In the neck part of a two-stage object detection network, feature fusion is generally carried out in either a top-down or bottom-up manner. However, two types of imbalance may exist: feature imbalance in the neck of the model and gradient imbalance in the region of interest extraction layer due to the scale changes of objects. The deeper the network is, the more abstract the learned features are, that is to say, more semantic information can be extracted. However, the extracted image background, spatial location, and other resolution information are less. In contrast, the shallow part can learn little semantic information, but a lot of spatial location information. We propose the Both Ends to Centre to Multiple Layers (BEtM) feature fusion method to solve the feature imbalance problem in the neck and a Multi-level Region of Interest Feature Extraction (MRoIE) layer to solve the gradient imbalance problem. In combination with the Region-based Convolutional Neural Network (R-CNN) framework, our Balanced Feature Fusion (BFF) method offers significantly improved network performance compared with the Faster R-CNN architecture. On the MS COCO 2017 dataset, it achieves an average precision (AP) that is 1.9 points and 3.2 points higher than those of the Feature Pyramid Network (FPN) Faster R-CNN framework and the Generic Region of Interest Extractor (GRoIE) framework, respectively.

Fault localization analyzes the runtime information of two classes of test cases (i.e., passing test cases and failing test cases) to identify suspicious statements potentially responsible for a failure. However, the failing test cases are always far fewer than passing test cases in reality, and the class imbalance problem will affect fault localization effectiveness. To address this issue, we propose a data augmentation approach using conditional variational auto-encoder to synthesize new failing test cases for FL. The experimental results show that our approach significantly improves six state-of-the-art fault localization techniques.

Deployment of machine-type communications (MTCs) over the current cellular network could lead to severe overloading of the radio access network of Long Term Evolution (LTE)-based systems. This paper proposes a slotted access-based solution, called the Slotted Access For Group Paging (SAFGP), to cope with the paging-induced MTC traffic. The proposed SAFGP splits paged devices into multiple access groups, and each group is then allocated separate radio resources on the LTE's Physical Random Access Channel (PRACH) in a periodic manner during the paging interval. To support the proposed scheme, a new adaptive barring algorithm is proposed to stabilize the number of successful devices in each dedicated access slot. The objective is to let as few devices transmitting preambles in an access slot as possible while ensuring that the number of preambles selected by exactly one device approximates the maximum number of uplink grants that can be allocated by the eNB for an access slot. Analysis and simulation results demonstrate that, given the same amount of time-frequency resources, the proposed method significantly improves the access success and resource utilization rates at the cost of slightly increasing the access delay compared to state-of-the-art methods.

A new approach for multi-target tracking in an occlusion environment is presented. In pedestrian tracking using a video camera, pedestrains must be tracked accurately and continuously in the images. However, in a crowded environment, the conventional tracking algorithm has a problem in that tracks do not continue when pedestrians are hidden behind the foreground object. In this study, we propose a robust tracking method for occlusion that introduces a degeneration hypothesis that relaxes the track hypothesis which has one measurement to one track constraint. The proposed method relaxes the hypothesis that one measurement and multiple trajectories are associated based on the endpoints of the bounding box when the predicted trajectory is approaching, therefore the continuation of the tracking is improved using the measurement in the foreground. A numerical evaluation using MOT (Multiple Object Tracking) image data sets is performed to demonstrate the effectiveness of the proposed algorithm.

Currently, unmanned aerial vehicles (UAV) have been widely used in many applications, such as in transportation logistics, public safety, or even in non-terrestrial networks (NTN). In all these scenarios, it is an important issue to model channel behavior between the UAV and the user equipment (UE) on the ground. Among these channel features, a critical parameter that dominates channel behavior is the probability of the line-of-sight (LOS), since the statistical property of the channel fading can be either Ricean or Rayleigh, depending on the existence of LOS. Besides, with knowledge of LOS probability, operators can design approaches or schemes to maximum system performance, such as the serving coverage, received signal to noise ratio (SNR), or the bit error rate (BER) with the limited transmitted power. However, the LOS UAV channel is likely difficult to acquire or derive, as it depends on the deployment scenario, such as an urban or rural area. In this paper, we generated four different scenarios defined by the ITU via the ray tracing simulator. Then, we used the spatial geometric relation and the curve fitting approach to derive the analytic models to predict the probability of the UAV LOS channels for different scenarios. Results show that our proposed relationships yield better prediction results than the methods in the literature. Besides, an example of establishing UAV self-awareness ability for the deployed environment via using proposed models is also provided in this paper.

The final exponentiation affects the efficiency of pairing computations especially on pairing-friendly curves with high embedding degree. We propose an efficient method for computing the hard part of the final exponentiation on the KSS18 curve at the 192-bit security level. Implementations indicate that the computation of the final exponentiation is 8.74% faster than the previously fastest result.

This paper details the design of a plate that controls the beam direction in an aperture array excited by a waveguide 2-plane hybrid coupler. The beam direction can be controlled in the range of ±15-32deg. in the quasi H-plane, and ±26-54deg. in the quasi E-plane at the design frequency of 66.425GHz. Inductive irises are introduced into tapered waveguides in the plate and the reflection is suppressed by narrow apertures. A plate that has a larger tilt angle in the quasi E-plane and another plate with conventional rectangular waveguide ports as a reference are fabricated and measured. The measured values agree well with the simulation results.

This paper reports on the ambipolar conduction for the λ-Deoxyribonucleic Acid (DNA) field effect transistor (FET) with 450, 400 and 250 base pair experimentally and theoretically. It was found that the drain current of the p-type DNA/Si FET increased as the ratio of the guanine-cytosine (GC) pair increased and that of the n-type DNA/Si FET decreased as the ratio of the adenine-thymine (AT) pair decreased, and the ratio of the GC pair and AT pair was controlled by the total number of the base pair. In addition, it was found that the hole conduction mechanism of the 400 bp DNA/Si FET was polaron hopping and its activation energy was 0.13eV. By considering the electron affinity of the adenine, thymine, guanine, and cytosine, the ambipolar characteristics of the DNA/Si FET was understood. The holes are injected to the guanine base for the negative gate voltage, and the electrons are injected to the adenine, thymine, and cytosine for the positive gate voltage.

We investigate a problem of finding the minimum, in which each user has a real value, and we want to estimate the minimum of these values under the local differential privacy constraint. We reveal that this problem is fundamentally difficult, and we cannot construct a consistent mechanism in the worst case. Instead of considering the worst case, we aim to construct a private mechanism whose error rate is adaptive to the easiness of estimation of the minimum. As a measure of easiness, we introduce a parameter α that characterizes the fatness of the minimum-side tail of the user data distribution. As a result, we reveal that the mechanism can achieve O((ln6N/ε2N)1/2α) error without knowledge of α and the error rate is near-optimal in the sense that any mechanism incurs Ω((1/ε2N)1/2α) error. Furthermore, we demonstrate that our mechanism outperforms a naive mechanism by empirical evaluations on synthetic datasets. Also, we conducted experiments on the MovieLens dataset and a purchase history dataset and demonstrate that our algorithm achieves Õ((1/N)1/2α) error adaptively to α.

Query-by-example spoken term detection (QbE-STD) is a task of using speech queries to match utterances, and the acoustic word embedding (AWE) method of generating fixed-length representations for speech segments has shown high performance and efficiency in recent work. We propose an AWE training method using a label-adversarial network to reduce the interference information learned during AWE training. Experiments demonstrate that our method achieves significant improvements on multilingual and zero-resource test sets.

A new software based in-situ training (SBIST) method to achieve high accuracies is proposed for binarized neural networks inference accelerator chips in which measured offsets in sense amplifiers (activation binarizers) are transformed into biases in the training software. To expedite this individual training, the initial values for the weights are taken from results of a common forming training process which is conducted in advance by using the offset fluctuation distribution averaged over the fabrication line. SPICE simulation inference results for the accelerator predict that the accuracy recovers to higher than 90% even when the amplifier offset is as large as 40mV only after a few epochs of the individual training.

In this paper, an experimental method is proposed for extracting the primary and secondary parameters of transmission lines with frequency dispersion. So far, there is no report of these methods being applied to transmission lines with frequency dispersion. This paper provides an experimental evaluation means of transmission lines with frequency dispersion and clarifies the issues when applying the proposed method. In the proposed experimental method, unnecessary components such as connectors are removed by using a simple de-embedding method. The frequency response of the primary and secondary parameters extracted by using the method reproduced all dispersion characteristics of a transmission line with frequency dispersion successfully. It is demonstrated that an accurate RLGC equivalent-circuit model is obtained experimentally, which can be used to quantitatively evaluate the frequency/time responses of shielded-FPC with frequency dispersion and to validate RLGC equivalent-circuit models extracted by using electromagnetic field analysis.

While social media is now used by many people and plays a role in distributing information, it has recently created an unexpected problem: the actual shrinkage of information sources. This is mainly due to the ease of connecting people with similar opinions and the recommendation system. Biased information distribution promotes polarization that divides people into multiple groups with opposing views. Also, people may receive only the seemingly positive information that they prefer, or may trigger them into holding onto their opinions more strongly when they encounter opposing views. This, combined with the characteristics of social media, is accelerating the polarization of opinions and eventually social division. In this paper, we propose a model of opinion formation on social media to simulate polarization. While based on the idea that opinion neutrality is only relative, this model provides new techniques for dealing with polarization.

This paper presents a deep neural network (DNN) based symbol detection and modulation classification detector (SDMCD) for mixed blind signals detection. Unlike conventional methods that employ symbol detection after modulation classification, the proposed SDMCD can perform symbol recovery and modulation identification simultaneously. A cumulant and moment feature vector is presented in conjunction with a low complexity sparse autoencoder architecture to complete mixed signals detection. Numerical results show that SDMCD scheme has remarkable symbol error rate performance and modulation classification accuracy for various modulation formats in AWGN and Rayleigh fading channels. Furthermore, the proposed detector has robust performance under the impact of frequency and phase offsets.

In recent years, there has been an increasing trend of applying artificial intelligence in many different fields, which has a profound and direct impact on human life. Consequently, this raises the need to understand the principles of model making predictions. Since most current high-precision models are black boxes, neither the AI scientist nor the end-user profoundly understands what is happening inside these models. Therefore, many algorithms are studied to explain AI models, especially those in the image classification problem in computer vision such as LIME, CAM, GradCAM. However, these algorithms still have limitations, such as LIME's long execution time and CAM's confusing interpretation of concreteness and clarity. Therefore, in this paper, we will propose a new method called Segmentation - Class Activation Mapping (SeCAM)/ This method combines the advantages of these algorithms above while at simultaneously overcoming their disadvantages. We tested this algorithm with various models, including ResNet50, InceptionV3, and VGG16 from ImageNet Large Scale Visual Recognition Challenge (ILSVRC) data set. Outstanding results were achieved when the algorithm has met all the requirements for a specific explanation in a remarkably short space of time.

In recent years, there has been significant interest in information-theoretic security techniques that encrypt physical layer signals. We have proposed chaos modulation, which has both physical layer security and channel coding gain, as one such technique. In the chaos modulation method, the channel coding gain can be increased using a turbo mechanism that exchanges the log-likelihood ratio (LLR) with an external concatenated code using the max-log approximation. However, chaos modulation, which is a type of Gaussian modulation, does not use fixed mapping, and the distance between signal points is not constant; therefore, the accuracy of the max-log approximated LLR degrades under poor channel conditions. As a result, conventional methods suffer from performance degradation owing to error propagation in turbo decoding. Therefore, in this paper, we propose a new LLR clipping method that can be optimally applied to chaos modulation by limiting the confidence level of LLR and suppressing error propagation. For effective clipping on chaos modulation that does not have fixed mappings, the average confidence value is obtained from the extrinsic LLR calculated from the demodulator and decoder, and clipping is performed based on this value, either in the demodulator or the decoder. Numerical results indicated that the proposed method achieves the same performance as the one using the exact LLR, which requires complicated calculations. Furthermore, the security feature of the proposed system is evaluated, and we observe that sufficient security is provided.

Low-density parity-check (LDPC) codes are widely used in communication systems for their high error-correcting performance. This survey introduces the elements of LDPC codes: decoding algorithms, code construction, encoding algorithms, and several classes of LDPC codes.

This work investigates the effect of channel estimation error on the average secrecy outage capacity of dual selection in the presence of multiple eavesdroppers. The dual selection selects a transmit antenna of Alice and Bob (i.e., user terminal) which provide the best received signal to noise ratio (SNR) using channel state information from every user terminals. Using Gaussian approximation, this paper obtains the tight analytical expression of the dual selection for the average secrecy outage capacity over channel estimation error and multiple eavesdroppers. Using asymptotic analysis, this work quantifies the high SNR power offset and the high SNR slope for the average secrecy outage capacity at high SNR.

Feature representation is a key component of most visual tracking algorithms. It is difficult to deal with complex appearance changes with low-level hand-crafted features due to weak representation capacities of such features. In this paper, we propose a novel tracking algorithm through combining a joint dictionary pair learning with convolutional neural networks (CNN). We utilize CNN model that is trained on ImageNet-Vid to extract target features. The CNN includes three convolutional layers and two fully connected layers. A dictionary pair learning follows the second fully connected layer. The joint dictionary pair is learned upon extracted deep features by the trained CNN model. The temporal variations of target appearances are learned in the dictionary learning. We use the learned dictionaries to encode target candidates. A linear combination of atoms in the learned dictionary is used to represent target candidates. Extensive experimental evaluations on OTB2015 demonstrate the superior performances against SOTA trackers.

Tile-based virtual reality (VR) video consists of high-resolution tiles that are displayed in accordance with the users' viewing directions and a low-resolution tile that is the entire VR video and displayed when users change their viewing directions. Whether users perceive quality degradation when watching tile-based VR video depends on high-resolution tile size, the quality of high- and low-resolution tiles, and network condition. The display time of low-resolution tile (hereafter delay) affects users' perceived quality because longer delay makes users watch the low-resolution tiles longer. Since these degradations of low-resolution tiles markedly affect users' perceived quality, these points have to be considered in the quality-estimation model. Therefore, we propose a bitstream-quality-estimation model for tile-based VR video streaming services and investigate the effect of bitstream parameters and delay on tile-based VR video quality. Subjective experiments on several videos of different qualities and a comparison between other video quality-estimation models were conducted. In this paper, we prove that the proposed model can improve the quality-estimation accuracy by using the high- and low-resolution tiles' quantization parameters, resolution, framerate, and delay. Subjective experimental results show that the proposed model can estimate the quality of tile-based VR video more accurately than other video quality-estimation models.