With the development of artificial intelligence, many studies have focused on evaluating abnormal situations by using various sensors, as industries try to automate some of the surveillance and security tasks traditionally performed by humans. In particular, mobile robots using multimodal sensors are being used for pilot operations aimed at helping security robots cope with various outdoor situations. Multiagent systems, which combine fixed and mobile systems, can provide more efficient coverage (than that provided by other systems), but network bottlenecks resulting from increased data processing and communication are encountered. In this report, we will examine recent trends in object recognition and abnormal-situation determination in various changing outdoor security robot environments, and describe an outdoor security robot platform that operates as a multiagent equipped with a multimodal sensor.

A drone without attaching guns or bombs can be a dangerous weapon, since its motor speed is greater than 3000 rpm, which is similar to that of a mower powered by a LiPo battery. The anti-drone system is the only means of detecting and neutralizing drone attacks. Many defense companies around the world provide solutions using various types of equipment (for example, radar, cameras, jamming guns, and net guns). ETRI has also developed a Low-Altitude Drone Detection (LADD) system consisting of Ku-band radar and an Electro-Optical/Infra-Red (EO/IR) camera. In this paper, we summarize recent technical advances in anti-drone systems around the world and introduce the features and describe the performance of the LADD system.

Human behavior and emotions are influenced by experiences accumulated through the past and present. To realize artificial intelligence technology that understands and sympathizes with humans, cognitive computing technology that automatically analyzes human behaviors, habits, and emotions associated with specific situations and uses past data and domain knowledge is required. In this study, we examine the latest research trends on human-understanding cognitive computing technology that recognizes human behavior and emotions, stores them as experience data, and provides services by analyzing the stored data. Further, we introduce high-quality data collection research in real-life and services for improving physical and mental health. We also review key issues essential for developing these technologies.

With the development of computing technology, the convergence of ICT with existing traditional industries is being attempted. In particular, with the recent advent of 5G, connectivity with numerous AuT (autonomous Things) in the real world as well as simple mobile terminals has increased. As more devices are deployed in the real world, the need for technology for devices to learn and act autonomously to communicate with humans has begun to emerge. This article introduces "Device to the Edge," a new computing paradigm that enables various devices in smart spaces (e.g., factories, metaverse, shipyards, and city centers) to perform ultra-reliable, low-latency and high-speed processing regardless of the limitations of capability and performance. The proposed technology, referred to as EdgeCPS, can link devices to augmented virtual resources of edge servers to support complex artificial intelligence tasks and ultra-proximity services from low-specification/low-resource devices to high-performance devices.

With the advent of the big data era, the memory capacity required for computing systems is rapidly increasing, especially in High Performance Computing systems. However, the number of DRAMs that can be used in a computing node is limited by the structural limitations of the hardware (for example, CPU specifications). Memory expansion technology has attracted attention as a means of overcoming this limitation. This technology expands the memory capacity by leveraging the external memory connected to the host system through hardware interface such as PCIe and CCIX. In this paper, we present an overview and describe the development trends of the memory expansion technology. We also provide detailed descriptions and use cases of the CCIX that provides higher bandwidth and lower latency than cases of the PCIe.

With increasing size of transformer-based neural networks, a light-weight algorithm and efficient AI accelerator has been developed to train these huge networks in practical design time. In this article, we present a survey of state-of-the-art research on the low-precision computational algorithms especially for floating-point formats and their hardware accelerator. We describe the trends by focusing on the work of two leading research groups-IBM and Seoul National University-which have deep knowledge in both AI algorithm and hardware architecture. For the low-precision algorithm, we summarize two efficient floating-point formats (hybrid FP8 and radix-4 FP4) with accuracy-preserving algorithms for training on the main research stream. Moreover, we describe the AI processor architecture supporting the low-bit mixed precision computing unit including the integer engine.

Recently, blockchain has been attracting attention as a high-reliability technology in various fields. However, the Proof-of-Work-based distributed consensus algorithm applied to representative blockchains, such as Bitcoin and Ethereum, has limitations in applications to various industries owing to its excessive resource consumption and performance limitations. To overcome these limitations, various distributed consensus algorithms have appeared, and recently, hybrid distributed consensus algorithms that use two or more consensus algorithms to achieve decentralization and scalability have emerged. This paper introduces the technological trends of the latest high-performance distributed consensus algorithms by analyzing representative hybrid distributed consensus algorithms.

Visual object tracking can be utilized in various applications and has attracted considerable attention in the field of computer vision. Visual object tracking technology is classified in various ways based on the number of tracking objects and the methodologies employed for tracking algorithms. This report briefly introduces the visual object tracking challenge that contributes to the development of single object tracking technology. Furthermore, we review ten Siamese network-based algorithms that have attracted attention, owing to their high tracking speed (despite the use of neural networks). In addition, we discuss the prospects of the Siamese network-based object tracking algorithms.