Smart agriculture stands as a promising domain for IoT-enabled technologies, with the potential to elevate crop quality, quantity, and operational efficiency. However, implementing a smart agriculture system encounters challenges such as the high latency and bandwidth consumption linked to cloud computing, Internet disconnections in rural locales, and the imperative of cost efficiency for farmers. Addressing these hurdles, this paper advocates a fog-based smart agriculture infrastructure integrating edge computing and LoRa communication. We tackle farmers’ prime concern of animal intrusion by presenting a solution leveraging low-cost PIR sensors, cameras, and computer vision to detect intrusions and predict animal locations using an innovative algorithm. Our system detects intrusions pre-emptively, identifies intruders, forecasts their movements, and promptly alerts farmers. Additionally, we compare our proposed strategy with other approaches and measure their power consumptions, demonstrating significant energy savings afforded by our strategy. Experimental results highlight the effectiveness, energy efficiency, and cost-effectiveness of our system compared to state-of-the-art systems.

Modern Internet of Things (IoT) environments with thousands of low-end and diverse IoT nodes with complex interactions among them and often deployed in remote and/or wild locations present some unique challenges that make traditional node compromise detection services less effective. This article presents the design, implementation, and evaluation of a fog-based architecture that utilizes the concept of a digital twin to detect compromised IoT nodes exhibiting malicious behaviors by either producing erroneous data and/or being used to launch network intrusion attacks to hijack other nodes eventually causing service disruption. By defining a digital twin of an IoT infrastructure at a fog server, the architecture is focused on monitoring relevant information to save energy and storage space. This article presents a prototype implementation for the architecture utilizing malicious behavior datasets to perform misbehaving node classification. An extensive accuracy and system performance evaluation was conducted based on this prototype. Results show good accuracy and negligible overhead especially when employing deep learning techniques, such as multilayer perceptron.

In community science on air quality, low-cost air monitors have emerged as an opportunity to democratize data reporting and support knowledge justice by providing participants with instantaneous access to air quality data. In this study, we equipped residents in four environmental justice communities in North Denver with low-cost air monitors to collect real-time air quality data for four separate 30-day field deployments over two years. We conceptualize an improvement to conventional report-back processes by suggesting a 3-part approach - a reciprocal reporting process that includes 1) bidirectional open channels of communication with participants, 2) democratized data access via instant monitor data and written data summaries, and 3) responsive intervention opportunities to respond in real-time to participants air quality concerns. Through 120 interviews with 30 air quality monitor users after each of the four field deployments, we identify how this reciprocal reporting process increased Air Quality (AQ) awareness and supported distinct modes of environmental learning, which we term data-driven, health-conscious, and progressive logics of inquiry. In addition, this non-prescriptive approach centered participants' alternative ways of knowing, such as sensory experiences to understand pollution exposure, and fostered collective learning that ultimately furthered knowledge justice. Our study highlights the potential for a more robust and holistic approach to report-back processes within community science projects to foster flexibility, reciprocity, and responsiveness.

In the free online game industry, churn prediction is an important research topic. Reducing the churn rate of a game significantly helps with the success of the game. Churn prediction helps a game operator identify possible churning players and keep them engaged in the game via appropriate operational strategies, marketing strategies, and/or incentives. Playtime related features are some of the widely used universal features for most churn prediction models. In this paper, we consider developing new universal features for churn predictions for long-term players based on players' playtime. In particular, we measure playtime regularity using the notion of entropy and cross-entropy from information theory. After we calculate the playtime regularity of players from data sets of six free online games of different types. We leverage information from players' playtime regularity in the form of universal features for churn prediction. Experiments show that our developed features are better at predicting churners compared to baseline features. Thus, the experiment results imply that our proposed features could utilize the information extracted from players' playtime more effectively than related baseline playtime features.

Edge computing has become a promising computing paradigm for building IoT (Internet of Things) applications, particularly applications with latency and privacy constraints. However, these applications typically tend to be compute-intensive and compute resources are limited at the edge when compared to the cloud, so it is important to efficiently utilize all computing resources available at the edge. A key challenge in utilizing these resources is the scheduling of different computing tasks in a dynamically varying, highly hybrid computing environment. We describe the design, implementation, and evaluation of a dynamic distributed scheduler for the edge that constantly monitors the current state of the computing infrastructure and dynamically schedules various computing tasks to ensure that all application constraints are met in another paper. Based on that, this paper mainly proposes a profile evaluation method and results when applying an augmented reality application on distributed systems at the edge. With that work done, we propose and implement a good solution to efficiently distribute edge AI applications at the edge.