ILSTMA: Enhancing Accuracy and Speed of Long-Term and Short-Term Memory Architecture by Zongyu Ming, Zimu Wu, Genlang Chen

“…Furthermore, our proposed most relevant dialogue retrieval process substantially enhances the answer accuracy of LLMs while examining the potential of the two most commonly used memory retrieval algorithms. …”
Get full text

Deep-learning-based buffalo identification through muzzle pattern images by O. Ermetin, H. K. Örnek

“…The accuracy of SqueezeNet and GoogLeNet is 99.88 %, and the recall of these algorithms is 0.999. The precision of SqueezeNet is 0.998, while GoogLeNet's precision is 0.997. …”
Get full text

The Role of Artificial Intelligence (AI) in the Future of Forestry Sector Logistics by Leonel J. R. Nunes

“…Results: The results demonstrated that optimization algorithms reduced transportation costs and carbon emissions. …”
Get full text

AI-Based model for site-selecting earthquake emergency shelters by Amirmasoud Amiran, Behrouz Behnam, Sanaz Seyedin

“…Except for LR, the other algorithms achieved F1 scores between 0.7 and 1.0 in selecting emergency shelter sites. …”
Get full text

From Surveillance to Sentencing: Evaluating AI's Role in Indian Criminal Justice by Kumar Navin

“…Technologies such as predictive policing, facial recognition, natural language processing, and data analytics offer the potential for faster response times, higher accuracy, and improved investigative outcomes. Predictive algorithms can identify crime-prone areas, while facial recognition systems can swiftly pinpoint suspects—tasks that once required significant time and manpower. …”
Get full text

Will Central Bank Digital Currencies (CBDC) and blockchain cryptocurrencies coexist in the post quantum era? by Abraham Itzhak Weinberg, Pythagoras Petratos, Alessio Faccia

“…It examines the implications of emerging quantum algorithms and cryptographic techniques such as Multi-Party Computation (MPC) and Oblivious Transfer (OT). …”
Get full text

Towards Early Fault Tolerance on a 2×N Array of Qubits Equipped with Shuttling by Adam Siegel, Armands Strikis, Michael Fogarty

“…This work thus brings us one step closer to the execution of quantum algorithms that outperform classical machines.…”
Get full text

Conformal prediction for uncertainty quantification in dynamic biological systems. by Alberto Portela, Julio R Banga, Marcos Matabuena

“…As an alternative, we propose using conformal predictions methods and introduce two novel algorithms designed for dynamic biological systems. …”
Get full text

Comparative Analysis of Supervised Learning Techniques for Forecasting PV Current in South Africa by Ely Ondo Ekogha, Pius A. Owolawi

“…The optimal technique must effectively manage rapid weather fluctuations while maintaining high accuracy in forecasting the performance of a PV panel. …”
Get full text

Machine Learning-Based Methods for the Seismic Damage Classification of RC Buildings by Sung Hei Luk

“…In this study, the XGBoost method generally outperforms the other algorithms, with the highest accuracy and generalizability. …”
Get full text

Convolutional neural network model over encrypted data based on functional encryption by Chen WANG, Jiarun LI, Jian XU

“…Currently, homomorphic encryption, secure multi-party computation, and other encryption schemes are used to protect the privacy of sensitive data in outsourced convolutional neural network (CNN) models.However, the computational and communication overhead caused by the above schemes would reduce system efficiency.Based on the low cost of functional encryption, a new convolutional neural network model over encrypted data was constructed using functional encryption.Firstly, two algorithms based on functional encryption were designed, including inner product functional encryption and basic operation functional encryption algorithms to implement basic operations such as inner product, multiplication, and subtraction over encrypted data, reducing computational and communication costs.Secondly, a secure convolutional computation protocol and a secure loss optimization protocol were designed for each of these basic operations, which achieved ciphertext forward propagation in the convolutional layer and ciphertext backward propagation in the output layer.Finally, a secure training and classification method for the model was provided by the above secure protocols in a module-composable way, which could simultaneously protect the confidentiality of user data as well as data labels.Theoretical analysis and experimental results indicate that the proposed model can achieve CNN training and classification over encrypted data while ensuring accuracy and security.…”
Get full text

Signal Quality Index Estimator for Complex-Lead type ECG beat detectors by Hintermüller Christoph, Blessberger Hermann, Steinwender Clemens

“…In the past decades various algorithms to detect and delineate ECG beats have been developed. …”
Get full text

Using the power of artificial intelligence to improve the diagnosis and management of nonmelanoma skin cancer by Fahimeh Abdollahimajd, Fatemeh Abbasi, Alireza Motamedi, Narges Koohi, Reza Mohamoud Robati, Mona Gorji

“…Nonmelanoma skin cancer (NMSC), including basal cell carcinoma and squamous cell carcinoma, is the most prevalent type of skin cancer. While generally less aggressive than melanoma, early detection and treatment are crucial to prevent the complications. …”
Get full text

Quantum-enhanced intelligent system for personalized adaptive radiotherapy dose estimation by Radhey Lal, Rajiv Kumar Singh, Dinesh Kumar Nishad, Saifullah Khalid

“…Quantum-enhanced Monte Carlo simulations, employing algorithms such as Harrow-Hassidim-Lloyd (HHL) and Variational Quantum Eigensolver (VQE), achieve computational speedups of 8–15 times compared to classical methods while maintaining high accuracy. …”
Get full text

Competitive plasticity to reduce the energetic costs of learning. by Mark C W van Rossum, Aaron Pache

“…In particular in this case, large savings can be achieved while only incurring a slightly worse learning time. …”
Get full text

On the Importance of Learning Non‐Local Dynamics for Stable Data‐Driven Climate Modeling: A 1D Gravity Wave‐QBO Testbed by Hamid A. Pahlavan, Pedram Hassanzadeh, M. Joan Alexander

“…Abstract Model instability remains a core challenge for data‐driven parameterizations, especially those developed with supervised algorithms, and rigorous methods to address it are lacking. …”
Get full text

A Scoping Study on Lightweight Cryptography Reviews in IoT by Ikenna Rene Chiadighikaobi, Nurliza Katuk

“…Many scholarly studies in literature report the enhancement of conventional cryptographic algorithms and the development of new algorithms. This significant number of studies resulted in the rise of many review studies on LWC in IoT. …”
Get full text

Comprehensive datasets for RNA design, machine learning, and beyond by Jan Badura, Agnieszka Rybarczyk, Tomasz Zok

“…Accurately predicting RNA secondary structures and designing sequences that fold into specific configurations remain significant challenges in computational biology, with far-reaching implications for medicine, synthetic biology, and biotechnology. While machine learning methodologies have been proposed to enhance prediction capabilities, they require high-quality training data. …”
Get full text

The Ghost of Middle Management: Automation, Control, and Heterarchy in the Platform Firm by Janet A. Vertesi, Diana Enriquez

“…In an effort to attend to the distinct organizational form of algorithmic management, we interrogate the arrangement of platform labor through the lens of the post-bureaucratic organization instead of that of the industrialized factory. …”
Get full text

Redefining the role of supervisors in the era of artificial intelligence: implications for hybrid postgraduate research governance by Bunmi Isaiah Omodan

“…This article examines the implications of AI on supervisory roles, focusing on how algorithmic systems are reshaping mentorship, academic oversight, and ethical accountability. …”
Get full text