Shipping is integral to global trade, with increasing maritime traffic elevating safety risks. Accurate trajectory prediction based on Automatic Identification System (AIS) data is essential to prevent collisions and enhance navigational safety. This study introduces a novel Mamdani Fuzzy Inference System (MFIS)-based alpha-beta filter for vessel trajectory prediction, addressing the limitations of conventional static parameter tuning. The proposed method dynamically adjusts alpha and beta parameters using fuzzy logic and processes speed, heading, latitude, and longitude inputs to predict trajectories over extended periods. The fuzzy alpha-beta filter’s performance was evaluated on AIS data from 50 ships using metrics such as Average Displacement Error (ADE), Final Displacement Error (FDE), Non-Linear ADE (NL-ADE), and$R^{2}$. It achieved superior accuracy (ADE: 0.020, FDE: 0.031, NL-ADE: 0.011,$R^{2}$: 0.97) compared to conventional and deep learning models, demonstrating its efficacy in complex maritime scenarios. These findings mark a significant advancement in trajectory prediction systems, enhancing maritime safety and operational efficiency.

Efficient energy utilization while ensuring occupants’ comfort remains a primary objective in smart home environments. This study presents a novel smart home management methodology that integrates Deep Neural Networks (DNNs) with an optimization algorithm to enhance energy efficiency and user comfort. Unlike traditional approaches, which often focus on individual aspects of energy management or user comfort, our method comprehensively addresses both aspects by considering key environmental factors such as air quality, temperature, and illumination. By employing specialized DNNs, our approach dynamically adjusts home conditions to align with user preferences, thereby enhancing overall comfort and satisfaction. The primary innovation of our methodology lies in the Comfort Index Calculation System, which utilizes advanced DNNs to precisely quantify user comfort based on environmental conditions. This system enables our optimization algorithm to iteratively adjust environmental settings, striking a balance between user comfort and energy consumption. By continuously learning from user feedback and environmental data, our integrated approach ensures that smart homes adapt to occupants’ evolving preferences and external conditions, thereby offering a more personalized and responsive living environment. Our results demonstrate the capability of this integrated approach in improving smart home environments, offering significant implications for environmental living and smart building automation. By bridging the gap between energy efficiency and user comfort, our study contributes to advancing the field of smart home management, ultimately realizing the full potential of energy-efficient and comfortable living environments.

Epilepsy is a prevalent neurological disorder that affects various aspects of an individual’s life, including economic, social, and biological aspects. Despite medication, many individuals with epilepsy suffer from uncontrolled seizures and the side effects of anticonvulsants. The condition also causes difficulties with information processing speed, memory, and individual attention, which may be due to the seizures, underlying causes of the condition, or the drugs used to treat it. This paper describes the preparation and development of a novel video-based method for future research on epileptic seizures in mice. Seizures were induced in mice using pilocarpine hydrochloride (100-160 mg/kg) and electric shock via ear-clip electrodes (5 mA, 60 Hz, 0.2 s stimulus duration). A 20-second video was recorded for each scenario, and then labeling was performed for each frame (600 frames in a 20-second clip) using Labelbox software for 15 entities in the mice, including the head, nose, shoulder, pelvis, tail0, tail1, tail2, arm-L0, arm-L1, arm-R0, arm-R1, leg-L0, leg-L1, leg-R0, and leg-R1.

In this paper, we have developed two neural network-based algorithms: the neural network-based Kalman filter (KF) algorithm and the neural network-based alpha-beta (α-β) filter algorithm. These algorithms incorporate a neural network to improve prediction accuracy and performance. Both algorithms consist of three input layers (temperature sensor, humidity sensor, and sensor readings), 15 hidden layers, and different output layers. The KF algorithm has a single output layer, while the alpha-beta filter algorithm has two output layers. These output layers dynamically interact with the KF algorithm and α-β filter to predict the final output values. For the KF algorithm, we consider two factors: R computation and the noise factor F. To evaluate the performance of these algorithms, we utilize the root mean square error (RMSE). The sensor readings for both algorithms are relatively high, specifically 5.215. Through the neural network-based alpha-beta filter, we achieved a minimum error of 3.21. In the case of the neural network based Kalman filter, we obtained the best-case result of 2.41 with R=14 and F=0.01. The proposed neural network-based system yields improved results compared to the simple Kalman filter and alpha-beta filter algorithms.

This article examines differential privacy on federated learning. While recent studies are actively exploring this topic in conventional network environment, there are few studies that address the topic in vehicular networks. In particular, this research investigates the trade-off between accuracy performance and level of data protection. We have applied a local differential privacy with adaptive clipping method to two different federated learning models running on vehicular networks and conduct experiments under two different mobility scenarios. Results show that privacy-enhanced federate learning models degrade performance by 2.96% - 42.97%, representing that a vehicular network is sensitive to vehicles’ mobilities, learning models, and privacy solutions. With initial results, we plan to bring research questions for open discussion to audience.

Federated Learning is expected to mitigate data privacy risks but introduces more vulnerable surfaces due to its distributed nature. This paper investigates a poisoning attack on federated learning. While recent studies are actively exploring this topic in classification models of learning such as image recognition, there are few studies that address the topic in regression models. This article especially examines the impacts of poisoning attacks on the performance of load forecasting, which has hardly studied yet in academia. To this end, at first, Long Short-Term Memory is implemented on federated learning for load forecasting using publicly available energy data. The first experiment demonstrates how distributed learning affects forecasting performance. Then, we implement two poisoning attacks on the federated learning setting and run experiments to enumerate their impacts on prediction accuracy of load forecasting. Lastly, this paper proposes a spectral clustering algorithm to detect two poisoning attacks and mitigate their impacts and evaluates its performance. Experimental results demonstrate that the proposed algorithm increases forecasting accuracy by 175.9% on a sign flipping attack and by 174.8% on an additive noise attack.

As the capabilities for vehicular communications have become widespread, periodic beaconing is becoming fundamental to tracking neighbors. Specifically, a vehicle periodically broadcasts its kinematic data and receivers estimate the sender’s evolving position. To ensure safety, tracking neighbors via beaconing requires position errors and transmission delay to be small. To satisfy stringent requirements, previous proposals have employed multiple RF devices based on the unrealistic assumption that vehicles have the same type of RF devices. In reality, vehicles possess different RF devices (heterogeneous vehicle conditions). Satisfying the requirements under heterogeneous conditions is challenging because network connectivity is low and multi-hop transmissions to improve the connectivity aggravate network congestion. To address this challenge, we propose a novel scheme using a model-based trajectory prediction and multi-hop transmissions adaptively. To maintain accuracy of the model, each vehicle creates a model for predicting its own trajectory and distributes the model. For reliable multihop transmissions, our scheme employs periodic scan for translator and disconnected neighbors (PSTN) and probabilistic relay (PR). To our knowledge, this is the first to consider heterogeneous vehicle conditions for tracking neighbors via beaconing. Evaluation confirms that our scheme tracks neighbors more accurately than previous work.

This paper presents our extensive investigation of the security aspects of control plane procedures based on dynamic testing of the control components in operational Long Term Evolution (LTE) networks. For dynamic testing in LTE networks, we implemented a semi-automated testing tool, named LTEFuzz, by using open-source LTE software over which the user has full control. We systematically generated test cases by defining three basic security properties by closely analyzing the standards. Based on the security property, LTEFuzz generates and sends the test cases to a target network, and classifies the problematic behavior by only monitoring the device-side logs. Accordingly, we uncovered 36 vulnerabilities, which have not been disclosed previously. These findings are categorized into five types: Improper handling of (1) unprotected initial procedure, (2) crafted plain requests, (3) messages with invalid integrity protection, (4) replayed messages, and (5) security procedure bypass. We confirmed those vulnerabilities by demonstrating proof-of-concept attacks against operational LTE networks. The impact of the attacks is to either deny LTE services to legitimate users, spoof SMS messages, or eavesdrop/manipulate user data traffic. Precise root cause analysis and potential countermeasures to address these problems are presented as well. Cellular carriers were partially involved to maintain ethical standards as well as verify our findings in commercial LTE networks.

The Energy Service Interface (ESI), sitting at the boundary of a customer facility, plays a communication gateway role - interconnecting internal customer energy resources to external systems. A number of customer energy services are realized over the interconnected communications, which then contributes to smart grid interoperation eventually. In this paper, we examine the design issues of the ESI. To facilitate bi-directional customer energy services, the ESI must serve as both a service consumer and a service provider. At the same time, it must protect the customer energy resources from external threats and maximize the interoperation. To verify the issues, we build and deploy two ESI testbeds. Throughout experiments with a couple of energy service scenarios, we verify that the ESI plays the service "prosumer" in an interoperable manner. We also evaluate the performance of the security mechanism applied to the ESI and examine the potential of exploiting the Cloud technology for the ESI deployment. To the best of authors' knowledge, this is the first deployment of the ESI that addresses the fundamental, functional requirements.

Providing vehicles' position is essential in VANETs. Currently, GPS positioning is widely used, but the accuracy is not adequate for emerging safety applications. In order to provide accurate positioning, this paper proposes RF-GPS, a RFID-assisted localization system that reliably supports lane-level position accuracy. It improves accuracy of the GPS system by employing a DGPS-like concept. It also allows vehicles without GPS to compute their position by contacting GPS equipped neighbors. We evaluate the performance of the proposed localization system via simulation.

Abstract This paper takes care of an evolution of web architecture for Telematics services on ubiquitous environments. Telematics has become one of upcoming convergence fields where many kinds of services are now be operated or planned to be launched. However, most of Telematics services are currently operated in a closed architecture: they require hardware and software configurations exclusively. In order to achieve ubiquitous capabilities in Telematics model, this paper proposes a web service platform for Telematics based on web service architecture. With the proposed Telematics service broker, service providers can register their services, and service consumers can find what services are available and how to use them. Adopting open architecture, the platform will contribute to efficient provision of Telematics services in upcoming ubiquitous environments.

Recently, there has been rising concerns to provide more diverse geographic information services through the wireless Internet. However it takes too much time to transfer geographic data from server to client under the wireless Internet. It is due to the heavy geographic data and slow wireless communication speed. Also the data transmission has been restricted by mobile device capability. These lead to the limit in terms of using geographic information in the wireless environment. So it should be preceded with an effective process of reducing data size, which helps to transfer the geographic data more effectively. Macromedia's flash is real defector of vector animation with Web animation and programming capability. Flash has little data volume because it supports vector drawing techniques, and it is able to make an intuitional, dynamic, and high-quality image in real time on the Web. Besides more than 2.3 hundreds million people use it, and it is operated in the most of Web browser and computing environment. This thesis proposes a new strategy based on the dynamically generated flash using geographic data in the server side. The implementation of applicable flash shows that it considerably reduces data size and it offer fast performance and smart graphic interface on PDA.