Article
Computer Science, Information Systems
Aiguo Wang, Jing Yang, Ning An
Summary: This study formalizes the problem of missing values in microarray data under a regularized sparse framework and proposes local learning-based imputation models with elastic net regularization to accurately estimate missing entries in gene expression profiles. Experimental results demonstrate the superiority of elastic net over other methods in terms of statistical analysis metrics.
Article
Computer Science, Artificial Intelligence
Manar D. Samad, Sakib Abrar, Norou Diawara
Summary: This paper proposes methods to improve the imputation accuracy of the MICE algorithm by using ensemble learning and deep neural networks. The results of extensive analyses on multiple datasets show that the proposed methods outperform other state-of-the-art imputation algorithms, leading to better imputation accuracy and classification accuracy.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Biochemical Research Methods
Xinshan Zhu, Jiayu Wang, Biao Sun, Chao Ren, Ting Yang, Jie Ding
Summary: By using ensemble learning, this study combines multiple single imputation methods to improve imputation performance, allowing for more efficient utilization of known data information for missing data imputation.
BMC BIOINFORMATICS
(2021)
Article
Biochemical Research Methods
Ron Zeira, Max Land, Alexander Strzalkowski, Benjamin J. Raphael
Summary: PASTE is a method for aligning and integrating spatial transcriptomics data from adjacent tissue slices, which utilizes transcriptomic similarity and spatial coordinates to increase downstream analysis power. PASTE accurately aligns spots, constructs 3D alignments or integrates into a consensus slice, and improves the identification of cell types and differentially expressed genes.
Article
Engineering, Multidisciplinary
Awadhesh K. Pandey, G. N. Singh, Neveen Sayed-Ahmed, Hanaa Abu-Zinadah
Summary: The treatment of incomplete data is crucial in statistical data analysis, and missing values can create challenges for researchers. Utilizing imputation methods with ancillary information can lead to improved estimation accuracy.
ALEXANDRIA ENGINEERING JOURNAL
(2021)
Article
Multidisciplinary Sciences
Hannah Voss, Simon Schlumbohm, Philip Barwikowski, Marcus Wurlitzer, Matthias Dottermusch, Philipp Neumann, Hartmut Schlueter, Julia E. Neumann, Christoph Krisp
Summary: HarmonizR is an efficient tool for missing data tolerant experimental variance reduction, which does not require data imputation and can be easily adjusted for individual dataset properties and user preferences. It demonstrated successful data harmonization for different tissue preservation techniques, LC-MS/MS instrumentation setups, and quantification approaches, and outperformed data imputation methods in detecting significant proteins.
NATURE COMMUNICATIONS
(2022)
Article
Computer Science, Information Systems
Azza Ali, Mervat Abu-Elkheir, Ahmed Atwan, Mohammed Elmogy
Summary: This study proposes a Fuzzy K-Top Matching Value (FKTM) method for imputing missing values, which uses intelligent estimates based on similar records to fill in missing numerical and categorical data, reducing bias. The proposed approach outperforms existing strategies and achieves high accuracy in experiments on Immunotherapy and Cryotherapy datasets.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2023)
Article
Computer Science, Artificial Intelligence
Renato Bruni, Cinzia Daraio, Davide Aureli
Summary: Educational institutions data are crucial for analyses on educational systems, but often contain missing values. This study focuses on European Tertiary Education Register data and proposes artificial data imputation techniques to address missing values, achieving close proximity between imputed and original values.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Wei-Chao Lin, Chih-Fong Tsai, Jia Rong Zhong
Summary: This study compares the performance of multilayer perceptron (MLP) and deep belief networks (DBN) in missing value imputation, with DBN performing the best. In addition, the research finds that when considering the discretization of continuous data, the choice of imputation algorithm is more important than the order in which the two steps are combined.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Caio Ribeiro, Alex A. Freitas
Summary: This article proposes a data-driven missing value imputation approach that performs feature-wise selection of the best imputation method, resulting in more accurate estimations for missing data and better performing classifiers in human ageing studies. Additionally, longitudinal data-specific imputation methods were observed to have very accurate estimations, highlighting the importance of utilizing temporal information for machine learning applications.
ARTIFICIAL INTELLIGENCE REVIEW
(2021)
Article
Multidisciplinary Sciences
Harvard Wai Hann Hui, Weijia Kong, Hui Peng, Wilson Wen Bin Goh
Summary: Data analysis is complex due to technical issues such as missing values and batch effects. Existing methods for missing value imputation (MVI) and batch correction do not consider the confounding impact of MVI on batch correction. Modelling three imputation strategies, it was found that explicit consideration of batch covariates is important for improved outcomes, while certain strategies may generate errors, diluting batch effects and increasing noise. Careless imputation in the presence of non-negligible covariates like batch effects should be avoided.
SCIENTIFIC REPORTS
(2023)
Article
Computer Science, Artificial Intelligence
Yongshun Gong, Zhibin Li, Jian Zhang, Wei Liu, Yilong Yin, Yu Zheng
Summary: As urbanization continues to develop, gathering and utilizing massive amounts of urban statistical data has become increasingly important in various domains. However, these fine-grained statistical data often suffer from missing values, which can distort urban analysis. To address this issue, we propose an improved spatial multi-kernel learning method that incorporates adaptive-weight non-negative matrix factorization to accurately impute missing values.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Engineering, Multidisciplinary
Han Honggui, Sun Meiting, Wu Xiaolong, Li Fangyu
Summary: This article proposes a double-cycle weighted imputation (DCWI) method to deal with multiple missing patterns in the wastewater treatment process. The method maximizes the utilization of available information to improve imputation accuracy and experimental results show its superiority over comparison methods.
SCIENCE CHINA-TECHNOLOGICAL SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Tao Su, Ying Shi, Jicheng Yu, Changxi Yue, Feng Zhou
Summary: A novel statistical and machine learning-based imputation method is proposed for handling missing values in smart grid data, showing superior performance compared to commonly used methods. The method combines one-dimensional interpolation and linear compensation to capture global and local variations, reducing RMSE by 29.19% and MAE by 44.73% on average, with the best R-2 closest to 1.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Eunseo Oh, Hyunsoo Lee
Summary: As the importance of data-based predictive maintenance frameworks rises, missing values in industrial data become an emerging issue. This study proposes a missing value estimation method based on Gaussian progress regression and corrects them using quantum mechanics-based stochastic differential equation and Ito's lemma. This method enables more accurate data analysis.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Chemistry, Analytical
Juan M. Corchado, Pablo Chamoso, Guillermo Hernandez, Agustin San Roman Gutierrez, Alberto Rivas Camacho, Alfonso Gonzalez-Briones, Francisco Pinto-Santos, Enrique Goyenechea, David Garcia-Retuerta, Maria Alonso-Miguel, Beatriz Bellido Hernandez, Diego Valdeolmillos Villaverde, Manuel Sanchez-Verdejo, Pablo Plaza-Martinez, Manuel Lopez-Perez, Sergio Manzano-Garcia, Ricardo S. Alonso, Roberto Casado-Vara, Javier Prieto Tejedor, Fernando de la Prieta, Sara Rodriguez-Gonzalez, Javier Parra-Dominguez, Mohd Saberi Mohamad, Saber Trabelsi, Enrique Diaz-Plaza, Jose Alberto Garcia-Coria, Tan Yigitcanlar, Paulo Novais, Sigeru Omatu
Summary: This paper presents an efficient cyberphysical platform for smart city management, which can utilize various data sources and includes a complete artificial intelligence suite, enabling adaptation to new requirements and running effective computational and artificial intelligence algorithms.
Article
Neurosciences
Shu Chai Ching, Lim Jing Wen, Nor Ismaliza Mohd Ismail, Irene Looi, Cheah Wee Kooi, Long Soo Peng, Lee Soon Mui, Jayashamani Tamibmaniam, Prema Muninathan, Ong Beng Hooi, Siti Maisarah Md Ali, Muhammad Radzi Abu Hassan, Mohd Saberi Mohamad, Lyn R. Griffiths, Loo Keat Wei
Summary: This study found that the SLC17A3 rs9379800 polymorphism and its gene expression are significantly associated with ischemic stroke risk among the Malay population in the Northern region of Malaysia. However, no significant associations were observed for PITX2, NINJ2, TWIST1, Rasip1, and MUT polymorphisms with ischemic stroke risk. Lower mRNA expression levels of Rasip1, SLC17A3, MUT and FERD3L were observed among cases.
JOURNAL OF STROKE & CEREBROVASCULAR DISEASES
(2021)
Review
Engineering, Chemical
Aina Umairah Mazlan, Noor Azida Sahabudin, Muhammad Akmal Remli, Nor Syahidatul Nadiah Ismail, Mohd Saberi Mohamad, Hui Wen Nies, Nor Bakiah Abd Warif
Summary: This paper discusses the importance of using data-driven models with predictive ability in medical and healthcare, particularly focusing on the application of machine learning (ML) and deep learning (DL) in cancer classification. While various methods have been applied to cancer classification, successful techniques mainly revolve around supervised and deep learning methods.
Article
Mathematical & Computational Biology
Mei Yen Man, Mohd Saberi Mohamad, Yee Wen Choon, Mohd Arfian Ismail
Summary: Microorganisms commonly produce high-demand industrial products like fuels and vitamins, and microbial strains can be optimized through metabolic engineering, which includes gene knockout to maximize production rates.
JOURNAL OF INTEGRATIVE BIOINFORMATICS
(2021)
Article
Mathematical & Computational Biology
Mohd Izzat Yong, Mohd Saberi Mohamad, Yee Wen Choon, Weng Howe Chan, Hasyiya Karimah Adli, Khairul Nizar Syazwan Wsw, Nooraini Yusoff, Muhammad Akmal Remli
Summary: Metabolic engineering plays an important role in biomass production, particularly in microbial biomass production. In order to address the unrealistic flux distribution issue in prior work, a hybrid method of Bees Algorithm and Regulatory On/Off Minimization (BAROOM) was used.
JOURNAL OF INTEGRATIVE BIOINFORMATICS
(2022)
Article
Computer Science, Theory & Methods
Jun Bin Tan, Yee Wen Choon, Kohbalan Moorthy, Hasyiya Karimah Adli, Muhammad Akmal Remli, Mohd Arfian Ismail, Zuwairie Ibrahim, Mohd Saberi Mohamad
Summary: This paper proposes a hybrid approach of ant colony optimization-genetic algorithm-flux balance analysis (ACOGAFBA) to enhance the succinic acid production of E. coli by identifying genes to be knocked out. The results show that ACOGAFBA can identify the set of knockout genes to improve succinic acid production in E. coli.
INTERNATIONAL JOURNAL OF MODELING SIMULATION AND SCIENTIFIC COMPUTING
(2023)
Review
Chemistry, Analytical
Hasyiya Karimah Adli, Muhammad Akmal Remli, Khairul Nizar Syazwan Wan Salihin Wong, Nor Alina Ismail, Alfonso Gonzalez-Briones, Juan Manuel Corchado, Mohd Saberi Mohamad
Summary: As the most popular technologies of the 21st century, AI and IoT have played a vital role in transforming the agricultural industry during the pandemic. The convergence of AI and IoT has sparked interest in AIoT, which significantly addresses challenges in agriculture such as pest management and post-harvest management. This paper presents a systematic literature review of AIoT, highlighting its current progress, applications, advantages, and challenges for adoption in modern agriculture.
Article
Mathematical & Computational Biology
Ahmad Muhaimin Ismail, Muhammad Akmal Remli, Yee Wen Choon, Nurul Athirah Nasarudin, Nor-Syahidatul N. Ismail, Mohd Arfian Ismail, Mohd Saberi Mohamad
Summary: Accurate kinetic parameters are necessary for analyzing metabolic pathways in systems biology. The fermentation pathway in the Saccharomyces cerevisiae kinetic model can be simulated to save time in the optimization process. Parameter estimation is conducted to obtain optimal values for parameters related to the fermentation process, which is essential to avoid erroneous conclusions. The Artificial Bee Colony algorithm (ABC) is proposed to estimate the parameters in the fermentation pathway, providing more accurate values compared to other estimation algorithms.
JOURNAL OF INTEGRATIVE BIOINFORMATICS
(2023)
Review
Pharmacology & Pharmacy
Marim Elkashlan, Rahaf M. Ahmad, Malak Hajar, Fatma Al Jasmi, Juan Manuel Corchado, Nurul Athirah Nasarudin, Mohd Saberi Mohamad
Summary: The emergence of SARS-CoV-2 has posed a serious threat worldwide, calling for efficient solutions. Drug repurposing, particularly through machine learning, offers a promising approach to identify potential inhibitors. Reliable digital databases are important for data extraction in machine learning-based drug repurposing.
FRONTIERS IN PHARMACOLOGY
(2023)
Review
Computer Science, Artificial Intelligence
Yingna Zhong, Kauthar Mohd Daud, Ain Najiha Binti Mohamad Nor, Richard Adeyemi Ikuesan, Kohbalan Moorthy
Summary: Handwritten character recognition is invaluable in society, especially for Chinese characters. Convolutional neural networks have achieved outstanding results in offline handwritten character recognition.
JOURNAL OF ADVANCED COMPUTATIONAL INTELLIGENCE AND INTELLIGENT INFORMATICS
(2023)
Review
Computer Science, Information Systems
Sherzod Turaev, Saja Al-Dabet, Aiswarya Babu, Zahiriddin Rustamov, Jaloliddin Rustamov, Nazar Zaki, Mohd Saberi Mohamad, Chu Kiong Loo
Summary: Body language is a nonverbal form of communication that includes movements, postures, gestures, and expressions of the body. It expresses human feelings, thoughts, and intentions, and also reveals physical and psychological health conditions. The importance of studying the body language of people with health conditions can be seen through various reports in literature.
Proceedings Paper
Computer Science, Cybernetics
Mohd Izzat Yong, Mohd Saberi Mohamad, Yee Wen Choon, Weng Howe Chan, Hasyiya Karimah Adli, Khairul Nizar W. S. W. Syazwan, Nooraini Yusoff, Muhammad Akmal Remli
Summary: Metabolic engineering is widely used for biomass production using microorganisms, and metabolic network models are employed for optimizing production and suggesting modifications. The BAROOM method, a hybrid of Bees Algorithm and Regulatory On/Off Minimization, improves lactate production in a model organism by identifying optimal genes to be knocked out, outperforming other methods.
PRACTICAL APPLICATIONS OF COMPUTATIONAL BIOLOGY & BIOINFORMATICS, PACBB 2021
(2022)
Article
Computer Science, Artificial Intelligence
Wan Ting Leong, Mohd Saberi Mohamad, Kohbalan Moorthy, Yee Wen Choon, Hasyiya Karimah Adli, Khairul Nizar W. S. W. Syazwan, Loo Keat Wei, Nazar Zaki
Summary: Metabolic engineering using microorganisms is a method to produce high-demand industrial products. This paper proposes a hybrid method of firefly algorithm and dynamic flux balance analysis to predict the gene knockout list for ethanol production.
INTERNATIONAL JOURNAL OF SWARM INTELLIGENCE RESEARCH
(2022)