Article
Computer Science, Artificial Intelligence
Irem Tasci, Burak Tasci, Prabal D. Barua, Sengul Dogan, Turker Tuncer, Elizabeth Emma Palmer, Hamido Fujita, U. Rajendra Acharya
Summary: This study presents a large EEG signal dataset and investigates the detection ability of a new hypercube pattern-based framework for epilepsy. A total of 245 feature vectors were extracted and fed to a kNN classifier, achieving high classification accuracy.
INFORMATION FUSION
(2023)
Article
Computer Science, Artificial Intelligence
Francisco Souza, Cristiano Premebida, Rui Araujo
Summary: This paper presents a novel feature selection method based on conditional mutual information. The method incorporates high order dependencies into the feature selection process and speeds up the process through a greedy search procedure. Experimental results show that the proposed method outperforms other algorithms in terms of accuracy and speed.
PATTERN RECOGNITION
(2022)
Article
Biology
Xin Huang, Zeyu Wang, Benzhe Su, Xinyu He, Bing Liu, Baolin Kang
Summary: The research proposed a computational strategy for metabolic network construction based on the overlapping ratio for studying the effect of disease treatment. Analysis of HD-pattern-dependent changes in plasma metabolites was conducted, revealing metabolic similarities and differences in patients' response to HD and HFD, providing guidance for personalized dialysis therapy.
COMPUTATIONAL BIOLOGY AND CHEMISTRY
(2021)
Article
Computer Science, Artificial Intelligence
Jefferson G. Martins, Luiz E. S. Oliveira, Daniel Weingaertner, Andersson Barison, Gerlon A. R. Oliveira, Luciano M. Liao
Summary: Forests are being exploited disorderly and many species are endangered, prompting the need for a spatial distribution plan. Researchers facing a lack of representative databases can benefit from introducing new databases and proposing selection strategies to improve outcomes.
Article
Biochemical Research Methods
Prabina Kumar Meher, Anil Rai, Atmakuri Ramakrishna Rao
Summary: This study introduces a novel computational tool for predicting the multiple localization of mRNAs. Based on the proposed approach, an online prediction server mLoc-mRNA is accessible at http://cabgrid.res.in:8080/mlocmrna/. The developed approach is believed to supplement the existing tools and techniques for the localization prediction of mRNAs.
BMC BIOINFORMATICS
(2021)
Review
Chemistry, Applied
Adriano de Araujo Gomes, Silvana M. Azcarate, Paulo Henrique Gonsalves Dias Diniz, David Douglas de Sousa Fernandes, Germano Veras
Summary: Food analysis is crucial for ensuring the quality and integrity of food products, and selecting effective variables is key to improving the accuracy and robustness of models. By discarding non-informative and redundant signals, more accurate and interpretable models can be established.
Article
Genetics & Heredity
Hongyu Wang, Zhaomin Yao, Renli Luo, Jiahao Liu, Zhiguo Wang, Guoxu Zhang
Summary: OMIC is a novel approach that analyzes genetic or molecular profiles and explores the correlation between different features using a convolutional neural network (CNN). By transforming transcriptomic features into LaCOme features, it has been shown to outperform the original transcriptomic features in classification performance. This method enhances computational analysis results and provides valuable information in OMIC data analysis.
Article
Computer Science, Information Systems
Erdal Tasci, Aybars Ugur
Summary: With the increasing number of digital images, computer-aided classification of image types is widely used. The feature extraction and selection stages play a crucial role in improving classification performance. In this study, a novel pattern recognition framework combining diverse and large-scale handcrafted feature extraction methods and the selection stage is developed. Genetic algorithms are used for feature selection. Experimental results show high accuracy rates on different datasets, making the proposed method competitive with existing state-of-the-art methods.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Automation & Control Systems
Victor Hamer, Pierre Dupont
Summary: Current feature selection methods, especially in high-dimensional data, may suffer from instability, but a new stability measure proposed in this work, which incorporates the importance of selected features in predictive models, has been shown to correct overly optimistic estimates and improve decision-making accuracy.
JOURNAL OF MACHINE LEARNING RESEARCH
(2021)
Article
Computer Science, Information Systems
Tapas Bhadra, Sanghamitra Bandyopadhyay
Summary: The paper proposes a novel supervised feature selection approach based on dense subgraph discovery. The algorithm proceeds in two phases to select features with maximal average class relevance, minimal average pairwise redundancy, and good discriminating power. Experimental results show the proposed approach is competitive with conventional and state-of-the-art algorithms in supervised feature selection.
INFORMATION SCIENCES
(2021)
Article
Oncology
Erdal Tasci, Sarisha Jagasia, Ying Zhuge, Mary Sproull, Theresa Cooley Zgela, Megan Mackey, Kevin Camphausen, Andra Valentina Krauze
Summary: Glioblastomas are aggressive and fatal brain cancers, and analyzing proteomic data can help identify biomarkers and evaluate treatment response. This study used a novel rank-based feature weighting method to select discriminative proteomic features in GBM patients before and after chemoirradiation. The results showed promising accuracy rates and identified novel biomarkers with prognostic relevance.
Article
Engineering, Chemical
Silin Rao, Jingtao Wang
Summary: Fault diagnosis rate (FDR) and fault diagnosis timeliness (FDT) are critical to fault diagnosis models in industrial processes. To address the trade-off between high FDR and low timeliness, a multiple pattern representation-convolutional neural network (MPR-CNN) is proposed, which compensates for the time-length reduction of data by enhancing the data thickness and extracting richer features. Experimental results show that MPR-CNN significantly improves fault diagnosis performance and outperforms other CNN structure-based models.
JOURNAL OF THE TAIWAN INSTITUTE OF CHEMICAL ENGINEERS
(2023)
Article
Computer Science, Artificial Intelligence
Shao Liu, Jiaqi Yang, Sos S. Agaian, Changhe Yuan
Summary: The article introduces three novel features and a mature model structure for artistic movement recognition of portrait paintings, showing the successful application of these features in various neural networks through extensive evaluation. Additionally, a new portrait database containing 927 paintings from 6 different art movements is presented, demonstrating the superiority of the proposed method over state-of-the-art approaches.
IMAGE AND VISION COMPUTING
(2021)
Article
Engineering, Electrical & Electronic
Yi Yang, Hairong Fang
Summary: This article proposes a feature smoothing algorithm based on CNN to improve the precision and accuracy of feature smoothing for large and complex curved workpieces through three stages of processing.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Engineering, Civil
Jili Tao, Ridong Zhang
Summary: In this study, driving cycles were analyzed to optimize neural network structure and parameters using genetic algorithm. The extracted features of driving behavior were used to design a classifier, which showed improved classification capability and faster real-time classification speed.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Medicine, General & Internal
Zofia Wicik, Ceren Eyileten, Daniel Jakubik, Sergio N. Simoes, David C. Martins, Rodrigo Pavao, Jolanta M. Siller-Matula, Marek Postula
JOURNAL OF CLINICAL MEDICINE
(2020)
Article
Biochemical Research Methods
Robson P. Bonidia, Lucas D. H. Sampaio, Douglas S. Domingues, Alexandre R. Paschoal, Fabricio M. Lopes, Andre C. P. L. F. de Carvalho, Danilo S. Sanches
Summary: This study proposes a research on feature extraction approaches based on mathematical features to address the challenge of extracting significant discriminatory information from biological sequence data. Through case studies and experiments, the effectiveness and robustness of the new algorithm are demonstrated.
BRIEFINGS IN BIOINFORMATICS
(2021)
Article
Automation & Control Systems
Douglas Felipe Pereira, Pedro Henrique Bugatti, Fabricio Martins Lopes, Andre Luis Siqueira Marques de Souza, Priscila Tiemi Maeda Saito
Summary: This article discusses the challenges seed companies face in pursuing excellence in production quality, and proposes soybean seed vigor learning and classification methods to address these issues. The research found that active learning methods can achieve higher classification accuracy more quickly, while reducing the number of labeled samples required in the learning process.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2021)
Article
Multidisciplinary Sciences
Alex Nunes da Silva Junior, Matheus Montanini Breve, Jesus Pascual Mena-Chalco, Fabricio Martins Lopes
Summary: This study analyzes and characterizes the co-authorship networks of academic Brazilian graduate programs in computer science, exploring different network topologies and quality indices related to the assessment unit CAPES.
Letter
Biochemical Research Methods
Fabricio Martins Lopes, Matheus H. Pimenta-Zanon
Summary: This article identifies a conceptual error in a published paper and provides the correct method and results to prevent the method from being misused or replicated.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Biochemistry & Molecular Biology
Ceren Eyileten, Zofia Wicik, Sergio N. Simoes, David C. Martins-Jr, Krzysztof Klos, Wojciech Wlodarczyk, Alice Assinger, Dariusz Soldacki, Andrzej Chcialowski, Jolanta M. Siller-Matula, Marek Postula
Summary: By utilizing bioinformatic and co-expression analysis, this study identified and validated miRNAs associated with thrombosis in COVID-19 patients, which can serve as potential diagnostic and prognostic biomarkers for disease severity. The findings contribute to our understanding of the pathogenesis of COVID-19 and the identification of novel predictive markers.
Review
Biochemistry & Molecular Biology
Juliana Costa-Silva, Douglas S. Domingues, David Menotti, Mariangela Hungria, Fabricio Martins Lopes
Summary: This paper provides a review of the pipeline for differential expression analysis, discussing the steps, methods, challenges, and tutorial aspects. It aims to guide new entrants and assist established users in updating their analysis pipelines.
COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL
(2023)
Article
Biochemistry & Molecular Biology
Marcus Vinicius C. Santos, Arthur S. S. Feltrin, Isabele C. C. Costa-Amaral, Liliane R. R. Teixeira, Jamila A. A. Perini, David C. C. Martins Jr, Ariane L. L. Larentis
Summary: Network Medicine is a useful platform for studying the molecular complexity of complex diseases and identifying disease modules and pathways. It can provide insights into how environmental chemical exposures affect human cells and help monitor and prevent exposure-related diseases. In this study, benzene and malathion-exposed differentially expressed genes were used to construct interaction networks and identify important hub genes associated with these chemicals.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2023)
Review
Biochemistry & Molecular Biology
Juliana Costa-Silva, Mariangela Hungria, Douglas S. Domingues, David Menotti, Fabricio Martins Lopes
Summary: This paper provides a comprehensive review of the computational analysis pipeline for differential gene expression analysis from RNA-seq data. It introduces the objectives, methods, and properties of each step, presents a timeline of the computational methods, and discusses the relationships between important tools. The paper serves as a tutorial for beginners and helps established users update their analysis pipelines.
COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Matheus H. Pimenta-Zanon, Vinicius Augusto De Souza, Ronaldo Fumio Hashimoto, Fabricio Martins Lopes
Summary: During the COVID-19 pandemic, genetic mutations in the SARS-CoV-2 virus have resulted in increased infectivity. The existing classification and identification methods for variants are computationally complex and cannot handle large numbers of sequences simultaneously. This study proposes an alignment-free method called BASiNETEntropy for classifying SARS-CoV-2 variants of concern. The method maps biological sequences into a network, selects informative edges through entropy maximization, and extracts topological measurements as feature vectors for classification. Experimental results demonstrate high accuracy in classifying variants of concern, contributing to reducing the feature space. Unique patterns are also extracted for each variant relative to the reference sequence. The proposed method is implemented as an open-source tool in R language.
AMBIENT INTELLIGENCE IN HEALTH CARE, ICAIHC 2022
(2023)
Meeting Abstract
Cardiac & Cardiovascular Systems
J. Jarosz-Popek, C. Eyileten, Z. Wicik, A. Nowak, M. Wolska, A. Shahzadi, D. Jakubik, S. N. Simoes, D. C. Martins, J. Siller-Matula, M. Postula
EUROPEAN HEART JOURNAL
(2022)
Meeting Abstract
Cardiac & Cardiovascular Systems
D. Keshwani, C. Eyileten, Z. Wicik, A. Nowak, D. Jakubik, S. N. Simoes, D. C. Martins-, A. Shahzadi, J. Jarosz-Popek, M. Wolska, J. Siller-Matula, M. Postula
EUROPEAN HEART JOURNAL
(2022)
Proceedings Paper
Engineering, Biomedical
Carlos R. P. Tovar, David C. Martins-, Luiz C. S. Rozante, Eloi Araujo
Summary: The paper presents a computationally efficient method to identify attractor fields in coupled Boolean networks (CBNs), a class of models with potential applications in Systems Biology. Experimental results demonstrate that the proposed method is capable of recovering the dynamics structure of large-scale CBNs in a feasible time.
2022 IEEE 22ND INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOENGINEERING (BIBE 2022)
(2022)
Proceedings Paper
Computer Science, Information Systems
Julio Marcos Gomes Junior, Fabricio Martins Lopes
Summary: This paper proposes an approach to classify employee absenteeism using neural networks and Layer-wise relevance propagation. It can identify the most relevant features, assign relevance scores for absenteeism classification, and explain the reasons for absenteeism, which is important for human resource management and occupational medicine.
2022 IEEE-EMBS INTERNATIONAL CONFERENCE ON BIOMEDICAL AND HEALTH INFORMATICS (BHI) JOINTLY ORGANISED WITH THE IEEE-EMBS INTERNATIONAL CONFERENCE ON WEARABLE AND IMPLANTABLE BODY SENSOR NETWORKS (BSN'22)
(2022)
Proceedings Paper
Computer Science, Interdisciplinary Applications
Rodrigo A. de O. Siqueira, Marco A. Stefanes, Luiz C. S. Rozante, David C. Martins-Jr, Jorge E. S. de Souza, Eloi Araujo
Summary: Multiple sequence alignment is essential in representing biological sequence similarities, but due to the complexity of the problem, only approximate solutions are possible. This study introduces a Multi-GPU approach for efficient handling of large-scale lengthy sequence alignments compared to existing methods.
COMPUTATIONAL SCIENCE AND ITS APPLICATIONS, ICCSA 2021, PT I
(2021)
Article
Computer Science, Information Systems
Xia Liang, Jie Guo, Peide Liu
Summary: This paper investigates a novel consensus model based on social networks to manage manipulative and overconfident behaviors in large-scale group decision-making. By proposing a novel clustering model and improved methods, the consensus reaching is effectively facilitated. The feedback mechanism and management approach are employed to handle decision makers' behaviors. Simulation experiments and comparative analysis demonstrate the effectiveness of the model.
INFORMATION SCIENCES
(2024)
Article
Computer Science, Information Systems
Xiang Li, Haiwang Guo, Xinyang Deng, Wen Jiang
Summary: This paper proposes a method based on class gradient networks for generating high-quality adversarial samples. By introducing a high-level class gradient matrix and combining classification loss and perturbation loss, the method demonstrates superiority in the transferability of adversarial samples on targeted attacks.
INFORMATION SCIENCES
(2024)
Article
Computer Science, Information Systems
Lingyun Lu, Bang Wang, Zizhuo Zhang, Shenghao Liu
Summary: Many recommendation algorithms only rely on implicit feedbacks due to privacy concerns. However, the encoding of interaction types is often ignored. This paper proposes a relation-aware neural model that classifies implicit feedbacks by encoding edges, thereby enhancing recommendation performance.
INFORMATION SCIENCES
(2024)
Article
Computer Science, Information Systems
Jaehong Yu, Hyungrok Do
Summary: This study discusses unsupervised anomaly detection using one-class classification, which determines whether a new instance belongs to the target class by constructing a decision boundary. The proposed method uses a proximity-based density description and a regularized reconstruction algorithm to overcome the limitations of existing one-class classification methods. Experimental results demonstrate the superior performance of the proposed algorithm.
INFORMATION SCIENCES
(2024)
Article
Computer Science, Information Systems
Hui Tu, Shifei Ding, Xiao Xu, Haiwei Hou, Chao Li, Ling Ding
Summary: Border-Peeling algorithm is a density-based clustering algorithm, but its complexity and issues on unbalanced datasets restrict its application. This paper proposes a non-iterative border-peeling clustering algorithm, which improves the clustering performance by distinguishing and associating core points and border points.
INFORMATION SCIENCES
(2024)
Article
Computer Science, Information Systems
Long Tang, Pan Zhao, Zhigeng Pan, Xingxing Duan, Panos M. Pardalos
Summary: In this work, a two-stage denoising framework (TSDF) is proposed for zero-shot learning (ZSL) to address the issue of noisy labels. The framework includes a tailored loss function to remove suspected noisy-label instances and a ramp-style loss function to reduce the negative impact of remaining noisy labels. In addition, a dynamic screening strategy (DSS) is developed to efficiently handle the nonconvexity of the ramp-style loss.
INFORMATION SCIENCES
(2024)
Article
Computer Science, Information Systems
Raghunathan Krishankumar, Sundararajan Dhruva, Kattur S. Ravichandran, Samarjit Kar
Summary: Health 4.0 is gaining global attention for better healthcare through digital technologies. This study proposes a new decision-making framework for selecting viable blockchain service providers in the Internet of Medical Things (IoMT). The framework addresses the limitations in previous studies and demonstrates its applicability in the Indian healthcare sector. The results show the top ranking BSPs, the importance of various criteria, and the effectiveness of the developed model.
INFORMATION SCIENCES
(2024)
Article
Computer Science, Information Systems
Tao Tan, Hong Xie, Liang Feng
Summary: This paper proposes a heterogeneous update idea and designs HetUp Q-learning algorithm to enlarge the normalized gap by overestimating the Q-value corresponding to the optimal action and underestimating the Q-value corresponding to the other actions. To address the limitation, a softmax strategy is applied to estimate the optimal action, resulting in HetUpSoft Q-learning and HetUpSoft DQN. Extensive experimental results show significant improvements over SOTA baselines.
INFORMATION SCIENCES
(2024)
Article
Computer Science, Information Systems
Chao Yang, Xianzhi Wang, Lina Yao, Guodong Long, Guandong Xu
Summary: This paper proposes a dynamic transformer-based architecture called Dyformer for multivariate time series classification. Dyformer captures multi-scale features through hierarchical pooling and adaptive learning strategies, and improves model performance by introducing feature-map-wise attention mechanisms and a joint loss function.
INFORMATION SCIENCES
(2024)
Article
Computer Science, Information Systems
Xiguang Li, Baolu Feng, Yunhe Sun, Ammar Hawbani, Saeed Hammod Alsamhi, Liang Zhao
Summary: This paper proposes an enhanced scatter search strategy, using opposition-based learning, to solve the problem of automated test case generation based on path coverage (ATCG-PC). The proposed ESSENT algorithm selects the path with the lowest path entropy among the uncovered paths as the target path and generates new test cases to cover the target path by modifying the dimensions of existing test cases. Experimental results show that the ESSENT algorithm outperforms other state-of-the-art algorithms, achieving maximum path coverage with fewer test cases.
INFORMATION SCIENCES
(2024)
Article
Computer Science, Information Systems
Shirin Dabbaghi Varnosfaderani, Piotr Kasprzak, Aytaj Badirova, Ralph Krimmel, Christof Pohl, Ramin Yahyapour
Summary: Linking digital accounts belonging to the same user is crucial for security, user satisfaction, and next-generation service development. However, research on account linkage is mainly focused on social networks, and there is a lack of studies in other domains. To address this, we propose SmartSSO, a framework that automates the account linkage process by analyzing user routines and behavior during login processes. Our experiments on a large dataset show that SmartSSO achieves over 98% accuracy in hit-precision.
INFORMATION SCIENCES
(2024)
Article
Computer Science, Information Systems
Renchao Wu, Jianjun He, Xin Li, Zuguo Chen
Summary: This paper proposes a memetic algorithm with fuzzy-based population control (MA-FPC) to solve the joint order batching and picker routing problem (JOBPRP). The algorithm incorporates batch exchange crossover and a two-level local improvement procedure. Experimental results show that MA-FPC outperforms existing algorithms in terms of solution quality.
INFORMATION SCIENCES
(2024)
Article
Computer Science, Information Systems
Guoxiang Zhong, Fagui Liu, Jun Jiang, Bin Wang, C. L. Philip Chen
Summary: In this study, we propose the AMFormer framework to address the problem of mixed normal and anomaly samples in deep unsupervised time-series anomaly detection. By refining the one-class representation and introducing the masked operation mechanism and cost sensitive learning theory, our approach significantly improves anomaly detection performance.
INFORMATION SCIENCES
(2024)
Article
Computer Science, Information Systems
Jin Zhou, Kang Zhou, Gexiang Zhang, Ferrante Neri, Wangyang Shen, Weiping Jin
Summary: In this paper, the authors focus on the issue of multi-objective optimisation problems with redundant variables and indefinite objective functions (MOPRVIF) in practical problem-solving. They propose a dual data-driven method for solving this problem, which consists of eliminating redundant variables, constructing objective functions, selecting evolution operators, and using a multi-objective evolutionary algorithm. The experiments conducted on two different problem domains demonstrate the effectiveness, practicality, and scalability of the proposed method.
INFORMATION SCIENCES
(2024)
Article
Computer Science, Information Systems
Georgios Charizanos, Haydar Demirhan, Duygu Icen
Summary: This article proposes a new fuzzy logistic regression framework that addresses the problems of separation and imbalance while maintaining the interpretability of classical logistic regression. By fuzzifying binary variables and classifying subjects based on a fuzzy threshold, the framework demonstrates superior performance on imbalanced datasets.
INFORMATION SCIENCES
(2024)