Efficient Object Detection Using Semantic Region of Interest Generation with Light-Weighted LiDAR Clustering in Embedded Processors.

Many fields are currently investigating the use of convolutional neural networks to detect specific objects in three-dimensional data. While algorithms based on three-dimensional data are more stable and insensitive to lighting conditions than algorithms based on two-dimensional image data, they require more computation than two-dimensional data, making it difficult to drive CNN algorithms using three-dimensional data in lightweight embedded systems. In this paper, we propose a method to process three-dimensional data through a simple algorithm instead of complex operations such as convolution in CNN, and utilize its physical characteristics to generate ROIs to perform a CNN object detection algorithm based on two-dimensional image data. After preprocessing the LiDAR point cloud data, it is separated into individual objects through clustering, and semantic detection is performed through a classifier trained based on machine learning by extracting physical characteristics that can be utilized for semantic detection. The final object recognition is performed through a 2D-based object detection algorithm that bypasses the process of tracking bounding boxes by generating individual 2D image regions from the location and size of objects initially detected by semantic detection. This allows us to utilize the physical characteristics of 3D data to improve the accuracy of 2D image-based object detection algorithms, even in environments where it is difficult to collect data from camera sensors, resulting in a lighter system than 3D data-based object detection algorithms. The proposed model achieved an accuracy of 81.84% on the YOLO v5 algorithm on an embedded board, which is 1.92% higher than the typical model. The proposed model achieves 47.41% accuracy in an environment with 40% higher brightness and 54.12% accuracy in an environment with 40% lower brightness, which is 8.97% and 13.58% higher than the general model, respectively, and can achieve high accuracy even in non-optimal brightness environments. The proposed technique also has the advantage of reducing the execution time depending on the operating environment of the detection model.

Optimized Replication of ADC-Based Particle Counting Algorithm with Reconfigurable Multi-Variables in Pseudo-Supervised Digital Twining of Reference Dust Sensor Systems.

As the application fields for digital twins have expanded, various studies have been conducted with the objective of optimizing the costs. Among these studies, research on low-power and low-performance embedded devices has been implemented at a low cost by replicating the performance of existing devices. In this study, we attempt to obtain similar particle count results in a single-sensing device replicated from the particle count results in a multi-sensing device without knowledge of the particle count acquisition algorithm of the multi-sensing device. Through filtering, we suppressed the noise and baseline movements of the raw data of the device. In addition, in the process of determining the multi-threshold for obtaining the particle counts, the existing complex particle count determination algorithm was simplified to make it possible to utilize the look-up table. The proposed simplified particle count calculation algorithm reduced the optimal multi-threshold search time by 87% on average and the root mean square error by 58.5% compared to existing method. In addition, it was confirmed that the distribution of particle count from optimal multi-thresholds has a similar shape to that from multi-sensing devices.

Efficient Object Detection Based on Masking Semantic Segmentation Region for Lightweight Embedded Processors.

Because of the development of image processing using cameras and the subsequent development of artificial intelligence technology, various fields have begun to develop. However, it is difficult to implement an image processing algorithm that requires a lot of calculations on a light board. This paper proposes a method using real-time deep learning object recognition algorithms in lightweight embedded boards. We have developed an algorithm suitable for lightweight embedded boards by appropriately using two deep neural network architectures. The first architecture requires small computational volumes, although it provides low accuracy. The second architecture uses large computational volumes and provides high accuracy. The area is determined using the first architecture, which processes semantic segmentation with relatively little computation. After masking the area using the more accurate deep learning architecture, object detection is implemented with improved accuracy, as the image is filtered by segmentation and the cases that have not been recognized by various variables, such as differentiation from the background, are excluded. OpenCV (Open source Computer Vision) is used to process input images in Python, and images are processed using an efficient neural network (ENet) and You Only Look Once (YOLO). By running this algorithm, the average error can be reduced by approximately 2.4 times, allowing for more accurate object detection. In addition, object recognition can be performed in real time for lightweight embedded boards, as a rate of about 4 FPS (frames per second) is achieved.

GPCR Agonist-to-Antagonist Conversion: Enabling the Design of Nucleoside Functional Switches for the A2A Adenosine Receptor.

Modulators of the G protein-coupled A2A adenosine receptor (A2AAR) have been considered promising agents to treat Parkinson's disease, inflammation, cancer, and central nervous system disorders. Herein, we demonstrate that a thiophene modification at the C8 position in the common adenine scaffold converted an A2AAR agonist into an antagonist. We synthesized and characterized a novel A2AAR antagonist, 2 (LJ-4517), with Ki = 18.3 nM. X-ray crystallographic structures of 2 in complex with two thermostabilized A2AAR constructs were solved at 2.05 and 2.80 Å resolutions. In contrast to A2AAR agonists, which simultaneously interact with both Ser2777.42 and His2787.43, 2 only transiently contacts His2787.43, which can be direct or water-mediated. The n-hexynyl group of 2 extends into an A2AAR exosite. Structural analysis revealed that the introduced thiophene modification restricted receptor conformational rearrangements required for subsequent activation. This approach can expand the repertoire of adenosine receptor antagonists that can be designed based on available agonist scaffolds.

Runtime ML-DL Hybrid Inference Platform Based on Multiplexing Adaptive Space-Time Resolution for Fast Car Incident Prevention in Low-Power Embedded Systems.

Forward vehicle detection is the key technique to preventing car incidents in front. Artificial intelligence (AI) techniques are used to more accurately detect vehicles, but AI-based vehicle detection takes a lot of processing time due to its high computational complexity. When there is a risk of collision with a vehicle in front, the slow detection speed of the vehicle may lead to an accident. To quickly detect a vehicle in real-time, a high-speed and lightweight vehicle detection technique with similar detection performance to that of an existing AI-based vehicle detection is required. In addition, to apply forward collision warning system (FCWS) technology to vehicles, it is important to provide high performance based on low-power embedded systems because the vehicle's battery consumption must remain low. The vehicle detection algorithm occupies the most resources in FCWS. To reduce power consumption, it is important to reduce the computational complexity of an algorithm, that is, the amount of resources required to run it. This paper describes a method for fast, accurate forward vehicle detection using machine learning and deep learning. To detect a vehicle in consecutive images consistently, a Kalman filter is used to predict the bounding box based on the tracking algorithm and correct it based on the detection algorithm. As a result, its vehicle detection speed is about 25.85 times faster than deep-learning-based object detection is, and its detection accuracy is better than machine-learning-based object detection is.

Cannabinoid Receptor Type 1 Regulates Drug Reward Behavior via Glutamate Decarboxylase 67 Transcription.

Interaction of cannabinoid receptor type 1 (CB1) and GABAergic neuronal activity is involved in drug abuse-related behavior. However, its role in drug-dependent Pavlovian conditioning is not well understood. In this study, we aimed to evaluate the effects of a CB1 agonist, JWH-210, on the development of conditioned place preference (CPP)-induced by methamphetamine (METH). Pretreatment with a synthetic cannabinoid, JWH-210 (CB1 agonist), increased METH-induced CPP score and METH-induced dopamine release in acute striatal slices. Interestingly, CB1 was expressed in glutamate decarboxylase 67 (GAD67) positive cells, and overexpression of CB1 increased GAD67 expression, while CB1 knockdown reduced GAD67 expression in vivo and in vitro. GAD67 is known as an enzyme involved in the synthesis of GABA. CB1 knockdown in the mice striatum increased METH-induced CPP. When GAD67 decreased in the mice striatum, mRNA level of CB1 did not change, suggesting that CB1 can regulate GAD67 expression. GAD67 knockdown in the mouse striatum augmented apomorphine (dopamine receptor D2 agonist)-induced climbing behavior and METH-induced CPP score. Moreover, in the human brain, mRNA level of GAD67 was found to be decreased in drug users. Therefore, we suggest that CB1 potentiates METH-induced CPP through inhibitory GABAergic regulation of dopaminergic neuronal activity.

Lightweight Microcontroller with Parallelized ECC-Based Code Memory Protection Unit for Robust Instruction Execution in Smart Sensors.

Embedded systems typically operate in harsh environments, such as where there is external shock, insufficient power, or an obsolete sensor after the replacement cycle. Despite these harsh environments, embedded systems require data integrity for accurate operation. Unintended data changes can cause a serious error in reduced instruction set computer (RISC)-based small embedded systems. For instance, if communication is performed on an edge, where there is insufficient power supply, the peak threshold is not reached, resulting in data transmission failure or incorrect data transmission. To ensure data integrity, we use an error-correcting code (ECC), which can detect and correct errors. The ECC parity bit and data are stored together using additional ECC memory, and the original data are extracted through the ECC decoding process. The process of extracting the original data is executed in the instruction fetch stage, where a bottleneck appears in the RISC-based structure. When the ECC decoding process is executed in the bottleneck, the instruction fetch stage increases the instruction fetch time and significantly reduces the overall performance. In this study, we attempt to minimize the effect of ECC on the transmission speed by executing the ECC decoding process in parallel to improve speed by degrading the bottleneck. To evaluate the performance of a parallelized ECC decoding block, we applied the proposed method to the tiny processing unit (TPU) with a RISC-based von Neumann structure and compared memory usage, speed, and reliability according to different transmission success rates in each model. The experiment was conducted using a benchmark that repeatedly executed several 3*3 matrix calculations, and reliability improvement was compared by corrupting the stored random date to confirm the reliability of the transmission success rate. As a result, in the proposed model, using the additional parity bits for parallel processing, memory usage increased by 10 bits per instruction, reducing the data rate from 80 to 61%. However, it showed an improvement in overall reliability and a 7% increase in speed.

Robust Intra-Body Communication Using SHA1-CRC Inversion-Based Protection and Error Correction for Securing Electronic Authentication.

The explosive increase in the number of IoT devices requires various types of communication methods. This paper presents secure personal authentication using electrostatic coupling Intra-body communication (IBC) based on frequency shift keying (FSK) and error correction. The proposed architecture uses GPIO for a transmitter and analog-to-digital conversion (ADC) for a receiver. We mplemented FSK modulation, demodulation, data protection, and error correction techniques in the MCU software without applying hardware devices. We used the characteristic that the carrier signal is 50% duty square wave for 1-bit error correction and applied a method of randomly inverting SHA1 hash data to protect user authentication data during transmission. The transmitter modulates binary data using a square wave as a carrier signal and transmits data through the human body. The receiver demodulates the signal using ADC and decrypts the demodulated binary data. To determine the carrier frequency from ADC results, we applied a zero-crossing algorithm which is used to detect edge characteristics in image processing. When calculating the threshold value within the zero-crossing algorithm, we implemented an adaptive threshold setting technique utilizing Otsu's binarization technique. We found that the size of the electrode pad does not affect the signal strength, but the distance between the electrode pad and the skin has a significant effect on the signal strength. Our results show that binary data modulated with a square wave can be successfully transmitted through the human body, and, when 1-bit error correction is applied, the byte error rate on the receiver side is improved around 3.5% compared to not applying it.

Accuracy-Power Controllable LiDAR Sensor System with 3D Object Recognition for Autonomous Vehicle.

Light detection and ranging (LiDAR) sensors help autonomous vehicles detect the surrounding environment and the exact distance to an object's position. Conventional LiDAR sensors require a certain amount of power consumption because they detect objects by transmitting lasers at a regular interval according to a horizontal angular resolution (HAR). However, because the LiDAR sensors, which continuously consume power inefficiently, have a fatal effect on autonomous and electric vehicles using battery power, power consumption efficiency needs to be improved. In this paper, we propose algorithms to improve the inefficient power consumption of conventional LiDAR sensors, and efficiently reduce power consumption in two ways: (a) controlling the HAR to vary the laser transmission period (TP) of a laser diode (LD) depending on the vehicle's speed and (b) reducing the static power consumption using a sleep mode, depending on the surrounding environment. The proposed LiDAR sensor with the HAR control algorithm reduces the power consumption of the LD by 6.92% to 32.43% depending on the vehicle's speed, compared to the maximum number of laser transmissions (Nx.max). The sleep mode with a surrounding environment-sensing algorithm reduces the power consumption by 61.09%. The algorithm of the proposed LiDAR sensor was tested on a commercial processor chip, and the integrated processor was designed as an IC using the Global Foundries 55 nm CMOS process.

mIoT: Metamorphic IoT Platform for On-Demand Hardware Replacement in Large-Scaled IoT Applications.

As the Internet of Things (IoT) is becoming more pervasive in our daily lives, the number of devices that connect to IoT edges and data generated at the edges are rapidly increasing. On account of the bottlenecks in servers, due to the increase in data, as well as security and privacy issues, the IoT paradigm has shifted from cloud computing to edge computing. Pursuant to this trend, embedded devices require complex computation capabilities. However, due to various constraints, edge devices cannot equip enough hardware to process data, so the flexibility of operation is reduced, because of the limitations of fixed hardware functions, relative to cloud computing. Recently, as application fields and collected data types diversify, and, in particular, applications requiring complex computation such as artificial intelligence (AI) and signal processing are applied to edges, flexible processing and computation capabilities based on hardware acceleration are required. In this paper, to meet these needs, we propose a new IoT platform, called a metamorphic IoT (mIoT) platform, which can various hardware acceleration with limited hardware platform resources, through on-demand transmission and reconfiguration of required hardware at edges instead of via transference of sensing data to a server. The proposed platform reconfigures the edge's hardware with minimal overhead, based on a probabilistic value, known as callability. The mIoT consists of reconfigurable edge devices based on RISC-V architecture and a server that manages the reconfiguration of edge devices based on callability. Through various experimental results, we confirmed that the callability-based mIoT platform can provide the hardware required by the edge device in real time. In addition, by performing various functions with small hardware, power consumption, which is a major constraint of IoT, can be reduced.

Optimized Combination of Local Beams for Wireless Sensor Networks.

This paper proposes an optimization algorithm to determine the optimal coherent combination candidates of distributed local beams in a wireless sensor network. The beams are generated from analog uniform linear arrays of nodes and headed toward the random directions due to the irregular surface where the nodes are mounted. Our algorithm is based on one of the meta-heuristic schemes (i.e., the single-objective simulated annealing) and designed to solve the objective of minimizing the average interference-to-noise ratio (INR) under the millimeter wave channel, which leads to the reduction of sidelobes. The simulation results show that synthesizing the beams on the given system can form a deterministic mainlobe with considerable and unpredictable sidelobes in undesired directions, and the proposed algorithm can decrease the average INR (i.e., the average improvement of 12.2 dB and 3.1 dB are observed in the directions of π 6 and 2 π 3 , respectively) significantly without the severe loss of signal-to-noise ratio (SNR) in the desired direction.

Efficient Fiducial Point Detection of ECG QRS Complex Based on Polygonal Approximation.

Electrocardiogram signal analysis is based on detecting a fiducial point consisting of the onset, offset, and peak of each waveform. The accurate diagnosis of arrhythmias depends on the accuracy of fiducial point detection. Detecting the onset and offset fiducial points is ambiguous because the feature values are similar to those of the surrounding sample. To improve the accuracy of this paper's fiducial point detection, the signal is represented by a small number of vertices through a curvature-based vertex selection technique using polygonal approximation. The proposed method minimizes the number of candidate samples for fiducial point detection and emphasizes these sample's feature values to enable reliable detection. It is also sensitive to the morphological changes of various QRS complexes by generating an accumulated signal of the amplitude change rate between vertices as an auxiliary signal. To verify the superiority of the proposed algorithm, error distribution is measured through comparison with the QT-DB annotation provided by Physionet. The mean and standard deviation of the onset and the offset were stable as - 4.02 ± 7.99 ms and - 5.45 ± 8.04 ms, respectively. The results show that proposed method using small number of vertices is acceptable in practical applications. We also confirmed that the proposed method is effective through the clustering of the QRS complex. Experiments on the arrhythmia data of MIT-BIH ADB confirmed reliable fiducial point detection results for various types of QRS complexes.

PTZ Camera-Based Displacement Sensor System with Perspective Distortion Correction Unit for Early Detection of Building Destruction.

This paper presents a pan-tilt-zoom (PTZ) camera-based displacement measurement system, specially based on the perspective distortion correction technique for the early detection of building destruction. The proposed PTZ-based vision system rotates the camera to monitor the specific targets from various distances and controls the zoom level of the lens for a constant field of view (FOV). The proposed approach adopts perspective distortion correction to expand the measurable range in monitoring the displacement of the target structure. The implemented system successfully obtains the displacement information in structures, which is not easily accessible on the remote site. We manually measured the displacement acquired from markers which is attached on a sample of structures covering a wide geographic region. Our approach using a PTZ-based camera reduces the perspective distortion, so that the improved system could overcome limitations of previous works related to displacement measurement. Evaluation results show that a PTZ-based displacement sensor system with the proposed distortion correction unit is possibly a cost effective and easy-to-install solution for commercialization.

The LIM protein complex establishes a retinal circuitry of visual adaptation by regulating Pax6 α-enhancer activity.

The visual responses of vertebrates are sensitive to the overall composition of retinal interneurons including amacrine cells, which tune the activity of the retinal circuitry. The expression of Paired-homeobox 6 (PAX6) is regulated by multiple cis-DNA elements including the intronic α-enhancer, which is active in GABAergic amacrine cell subsets. Here, we report that the transforming growth factor ß1-induced transcript 1 protein (Tgfb1i1) interacts with the LIM domain transcription factors Lhx3 and Isl1 to inhibit the α-enhancer in the post-natal mouse retina. Tgfb1i1-/- mice show elevated α-enhancer activity leading to overproduction of Pax6ΔPD isoform that supports the GABAergic amacrine cell fate maintenance. Consequently, the Tgfb1i1-/- mouse retinas show a sustained light response, which becomes more transient in mice with the auto-stimulation-defective Pax6ΔPBS/ΔPBS mutation. Together, we show the antagonistic regulation of the α-enhancer activity by Pax6 and the LIM protein complex is necessary for the establishment of an inner retinal circuitry, which controls visual adaptation.

Accuracy-energy configurable sensor processor and IoT device for long-term activity monitoring in rare-event sensing applications.

A specially designed sensor processor used as a main processor in IoT (internet-of-thing) device for the rare-event sensing applications is proposed. The IoT device including the proposed sensor processor performs the event-driven sensor data processing based on an accuracy-energy configurable event-quantization in architectural level. The received sensor signal is converted into a sequence of atomic events, which is extracted by the signal-to-atomic-event generator (AEG). Using an event signal processing unit (EPU) as an accelerator, the extracted atomic events are analyzed to build the final event. Instead of the sampled raw data transmission via internet, the proposed method delays the communication with a host system until a semantic pattern of the signal is identified as a final event. The proposed processor is implemented on a single chip, which is tightly coupled in bus connection level with a microcontroller using a 0.18 µm CMOS embedded-flash process. For experimental results, we evaluated the proposed sensor processor by using an IR- (infrared radio-) based signal reflection and sensor signal acquisition system. We successfully demonstrated that the expected power consumption is in the range of 20% to 50% compared to the result of the basement in case of allowing 10% accuracy error.