GLULA: Linear attention-based model for efficient human activity recognition from wearable sensors.

Body-worn sensor data is used in monitoring patient activity during rehabilitation and also can be extended to controlling rehabilitation devices based on the activity of the person. The primary focus of research has been on effectively capturing the spatiotemporal dependencies in the data collected by these sensors and efficiently classifying human activities. With the increasing complexity and size of models, there is a growing emphasis on optimizing their efficiency in terms of memory usage and inference time for real-time usage and mobile computers. While hybrid models combining convolutional and recurrent neural networks have shown strong performance compared to traditional approaches, self-attention-based networks have demonstrated even superior results. However, instead of relying on the same transformer architecture, there is an opportunity to develop a novel framework that incorporates recent advancements to enhance speed and memory efficiency, specifically tailored for human activity recognition (HAR) tasks. In line with this approach, we present GLULA, a unique architecture for HAR. GLULA combines gated convolutional networks, branched convolutions, and linear self-attention to achieve efficient and powerful solutions. To enhance the performance of our proposed architecture, we employed manifold mixup as an augmentation variant which proved beneficial in limited data settings. Extensive experiments were conducted on five benchmark datasets: PAMAP2, SKODA, OPPORTUNITY, DAPHNET, and USC-HAD. Our findings demonstrate that GLULA outperforms recent models in the literature on the latter four datasets but also exhibits the lowest parameter count and close to the fastest inference time among state-of-the-art models.

A decision support system for assessing landfill performance.

Designing environmentally sound landfills is a challenging engineering task due to complex interactions of numerous design variables; such as landfill size, waste characteristics, and site hydrogeology. Decision support systems (DSS) can be utilized to handle these complex interactions and to aid in a performance-based landfill design by coupling system simulation models (SSM). The aim of this paper is to present a decision support system developed for a performance-based landfill design. The developed DSS is called Landfill Design Decision Support System - LFDSS. A two-step DSS framework, composed of preliminary design and detailed design phases, is set to effectively couple and run the SSMs and calculation modules. In preliminary design phase, preliminary design alternatives are proposed using general site data. In detailed design phase, proposed design alternatives are further simulated under site-specific data using SSMs for performance evaluation. LFDSS calculates the required landfill volume, performs landfill base contour design, proposes preliminary design alternatives based on general site conditions, evaluates the performance of the proposed designs, calculates the factor of safety values for slope stability analyses, and performs major cost calculations. The DSS evaluates the results of all landfill design alternatives, and determines whether the design satisfies the predefined performance criteria. The DSS ultimately enables comparisons among different landfill designs based on their performances (i.e. leachate head stability, and groundwater contamination), constructional stability and costs. The developed DSS was applied to a real site, and the results demonstrated the strengths of the developed system on designing environmentally sound and feasible landfills.