Leveraging transformers and explainable AI for Alzheimer's disease interpretability. by Humaira Anzum, Nabil Sadd Sammo, Shamim Akhter

“…Many researches have been undertaken to use computer vision on MRI images, and their accuracy ranges from 80-90%, new computer vision algorithms and cutting-edge transformers have the potential to improve this performance.We utilize advanced transformers and computer vision algorithms to enhance diagnostic accuracy, achieving an impressive 99% accuracy in categorizing Alzheimer's disease stages through translating RNA text data and brain MRI images in near-real-time. …”
Get full text

Energy management system design for high energy consuming enterprises integrating the Internet of Things and neural networks by Zhaolin Wang, Zhiping Zhang

“…The combination of neural network model prediction and optimization algorithms can achieve real-time monitoring, prediction, and optimization control of energy consumption. …”
Get full text

A Soft Sensor Based Inference Engine for Water Quality Assessment and Prediction by Micheal A Ogundero, Theophilus A Fashanu, Foluso O Agunbiade, Kehinde Orolu, Ahmed A Yinusa, Usman A Daudu, Muhammed O H Amuda

“…In outcomes, computational metrics of the pH prediction model returns Mean Squared Error (MSE) of 0.0163 for training and 0.1024 for validation. …”
Get full text

Diagnostic accuracy of artificial intelligence for obstructive sleep apnea detection: a systematic review by Sara Haghighat, Muhammed Joghatayi, Julien Issa, Sarina Azimian, Janet Brinz, Ali Ashkan, Akhilanand Chaurasia, Zahra Rahimian, Linda Sangalli

“…From the included articles, data were extracted regarding patients and datasets, type of AI model applied, accuracy report, and explainability of the AI model. …”
Get full text

Inferring Mechanical Properties of Wire Rods via Transfer Learning Using Pre-Trained Neural Networks by Adriany A. F. Eduardo, Gustavo A. S. Martinez, Ted W. Grant, Lucas B. S. Da Silva, Wei-Liang Qian

“…By proper calibration and fine-tuning, observed improvements over the standard CNN models are reflected by good training and test accuracies in order to predict the material’s mechanical properties, with efficiency demonstrated by the loss function’s rapid convergence. …”
Get full text

Comparison of light gradient boosting and logistic regression for interactomic hub genes in Porphyromonas gingivalis and Fusobacterium nucleatum-induced periodontitis with Alzheime... by Pradeep Kumar Yadalam, Shubhangini Chatterjee, Prabhu Manickam Natarajan, Carlos M. Ardila, Carlos M. Ardila

“…The accuracy of logistic regression and light gradient boosting was 67% and 60%, respectively.DiscussionThe logistic regression model demonstrated superior accuracy and balance compared to the light gradient boosting model, indicating its potential for future improvements in predicting hub genes in periodontal and Alzheimer's diseases.…”
Get full text

Callback time preference for prescreening visits among Black residents in the Boston area: findings from two randomized controlled trials by Ruth Zeto, Oluwagbemisola Ibikunle, Jingyi Cao, Hannah Col, Dhrumil Patil, Ruth-Alma Turkson-Ocran, Mingyu Zhang, Timothy B. Plante, Stephen P. Juraschek

“…Gender was estimated based on first name, using a published algorithm. Odds ratios (OR) were determined via logistic regression models with adjustment for estimated gender, recruitment source, method of inquiry, and first call during preferred callback time. …”
Get full text

Efficient and practical Hamiltonian simulation from time-dependent product formulas by Jan Lukas Bosse, Andrew M. Childs, Charles Derby, Filippo Maria Gambetta, Ashley Montanaro, Raul A. Santos

“…We illustrate this via extensive numerical simulations for several models. For instance, in the strong-field regime of the 1D transverse-field Ising model, our algorithms achieve an improvement of one order of magnitude in both the system size and evolution time that can be simulated with a fixed budget of 1000 arbitrary 2-qubit gates, compared with standard Trotter formulas.…”
Get full text

Bootstrapping the 3d Ising stress tensor by Cyuan-Han Chang, Vasiliy Dommes, Rajeev S. Erramilli, Alexandre Homrich, Petr Kravchuk, Aike Liu, Matthew S. Mitchell, David Poland, David Simmons-Duffin

“…We also describe several improvements made along the way to algorithms and software tools for the numerical bootstrap.…”
Get full text

Machine learning-based prediction method for open-pit mining truck speed distribution in manned operation by Changyou XU, Gang CHEN, Qiuxia ZHANG, Bo WANG, Hongwang ZHANG, Hongrui LI, Weiwei QIN, Muyang LI

“…Among these models, the Random Forest-based model exhibited lower mean squared error and a higher coefficient of determination, outperforming the XGBoost-based model. …”
Get full text

Tensor RT optimized driver drowsiness detection system using edge device by Chandramohan Dhasarathan, Sambasivam Gnanasekaran, Arnab Pattanayak, Gourav Kumar, Kartik Vig, Vaibhav Narain, K.M. Deva Narayan, Sunidhi Garg

“…The proposed approach utilizes multiple models to improve and accurately detecting driver drowsiness, with the models being InceptionV3, ResNet50, VGG-16, and MobileNetV1. …”
Get full text

Propagating observation errors to enable scalable and rigorous enumeration of plant population abundance with aerial imagery by Andrii Zaiats, T. Trevor Caughlin, Jennyffer Cruz, David S. Pilliod, Megan E. Cattau, Rongsong Liu, Richard Rachman, Maisha Maliha, Donna Delparte, John D. J. Clare

“…Our study demonstrates that integrated models accounting for imperfect detection improve estimates of plant population abundance derived from inherently imperfect UAS imagery. …”
Get full text

Machine learning applications to classify and monitor medication adherence in patients with type 2 diabetes in Ethiopia by Ewunate Assaye Kassaw, Ewunate Assaye Kassaw, Ashenafi Kibret Sendekie, Ashenafi Kibret Sendekie, Bekele Mulat Enyew, Biruk Beletew Abate, Biruk Beletew Abate

“…Eight widely used ML algorithms were employed to develop the models, and their performance was evaluated using metrics such as accuracy, precision, recall, and F1 score. …”
Get full text

opstool: A Python library for OpenSeesPy analysis automation, streamlined pre- and post-processing, and enhanced data visualization by Yexiang Yan, Yazhou Xie

“…In addition, it integrates adaptive iteration algorithms to improve convergence issues in nonlinear static and dynamic response analyses. …”
Get full text

Real-Time Football Match Prediction Platform by An Zhongqi

“…Future work will focus on enhancing model algorithms and incorporating more complex data sources, such as social media sentiment analysis, to further improve prediction accuracy.…”
Get full text

Litter accumulation and fire risks show direct and indirect climate-dependence at continental scale by Mark A. Adams, Mathias Neumann

“…Results provide guidance for future decomposition studies. Algorithms reported here can significantly improve accuracy and reliability of predictions of carbon and nutrient dynamics and fire risk.…”
Get full text

Secure and efficient batch authentication scheme based on dynamic revocation mechanism in space information network by Yinghui ZHANG, Lingyun HU, Yixin LI, Jianting NING, Dong ZHENG

“…A secure and efficient batch authentication scheme based on dynamic revocation mechanism was proposed for the problem of cross-domain authentication of a large number of mobile users in space information networks.Early key negotiation was achieved by predicting the satellite trajectory and updating the session key in real time.Algorithms were designed for a single as well as a large number of mobile terminals to perform signing and verification, which effectively reduce the computational burden of satellites.Cuckoo filters were adopted by the new scheme to achieve dynamic revocation and malicious access control of mobile terminals.Finally, under the Diffie-Hellman assumption, the proposed scheme was proved to be resistant to replay and man-in-the-middle attacks based on a random oracle model and automated validation of internet security protocols and applications.Security goals such as traceability and revocability were achieved by the scheme, thus improving the efficiency of transmission and computation by more than 80% and 20%, respectively, compared with the existing optimal scheme.…”
Get full text

Dual-Stage Gated Segmented Multimodal Emotion Recognition Method—***¹ , ***¹ , ***², ***¹

“…The interaction stage leverages the OAGL fusion strategy to model global-local cross-modal interactions, improving the efficiency of feature fusion. …”
Get full text

Essay Answer Detection System Uses Cosine Similarity and Similarity Scoring in Sentences by Siti Yuliyanti, Diah Hidayatul Ula

“…The result, system's potential in educational contexts was demonstrated by testing it on essay responses. To improve accuracy and usability, future developments could use sophisticated text scoring algorithms and provide more features. …”
Get full text

Mapping Data to Concepts: Enhancing Quantum Neural Network Transparency with Concept-Driven Quantum Neural Networks by Jinkai Tian, Wenjing Yang

“…The algorithmic design of CD-QNN is comprehensively analyzed, detailing the roles of the concept generator, feature extractor, and feature integrator in improving and balancing model expressivity and interpretability. …”
Get full text