Securing the vast volumes of data exchanged over networks is crucial in IoT (Internet of Things) applications. This study introduces an innovative image encryption algorithm that combines the interactive properties of...
详细信息
ISBN:
(数字)9798350387490
ISBN:
(纸本)9798350387506
Securing the vast volumes of data exchanged over networks is crucial in IoT (Internet of Things) applications. This study introduces an innovative image encryption algorithm that combines the interactive properties of Cellular Automata (CA) and the Henon map to improve both security and performance. CA, renowned for its simplicity and parallelism, are utilized to produce intricate pseudorandom sequences. These sequences are then used as the keystream for encryption purposes. Whereas, the Henon map is employed to incorporate further levels of unpredictability and intricacy into the encryption procedure. The proposed method is thoroughly assessed through considerable experimentation and is compared with existing methodologies. The findings demonstrate substantial enhancements with respect to various standard metrics such as “Mean Squared Error (MSE)”., “Peak Signal-to-Noise Ratio (PSNR)”., “Unified Average Changing Intensity (UACI)”., and “Number of Pixels Change Rate (NPCR)” measurements., underscoring the resilience and efficacy of the proposed methodology. The results emphasize the capability of this hybrid method to offer a secure and robust performance for image encryption in IoT applications. This method guarantees the integrity and confidentiality of data while outperforming current encryption techniques in performance.
Recently, Artificial Intelligence (AI) Techniques have received significant interest across the different fields for data analysis and decision-making. Ransomware detection using AI has been a challenging research pro...
详细信息
We propose an interactive information kiosk for tracking and visualizing visitor activities in museums. Each visitor is assigned a sheet of paper with one’s own QR code and recocnized by presenting the code before in...
详细信息
ISBN:
(数字)9798350355079
ISBN:
(纸本)9798350355086
We propose an interactive information kiosk for tracking and visualizing visitor activities in museums. Each visitor is assigned a sheet of paper with one’s own QR code and recocnized by presenting the code before interacting with our kiosks and other exhibits. The proposed kiosk has a 32 inch LCD built into a wooden stand and a inexpensive two-dimensional LiDAR sensor mounted at the top to detect visitor interactions of hand gestures towards the display surface. We implemented a four-choice quiz with 40 questions, an personal review of visitor activity, and a museum floor guide which can be scrolled using hand gestures. A server system has been also developed to collect information from kiosks and summarize it. A series of experiments was conducted in a local science museum for two days to evaluate the proposed system to track and visualize visitor activities. Our future work includes improving the system with various sensors and larger-scale experiments with more kiosks with multiple types of content.
The interesting properties of both Tin monoxide (SnO) and Zinc Oxide (ZnO) semiconductors allow to predict promising photovoltaic performance of n-ZnO/p-SnO heterojunction. In this work, one-dimensional numerical simu...
详细信息
Google stadia is a cloud service that provides real-time gaming to remote users, and it pursues to deliver a high volume of multimedia data within low latency for a high level of user experience. It is known well that...
详细信息
In autonomous driving system, building a rigorous object detection model unaffected by conditions, such as weather or time-of-day, is essential for safety. However, as deep learning models are often limited in general...
详细信息
We propose an interactive projection system that uses two projectors and a two-dimensional LiDAR sensor. A mirror was used to reflect a portion of the scanning plane of the sensor to detect the location of the user on...
详细信息
ISBN:
(数字)9798350355079
ISBN:
(纸本)9798350355086
We propose an interactive projection system that uses two projectors and a two-dimensional LiDAR sensor. A mirror was used to reflect a portion of the scanning plane of the sensor to detect the location of the user on the floor and that of the touch. Three-dimensional colored models of small creatures, such as frogs and mantis, were displayed on the floor screen, whereas the front screen on the wall was used to provide mini quizzes and information about the creature. User experiments were conducted at a science museum to evaluate the proposed system. Seventeen participants rated our system at 4.23 on a scale of 1 to 5 in terms of interest, usability, and helpfulness.
We consider a setting involving N agents, where each agent interacts with an environment modeled as a Markov Decision Process (MDP). The agents’ MDPs differ in their reward functions, capturing heterogeneous objectiv...
详细信息
ISBN:
(数字)9798350316339
ISBN:
(纸本)9798350316346
We consider a setting involving N agents, where each agent interacts with an environment modeled as a Markov Decision Process (MDP). The agents’ MDPs differ in their reward functions, capturing heterogeneous objectives/tasks. The collective goal of the agents is to communicate intermittently via a central server to find a policy that maximizes the average of long-term cumulative rewards across environments. The limited existing work on this topic either only provide asymptotic rates, or generate biased policies, or fail to establish any benefits of collaboration. In response, we propose Fast-FedPG - a novel federated policy gradient algorithm with a carefully designed bias-correction mechanism. Under a gradient-domination condition, we prove that our algorithm guarantees (i) fast linear convergence with exact gradients, and (ii) sublinear rates that enjoy a linear speedup w.r.t. the number of agents with noisy, truncated policy gradients. Notably, in each case, the convergence is to a globally optimal policy with no heterogeneity-induced bias. In the absence of gradient-domination, we establish convergence to a first-order stationary point at a rate that continues to benefit from collaboration.
The current capabilities of deepfake and Artificial Intelligence (AI) technologies make it difficult to distinguish what is original from what is fabricated. Electronic documents can be digitally signed to verify and ...
详细信息
ISBN:
(数字)9798331504847
ISBN:
(纸本)9798331504854
The current capabilities of deepfake and Artificial Intelligence (AI) technologies make it difficult to distinguish what is original from what is fabricated. Electronic documents can be digitally signed to verify and authenticate their information, making them admissible as evidence in court. In contrast, images and videos from Internet of Things (IoT) devices-such as police body cameras, security cameras, and smartphones are susceptible to deepfake manipulation, which can undermine their authenticity in legal proceedings. This research hypothesizes that digitally signing image and video data utilizing hardware cryptographic coprocessors could render them admissible in court. Utilizing our processes will also identify if any manipulation of the image data has occurred. Our approach addresses a critical need in the justice system to combat the challenges deepfakes pose and could pave the way for enhanced trust in digital evidence, bolstering the integrity of the judicial process.
In today's era, medical data is the most crucial statistic for an individual. With the increase in chronic diseases, medical experts must keep an eye on the disease trends. For early detection of the disease, it i...
详细信息
暂无评论