Ayaz Hussain¹, Asad Hayat², Muhammad Hasnain^1,*

Journal on Artificial Intelligence, Vol.7, pp. 485-498, 2025, DOI:10.32604/jai.2025.071933 - 17 November 2025

Abstract Violent hate speech and scapegoating people against one another have emerged as a rising worldwide issue. But identifying and combating such content is crucial to create safer and more inclusive societies. The current study conducted research using Machine Learning models to classify hate speech and overcome the limitations posed in the existing detection techniques. Logistic Regression (LR), Random Forest (RF), K-Nearest Neighbour (KNN) and Decision Tree were used on top of a publicly available hate speech dataset. The data was preprocessed by cleaning the text and tokenization and using normalization techniques to efficiently train the… More >

Qinzhen Fang^1,2, Dongliang Peng^1,2, Lu Zeng^1,2,*, Zixuan Jiang^1,2

Journal on Artificial Intelligence, Vol.7, pp. 469-484, 2025, DOI:10.32604/jai.2025.073016 - 06 November 2025

Abstract To address the issues of small target miss detection, false positives in complex scenarios, and insufficient real-time performance in maglev train foreign object intrusion detection, this paper proposes a multi-module fusion improvement algorithm, YOLO11-FADA (Fusion of Augmented Features and Dynamic Attention), based on YOLO11. The model achieves collaborative optimization through three key modules: The Local Feature Augmentation Module (LFAM) enhances small target features and mitigates feature loss during down-sampling through multi-scale feature parallel extraction and attention fusion. The Dynamically Tuned Self-Attention (DTSA) module introduces learnable parameters to adjust attention weights dynamically, and, in combination with More >

Amit Prakash Singh¹, Kajal Kaul^1,*, Anuradha Chug¹, Ravinder Kumar², Veerubommu Shanmugam²

Journal on Artificial Intelligence, Vol.7, pp. 451-468, 2025, DOI:10.32604/jai.2025.070773 - 06 November 2025

Abstract In agricultural farms in India where the staple diet for most of the households is potato, plant leaf diseases, namely Potato Early Blight (PEB) and Potato Late Blight (PLB), are quite common. The class label Plant Healthy (PH) is also used. If these diseases are not identified early, they can cause massive crop loss and thereby incur huge economic losses to the farmers in the agricultural domain and can impact the gross domestic product of the nation. This paper presents a hybrid approach for potato plant disease severity estimation and classification of diseased and healthy… More >

Qiang Peng^1,2, Jia-Yu Yang¹, Xu-Yu Xiang^1,*

Journal on Artificial Intelligence, Vol.7, pp. 437-450, 2025, DOI:10.32604/jai.2025.072332 - 20 October 2025

Abstract Camellia oleifera is one of the four largest oil tree species in the world, and also an important economic crop in China, which has overwhelming economic benefits. However, Camellia oleifera is invaded by various diseases during its growth process, which leads to yield reduction and profit damage. To address this problem and ensure the healthy growth of Camellia oleifera, the purpose of this study is to apply the lightweight network to the identification and detection of camellia oleifolia leaf disease. The attention mechanism was combined for highlighting the local features and improve the attention of the model to the More >

Yan Zhou, Hengyang Wu^*

Journal on Artificial Intelligence, Vol.7, pp. 381-396, 2025, DOI:10.32604/jai.2025.071674 - 20 October 2025

Abstract Crack Detection is crucial for ensuring the safety and durability of buildings. With the advancement of deep learning, crack detection has increasingly adopted convolutional neural network (CNN)-based approaches, achieving remarkable progress. However, current deep learning methods frequently encounter issues such as high computational complexity, inadequate real-time performance, and low accuracy. This paper proposes a novel model to improve the performance of concrete crack detection. Firstly, the You Only Look Once (YOLOv11) backbone replaces the original Real-Time Detection Transformer (RTDETR) backbone, reducing computational complexity and model size. Additionally, the Dynamic Snake Convolution (DSConv) has been introduced More >

Kadriye Simsek Alan^*, Ayca Durgut, Helin Doga Demirel

Journal on Artificial Intelligence, Vol.7, pp. 397-415, 2025, DOI:10.32604/jai.2025.071133 - 20 October 2025

Abstract Efficient utilization of processor and memory resources is essential for sustaining performance and energy efficiency in modern computing infrastructures. While earlier research has emphasized CPU utilization forecasting, joint prediction of CPU and memory usage under real workload conditions remains underexplored. This study introduces a machine learning–based framework for real-time prediction of CPU and RAM utilization using the Google Cluster Trace 2019 v3 dataset. The framework combines Extreme Gradient Boosting (XGBoost) with a MultiOutputRegressor (MOR) to capture nonlinear interactions across multiple resource dimensions, supported by a leakage-safe imputation strategy that prevents bias from missing values. Nested… More >

Muhammad Adeen Jamal¹, Bilal Khan^2,*, Sameed Ur Rehman¹, Wahab Khan¹

Journal on Artificial Intelligence, Vol.7, pp. 417-435, 2025, DOI:10.32604/jai.2025.070762 - 20 October 2025

Abstract The development of artificial intelligence (AI) has sparked the invention of chatbots, which are intelligent conversational agents. These chatbots have the potential to completely transform how people interact while enhancing user experience. This study explores the building along with its execution of a chatbot for customer service support at a university reception using recurrent neural networks (RNNs). To increase user requests, the accuracy of the information, and overall satisfaction with the service, it evaluates machine learning models including RNN, XLNet, and Bidirectional Encoder Representations from Transformers (BERT). In this research project, data were gathered from… More >

Fan Chen^*, Xian Bao, Jianlin Liu, Man Wang, Qiang Zhang

Journal on Artificial Intelligence, Vol.7, pp. 365-380, 2025, DOI:10.32604/jai.2025.069903 - 06 October 2025

Abstract The Thyristor-Controlled Series Compensator (TCSC) presents an effective solution for mitigating transmission congestion in power systems by regulating the distribution of line power flow. However, inherent faults within the TCSC may lead to an unintended intensification of transmission congestion in other sections of the system post-installation, resulting in non-coherent phenomena of line blocking. In response to this challenge, this paper introduces a novel two-stage site selection method for TCSC, emphasizing the enhancement of coherence in addressing line-blocking issues. Through rigorous non-coherent verification, this method mitigates the risk of line congestion deterioration due to TCSC faults.… More >

Eleena Sarah Mathew^*

Journal on Artificial Intelligence, Vol.7, pp. 347-363, 2025, DOI:10.32604/jai.2025.069841 - 06 October 2025

Abstract This review paper explores advanced methods to prompt Large Language Models (LLMs) into generating objectionable or unintended behaviors through adversarial prompt injection attacks. We examine a series of novel projects like HOUYI, Robustly Aligned LLM (RA-LLM), StruQ, and Virtual Prompt Injection that compel LLMs to produce affirmative responses to harmful queries. Several new benchmarks, such as PromptBench, AdvBench, AttackEval, INJECAGENT, and RobustnessSuite, have been created to evaluate the performance and resilience of LLMs against these adversarial attacks. Results show significant success rates in misleading models like Vicuna-7B, LLaMA-2-7B-Chat, GPT-3.5, and GPT-4. The review highlights limitations… More >

Ragava Raja R^1,2,*, Girish Khanna R³

Journal on Artificial Intelligence, Vol.7, pp. 301-327, 2025, DOI:10.32604/jai.2025.069693 - 22 September 2025

Abstract Packaging materials are indispensable in modern industries but also significantly contribute to environmental degradation, resource consumption, and waste generation. This systematic review critically assesses the integration of artificial intelligence (AI), life cycle sustainability assessment (LCSA) following ISO 14040 standards, and circularity mapping to overcome sustainability barriers in packaging. The study identifies environmental, economic, and social hotspots across the life cycle stages of packaging materials by examining real-world case studies such as Coca-Cola’s adoption of recycled PET bottles and Unilever’s commitment to 100% recyclable plastic. AI technologies highlight transformative tools for optimising resource allocation, enhancing waste… More >