Bacterial recognition and classification play a vital role in diagnosing disease by determining the presence of large bacteria in the specimens and the symptoms. Artificial intelligence and computer vision widely applied in the medical domain enable improving accuracy and reducing the bacterial recognition and classification time, which aids in making clinical decisions and choosing the proper treatment. This paper aims to provide an approach of 33 bacteria strains’ automated classification from the Digital Images of Bacteria Species (DIBaS) dataset based on small-scale depthwise separable convolutional neural networks. Our five-layer architecture has significant advantages due to the compact model, low computational cost, and reliable recognition accuracy. The experimental results proved that the proposed design reached the highest accuracy of $96.28\%$ with a total of 6600 images and can be executed on limited-resource devices of $3.23$ million parameters and $40.02$ million multiply–accumulate operations (MACs). The number of parameters in this architecture is seven times less than the smallest model listed in the literature.

This paper proposes constructing a smart parking service model based on the Internet of Things and Fog computing architecture. The weaknesses of previous parking service delivery systems are that they did not offer a complete set of end-to-end parking services, such as inaccurate information about parking in real-time, poor system storage and expansion capacity, and knowledge to assist the driver in successfully reaching the parking space at a minimum cost. Therefore, our system offers a complete set of parking assistance services, from when the driver searches and makes a reservation to navigation services that help the driver successfully park at the desired parking spot. To address the problems of storage and system expansion, we also implemented services based on the Internet of Things and Fog computing platforms. The simulation and experimental implementation results show that the services we designed significantly improve the performance of the existing parking system compared to the other systems. Real-time vehicles are handled quickly, significantly reducing driver costs and increasing profits for managers.

Home Security Systems (HSSs) have received much attention and have been widely adopted for practical deployment. However, detection and warning accuracy still need to be improved, along with the range of the realm, making it challenging to satisfy the user demands. This study proposes a security monitoring system based on mobile robots and the Internet of Things (IoT), allowing users to monitor and control devices remotely. The mobile robot integrated sensor systems and surveillance cameras are utilized for unauthorized early intrusion detection and to give users instant warnings. The data collected by the robot were stored on the Firebase Cloud server, and a mobile application and a Telegram interface were integrated to manage and control the system. In addition, adaptive motion control was adopted to correct errors in the robot’s trajectory. The implementation results proved that this system operated effectively with a minimal response delay of 0.87–1.67 s and a high detection accuracy (96.25%) in two experimental cases, which makes it suitable for real-time applications.

The breakdown of Moore’s Law has shifted deep learning acceleration from compute-bound to memory-bound optimization, necessitating comprehensive co-design across multiple abstraction layers. This analysis examines key co-design methodologies spanning the algorithm-architecture, architecture-physics, and integration-system domains for modern AI hardware, addressing the limitations of conventional silicon approaches. CNNs match spatial hardware arrays with tailored dataflow mapping, while GNNs manage irregular access patterns. Similarly, LLM accelerators embed key-value cache optimizations and hierarchical compression directly into the silicon, and edge inference systems adapt to physical constraints by jointly tailoring quantization at the hardware-software boundary. Furthermore, architecture and physics co-design methods, including processing-in-memory architectures, non-volatile memory interfaces, and neuromorphic computing, directly challenge von Neumann bottlenecks by integrating computation with storage at the circuit level. Chiplet ecosystems, 3D stacking, and advanced interconnect architectures enable system scaling beyond single-die limitations, with thermal management and power delivery emerging as critical factors in post-Moore hardware deployment. This survey presents a multi-level co-design perspective for AI accelerators, unifying algorithmic, architectural, and system layers through a cross-layer taxonomy and a general analytical model for computation and data movement. By synthesizing quantitative evidence across state-of-the-art designs and outlining key open challenges, it provides a structured overview of modern accelerator trends and the remaining technical gaps in the field.

Evaluating the quality of text summarization for Vietnamese is both critical and challenging, particularly as the demand for reliable automatic summarization grows in Vietnamese-language applications. This field has currently been constrained by traditional evaluation methods such as ROUGE and BLEU, which primarily focus on word matching and struggle to assess how effectively a summary conveys meaning and information. Vietnamese presents significant challenges because of its complex morphology, flexible word order, and nuanced semantic relationships. Consequently, traditional metrics often fail to accurately differentiate between summaries of varying quality, complicating robust evaluation. In this study, we apply the FineSurE framework semantics-based evaluation method that leverages large language models to evaluate Vietnamese news summarization. We use the ViMs dataset, comprising 1,945 Vietnamese news articles with expert-annotated summaries and key facts, to benchmark our approach. Experimental results indicate that, although the two summary variants concise and detailed differ significantly in quality, both achieve uniformly high ROUGE scores (all above 92%), which highlights the insensitivity of traditional metrics. In contrast, FineSurE provides much clearer scores, demonstrating that the detailed summaries are significantly more accurate (85.38% compared to 53.12%) and complete (42.39% compared to 13.75%). This underscores FineSurE's superior ability to identify important quality differences in summarizing Vietnamese texts.