Journal of Ambient Intelligence and Smart Environments

We propose a framework for predicting sensor event sequences (SES) in smart homes, which can proactively support residents’ activities and alert them if activities are not completed as intended. We leverage ongoing activity recognition to enhance the prediction performance, employing a GPT2-based model typically used for sentence generation. We hypothesize that the relationship between ongoing activities and SES patterns is akin to the relationship between topics and word sequence patterns in natural language processing (NLP), enabling us to apply the GPT2-based model to SES prediction. We empirically evaluated our method using two real-world datasets in which residents performed their usual daily activities. Our experimental results demonstrates that the use of the GPT2-based model significantly improves the F1 value of SES prediction from 0.461 to 0.708 compared to the state-of-the-art method, and that leveraging knowledge on ongoing activity can further improve performance to 0.837. Achieving these SES predictions using the ongoing activity recognition model required simple feature engineering and modeling, yielding a performance rate of approximately 80%.

The “Wireless Sensor Networks (WSN)” has gained a lot of interest among research scholars and has been utilized in various advanced applications in distinct fields. Along with the load balancing techniques, the clustering scheme also prolongs the network’s overall lifespan. The “Cluster Head (CH)” performs the task of load balancing between the nodes in the “Clustering algorithm”; hence, the CH selection procedure is regarded as a critical task in the case of the clustering algorithms. Depending on the CH selection and cluster nodes, the rate of energy consumed by these CHs will be reduced in the wireless sensor. CH selection is a promising solution for the transmission of information within various parameters. Thus, CH selection leads to an increase in the duration of the system and a reduction in the energy utilization by the nodes. Therefore, an “optimization-based CH selection” mechanism in WSN is developed in this paper along with an enhanced node communication performance prediction strategy to provide better communication between the “Sensor Nodes (SNs)” with limited energy expenditure. The node’s communication performance is predicted using the Adaptive Fuzzy, in which metrics such as bit rate, latency, throughput, loss, and packet delivery ratio are specified as the input to the network. Here, the parameters within the fuzzy network are tuned with the help of the recommended “Hybrid Position of Heap and African Buffalo Optimization (HP-HABO)”. Then, to perform efficient node clustering, the “Optimal K-Means Clustering (OKMC)” approach is executed and the CHs are formed using the developed HP-HABO. The objective function depends on the constraints like energy, distance, and predicted communication performance attained by forming these CHs. The performance of the developed CH selection mechanism is verified by analyzing the experimental outcome of the proposed technique with different optimization algorithms and previous works concerning the objective constraints.

This paper is dedicated to the development and research of the advanced IoT-based fuzzy control system of the irrigation process for smart farming complexes of various types. The proposed automatic control system makes it possible to attain sufficiently high quality indicators of the soil moisture and pH control, which significantly improve the overall efficiency of irrigation processes and, as a result, the processes of growing various plants. In particular, more accurate control of soil moisture and pH allows improving soil microbial activity, optimizing nutrient uptake, increasing water utilization efficiency within the cultivated plants, which directly contribute to increased crop yields and sustainable resource management in agriculture. The designed system is created based on the principles of (a) hierarchical two-level IoT-based control, (b) simple and reliable two-channel fuzzy logic control with high performance and accuracy, as well as (c) easy customization and adaptability for various smart farming complexes. To evaluate the effectiveness of the proposed advanced system, the simulation experiments for automatic control of an irrigation process using the developed fuzzy controllers are carried out in this study at given optimal parameters (soil moisture and pH level) of growing conditions for two different crops: tomato and beet. The analysis of the obtained results of computer simulation shows that the designed system has higher efficiency and quality indicators compared to existing analogs when used for two different crops with significantly different optimal parameters of growing conditions.

In this study, we present a novel framework for detecting anomalies in everyday activities within a smart-home environment. Our method utilizes the growing neural gas (GNG) concept to dynamically adapt to the changing behaviors of monitored individuals, eliminating the need for supervised input. To develop and evaluate our framework, we collected real-life data from environmental sensors that tracked the daily activities of 17 elderly subjects over a continuous two-year period. The proposed approach is highly versatile, capable of detecting a wide range of anomalies associated with daily living activities. We focus on activities that exhibit abnormal duration, frequency, or entirely new behaviors that deviate from established routines. The performance evaluation of our framework revolves around two key aspects: reliability and adaptability. Reliability measures the accuracy of detecting unusual events, while adaptability assesses the system’s ability to accommodate changes in user behavior. This involves recognizing recurrent anomalous behaviors as new norms over time and transitioning from persistent anomalies during an initial phase. Our proposed anomaly detection system demonstrates promising results in real-life scenarios. It achieves good reliability, with true negative rate and true positive rate exceeding 90% and 80% respectively, across all activities and users. Additionally, the system swiftly adapts to new individuals or their evolving behaviors, adjusting within a span of 3 to 7 days for new behaviors.

Greenhouses constitute intricate systems where numerous variables play a pivotal role in enhancing crop yields within the framework of intensive agriculture. Consequently, real-time monitoring and visualization of these variables are imperative to strike a balance between resource efficiency and production maximization. Furthermore, the ability to make predictive assessments regarding these variables is essential to avert potential greenhouse disasters. In this article, we introduce an intelligent alert system designed to efficiently oversee agricultural operations within a functioning greenhouse, ultimately bolstering productivity through the optimization of crop growth and energy consumption. This system comprises a web application, GreenhouseGuard, which improves the graphical and statistical representation of data collected by a network of sensors strategically positioned throughout the greenhouse, as well as the forecasts generated from this data. These sensors are strategically located to provide more precise real-time data readings, thereby minimizing error margins. Moreover, GreenhouseGuard offers diverse data visualization options and forecasts of greenhouse variables to enable in-depth analysis of the acquired information. Consequently, this alert system empowers greenhouse managers to proactively address abnormal situations that may jeopardize their crop yields.