Machine learning
Research conducted at Mettu University highlights the importance of sociodemographic, economic, and personal factors influencing intention to use family planning (FP) in Ethiopia. By analyzing secondary data from the Ethiopian Performance Monitoring and Accountability 2021 survey, the study employed machine learning algorithms to identify the key determinants of intention to
Machine learning
Researchers at Mzumbe University in Morogoro, Tanzania, have proposed a machine learning algorithm to quantify the magnitude of academic misconduct among undergraduate students. According to the study, over 80% of students engage in the practice of academic misconduct, posing a significant risk to the quality of graduates. The proposed algorithm,
Machine learning
Artificial intelligence and machine learning have the potential to revolutionize sustainable agriculture by enabling real-time evaluations of crop output and health. Researchers at King Faisal University in Al Ahsa, Saudi Arabia, have employed a transfer learning approach to estimate above-ground biomass (AGB) in pearl millet using pre-trained convolutional neural networks
Artificial intelligence
Researchers at the University of Maribor have investigated the application of artificial intelligence (AI) in building engineering for historic buildings in the former Austro-Hungarian Empire. By leveraging AI algorithms and decision trees, the study aims to improve engineers' knowledge of these buildings and facilitate the construction process. The research
Artificial intelligence
Researchers at Korea University have made a groundbreaking discovery in predicting workplace absenteeism using machine learning and network analysis. The study, which analyzed data from over 3 years (July 2007 to July 2010), found that absenteeism is strongly related to various psychological, social, and economic factors. The researchers developed a
Machine learning
Researchers from Tezpur University in Assam, India, have developed a novel technique to detect epileptic seizures using machine learning and deep learning algorithms on electroencephalography (EEG) inputs. The research, published in the journal Bioengineering, aims to improve the efficiency and accuracy of epilepsy diagnosis and treatment. The team, led by
Machine learning
Researchers at Shandong University have developed a novel framework, known as Federated Weighted Learning Algorithm (FWLA), to mitigate poisoning attacks in distributed machine learning. According to the study, existing defense methods are often rigid and lack adaptability to dynamic adversarial behaviors, leading to high computational costs. FWLA, on the other
Machine learning
Researchers at Guangdong University of Science and Technology have proposed innovative semi-supervised attribute selection algorithms for partially labeled multiset-valued data, aiming to overcome the limitations of traditional machine learning approaches. The study highlights the importance of addressing incomplete information within a system, which can be effectively tackled through the application
Machine learning
New research has shed light on the effective use of Machine Learning (ML) and Deep Learning (DL) in firewall anomaly detection, a critical area of cybersecurity. In a study conducted by researchers at the National Engineering School in Sfax, Tunisia, the team developed advanced techniques leveraging ML and DL to
Machine learning
Researchers from the Affiliated Hospital of Qingdao University have made a significant discovery in the field of colon cancer, identifying efferocytosis-related genes (ERRGs) as key regulators of the disease. The study, published in the Journal of Gastroenterology and Hepatology, reveals that ERRGs are dysregulated in colon adenocarcinoma (COAD) and provide
Algorithms
Researchers from the School of Automation have made significant contributions to the field of artificial intelligence by developing a novel approach to multi-agent reinforcement learning (MARL). This breakthrough has far-reaching implications for the design of intelligent systems that can effectively interact with their environment. According to the study, traditional reinforcement
Algorithms
Researchers from Zhejiang University have developed a new algorithm called TPN (Triple Network Algorithm) that combines the temporal-difference and policy gradient theorems to improve the convergence and stability of deep reinforcement learning. The TPN algorithm uses three networks to estimate the state value, action value, and policy, which are trained
