Electroencephalography (EEG) has found many applications cutting across many domains, such as digital health, affective computing, and human-machine interfaces. However, its widespread adoption in practice has been primarily inhibited by its susceptibility to noise artifacts and the low spatial resolution of electrodes on commercial EEG sensors. While several prior works have investigated techniques for detecting and extracting noise, our understanding of performance degradation due to electrode sparsity remains limited. In this work, we explore the feasibility of using Functional Connectivity (FC) for improving the EEG sensing-based accuracy using two exemplars downstream, working memory-related tasks: (a) cognitive task load (CTL) assessment and (b) high attentional event-evoked potential (EEP) episodes detection. This paper proposes an integrated approach, EEGAmp+, that first utilizes channel-wise functional connectivity modules using independent component analysis (ICA) coupled with cosine distance for EEG signal reconstruction for cognitive task load assessment tasks. This is then coupled with a sliding window change point detection technique paired with continuous wavelet transformation (CWT) to extract high attentional EEP episodes. Our empirical results indicate that using independent component analysis (ICA) coupled with FC to improve spatial resolution increased cognitive load assessment accuracy by [5.6
In response to the escalating demand for Indoor Positioning Services (IPS) everywhere, this study explores techniques to enhance accuracy and adaptability in a dynamic environment. Leveraging the WiFi fingerprinting and the Channel State Information (CSI) phase of a dataset collected inside the University of Passau in Germany, this research introduces a groundbreaking approach by integrating Dueling Q-Network (Dueling QN) within Deep Reinforcement Learning (DRL). The trained agent achieves precise localization within a remarkable 0 cm distance error, even without prior knowledge of the floor plan. Experimental results compare the position predicted using CSI phase and CSI amplitude, providing insights into their respective contributions. The promising findings emphasize the potential of DRL as a robust solution, opening new avenues for exploration and application in 3D WiFi datasets.
The Industrial Internet of Things (IIoT) is a transformative paradigm that integrates smart sensors, advanced analytics, and robust connectivity within industrial processes, enabling real-time data-driven decision-making and enhancing operational efficiency across diverse sectors, including manufacturing, energy, and logistics. IIoT is susceptible to various attack vectors, with Advanced Persistent Threats (APTs) posing a particularly grave concern due to their stealthy, prolonged, and targeted nature. The effectiveness of machine learning-based intrusion detection systems in APT detection has been documented in the literature. However, existing cybersecurity datasets often lack crucial attributes for APT detection in IIoT environments. Incorporating insights from prior research on APT detection using provenance data and intrusion detection within IoT systems, we present the CICAPT-IIoT dataset. The main goal of this paper is to propose a novel APT dataset in the IIoT setting that includes essential information for the APT detection task. In order to achieve this, a testbed for IIoT is developed, and over 20 attack techniques frequently used in APT campaigns are included. The performed attacks create some of the invariant phases of the APT cycle, including Data Collection and Exfiltration, Discovery and Lateral Movement, Defense Evasion, and Persistence. By integrating network logs and provenance logs with detailed attack information, the CICAPT-IIoT dataset presents foundation for developing holistic cybersecurity measures. Additionally, a comprehensive dataset analysis is provided, presenting cybersecurity experts with a strong basis on which to build innovative and efficient security solutions.
This paper addresses the challenge of minimizing the number of sensors needed to detect available on-street parking spaces while maintaining high accuracy. By utilizing a natural-selection inspired genetic algorithm, we aim to optimize sensor deployment on moving vehicles, such as buses and taxis, to effectively monitor parking availability. Traditional fixed sensor systems are labor-intensive and vulnerable to environmental damage. Our approach leverages mobile sensors, which provide cost-effective and accurate parking information. The findings highlight the efficiency of the proposed genetic algorithm in solving complex optimization problems related to parking sensor allocation in urban environments.
Smart devices would often communicate with other entities in their surroundings, to engage an interaction or get information about the environment. For example, a blind person may want her smartwatch advertising about her disability so that the environment adapts. Short distance wireless communications, such as BLE are a good support for this style of short-lived and immediate communications. However, building applications using these communication interfaces are not so easy as the protocols involved are typically packet level messages, and higher level middleware such as message buses or event based systems are designed in the context of general networking, not “spontaneous” communication system. This paper proposes a higher level protocol to better support ephemeral interactions at the application level, based on a shared data space. The proposed framework allows anonymous communication among nodes, reflects their physical context to the application, while not depending on MAC addressing. It is based on the idea of having the data addressable while it is relevant. We propose a generic packet structure that accommodates different roles and application fields. BLE Connectionless mode is used to transmit data. The system is implemented on ESP32 where multiple application fields are demonstrated to fit under the proposed communication paradigm.
