An unity-gain 1-bit flip-around digital-to-analog converter (FADAC), without any capacitor matching issue, is proposed as the front-end input stage in a pipelined analog-to-digital converter (ADC), allowing an input signal voltage swing up to be doubled. This large input swing, coupled with the inherent large feedback factor (ideally β = 1) of the proposed FADAC, enables a power-efficient low-voltage high-resolution pipelined ADC design. The 1-bit FADAC is exploited in a SHA-less and opamp-sharing pipelined ADC, exhibiting 12-bit resolution with an input swing of 1.8 Vpp under a 1.1 V power supply. Fabricated in a 0.13-μm CMOS process, the prototype ADC achieves a measured signal-to-noise plus distortion ratio (SNDR) of 66.4 dB and a spurious-free dynamic range (SFDR) of 76.7 dB at 20 MS/s sampling rate. The ADC dissipates 5.2 mW of power and occupies an active area of 0.44 mm². The measured differential nonlinearity (DNL) is +0.72/−0.52 least significant bit (LSB) and integral nonlinearity (INL) is +0.84/−0.75 LSB at a 3-MHz sinusoidal input. Full article

The strap-down missile-borne image guidance system can be easily affected by the unwanted jitters of the motion of the camera, and the subsequent recognition and tracking functions are also influenced, thus severely affecting the navigation accuracy of the image guidance system. So, a real-time image stabilization technology is needed to help improve the image quality of the image guidance system. To satisfy the real-time and accuracy requirements of image stabilization in the strap-down missile-borne image guidance system, an image stabilization method based on optical flow and image matching with binary feature descriptors is proposed. The global motion of consecutive frames is estimated by the pyramid Lucas-Kanade (LK) optical flow algorithm, and the interval frames image matching based on fast retina keypoint (FREAK) algorithm is used to reduce the cumulative trajectory error. A Kalman filter is designed to smooth the trajectory, which is conducive to fitting to the main motion of the guidance system. Simulations have been carried out, and the results show that the proposed algorithm improves the accuracy and real-time performance simultaneously compared to the state-of-art algorithms. Full article

A large portion of user-generated content published on the Web consists of opinions and reviews on products, services, and places in textual form. Many travellers and tourists routinely rely on such content to drive their choices, shaping trips and visits to any place on earth, and specifically to select hotels in large cities. In the context of hospitality management, a challenging research problem is to identify effective strategies to explain hotel reviews and ratings and their correlation with the urban context. Under this umbrella, the paper investigates the use of sentence-based embedding models to deeply explore the similarities and dissimilarities between cities in terms of the corresponding hotel reviews and the surrounding points of interests. Reviews and point of interest (POI) descriptions are jointly modelled in a unified latent space, allowing us to deeply investigate the dependencies between guest feedbacks and the hotel neighborhood at different aggregation levels. The experiments performed on public TripAdvisor hotel-review datasets confirm the applicability and effectiveness of the proposed approach. Full article

In this paper, we analyze the characteristics of the load forecasting task in the Energy Internet context and the deficiencies of existing methods and then propose a data driven approach for one-hour-ahead load forecasting based on the deep learning paradigm. The proposed scheme involves three aspects. First, we formulate a historical load matrix (HLM) with spatiotemporal correlation combined with the EI scenario and then create a three-dimensional historical load tensor (HLT) that contains the HLMs for multiple consecutive time points before the forecasted hour. Second, we preprocess the HLT leveraging a novel low rank decomposition algorithm and different load gradients, aiming to provide a forecasting model with richer input data. Third, we develop a deep forecasting framework (called the 3D CNN-GRU) featuring a feature learning module followed by a regression module, in which the 3D convolutional neural network (3D CNN) is used to extract the desired feature sequences with time attributes, while the gated recurrent unit (GRU) is responsible for mapping the sequences to the forecast values. By feeding the corresponding load label into the 3D CNN-GRU, our proposed scheme can carry out forecasting tasks for any zone covered by the HLM. The results of self-evaluation and a comparison with several state-of-the-art methods demonstrate the superiority of the proposed scheme. Full article

This paper presents a novel error detection linear feedback shift register (ED-LFSR), which can be used to realize error detection with a small hardware overhead for various applications such as error-correction codes, encryption algorithms and pseudo-random number generation. Although the traditional redundancy methods allow the incorporation of the error detection/correction capability in the original LFSRs, they suffer from a considerable amount of hardware overheads. The proposed ED-LFSR alleviates such problems by employing the parity check technique. The experimental results indicate that the proposed ED-LFSR requires an additional area of only 31.1% compared to that required by the conventional LFSR and it saves 39.1% and 31.9% of the resources compared to the corresponding utilization of the hardware and time redundancy methods. Full article

This paper presents a compact planar multiple input multiple output (MIMO) antenna for super wide band (SWB) applications. The presented MIMO antenna comprises two identical patches on the same substrate. Dimensions of the MIMO antenna are 0.17λ × 0.20λ × 0.006λ mm³, with respect to the lowest resonance of 1.30 GHz. The SWB antenna was manufactured using F4B substrate having a dielectric constant of 2.65 that provides a percent impedance bandwidth and bandwidth ratio of 187% and 30.76:1, respectively. The mutual coupling between the antenna elements is suppressed by placing a T-shaped corrugated strip in the mid of two antenna elements. The proposed MIMO antenna exhibits maximum diversity gain of 10 dB, low mutual coupling (<−20 dB), low envelope correlation coefficient (ECC < 0.02), efficiency >80%, and low reflection coefficient (<−10 dB) in the SWB frequency range (1.30 GH–40 GHz). The presented antenna is a good candidate for SWB applications. The designed antenna has been experimentally validated, and the simulated results were also verified. Full article

Based on the 3D Reduced Inertial Sensor System (3D-RISS) and the Machine Learning Enhanced Visual Data (MLEVD), an integrated vehicle navigation system is proposed in this paper. In demanding conditions such as outdoor satellite signal interference and indoor navigation, this work incorporates vehicle smooth navigation. Firstly, a landmark is set up and both of its size and position are accurately measured. Secondly, the image with the landmark information is captured quickly by using the machine learning. Thirdly, the template matching method and the Extended Kalman Filter (EKF) are then used to correct the errors of the Inertial Navigation System (INS), which employs the 3D-RISS to reduce the overall cost and ensuring the vehicular positioning accuracy simultaneously. Finally, both outdoor and indoor experiments are conducted to verify the performance of the 3D-RISS/MLEVD integrated navigation technology. Results reveal that the proposed method can effectively reduce the accumulated error of the INS with time while maintaining the positioning error within a few meters. Full article

Using the AdaBoost method may increase the accuracy and reliability of a framework for daily activities and environment recognition. Mobile devices have several types of sensors, including motion, magnetic, and location sensors, that allow accurate identification of daily activities and environment. This paper focuses on the review of the studies that use the AdaBoost method with the sensors available in mobile devices. This research identified the research works written in English about the recognition of daily activities and environment recognition using the AdaBoost method with the data obtained from the sensors available in mobile devices that were published between 2012 and 2018. Thus, 13 studies were selected and analysed from 151 identified records in the searched databases. The results proved the reliability of the method for daily activities and environment recognition, highlighting the use of several features, including the mean, standard deviation, pitch, roll, azimuth, and median absolute deviation of the signal of motion sensors, and the mean of the signal of magnetic sensors. When reported, the analysed studies presented an accuracy higher than 80% in recognition of daily activities and environments with the Adaboost method. Full article

The main objective of this paper was to conceive a new electronic control circuit to the throttle device. The throttle mechanical actuator is the most important part in an automotive gasoline engine. Among the different control strategies recently reported, an easy to implement control scheme is an open research topic in the analog electronic engineering field. Hence, we propose using the nonlinear dwell switching control theory for an analog electronic control unit, to manipulate an automotive throttle plate. Due to the switching mechanism commuting between a stable and an unstable controllers, the resultant closed-loop system is robust enough to the control objective. This fact is experimentally evidenced. The proposed electronic controller uses operational amplifiers along with an Arduino unit. This unit is just employed to generate the related switching signal that can be replaced by using, for instance, the timer IC555. Thus, this study is a contribution on design and realization of an electronic control circuit to the throttle device. Full article

The application of deep convolutional neural networks (CNN) in the field of medical image processing has attracted extensive attention and demonstrated remarkable progress. An increasing number of deep learning methods have been devoted to classifying ChestX-ray (CXR) images, and most of the existing deep learning methods are based on classic pretrained models, trained by global ChestX-ray images. In this paper, we are interested in diagnosing ChestX-ray images using our proposed Fusion High-Resolution Network (FHRNet). The FHRNet concatenates the global average pooling layers of the global and local feature extractors—it consists of three branch convolutional neural networks and is fine-tuned for thorax disease classification. Compared with the results of other available methods, our experimental results showed that the proposed model yields a better disease classification performance for the ChestX-ray 14 dataset, according to the receiver operating characteristic curve and area-under-the-curve score. An ablation study further confirmed the effectiveness of the global and local branch networks in improving the classification accuracy of thorax diseases. Full article

In this paper we show how to efficiently implement parallel discrete simulations on multicore and GPU architectures through a real example of an application: a cellular automata model of laser dynamics. We describe the techniques employed to build and optimize the implementations using OpenMP and CUDA frameworks. We have evaluated the performance on two different hardware platforms that represent different target market segments: high-end platforms for scientific computing, using an Intel Xeon Platinum 8259CL server with 48 cores, and also an NVIDIA Tesla V100 GPU, both running on Amazon Web Server (AWS) Cloud; and on a consumer-oriented platform, using an Intel Core i9 9900k CPU and an NVIDIA GeForce GTX 1050 TI GPU. Performance results were compared and analyzed in detail. We show that excellent performance and scalability can be obtained in both platforms, and we extract some important issues that imply a performance degradation for them. We also found that current multicore CPUs with large core numbers can bring a performance very near to that of GPUs, and even identical in some cases. Full article

Segmenting an image of a nucleus is one of the most essential tasks in a leukemia diagnostic system. Accurate and rapid segmentation methods help the physicians identify the diseases and provide better treatment at the appropriate time. Recently, hybrid clustering algorithms have started being widely used for image segmentation in medical image processing. In this article, a novel hybrid histogram-based soft covering rough k-means clustering (HSCRKM) algorithm for leukemia nucleus image segmentation is discussed. This algorithm combines the strengths of a soft covering rough set and rough k-means clustering. The histogram method was utilized to identify the number of clusters to avoid random initialization. Different types of features such as gray level co-occurrence matrix (GLCM), color, and shape-based features were extracted from the segmented image of the nucleus. Machine learning prediction algorithms were applied to classify the cancerous and non-cancerous cells. The proposed strategy is compared with an existing clustering algorithm, and the efficiency is evaluated based on the prediction metrics. The experimental results show that the HSCRKM method efficiently segments the nucleus, and it is also inferred that logistic regression and neural network perform better than other prediction algorithms. Full article

Inspired from the promising performances achieved by recurrent neural networks (RNN) and convolutional neural networks (CNN) in action recognition based on skeleton, this paper presents a deep network structure which combines both CNN for classification and RNN to achieve attention mechanism for human interaction recognition. Specifically, the attention module in this structure is utilized to give various levels of attention to various frames by different weights, and the CNN is employed to extract the high-level spatial and temporal information of skeleton data. These two modules seamlessly form a single network architecture. In addition, to eliminate the impact of different locations and orientations, a coordinate transformation is conducted from the original coordinate system to the human-centric coordinate system. Furthermore, three different features are extracted from the skeleton data as the inputs of three subnetworks, respectively. Eventually, these subnetworks fed with different features are fused as an integrated network. The experimental result shows the validity of the proposed approach on two widely used human interaction datasets. Full article