeIT, which combines data-efficient image transformer architectures and knowledge distillation, to address the interior style classification problem. Experimental results demonstrate a significant improvement in predictive accuracy compared to other state-of-the-art methods.
Article
Computer Science, Artificial Intelligence
Shashank Kotyan, Danilo Vasconcellos Vargas
Summary: This article introduces a novel augmentation technique called Dynamic Scanning Augmentation to improve the accuracy and robustness of Vision Transformer (ViT). The technique leverages dynamic input sequences to adaptively focus on different patches, resulting in significant changes in ViT's attention mechanism. Experimental results demonstrate that Dynamic Scanning Augmentation outperforms ViT in terms of both robustness to adversarial attacks and accuracy against natural images.
Article
Computer Science, Artificial Intelligence
Hiba Alqasir, Damien Muselet, Christophe Ducottet
Summary: The article proposes a solution to improve the learning process of a classification network by providing shape priors, reducing the need for annotated data. The solution is tested on cross-domain digit classification tasks and a video surveillance application.
Article
Computer Science, Artificial Intelligence
Dexiu Ma, Mei Liu, Mingsheng Shang
Summary: This paper proposes a method using neural dynamics solvers to solve infinity-norm optimization problems. Two improved solvers are constructed and their effectiveness and superiority are demonstrated through theoretical analysis and simulation experiments.
Article
Computer Science, Artificial Intelligence
Francesco Gregoretti, Giovanni Pezzulo, Domenico Maisto
Summary: Active Inference is a computational framework that uses probabilistic inference and variational free energy minimization to describe perception, planning, and action. cpp-AIF is a header-only C++ library that provides a powerful tool for implementing Active Inference for Partially Observable Markov Decision Processes through multi-core computing. It is cross-platform and improves performance, memory management, and usability compared to existing software.
Article
Computer Science, Artificial Intelligence
Zelin Ying, Dawei Cheng, Cen Chen, Xiang Li, Peng Zhu, Yifeng Luo, Yuqi Liang
Summary: This paper proposes a novel stock market trends prediction framework called SMART, which includes a self-supervised stock technical data sequence embedding model S3E. By training with multiple self-supervised auxiliary tasks, the model encodes stock technical data sequences into embeddings and uses the learned sequence embeddings for predicting stock market trends. Extensive experiments on China A-Shares market and NASDAQ market prove the high effectiveness of our model in stock market trends prediction, and its effectiveness is further validated in real-world applications in a leading financial service provider in China.
Article
Computer Science, Artificial Intelligence
Hao Li, Hao Jiang, Dongsheng Ye, Qiang Wang, Liang Du, Yuanyuan Zeng, Liu Yuan, Yingxue Wang, C. Chen
Summary: DHGAT1, a dynamic hyperbolic graph attention network, utilizes hyperbolic metric properties to embed dynamic graphs. It employs a spatiotemporal self-attention mechanism and weighted node representations, resulting in excellent performance in link prediction tasks.
Article
Computer Science, Artificial Intelligence
Jiehui Huang, Zhenchao Tang, Xuedong He, Jun Zhou, Defeng Zhou, Calvin Yu-Chian Chen
Summary: This study proposes a progressive learning multi-scale feature blending model for image deraining tasks. The model utilizes detail dilation and texture extraction to improve the restoration of rainy images. Experimental results show that the model achieves near state-of-the-art performance in rain removal tasks and exhibits better rain removal realism.
Article
Computer Science, Artificial Intelligence
Lizhi Liu, Zilin Gao, Yinhe Wang, Yongfu Li
Summary: This paper proposes a novel discrete-time interconnected model for depicting complex dynamical networks. The model consists of nodes and edges subsystems, which consider the dynamic characteristic of both nodes and edges. By designing control strategies and coupling modes, the stabilization and synchronization of the network are achieved. Simulation results demonstrate the effectiveness of the proposed methods.