This systematic review and meta-analysis explores the integration of artificial intelligence (AI) technologies into forensic odontology from an intelligent systems perspective, with particular emphasis on enhancing identification accuracy, pattern recognition capabilities, and workflow efficiency. Traditional dental identification methods rely heavily on manual comparison of charts and radiographs, which are time-consuming and susceptible to human bias. Recent advancements in machine learning algorithms, deep learning-based image recognition networks, and intelligent decision-support systems have demonstrated significant potential in automating critical tasks such as bite-mark analysis, dent... More >

Sentiment analysis is a crucial component of intelligent information processing systems, enabling machines to understand and categorize human opinions expressed in text. While extensively studied for high-resource languages such as English and Chinese, it remains underexplored for low-resource languages like Urdu. This paper presents an intelligent multilingual sentiment analysis framework for Urdu text by integrating supervised machine learning techniques with a transformer-based model. We manually annotated and preprocessed a dataset collected from various Urdu blog websites, categorizing sentiments into positive, neutral, and negative classes. Four machine learning classifiers—Support V... More >

Cataracts are a leading cause of blindness in Pakistan, contributing to more than 54% of blindness cases in Pakistan, primarily due to poor living conditions, nutritional deficiencies, and limited healthcare access. Early detection is critical to avoid invasive treatments, but current diagnostic approaches often identify cataracts at advanced stages. This paper presents an advanced,automated cataract detection system using deep learning specifically the ResNet-50 architecture, to address this gap. The model processes fundus retinal images curated from diverse datasets, classified by ophthalmologic experts through a rigorous three-stage process. By leveraging the ResNet-50 model, cataracts ar... More >

The increasing deployment of intelligent cyber-physical systems (CPS), autonomous devices, and IoT infrastructures in Industry 4.0 has introduced complex and dynamic security challenges that static, identity-based mechanisms are no longer sufficient to address. Intelligent industrial environments demand security frameworks capable of fine-grained, context-aware, and adaptive access control that can operate at scale across heterogeneous networked systems. In response to this need, Attribute-Based Encryption (ABE) and Attribute-Based Authentication (ABA) have emerged as essential building blocks for intelligent security architectures, enabling policy-driven data protection and authentication t... More >

We investigate the use of deep learning models for retail sales forecasting in this research. Proper sales forecasting can lead to optimization in inventory management, marketing strategies, and other core business operations. This research evaluates deep learning models such as Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Multilayer Perceptron (MLP), and a hybrid CNN-LSTM model. The models are further improved by adding dense layers to process daily sales data from a major pharmaceutical company. The models are trained on 80% of the dataset and tested on the remaining 20%. Model performance is compared using Root Mean Square Error (RMSE) and Mean Absolute Error (MAE).... More >

This paper presents an AI-driven intelligent control system for precision spray applications that integrates real-time perception, neural network prediction, reinforcement learning optimization, and online Bayesian learning. A two-tier architecture is established: Tier 1 employs neural network-based feedback control for rapid pressure adjustment (0.1–0.3 MPa), while Tier 2 deploys an RL agent for optimal nozzle selection when pressure control is insufficient. The neural network model achieves high prediction accuracy with an RMSE of 3.2 $\mu$m on the test set. The RL agent demonstrates effective decision-making, attaining a 94.5% success rate in simulation and closed-loop experiments for m... More >

With the increasing complexity of the working environment and the diversification of mission requirements of UAVs, traditional UAVs have a fixed structure and single function. It is difficult to be applied in occasions with complex environments and changing load demands. The modular reconfigurable flight array (MRFA) is composed of no less than four isomorphic unit modules that are freely spliced together. By adding or removing flight unit modules and adjusting the arrangement of flight unit modules, the configuration of the MRFA can be changed, so that it can adapt to complex environments and then complete different flight missions. In the process of MRFA research and development, online co... More >

Accurate predictions of traffic flow are very meaningful to city managers. With such information, traffic systems can better coordinate traffic signals and reduce congestion. By understanding traffic patterns, navigation systems can provide real-time routing suggestions that avoid traffic jams, save time, and reduce fuel consumption. However, traffic flow will be interfered with by multiple factors such as collection time and place. In this paper, stochastic configuration networks (SCNs) are proposed to predict the traffic flow. The network is trained through stepwise construction, and the network parameters are effectively optimized based on the approximation theorem and convergence analysi... More >