More Like this

1. Design of the network intrusion detection systems for the internet of things infrastructure using machine learning algorithms

   https://doi.org/10.1117/12.2584499  

   Banadaki, Yaser M.; Brook, Jalen; Sharifi, Safura (March 2021, Design of Intrusion Detection Systems on the Internet of Things Infrastructure using Machine Learning Algorithms)

   Meyendorf, Norbert G.; Farhangdoust, Saman (Ed.)

   Network intrusion detection systems (NIDS) for Internet-of-Things (IoT) infrastructure are among the most critical tools to ensure the protection and security of networks against malicious cyberattacks. This paper employs four machine learning algorithms and evaluates their performance in NIDS considering the accuracy, precision, recall, and F-score. The comparative analysis conducted using the CICIDS2017 dataset reveals that the Boosted machine learning techniques perform better than the other algorithms reaching the predicted accuracy of above 99% in detecting cyberattacks. Such ML-based attack detectors also have the largest weighted metrics of F1-score, precision, and recall. The results assist the network engineers in choosing the most effective machine learning-based NIDS to ensure network security for today’s growing IoT network traffic. 

   more » « less
2. Impact of Virtual Reality on Motor-Skill Performance in Children with Autism Spectrum Disorder

   Tran, Ngoc; Liang, Irene; Liu, Ting; Valles, Damian (June 2024, ASEE)

   Autism Spectrum Disorder (ASD) is a neurodevelopmental condition often associated with delayed motor skills. The Motor Assessment Battery for Children – Second Edition (MABC-2) is a standardized motor assessment for identifying motor delays pertaining to ASD. It evaluates fine and gross motor tasks across three domains: Manual Dexterity, Aiming & Catching, and Balance. These tasks are categorized into three age bands: 3-6, 7-10, and 11-16. Virtual Reality (VR) has emerged as a promising intervention in the ASD realm. This study aimed to investigate the potential of VR to assist children with ASD in performing the gross motor skills (i.e., ball skills and balance) in the MABC-2. The children who participated in the study were attendees of a local Autism Summer Camp. Our research focused on adapting motor tasks for ages 7-10 (i.e., Age Band 2) to VR, as most campers fell in this age range. Within the VR environment, children could observe avatar demonstrations and practice motor skills in a highly immersive setting. The VR environment featured avatars demonstrating ball skills and balancing tasks. Developed with the Unity game engine, 3D software Blender, C# scripting, and mixed reality toolkits, this environment was tested on the Meta Quest 2 Oculus. The children's gross motor skill performance was scored before and after VR interactions. The test standard scores were categorized through a traffic-light scoring system comprising red, amber, and green zones. A standard score ≤4 is classified in the red zone, indicating a significant movement difficulty; a standard score >4 and ≤7 is classified in the amber zone, indicating a risk for movement difficulty; and a standard score >7 is classified in the green zone, indicating no movement difficulty detected. Following the VR intervention, we observed a notable improvement in the balance score (p < 0.05). Furthermore, using the Random Forest machine learning model, we analyzed a combined dataset of MABC-2 scores from 250 children across all age bands from the Autism Summer Camp in previous years and the MABC-2 scores from the 18 children in the present study. Our analysis revealed that Balance was crucial in classifying children with ASD with motor delays, with an importance score of 0.195, nearly double that of Manual Dexterity and Aiming & Catching. When the model was exclusively applied to the Balance component score, it achieved an impressive accuracy rate of 91% in identifying children with ASD. In summary, our findings underscore the promise of VR in enhancing balance among children with ASD. The Random Forest analysis reaffirmed the significant role of balance in identifying children with ASD. Given its precision in detecting children with ASD based on their balance performance, we anticipate the potential of future machine learning advancements in this field. Our research validates the effectiveness of a VR-based approach and emphasizes the significance of collaborative research in providing valuable support to the underserved ASD population. 

   more » « less
3. Understanding the Role of Connectivity Dynamics of Resting-State Functional MRI in the Diagnosis of Autism Spectrum Disorder: A Comprehensive Study

   https://doi.org/10.3390/bioengineering10010056  

   ElNakieb, Yaser; Ali, Mohamed T.; Elnakib, Ahmed; Shalaby, Ahmed; Mahmoud, Ali; Soliman, Ahmed; Barnes, Gregory Neal; El-Baz, Ayman (January 2023, Bioengineering)

   In addition to the standard observational assessment for autism spectrum disorder (ASD), recent advancements in neuroimaging and machine learning (ML) suggest a rapid and objective alternative using brain imaging. This work presents a pipelined framework, using functional magnetic resonance imaging (fMRI) that allows not only an accurate ASD diagnosis but also the identification of the brain regions contributing to the diagnosis decision. The proposed framework includes several processing stages: preprocessing, brain parcellation, feature representation, feature selection, and ML classification. For feature representation, the proposed framework uses both a conventional feature representation and a novel dynamic connectivity representation to assist in the accurate classification of an autistic individual. Based on a large publicly available dataset, this extensive research highlights different decisions along the proposed pipeline and their impact on diagnostic accuracy. A large publicly available dataset of 884 subjects from the Autism Brain Imaging Data Exchange I (ABIDE-I) initiative is used to validate our proposed framework, achieving a global balanced accuracy of 98.8% with five-fold cross-validation and proving the potential of the proposed feature representation. As a result of this comprehensive study, we achieve state-of-the-art accuracy, confirming the benefits of the proposed feature representation and feature engineering in extracting useful information as well as the potential benefits of utilizing ML and neuroimaging in the diagnosis and understanding of autism. 

   more » « less
4. Recursive Feature Elimination with Cross Validation for Alzheimer’s Disease Classification using Cognitive Exam Scores

   https://doi.org/10.1109/IMSA58542.2023.10217660  

   Freytes, Christian Yaphet; Perry Mayrand, Robin; Sawada, Luana Okino; Yan Liang, Thony; Curiel Cid, Rosie E.; Burke, Shanna; Loewenstein, David; Duara, Ranjan; Adjouadi, Malek (July 2023, 2023 Intelligent Methods, Systems, and Applications (IMSA))

   Prodromal detection of Alzheimer’s Disease(AD) is a substantial challenge in the research community. Among the tools used in AD diagnosis, cognitive exams are standard in most procedures. However, the barrage of cognitive examinations is both time and resource consuming. With the use of Machine Learning, Feature Elimination (FE) can be combined with classification algorithms to determine which cognitive exams are best suited for diagnosis. Using the results of FE, it can be determined if subsections of different composite scores can be combined to create a new enhanced and exhaustive exam. This paper implements a Recursive Feature Elimination with Cross Validation (RFECV) machine learning algorithm to determine which cognitive exams perform best for AD classification tasks. Out of 119 features, an average of 16 features were selected as optimal. These optimal features average 75% Accuracy, 70% Precision, and 75% Recall and an F1 Weighted score of 71% in classification. 

   more » « less
5. Proficient Annotation Recommendation in a Biomedical Content Authoring Environment

   https://doi.org/10.1007/978-3-031-21422-6_11  

   Abbas, Asim; Mbouadeu, Steve; Bisram, Avinash; Iqbal, Nadeem; Syed Ahmad Chan Bukhari (November 2022, In book: Knowledge Graphs and Semantic Web, 4th Iberoamerican Conference and third Indo-American Conference, KGSWC 2022, Madrid, Spain, November 21–23, 2022, Proceedings)

   Villazón-Terrazas, B. (Ed.)

   Given the ubiquity of unstructured biomedical data, significant obstacles still remain in achieving accurate and fast access to online biomedical content. Accompanying semantic annotations with a growing volume biomedical content on the internet is critical to enhancing search engines’ context-aware indexing, improving search speed and retrieval accuracy. We propose a novel methodology for annotation recommendation in the biomedical content authoring environment by introducing the socio-technical approach where users can get recommendations from each other for accurate and high quality semantic annotations. We performed experiments to record the system level performance with and without socio-technical features in three scenarios of different context to evaluate the proposed socio-technical approach. At a system level, we achieved 89.98% precision, 89.61% recall, and an 89.45% F1-score for semantic annotation recollection. Similarly, a high accuracy of 90% is achieved with the socio-technical approach compared to without, which obtains 73% accuracy. However almost equable precision, recall, and F1- score of 90% is gained by scenario-1 and scenario-2, whereas scenario-3 achieved relatively less precision, recall and F1-score of 88%. We conclude that our proposed socio-technical approach produces proficient annotation recommendations that could be helpful for various uses ranging from context-aware indexing to retrieval accuracy. 

   more » « less