Article
Computer Science, Artificial Intelligence
Asuncion Jimenez-Cordero, Sebastian Maldonado
Summary: Functional Data Analysis (FDA) is important, but classifying hybrid functional data with both functional and static covariates is challenging. This paper proposes an embedded feature selection approach for SVM classification, optimizing bandwidths and SVM parameters to improve classification rates. The methodology outperformed 17 other approaches, demonstrating robustness through sensitivity analysis.
APPLIED INTELLIGENCE
(2021)
Article
Automation & Control Systems
Hui-Ping Yin, Hai-Peng Ren
Summary: A symbol detection method based on genetic algorithm support vector machine is proposed to improve the bit error rate performance and simplify the symbol detection process in chaotic baseband wireless communication systems. By converting symbol decoding into a binary classification process, the proposed method outperforms traditional methods in terms of performance.
JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS
(2021)
Correction
Computer Science, Artificial Intelligence
Ala' M. Al-Zoubi, Mohammad A. Hassonah, Ali Asghar Heidari, Hossam Faris, Majdi Mafarja, Ibrahim Aljarah
Summary: During the typesetting process, there was an error in the publication of the authors' affiliations, which has since been corrected.
Article
Computer Science, Artificial Intelligence
Swarnajyoti Patra, Barnali Barman
Summary: A novel feature selection technique based on rough set theory is proposed in this work to reduce the dimensionality of hyperspectral images. The technique defines a new criterion by combining relevance and significance measures, and adopts a first order incremental search to select the most informative bands, showing better results compared to existing techniques. The proposed dependency measure definition is completely parameter free and computationally very cheap.
APPLIED SOFT COMPUTING
(2021)
Article
Computer Science, Artificial Intelligence
A. Ramirez-Morales, J. U. Salmon-Gamboa, Jin Li, A. G. Sanchez-Reyna, A. Palli-Valappil
Summary: This paper presents experimental studies on ensembles of binary classifiers based on individual support vector machines. The proposed GenBoost-SVM method uses an adaptive boosting algorithm to construct these ensembles. Genetic algorithms are used for pre-selections to reduce training times and address imbalanced data challenges. Diversity and early stopping are also considered in the ensembles to reduce generalization error. The study proposes 56 different types of ensembles that vary in support vector machine kernels, genetic selections, and diversity. The results show that the ensembles with genetic selections and diversity perform competitively compared to popular classifiers, and they outperform most of them for imbalanced data. The study also demonstrates that using different support vector machine kernels leads to enhanced performances. This is the first study to combine adaptive boosted ensembles, genetic selections, and support vector machines.
APPLIED INTELLIGENCE
(2023)
Article
Medicine, General & Internal
Essam H. H. Houssein, Hager N. N. Hassan, Nagwan Abdel Samee, Mona M. M. Jamjoom
Summary: Accurately categorizing cancers using microarray data is crucial, and computational intelligence approaches have been employed to analyze gene expression data. Selecting informative genes is believed to be the most difficult part of cancer diagnosis, and the proposed RUN-SVM approach combines the Runge Kutta optimizer with a support vector machine to select significant genes in cancer tissue detection. The approach is tested on different microarray datasets and statistically outperforms competing algorithms due to its innovative search technique.
Article
Computer Science, Artificial Intelligence
Yinan Guo, Zirui Zhang, Fengzhen Tang
Summary: Feature selection is important in machine learning to reduce complexity and simplify interpretation. A novel non-linear method proposed in this paper uses kernelized multi-class support vector machines and fast recursive feature elimination to select features that work well for all classes, resulting in lower computational time complexity.
PATTERN RECOGNITION
(2021)
Article
Computer Science, Artificial Intelligence
M. Tanveer, A. Tiwari, R. Choudhary, M. A. Ganaie
Summary: This study proposes a novel large scale pinball twin support vector machine (LPTWSVM) to address the limitations of the twin support vector machines (TWSVMs), using a unique pinball loss function and improving model performance by eliminating matrix inversion calculation and minimizing structural risk.
Correction
Computer Science, Artificial Intelligence
Ala' M. Al-Zoubi, Mohammad A. Hassonah, Ali Asghar Heidari, Hossam Faris, Majdi Mafarja, Ibrahim Aljarah
Summary: The affiliation information of authors Ali Asghar Heidari and Majdi Mafarja was mistakenly published during typesetting and has been corrected.
Article
Computer Science, Information Systems
Mohammad Aslani, Stefan Seipel
Summary: A novel instance selection method called BPLSH is designed to address the high computational complexity of SVMs in the training phase on large datasets. Experimental results show that BPLSH outperforms other methods in terms of classification accuracy, preservation rate, and execution time.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Information Systems
Xingyu Wu, Bingbing Jiang, Kui Yu, Huanhuan Chen
Summary: The article introduces a separation and recovery MB discovery algorithm (SRMB) that improves the accuracy and data efficiency of MB discovery through a two-phase discovery strategy to find more true positives. Experimental results demonstrate the effectiveness and superiority of SRMB in terms of MB discovery, BN structure learning, and feature selection.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Information Systems
Essam H. Houssein, Diaa Salama Abdelminaam, Hager N. Hassan, Mustafa M. Al-Sayed, Emad Nabil
Summary: This study investigates the importance of gene selection in cancer classification, proposing a BMO-SVM algorithm for selecting the most predictive and informative genes. Experimental comparisons with traditional metaheuristic optimization algorithms validate the high efficiency of the proposed algorithm.
Article
Computer Science, Artificial Intelligence
Khalid Y. Aram, Sarah S. Lam, Mohammad T. Khasawneh
Summary: This article introduces the Alternated Sorting Method Genetic Algorithm (ASMGA), which is a hybrid wrapper-filter algorithm for simultaneous feature selection and model selection for Support Vector Machine (SVM) classifiers. ASMGA approximates a set of Pareto optimal feature subsets based on three objectives: cost-sensitive error rate, feature subset size, and Max-Margin Feature Selection (MMFS)-based estimates of feature relevance and redundancy. The proposed algorithm outperforms canonical GA and NSGA-II on benchmark datasets, showing the potential of ASMGA in cost-sensitive feature selection.
KNOWLEDGE-BASED SYSTEMS
(2023)
Review
Behavioral Sciences
Reihaneh Ahmadi, Sama Rahimi-Jafari, Mahnaz Olfati, Nooshin Javaheripour, Farnoosh Emamian, Mohammad Rasoul Ghadami, Habibolah Khazaie, David C. Knight, Masoud Tahmasian, Amir A. Sepehry
Summary: Posttraumatic stress disorder (PTSD) is strongly associated with insomnia, and the prevalence of insomnia in PTSD patients is high. Screening and managing insomnia in PTSD patients are of great importance.
NEUROSCIENCE AND BIOBEHAVIORAL REVIEWS
(2022)
Article
Emergency Medicine
Danielle Kovalsky, Michael B. Roberts, Brian Freeze, Jeena Moss, Christopher W. Jones, Hope Kilgannon, Donald E. Edmondson, Stephen Trzeciak, Brian M. Fuller, Brian W. Roberts
Summary: Patients presenting to the emergency department for respiratory or cardiovascular emergencies who develop clinically significant PTSD symptoms 30 days post-discharge are at increased risk for hospital readmission within 24 months post-discharge.
ACADEMIC EMERGENCY MEDICINE
(2022)
Article
Public, Environmental & Occupational Health
Jaimie L. Gradus, Anthony J. Rosellini, Erzsebet Horvath-Puho, Tammy Jiang, Amy E. Street, Isaac Galatzer-Levy, Timothy L. Lash, Henrik T. Sorensen
Summary: This study utilized machine learning to examine sex-specific risk profiles for suicide attempts in Danish nationwide registry data. Findings identified substance use disorders/treatment, prescribed psychiatric medications, previous poisoning diagnoses, and stress disorders as important factors for predicting suicide attempts among men and women, with high-risk individuals in the top 5% accounting for a significant percentage of all attempts. The research highlights novel risk factors and urges for the focus of machine learning suicide research on high-risk subpopulations.
AMERICAN JOURNAL OF EPIDEMIOLOGY
(2021)
Article
Psychiatry
Katharina Schultebraucks, Karmel W. Choi, Isaac R. Galatzer-Levy, George A. Bonanno
Summary: The study investigated the development of depression and resilience in older adults after major life stressors, finding that multivariate PGS profiles provide information to accurately distinguish between different stress-related risk and resilience phenotypes.
Article
Neurosciences
Katharina Schultebraucks, Marit Sijbrandij, Isaac Galatzer-Levy, Joanne Mouthaan, Miranda Olff, Mirjam van Zuiden
Summary: This study utilized machine learning to analyze biomedical data collected within 48 hours post-trauma, successfully predicting individual risk for long-term PTSD and enabling future early risk detection, providing further insights into the complex etiology of PTSD.
NEUROBIOLOGY OF STRESS
(2021)
Article
Neurosciences
Shelly Sheynin, Lior Wolf, Ziv Ben-Zion, Jony Sheynin, Shira Reznik, Jackob Nimrod Keynan, Roee Admon, Arieh Shalev, Talma Hendler, Israel Liberzon
Summary: This study introduces a novel neural network model that utilizes fMRI data to predict PTSD symptoms in individuals exposed to trauma. The results show that this method outperforms previous techniques in predicting PTSD symptoms and can also predict PTSD symptom clusters and persistence. This is the first deep learning approach applied to fMRI data for predicting clinical outcomes related to PTSD.
Article
Neurosciences
Adriana Lori, Katharina Schultebraucks, Isaac Galatzer-Levy, Nikolaos P. Daskalakis, Seyma Katrinli, Alicia K. Smith, Amanda J. Myers, Ryan Richholt, Matthew Huentelman, Guia Guffanti, Stefan Wuchty, Felicia Gould, Philip D. Harvey, Charles B. Nemeroff, Tanja Jovanovic, Ekaterina S. Gerasimov, Jessica L. Maples-Keller, Jennifer S. Stevens, Vasiliki Michopoulos, Barbara O. Rothbaum, Aliza P. Wingo, Kerry J. Ressler
Summary: This study aimed to identify trajectory-based biomarkers using blood transcriptomes after trauma exposure. GRIN3B and AMOTL1 blood mRNA levels were significantly associated with chronic vs. resilient post-trauma symptom trajectories. Further genetic analysis revealed a potential association between GRIN3B variants and PTSD, suggesting GRIN3B may play a role in PTSD manifestation.
NEUROPSYCHOPHARMACOLOGY
(2021)
Article
Psychiatry
Jeanette Bonde Pollmann, Anni B. S. Nielsen, Soren Bo Andersen, Karen-Inge Karstoft
Summary: Previous research has shown a link between social support and PTSD symptoms in military personnel. This study examines how changes in perceived social support from pre- to 2.5 year post-deployment are associated with levels of PTSD symptoms. The results suggest that deterioration in perceived social support increases the risk of elevated PTSD symptoms post-deployment.
SOCIAL PSYCHIATRY AND PSYCHIATRIC EPIDEMIOLOGY
(2022)
Editorial Material
Psychiatry
Arieh Y. Shalev, Anna C. Barbano
PSYCHIATRY-INTERPERSONAL AND BIOLOGICAL PROCESSES
(2021)
Article
Neurosciences
Adam X. Maihofer, Karmel W. Choi, Jonathan R. Coleman, Nikolaos P. Daskalakis, Christy A. Denckla, Elizabeth Ketema, Rajendra A. Morey, Renato Polimanti, Andrew Ratanatharathorn, Katy Torres, Aliza P. Wingo, Clement C. Zai, Allison E. Aiello, Lynn M. Almli, Ananda B. Amstadter, Soren B. Andersen, Ole A. Andreassen, Paul A. Arbisi, Allison E. Ashley-Koch, S. Bryn Austin, Esmina Avdibegovic, Anders D. Borglum, Dragan Babic, Marie Baekvad-Hansen, Dewleen G. Baker, Jean C. Beckham, Laura J. Bierut, Jonathan Bisson, Marco P. Boks, Elizabeth A. Bolger, Bekh Bradley, Meghan Brashear, Gerome Breen, Richard A. Bryant, Angela C. Bustamante, Jonas Bybjerg-Grauholm, Joseph R. Calabrese, Jose M. Caldas-de-Almeida, Chia-Yen Chen, Anders M. Dale, Shareefa Dalvie, Jurgen Deckert, Douglas L. Delahanty, Michelle F. Dennis, Seth G. Disner, Katharina Domschke, Laramie E. Duncan, Alma Dzubur Kulenovic, Christopher R. Erbes, Alexandra Evans, Lindsay A. Farrer, Norah C. Feeny, Janine D. Flory, David Forbes, Carol E. Franz, Sandro Galea, Melanie E. Garrett, Aarti Gautam, Bizu Gelaye, Joel Gelernter, Elbert Geuze, Charles F. Gillespie, Aferdita Goci, Scott D. Gordon, Guia Guffanti, Rasha Hammamieh, Michael A. Hauser, Andrew C. Heath, Sian M. J. Hemmings, David Michael Hougaard, Miro Jakovljevic, Marti Jett, Eric Otto Johnson, Ian Jones, Tanja Jovanovic, Xue-Jun Qin, Karen-Inge Karstoft, Milissa L. Kaufman, Ronald C. Kessler, Alaptagin Khan, Nathan A. Kimbrel, Anthony P. King, Nastassja Koen, Henry R. Kranzler, William S. Kremen, Bruce R. Lawford, Lauren A. M. Lebois, Catrin Lewis, Israel Liberzon, Sarah D. Linnstaedt, Mark W. Logue, Adriana Lori, Bozo Lugonja, Jurjen J. Luykx, Michael J. Lyons, Jessica L. Maples-Keller, Charles Marmar, Nicholas G. Martin, Douglas Maurer, Matig R. Mavissakalian, Alexander McFarlane, Regina E. McGlinchey, Katie A. McLaughlin, Samuel A. McLean, Divya Mehta, Rebecca Mellor, Vasiliki Michopoulos, William Milberg, Mark W. Miller, Charles Phillip Morris, Ole Mors, Preben B. Mortensen, Elliot C. Nelson, Merete Nordentoft, Sonya B. Norman, Meaghan O'Donnell, Holly K. Orcutt, Matthew S. Panizzon, Edward S. Peters, Alan L. Peterson, Matthew Peverill, Robert H. Pietrzak, Melissa A. Polusny, John P. Rice, Victoria B. Risbrough, Andrea L. Roberts, Alex O. Rothbaum, Barbara O. Rothbaum, Peter Roy-Byrne, Kenneth J. Ruggiero, Ariane Rung, Bart P. F. Rutten, Nancy L. Saccone, Sixto E. Sanchez, Dick Schijven, Soraya Seedat, Antonia Seligowski, Julia S. Seng, Christina M. Sheerin, Derrick Silove, Alicia K. Smith, Jordan W. Smoller, Scott R. Sponheim, Dan J. Stein, Jennifer S. Stevens, Martin H. Teicher, Wesley K. Thompson, Edward Trapido, Monica Uddin, Robert J. Ursano, Leigh Luella van den Heuvel, Miranda Van Hooff, Eric Vermetten, Christiaan H. Vinkers, Joanne Voisey, Yunpeng Wang, Zhewu Wang, Thomas Werge, Michelle A. Williams, Douglas E. Williamson, Sherry Winternitz, Christiane Wolf, Erika J. Wolf, Rachel Yehuda, Keith A. Young, Ross McD Young, Hongyu Zhao, Lori A. Zoellner, Magali Haas, Heather Lasseter, Allison C. Provost, Rany M. Salem, Jonathan Sebat, Richard A. Shaffer, Tianying Wu, Stephan Ripke, Mark J. Daly, Kerry J. Ressler, Karestan C. Koenen, Murray B. Stein, Caroline M. Nievergelt
Summary: This study combines a quantitative measurement of posttraumatic stress disorder (PTSD) phenotype with lifetime trauma exposure (LTE) information to identify novel risk loci and demonstrate a high genetic overlap between PTSD and LTE.
BIOLOGICAL PSYCHIATRY
(2022)
Article
Engineering, Biomedical
Qianliang Li, Maya Coulson Theodorsen, Ivana Konvalinka, Kasper Eskelund, Karen-Inge Karstoft, Soren Bo Andersen, Tobias S. Andersen
Summary: This study developed a machine learning framework to investigate a wide range of EEG biomarkers for PTSD identification. The classifiers achieved a balanced test accuracy of up to 62.9% for predicting PTSD patients, and successfully identified two subtypes within PTSD. Alpha connectivity in attention networks was found to be particularly important for prediction and positively correlated with arousal symptom scores.
JOURNAL OF NEURAL ENGINEERING
(2022)
Article
Psychology, Clinical
Karen-Inge Karstoft, Cherie Armour
Summary: The present study compared eight frequently used self-report measures of trauma exposure and found variation in item content and measurement heterogeneity. Moderate overlap was observed among the different scales, with a small number of exposures included in multiple scales. The implications of measurement heterogeneity for clinical research and trauma-related research are discussed.
JOURNAL OF TRAUMATIC STRESS
(2023)
Article
Psychiatry
Karen -Inge Karstoft, Kasper Eskelund, Jaimie L. Gradus, Soren B. Andersen, Lars R. Nissen
Summary: Military personnel deployed to war zones are at increased risk of mental health problems, but accurate models for predicting these outcomes have not been developed.
JOURNAL OF PSYCHIATRIC RESEARCH
(2023)
Article
Psychiatry
Sofie Folke, Karen-Inge Karstoft, Soren Bo Andersen, Thanos Karatzias, Lars Ravnborg Nissen, Anni B. S. Nielsen
Summary: The purpose of this study was to examine risk factors and comorbidities of ICD-11 PTSD and CPTSD in a large sample of previously deployed, treatment-seeking soldiers and veterans. The results showed that CPTSD is more common and debilitating compared to PTSD, and risk factors for CPTSD include exposure to warfare or combat, longer duration since the traumatic event, and being single.
JOURNAL OF PSYCHIATRIC RESEARCH
(2023)
Article
Psychiatry
Sara Dorthea Nielsen, Rune H. B. Christensen, Trine Madsen, Karen-Inge Karstoft, Line Clemmensen, Michael E. Benros
Summary: This study aimed to develop machine learning models capable of predicting suicide and non-fatal suicide attempt as separate outcomes in the first 30 days after discharge from a psychiatric inpatient stay. The study used nationwide Danish registry data and trained predictive models to achieve good performance in predicting suicide attempts.
ACTA PSYCHIATRICA SCANDINAVICA
(2023)
Article
Health Care Sciences & Services
Isaac Galatzer-Levy, Anzar Abbas, Anja Ries, Stephanie Homan, Laura Sels, Vidya Koesmahargyo, Vijay Yadav, Michael Colla, Hanne Scheerer, Stefan Vetter, Erich Seifritz, Urte Scholz, Birgit Kleim
Summary: This study used open-source deep learning algorithms to extract measurements of facial, vocal, and movement behaviors from video interviews, comparing them with the severity of suicide risk. The results showed that digital measurements of facial affect, movement, and speech prevalence had strong effect sizes and linear associations with the severity of suicidal ideation.
JOURNAL OF MEDICAL INTERNET RESEARCH
(2021)
Article
Psychiatry
Anzar Abbas, Katharina Schultebraucks, Isaac R. Galatzer-Levy
Summary: Digital health technologies are advancing the characterization of mental health and functioning in more objective, sensitive, and scalable ways. Novel approaches for digital phenotyping of mental health are categorized based on how biomarker data are collected, but each approach faces challenges in validation, regulatory approval, and integration.
PSYCHIATRIC ANNALS
(2021)