The cyber threats in Electric Vehicle (EV) charging networks have become prevalent and targeting vehicle’s charging process and power supply from grid. It has been observed that the existing state of the art schemes ...
详细信息
Autism Spectrum Disorder (ASD) is a complex neurodevelopmental condition marked by social communication difficulties, re- stricted interests, and repetitive behaviors. Early and accurate diagnosis is critical for time...
详细信息
Autism Spectrum Disorder (ASD) is a complex neurodevelopmental condition marked by social communication difficulties, re- stricted interests, and repetitive behaviors. Early and accurate diagnosis is critical for timely intervention and improved outcomes. Traditional diagnostic methods, which rely on clinical observations and assessments, can be subjective and time-consuming. This study introduces a novel approach to predicting ASD using a machine learning technique, specifically a Bayesian-optimized Ran- dom Forest classification algorithm. The proposed method uses a comprehensive dataset containing various behavioral, cognitive, and demographic features associated with ASD. The Optimized Random Forest with Bayesian approach is used to categorize indi- viduals into two groups: those who have ASD and those who do not. To develop this ensemble learning technique, multiple decision trees are used, and to achieve higher performance as well as better capability to generalize, the hyperparameters are optimized with Bayesian optimization. Preliminary analysis and comparison with existing databases substantiated the findings and revealed the effectiveness of the proposed approach. The Bayesian-optimized Random Forest classifier achieved an accuracy value of 0.9890. Such performance is highly promising and could enable increased use of machine learning methods in timely and accurate diagno- sis of ASD. The proposed approach provides recommendations for a verified diagnostic technique when implemented and creates a strong foundation for future investigations into the use of machine learning for identifying and supporting children with ASD.
The rapid expansion of the Internet of Things (IoT) and mobile technologies has led to an increased reliance on Android devices for sensitive operations such as banking, online shopping, and communication. While Andro...
详细信息
The rapid expansion of the Internet of Things (IoT) and mobile technologies has led to an increased reliance on Android devices for sensitive operations such as banking, online shopping, and communication. While Android remains the dominant mobile operating system, its widespread adoption has made it a prime target for cyber threats, particularly Advanced Persistent Threats (APT) and sophisticated malware attacks. Traditional malware detection methods focus primarily on binary classification, failing to provide insights into the Tactics, Techniques, and Procedures (TTPs) used by adversaries. Understanding how malware operates is essential for strengthening cybersecurity defenses. To bridge this gap, we present DroidTTP, a solution designed to map Android malware behaviors to TTPs as defined by the MITRE ATT&CK framework. This system empowers security analysts with deeper insights into attacker methodologies, enabling more effective defense strategies. In this work, we curated a novel dataset explicitly designed to link MITRE TTPs to Android applications. Moreover, we developed an automated solution leveraging the Problem Transformation Approach (PTA) and Large Language Models (LLMs) to map Android applications to both Tactics and Techniques. Furthermore, we exploited LLMs for TTP predictions and experimented with two different strategies, specifically Retrieval-Augmented Generation with prompt engineering and LLM fine-tuning. Our approach follows a structured pipeline, including dataset creation for Android TTP prediction, hyperparameter tuning, data augmentation, feature selection, model development for prediction, and interpreting the model decision using SHAP. For Tactic classification, the Llama model achieved the highest performance among LLMs, with a Jaccard Similarity score of 0.9583 and a Hamming Loss of 0.0182. Similarly, for Technique classification, Llama outperformed other LLMs, attaining a Jaccard Similarity score of 0.9348 and a Hamming Loss of 0.0127.
Federated learning provides a privacy-preserving modeling schema for distributed data, which coordinates multiple clients to collaboratively train a global model. However, data stored in different clients may be colle...
详细信息
Many Next-Generation consumer electronic devices would be distributed hybrid electronic systems, such as UAVs (Unmanned Aerial Vehicles) and smart electronic cars. The safety and risk control are the key issues for th...
详细信息
Many Next-Generation consumer electronic devices would be distributed hybrid electronic systems, such as UAVs (Unmanned Aerial Vehicles) and smart electronic cars. The safety and risk control are the key issues for the sustainability of such consumer electronic systems. The modeling of hybrid electronic systems is difficult to be abstracted by traditional Petri Nets. This also makes the reachable marking graph unable to be applied to Petri Nets of the hybrid electronic systems. This paper proposes a novel Petri Net to model and analyze the hybrid electronic systems. We name it a Semi-continuous Colored Petri Net (SCPN) that inherits the excellent modeling capabilities and analysis methods of Petri Nets, and can formally depict hybrid quantities. In addition, we propose the construction algorithm for an SCPN reachable marking graph and prove its finiteness. Finally, we model and analyze an Adaptive Cruise Control (ACC) system of smart electronic cars as an example to prove the validity of SCPN. We use the proposed SCPN to model and analyze the running process of an ACC system under the continuous deceleration scenario of the front vehicle. The application study shows that the ACC system has logic flaws under the constant headway strategy when the front vehicle continues to decelerate. Based on this analysis, improvements to the SCPN of the ACC system are made, effectively enhancing its safety and logical correctness.
Laparoscopic surgery constrains instrument motion around a fixed pivot point at the incision into a patient to minimize tissue trauma. Surgical robots achieve this through either hardware to software-based remote cent...
详细信息
There has been remarkable progress in the field of deep learning, particularly in areas such as image classification, object detection, speech recognition, and natural language processing. Convolutional Neural Network...
详细信息
Diffusion-Weighted Imaging (DWI) is a significant technique for studying white matter. However, it suffers from low-resolution obstacles in clinical settings. Post-acquisition Super-Resolution (SR) can enhance the res...
详细信息
Building robotic prostheses requires the creation of a sensor-based interface designed to provide the robotic hand with the control required to perform hand gestures. Traditional Electromyography (EMG) based prostheti...
详细信息
暂无评论