Journal of Circuits Systems and Computers最新文献

Apple-picking robot can promote the development of smart agriculture, and accurate object recognition in complex natural environments using deep learning algorithms is critical. However, research has shown that changes in illumination and object occlusion remain significant challenges for recognition. In order to improve the accuracy of apple apple-picking robot’s identification and positioning of apples in natural environment, a method using YOLOv5 (You Only Look Once, YOLO) combined with fast-guided filter is proposed. By introducing a fast-guided filtering module, the ability to extract image features is improved, and the problem of inaccurate occlusion targets and edge detection is solved; $K$-means clustering algorithm is introduced in improving YOLOv5, which can realize automatic adjustment of image size and step size; BiFPN structure is introduced in Neck network to add weighted feature fusion to highlight the detailed features. The results show that the algorithm proposed in this paper can well remove noise information such as occlusion edge blurring in apple images in a natural light environment. In the real orchard environment, the apple recognition accuracy rate reached 97.8%, the recall rate was 97.3% and the recognition rate was about 26.84$$fps. The results show that this research based on YOLOv5 and fast-guided filtering can realize fast and accurate identification of apple fruits in natural environment, and meet the practical application requirements of real-time target detection.

$K$-medoids clustering is a popular variant of $k$-means clustering and widely used in pattern recognition and machine learning. A main drawback of $k$-medoids clustering is that an improper initialization can cause it to get trapped in local optima. An improved $k$-medoids clustering algorithm, called INCKM algorithm, which is the first to apply incremental initialization to $k$-medoids clustering, was recently proposed to overcome this drawback. The INCKM algorithm requires the construction of a subset of candidate medoids determined by one hyperparameter for initialization, and meanwhile, it always fails when dealing with imbalanced datasets with an incorrect hyperparameter selection. In this paper, we propose a novel $k$-medoids clustering algorithm, called incremental $k$-means++ (INCKPP) algorithm, which initializes with a novel incremental manner, attempting to optimally add one new cluster center at each stage through a non-parametric and stochastic $k$-means++ initialization. The INCKPP algorithm overcomes the difficulty of hyperparameter selection in the INCKM algorithm, improves the clustering performance, and can deal with imbalanced datasets well. However, the INCKPP algorithm is not computationally efficient enough. To deal with this, we further propose an improved INCKPP algorithm, called INCKPP${}_{sample}$ algorithm which improves the clustering efficiency while maintaining the clustering performance of the INCKPP algorithm. Extensive results from experiments on both synthetic and real-world datasets, including imbalanced datasets, illustrate that the proposed algorithms outperforms than the other compared algorithms.

In the domain of process virtual machine (PVM) binary translation, the difference in address space layout between the guest program and the translated program requires the recalculation of jump instruction targets, resulting in suboptimal execution efficiency. This paper presents a novel method called SPC-Indexed Indirect Branch Hardware Cache Redirecting (SPCIC) technique. SPCIC utilizes specialized branch instruction to represent indirect branches from guest programs while frequently-used target addresses are cached in a customized hardware mapping table. When translating an indirect branch, SPCIC queries the jump target cache first to achieve a fast redirection unless the destination address is not cached. Besides, SPCIC merely falls back to the software-based remapping approach when the query fails, improving the translation efficiency to the greatest extent. SPCIC is implemented on the QEMU platform to accelerate the translation of ARM payloads into RISC-V. Experiments are carried on SPEC2006 to demonstrate the effectiveness of SPCIC for reducing the runtime overhead of indirect branch translation. The experimental results indicate up to 11% average improvement and 35% maximum improvement are obtained on the selected benchmark.

Traditional convolutional neural networks (CNNs) typically use fixed scale convolutional kernels for feature extraction when processing image classification tasks, while ignoring the multi-scale information present in the image. To overcome this limitation, we propose an algorithm based on multi-scale CNNs, which capture features at different levels by introducing convolutional kernels of different scales into the convolutional layer. In this study, we first designed a multi-scale convolutional layer consisting of multiple convolutional kernels of different scales to extract multi-scale features of the image. To further enhance classification performance, we introduced a multi-scale feature fusion module that can effectively fuse features of different scales and classify them through a fully connected layer. Then we conducted extensive experiments on several commonly used image classification datasets. The experimental results show that this network can not only effectively identify and locate hyperspectral image targets in different scenarios, but also reduce missed detections and false positives during the detection process. The average accuracy of the improved model has been improved, and the recognition accuracy of some small markers affected by external factors such as occlusion and lighting has also been improved. In addition, by comparing the detection effect of a single image, the progressiveness and anti-leakage ability of the improved model are proved. The image classification method based on multi-scale CNNs has broad application prospects in image recognition and feature extraction, and can provide valuable reference and reference for research in related fields.

This paper introduces a low-power fully differential fixed window level-crossing analog-to-digital converter (LC-ADC) for wireless medical implantable devices. The LC-ADC could be an excellent candidate for low-power systems due to the reduction of sampling points for bio-potential signals. Different from existing fixed window LC-ADCs, which use a 1-bit DAC or scaler and two reference levels to move the input signal to the comparison window, a simplified scheme is proposed in which the DAC or scaler is removed and a single-reference level is used to create the comparison window. The proposed LC-ADC utilizes a single-reference comparator, which leads to a simplified implementation and significant reduction in power consumption and circuit area. In addition, using a single reference level and removing DAC, leads to a decrease in the complexity of the controlling logic. The proposed LC-ADC is simulated in 0.18$$$\mu$m CMOS technology. The simulation results achieve an effective number of bits (ENOB) of up to 6.5 bits with about 59–141 nW power consumption under 0.8$$V supply and input signal bandwidth from 5$$Hz to 4$$kHz.

Recently, wireless body area network (WBAN) becomes a hot research topic in the advanced healthcare system. The WBAN plays a vital role in monitoring the physiological parameters of the human body with sensors. The sensors are small in size, and it has a small-sized battery with limited life. Hence, the energy is limited in the multi-hop routing process. The patient data is collected by the sensor, and the data are transmitted with high energy consumption. It causes failure in the data transmission path. To avoid this, the data transmission process should be optimized. This paper presents an advanced authentication and energy-efficient routing protocol (AAERP) for optimal routing paths in WBAN. Patients’ data are aggregated from the WBAN through the IoMT devices in the initial stage. To secure the patient’s private data, a hybrid mechanism of the elliptic curve cryptosystem (ECC) and Paillier cryptosystem is proposed for the data encryption process. Data security is improved by authenticating the data before transmission using an encryption algorithm. Before the routing process, the data encryption approach converts the original plain text data into ciphertext data. This encryption approach assists in avoiding intrusions in the network system. The encrypted data are optimally routed with the help of the teamwork optimization algorithm (TOA) approach. The optimal path selection using this optimization technique improves the effectiveness and robustness of the system. The experimental setup is performed by using Python software. The efficacy of the proposed model is evaluated by solving parameters like network lifetime, network throughput, residual energy, success rate, number of packets received, number of packets sent, and number of packets dropped. The performance of the proposed model is measured by comparing the obtained results with several existing models.

This paper proposes a novel hybrid technique for enhancing power quality (PQ) in distributed generation (DG) systems by deploying a unified power quality conditioner (UPQC). Here, the proposed hybrid method is the joint execution of white shark optimizer (WSO) and recalling-enhanced recurrent neural network (RERNN), called the WSO-RERNN technique. The primary objective of this novel approach is to effectively mitigate voltage sag and reduce voltage harmonics under varying load conditions. It is important to investigate the voltage sag, swell and harmonic distortion of the system to obtain an enhanced PQ of the energy supply. Therefore, this paper shows the brief impact of PQ in DG utilizing the proposed unified PQ conditioner controller. The WSO-RERNN control technique enhances the performance of the UPQC controller by providing the optimal control signal. By then, the efficiency of the proposed approach is done in MATLAB, and the performance is compared with those of existing optimization techniques, including Ant Lion Optimizer (ALO), Grey wolf optimization (GWO) and Salp swarm algorithm (SSA) methods.

This work suggests an all-digital temperature sensor with a high sampling rate that is based on a time-to-digital converter (TDC). Two on-chip voltage-controlled oscillators (VCOs) are used in the design of the sensor core, which senses temperatures between $-40^{\circ }$C and 200${}^{\circ }$C. For digital code conversion, the outputs of the VCO are fed into two asynchronous counters. In both low- and high- resolution modes, the error following two-point calibration is observed between $-1.08^{\circ }$C and $+1.06^{\circ }$C. The sensor’s ability to function in both high- and low-resolution modes based on conversion time is an important feature. At a sampling frequency of 0.19$$MHz, the maximum resolution achieved is 0.18${}^{\circ }$C. Additionally, the sensor has control logic built in to turn off the sensing as soon as the conversion is complete. At 90-nm process, 1.1$$V supply voltage and 27${}^{\circ }$C, the proposed sensor occupies $0.044{\mathrm{\text{mm}}}^2$ and consumes $817.5\mu \mathrm{\text{W}}$.

In order to ensure the flight safety of small unmanned aerial vehicles (UAVs), a deep neural network-fused mathematical modeling approach is put up for reliable flight control of small UAVs. First, engine torque, thrust eccentricity and initial stop angle are taken into full consideration. A six-degree-of-freedom nonlinear model is formulated for small UAVs, concerning both ground taxiing and air flight status. Then, the model was linearized using the principle of small disturbances. The linearized model expressions for both ground taxiing and air flight were provided. In addition, radial basis function neural networks are used for online approximation to address the nonlinearity and uncertainty caused by changes in aircraft aerodynamic parameters. At the same time, to compensate for the external disturbance and the approximation error of the neural network, the system robustness is improved by selecting reasonable design parameters. This helps the whole flight control system obtain better tracking control performance. At last, some simulation experiments are carried out to evaluate the performance of the proposed mathematical modeling framework. The simulation results show that the proposal has stronger convergence ability, smaller prediction error, and better performance. Thus, proper proactivity can be acknowledged.