Multi-modal semantic trajectory prediction has become a new challenge due to the rapid growth of multi-modal semantic trajectories with text message. Traditional RNN trajectory prediction methods have the following problems to process multi-modal semantic trajectory. The distribution of multi-modal trajectory samples shifts gradually with training. It leads to difficult convergency and long training time. Moreover, each modal feature shifts in different directions, which produces multiple distributions of dataset. To solve the above problems, MNERM (Mode Normalization Enhanced Recurrent Model) for multi-modal semantic trajectory is proposed. MNERM embeds multiple modal features together and combines the LSTM network to capture long-term dependency of trajectory. In addition, it designs Mode Normalization mechanism to normalize samples with multiple means and variances, and each distribution normalized falls into the action area of the activation function, so as to improve the prediction efficiency while improving greatly the training speed. Experiments on real dataset show that, compared with SERM, MNERM reduces the sensitivity of learning rate, improves the training speed by 9.120 times, increases HR@1 by 0.03, and reduces the ADE by 120 meters.

For the frequency-division-duplex (FDD)-based massive multiple-input multiple-output (MIMO) systems, channel state information (CSI) feedback plays a critical role. Although deep learning has been used to compress the CSI feedback, some issues like truncation and noise still need further investigation. Facing these practical concerns, we propose an improved model (called CsiNet-Plus), which includes a truncation process and a channel noise process. Simulation results demonstrate that the CsiNet-Plus outperforms the existing CsiNet. The performance interchangeability between truncated decimal digits and the signal-to-noise-ratio helps support flexible configuration.

As one of the most popular intelligent optimization algorithms, Simulated Annealing (SA) faces two key problems, the generation of perturbation solutions and the control strategy of the outer loop (cooling schedule). In this paper, we introduce the Gaussian Cloud model to solve both problems and propose a novel cloud annealing algorithm. Its basic idea is to use the Gaussian Cloud model with decreasing numerical character He (Hyper-entropy) to generate new solutions in the inner loop, while He essentially indicates a heuristic control strategy to combine global random search of the outer loop and local tuning search of the inner loop. Experimental results in function optimization problems (i.e. single-peak, multi-peak and high dimensional functions) show that, compared with the simple SA algorithm, the proposed cloud annealing algorithm will lead to significant improvement on convergence and the average value of obtained solutions is usually closer to the optimal solution.

We propose an image identification scheme for double-compressed encrypted JPEG images that aims to identify encrypted JPEG images that are generated from an original JPEG image. To store images without any visual sensitive information on photo sharing services, encrypted JPEG images are generated by using a block-scrambling-based encryption method that has been proposed for Encryption-then-Compression systems with JPEG compression. In addition, feature vectors robust against JPEG compression are extracted from encrypted JPEG images. The use of the image encryption and feature vectors allows us to identify encrypted images recompressed multiple times. Moreover, the proposed scheme is designed to identify images re-encrypted with different keys. The results of a simulation show that the identification performance of the scheme is high even when images are recompressed and re-encrypted.

We present an accurate and easy-to-use multi-sensor fusion toolbox for autonomous vehicles. It includes a ‘target-less’ multi-LiDAR (Light Detection and Ranging), and Camera-LiDAR calibration, sensor fusion, and a fast and accurate point cloud ground classifier. Our calibration methods do not require complex setup procedures, and once the sensors are calibrated, our framework eases the fusion of multiple point clouds, and cameras. In addition we present an original real-time ground-obstacle classifier, which runs on the CPU, and is designed to be used with any type and number of LiDARs. Evaluation results on the KITTI dataset confirm that our calibration method has comparable accuracy with other state-of-the-art contenders in the benchmark.

Fluctuations in nonlinear systems can enhance the synchronization with weak input signals. These nonlinear synchronization phenomena are classified as stochastic resonance and chaotic resonance. Many applications of stochastic resonance have been realized, utilizing its enhancing effect for the signal sensitivity. However, although some studies showed that the sensitivity of chaotic resonance is higher than that of stochastic resonance, only few studies have investigated the engineering application of chaotic resonance. A possible reason is that, in chaotic resonance, the chaotic state must be adjusted through internal parameters to reach the state that allows resonance. In many cases and especially in biological systems, such adjustments are difficult to perform externally. To overcome this difficulty, we developed a method to control the chaotic state for an appropriate state of chaotic resonance by using an external feedback signal. The method is called reducing the range of orbit (RRO) feedback method. Previously, we have developed the RRO feedback method for discrete chaotic systems. However, for applying the RRO feedback method to actual chaotic systems including biological systems, development of the RRO feedback signals in continuous chaotic systems must be considered. Therefore, in this study, we extended the RRO feedback method to continuous chaotic systems by focusing on the map function on the Poincaré section. We applied the extended RRO feedback method to Chua's circuit as a continuous chaotic system. The results confirmed that the RRO feedback signal can induce chaotic resonance. This study is the first to report the application of RRO feedback to a continuous chaotic system. The results of this study will facilitate further device development based on chaotic resonance.

This paper studies the joint optimization of precoding, transmit power and data rate allocation for energy-efficient full-duplex (FD) cloud radio access networks (C-RANs). A new nonconvex problem is formulated, where the ratio of total sum rate to total power consumption is maximized, subject to the maximum transmit powers of remote radio heads and uplink users. An iterative algorithm based on successive convex programming is proposed with guaranteed convergence to the Karush-Kuhn-Tucker solutions of the formulated problem. Numerical examples confirm the effectiveness of the proposed algorithm and show that the FD C-RANs can achieve a large gain over half-duplex C-RANs in terms of energy efficiency at low self-interference power levels.

As Internet-connected service is emerged, there has been a need for use cases where a lightweight cryptographic primitive meets both of a constrained hardware implementation requirement and a constrained embedded software requirement. One of the examples of these use cases is the PKES (Passive Keyless Entry and Start) system in an automotive domain. From the perspective on these use cases, one interesting direction is to investigate how small the memory (RAM/ROM) requirement of ARM-implementations of hardware-oriented stream ciphers can be. In this paper, we propose implementation techniques for memory-optimized implementations of lightweight hardware-oriented stream ciphers including Grain-128a specified in ISO/IEC 29167-13 for RFID protocols. Our techniques include data-dependency analysis to take a close look at how and in which timing certain variables are updated and also the way taking into account the structure of registers on the target micro-controller. In order to minimize RAM size, we reduce the number of general purpose registers for computation of Grain-128a's update and pre-output values. We present results of our memory-optimized implementations of Grain-128a, one of which requires 84 RAM bytes on ARM Cortex-M3.

For high transmission efficiency, good modulation schemes are expected. This paper focuses on the enhancement of the modulation scheme of free space optical turbo coded system. A free space optical turbo coded system using a new signaling scheme called hybrid PPM-OOK signaling (HPOS) is proposed and investigated. The theoretical formula of the bit error rate of the uncoded HPOS system is derived. The effective information rate performances (i.e. channel capacity) of the proposed HPOS turbo coded system are evaluated through computer simulation in free space optical channel, with weak, moderate, strong scintillation. The performance of the proposed HPOS turbo coded system is compared with those of the conventional OOK (On-Off Keying) turbo coded system and BPPM (Binary Pulse Position Modulation) turbo coded system. As results, the proposed HPOS turbo coded system shows the same tolerance capability to background noise and atmospheric turbulence as the conventional BPPM turbo coded system, and it has 1.5 times larger capacity.

We have developed a digital watermarking method that use neural networks to learn embedding and extraction processes that are robust against rotation and JPEG compression. The proposed neural networks consist of a stego-image generator, a watermark extractor, a stego-image discriminator, and an attack simulator. The attack simulator consists of a rotation layer and an additive noise layer, which simulate the rotation attack and the JPEG compression attack, respectively. The stego-image generator can learn embedding that is robust against these attacks, and also, the watermark extractor can extract watermarks without rotation synchronization. The quality of the stego-images can be improved by using the stego-image discriminator, which is a type of adversarial network. We evaluated the robustness of the watermarks and image quality and found that, using the proposed method, high-quality stego-images could be generated and the neural networks could be trained to embed and extract watermarks that are robust against rotation and JPEG compression attacks. We also showed that the robustness and image quality can be adjusted by changing the noise strength in the noise layer.

Cloud computing enables computational resource-limited devices to economically outsource much computations to the cloud. Modular exponentiation is one of the most expensive operations in public key cryptographic protocols, and such operation may be a heavy burden for the resource-constraint devices. Previous works for secure outsourcing modular exponentiation which use one or two untrusted cloud server model or have a relatively large computational overhead, or do not support the 100% possibility for the checkability. In this letter, we propose a new efficient and verifiable algorithm for securely outsourcing modular exponentiation in the two untrusted cloud server model. The algorithm improves efficiency by generating random pairs based on EBPV generators, and the algorithm has 100% probability for the checkability while preserving the data privacy.

A novel superpixel segmentation approach driven by uniform mixture model with spatially constrained (UMMS) is proposed. Under this algorithm, each observation, i.e. pixel is first represented as a five-dimensional vector which consists of colour in CLELAB space and position information. And then, we define a new uniform distribution through adding pixel position, so that this distribution can describe each pixel in input image. Applied weighted 1-Norm to difference between pixels and mean to control the compactness of superpixel. In addition, an effective parameter estimation scheme is introduced to reduce computational complexity. Specifically, the invariant prior probability and parameter range restrict the locality of superpixels, and the robust mean optimization technique ensures the accuracy of superpixel boundaries. Finally, each defined uniform distribution is associated with a superpixel and the proposed UMMS successfully implements superpixel segmentation. The experiments on BSDS500 dataset verify that UMMS outperforms most of the state-of-the-art approaches in terms of segmentation accuracy, regularity, and rapidity.

Numerous applications such as autonomous driving, satellite imagery sensing, and biomedical imaging use computer vision as an important tool for perception tasks. For Intelligent Transportation Systems (ITS), it is required to precisely recognize and locate scenes in sensor data. Semantic segmentation is one of computer vision methods intended to perform such tasks. However, the existing semantic segmentation tasks label each pixel with a single object's class. Recognizing object attributes, e.g., pedestrian orientation, will be more informative and help for a better scene understanding. Thus, we propose a method to perform semantic segmentation with pedestrian attribute recognition simultaneously. We introduce an attribute-aware loss function that can be applied to an arbitrary base model. Furthermore, a re-annotation to the existing Cityscapes dataset enriches the ground-truth labels by annotating the attributes of pedestrian orientation. We implement the proposed method and compare the experimental results with others. The attribute-aware semantic segmentation shows the ability to outperform baseline methods both in the traditional object segmentation task and the expanded attribute detection task.

There is currently much interest in the development of Optic Wireless and Visible Light Communication (VLC) systems in the ITS field. Research in VLC and boomerang systems in particular often remain at a theoretical or computer-simulated level. This paper reports the 3-stage development of a boomerang prototype communication and ranging system using visible light V2V communication via LEDs and photodiodes, with direct-sequence spread spectrum techniques. The system uses simple and widely available components aiming for a low-cost frugal innovation approach. Results show that while we have to improve the prototype distance measurement unit due to a margin of error, simultaneous communication and ranging is possible with our newly designed prototype. The benefits of further research and development of boomerang technology prototypes are confirmed.

In cognitive radio (CR) networks, spectrum sensing is an essential task for enabling dynamic spectrum sharing. However, the problem becomes quite challenging in wideband spectrum sensing due to high sampling pressure, limited power and computing resources, and serious channel fading. To overcome these challenges, this paper proposes a distributed collaborative spectrum sensing scheme based on 1-bit compressive sensing (CS). Each secondary user (SU) performs local 1-bit CS and obtains support estimate information from the signal reconstruction. To utilize joint sparsity and achieve spatial diversity, the support estimate information among the network is fused via the average consensus technique based on distributed computation and one-hop communications. Then the fused result on support estimate is used as priori information to guide the next local signal reconstruction, which is implemented via our proposed weighted binary iterative hard thresholding (BIHT) algorithm. The local signal reconstruction and the distributed fusion of support information are alternately carried out until reliable spectrum detection is achieved. Simulations testify the effectiveness of our proposed scheme in distributed CR networks.

The similarity of words extracted from the rich text relation network is the main way to calculate the semantic similarity. Complex relational information and text content in Wikipedia website, Community Question Answering and social network, provide abundant corpus for semantic similarity calculation. However, most typical research only focused on single relationship. In this paper, we propose a semantic similarity calculation model which integrates multiple relational information, and map multiple relationship to the same semantic space through learning representing matrix and semantic matrix to improve the accuracy of semantic similarity calculation. In experiments, we confirm that the semantic calculation method which integrates many kinds of relationships can improve the accuracy of semantic calculation, compared with other semantic calculation methods.

Because of its high throughput potentiality on short-range communications and inherent superiority of high precision on ranging and localization, ultra-wideband (UWB) technology has been attracting attention continuously in research and development (R&D) as well as in commercialization. The first domestic regulation admitting indoor UWB in Japan was released by the Ministry of Internal Affairs and Communications (MIC) in 2006. Since then, several revisions have been made in conjunction with UWB commercial penetration, emerging new trends of industrial demands, and coexistence evaluation with other wireless systems. However, it was not until May 2019 that MIC released a new revision to admit outdoor UWB. Meanwhile, the IEEE 802 LAN/MAN Standards Committee has been developing several UWB related standards or amendments accordingly for supporting different use cases. At the time when this paper is submitted, a new amendment known as IEEE 802.15.4z is undergoing drafting procedure which is expected to enhance ranging ability for impulse radio UWB (IR-UWB). In this paper, we first review the domestic UWB regulation and some of its revisions to get a picture of the domestic regulation transition from indoor to outdoor. We also foresee some anticipating changes in future revisions. Then, we overview several published IEEE 802 standards or amendments that are related to IR-UWB. Some features of IEEE 802.15.4z in drafting are also extracted from open materials. Finally, we show with our recent research results that time bias internal a transceiver becomes important for increasing localization accuracy.

Let us consider a situation where someone wants to encrypt his/her will on an existing blockchain, e.g. Bitcoin, and allow an encrypted will to be decryptable only if designated members work together. At a first glance, such a property seems to be easily provided by using conventional threshold encryption. However, this idea cannot be straightforwardly implemented since key pairs for an encryption mechanism is additionally required. In this paper, we propose a new threshold encryption scheme in which key pairs for ECDSA that are already used in the Bitcoin protocol can be directly used as they are. Namely, a unique key pair can be simultaneously used for both ECDSA and our threshold encryption scheme without losing security. Furthermore, we implemented our scheme on the Bitcoin regtest network, and show that it is fairly practical. For example, the execution time of the encryption algorithm Enc (resp., the threshold decryption algorithm Dec) is 0.2sec. (resp., 0.3sec.), and the total time is just only 3sec. including all the cryptographic processes and network communications for a typical parameter setting. Also, we discuss several applications of our threshold encryption scheme in detail: Claiming priority of intellectual property, sealed-bid auction, lottery, and coin tossing service.

A drastic increase in cyberattacks targeting Internet of Things (IoT) devices using telnet protocols has been observed. IoT malware continues to evolve, and the diversity of OS and environments increases the difficulty of executing malware samples in an observation setting. To address this problem, we sought to develop an alternative means of investigation by using the telnet logs of IoT honeypots and analyzing malware without executing it. In this paper, we present a malware classification method based on malware binaries, command sequences, and meta-features. We employ both unsupervised or supervised learning algorithms and text-mining algorithms for handling unstructured data. Clustering analysis is applied for finding malware family members and revealing their inherent features for better explanation. First, the malware binaries are grouped using similarity analysis. Then, we extract key patterns of interaction behavior using an N-gram model. We also train a multiclass classifier to identify IoT malware categories based on common infection behavior. For misclassified subclasses, second-stage sub-training is performed using a file meta-feature. Our results demonstrate 96.70% accuracy, with high precision and recall. The clustering results reveal variant attack vectors and one denial of service (DoS) attack that used pure Linux commands.

In this paper, we propose secure dictionary learning based on a random unitary transform for sparse representation. Currently, edge cloud computing is spreading to many application fields including services that use sparse coding. This situation raises many new privacy concerns. Edge cloud computing poses several serious issues for end users, such as unauthorized use and leak of data, and privacy failures. The proposed scheme provides practical MOD and K-SVD dictionary learning algorithms that allow computation on encrypted signals. We prove, theoretically, that the proposal has exactly the same dictionary learning estimation performance as the non-encrypted variant of MOD and K-SVD algorithms. We apply it to secure image modeling based on an image patch model. Finally, we demonstrate its performance on synthetic data and a secure image modeling application for natural images.