This study developed a mobile user flow for automatic body sizing systems, integrating forcing functions to reduce human errors and enhance usability. In the preliminary stage, users examined existing applications, and identified critical design requirements highlighting challenges and opportunities for improvement. In the subsequent stage, an experiment was conducted to determine optimal photographic conditions, establishing ideal settings (3 m distance, 1 m height, and 0°–5° angle) to minimize image distortion. Using these conditions, a mobile user flow was designed, incorporating three types of forcing functions (interlocks, lock-ins, and lockouts), along with visual and auditory cues such as a guide silhouette and countdown timer. Usability improved significantly compared to existing applications, as evidenced by increased emotional ratings at p < 0.05. This study underscores the effectiveness of the human-centered design approach in developing a mobile user flow that facilitates a seamless photographic process and ensures accurate outcomes in automatic body sizing systems.

We have seen many successful deployments of deep learning accelerator designs on different platforms and technologies, e.g., FPGA, ASIC, and Processing In-Memory platforms. However, the size of the deep learning models keeps increasing, making computations a burden on the accelerators. A naive approach to resolve this issue is to design larger accelerators; however, it is not scalable due to high resource requirements, e.g., power consumption and off-chip memory sizes. A promising solution is to utilize multiple accelerators and use them as needed, similar to conventional multiprocessing. For example, for smaller networks, we may use a single accelerator, while we may use multiple accelerators with proper network partitioning for larger networks. However, partitioning DNN models into multiple parts leads to large communication overheads due to inter-layer communications. In this paper, we propose a scalable solution to accelerate DNN models on multiple devices by devising a new model partitioning technique. Our technique transforms a DNN model into layer-wise partitioned models using an autoencoder. Since the autoencoder encodes a tensor output into a smaller dimension, we can split the neural network model into multiple pieces while significantly reducing the communication overhead to pipeline them. Our evaluation results conducted on state-of-the-art deep learning models show that the proposed technique significantly improves performance and energy efficiency. Our solution increases performance and energy efficiency by up to 30.5% and 28.4% with minimal accuracy loss as compared to running the same model on pipelined multi-block accelerators without the autoencoder.