The study proposes a personalised session-based recommender system that embeds items by using Word2Vec and sequentially updates the session and user embeddings with the hierarchicalization and aggregation of item embeddings. To process a recommendation request, the system constructs a real-time user embedding that considers users’ general preferences and sequential behaviour to handle short-term changes in user preferences with a low computational cost. The system performance was experimentally evaluated in terms of the accuracy, diversity, and novelty of the ranking of recommended items and the training and prediction times of the system for three different datasets. The results of these evaluations were then compared with those of the five baseline systems. According to the evaluation experiment, the proposed system achieved a relatively high recommendation accuracy compared with baseline systems and the diversity and novelty scores of the proposed system did not fall below 90% for any dataset. Furthermore, the training times of the Word2Vec-based systems, including the proposed system, were shorter than those of FPMC and GRU4Rec. The evaluation results suggest that the proposed recommender system succeeds in keeping the computational cost for training low while maintaining high-level recommendation accuracy, diversity, and novelty.

Webpage texts are often emphasized by decorations such as bold, italic, underline, and text color using HTML (HyperText Markup Language) tags and CSS (Cascading Style Sheets). However, users with visual impairment often struggle to recognize decorations appropriately because most screen readers do not read decorations appropriately. To overcome this limitation, we propose a method to read emphasized texts by changing the reading voice parameters of a screen reader and adding sound effects. First, the strong emphasis types and reading voices are investigated. Second, the intensity of the emphasis type is used to calculate a score. Then the score is used to assign the reading method for the emphasized text. Finally, the proposed method is evaluated by users with and without visual impairment. The proposed method can convey emphasized texts, but future improvements are necessary.

An efficient optical power splitter constructed by a metal-dielectric-metal plasmonic waveguide with a resonator structure has been analyzed. The method of solution is the finite difference time domain (FD-TD) method with the piecewise linear recursive convolution (PLRC) method. The resonator structure consists of input/output waveguides and a narrow waveguide with a T-junction. The power splitter with the resonator structure is expressed by an equivalent transmission-line circuit. We can find that the transmittance and reflectance calculated by the FD-TD method and the equivalent circuit are matched when the difference in width between the input/output waveguides and the narrow waveguide is small. It is also shown that the transmission wavelength can be adjusted by changing the narrow waveguide lengths that satisfy the impedance matching condition in the equivalent circuit.

To reduce the common mode voltage (CMV), suppress the CMV spikes, and improve the steady-state performance, a simplified reactive torque model predictive control (RT-MPC) for induction motors (IMs) is proposed. The proposed prediction model can effectively reduce the complexity of the control algorithm with the direct torque control (DTC) based voltage vector (VV) preselection approach. In addition, the proposed CMV suppression strategy can restrict the CMV within ±Vdc/6, and does not require the exclusion of non-adjacent non-opposite VVs, thus resulting in the system showing good steady-state performance. The effectiveness of the proposed design has been tested and verified by the practical experiment. The proposed algorithm can reduce the execution time by an average of 26.33% compared to the major competitors.

Model-based sensorless control of permanent magnet synchronous motor (PMSM) is promising for high-speed operation to estimate motor state, which is the speed and the position of the rotor, via electric signals of the stator, beside the inevitable fact that estimation accuracy is degraded by electromagnet interference (EMI) from switching devices of the converter. In this paper, the simulation system based on Luenberger observer and phase-locked loop (PLL) has been established, analyzing impacts of EMI on motor state estimations theoretically, exploring influences of EMI with different cutoff frequency, rated speeds, frequencies and amplitudes. The results show that Luenberger observer and PLL have strong immunity, which enable PMSM can still operate stably even under certain degrees of interference. EMI produces sideband harmonics that enlarge pulsation errors of speed and position estimations. Additionally, estimation errors are positively correlated with cutoff frequency of low-pass filter and the amplitude of EMI, and negatively correlated with rated speed of the motor and the frequency of EMI.  When the frequency is too high, its effects on motor state estimations are negligible. This work contributes to the comprehensive understanding of how EMI affects motor state estimations, which further enhances practical application of sensorless PMSM.

With the development of drone technology, concerns have arisen about the possibility of drones being equipped with threat payloads for terrorism and other crimes. A drone detection system that can detect drones carrying payloads is needed. A drone’s propeller rotation frequency increases with payload weight. Therefore, a method for estimating propeller rotation frequency will effectively detect the presence or absence of a payload and its weight. In this paper, we propose a method for classifying the payload weight of a drone by estimating its propeller rotation frequency from radar images obtained using a millimeter-wave fast-chirp-modulation multiple-input and multiple-output (MIMO) radar. For each drone model, the proposed method requires a pre-prepared reference dataset that establishes the relationships between the payload weight and propeller rotation frequency. Two experimental measurement cases were conducted to investigate the effectiveness of our proposal. In case 1, we assessed four drones (DJI Matrice 600, DJI Phantom 3, DJI Mavic Pro, and DJI Mavic Mini) to determine whether the propeller rotation frequency of any drone could be correctly estimated. In case 2, experiments were conducted on a hovering Phantom 3 drone with several payloads in a stable position for calculating the accuracy of the payload weight classification. The experimental results indicated that the proposed method could estimate the propeller rotation frequency of any drone and classify payloads in a 250 g step with high accuracy.

Cloud gaming systems allow users to play games that require high-performance computational capability on their mobile devices at any location. However, playing games through cloud gaming systems increases the Round-Trip Time (RTT) due to increased network delay. To simulate a local gaming experience for cloud users, we must minimize RTTs, which include network delays. The speculative video transmission pre-generates and encodes video frames corresponding to all possible user inputs and sends them to the user before the user’s input. The speculative video transmission mitigates the network, whereas a simple solution significantly increases the video traffic. This paper proposes tile-wise delta detection for traffic reduction of speculative video transmission. More specifically, the proposed method determines a reference video frame from the generated video frames and divides the reference video frame into multiple tiles. We calculate the similarity between each tile of the reference video frame and other video frames based on a hash function. Based on calculated similarity, we determine redundant tiles and do not transmit them to reduce traffic volume in minimal processing time without implementing a high compression ratio video compression technique. Evaluations using commercial games showed that the proposed method reduced 40-50% in traffic volume when the SSIM index was around 0.98 in certain genres, compared with the speculative video transmission method. Furthermore, to evaluate the feasibility of the proposed method, we investigated the effectiveness of network delay reduction with existing computational capability and the requirements in the future. As a result, we found that the proposed scheme may mitigate network delay by one to two frames, even with existing computational capability under limited conditions.

Information-centric networking (ICN) provides low-latency content delivery with in-network caching, but delivery latency depends on cache distance from consumers. To reduce delivery latency, a scheme to cluster domains and retain the main popular content in each cluster with a cache distribution range has been proposed, which enables consumers to retrieve content from neighboring clusters/caches. However, when the distribution of content popularity changes, all content caches may not be distributed adequately in a cluster, so consumers cannot retrieve them from nearby caches. We therefore propose a dynamic clustering scheme to adjust the cache distribution range in accordance with the change in content popularity and evaluate the effectiveness of the proposed scheme through simulation.

In software defined network (SDN), packet processing is commonly implemented using match-action model, where packets are processed based on matched actions in match action table. Due to the limited FPGA on-board resources, it is an important challenge to achieve large-scale high throughput based on exact matching (EM), while solving hash conflicts and out-of-order problems. To address these issues, this study proposed an FPGA-based EM table that leverages shared rule tables across multiple pipelines to eliminate memory replication and enhance overall throughput. An out-of-order reordering function is used to ensure packet sequencing within the pipelines. Moreover, to handle collisions and increase load factor of hash table, multiple hash table blocks are combined and an auxiliary CAM-based EM table is integrated in each pipeline. To the best of our knowledge, this is the first time that the proposed design considers the recovery of out-of-order operations in multi-channel EM table for high-speed network packets processing application. Furthermore, it is implemented on Xilinx Alveo U250 field programmable gate arrays, which has a million rules and achieves a processing speed of 200 million operations per second, theoretically enabling throughput exceeding 100 Gbps for 64-Byte size packets.

The very high path loss caused by molecular absorption becomes the biggest problem in Terahertz (THz) wireless communications. Recently, the multi-band ultra-massive multi-input multi-output (UM-MIMO) system has been proposed to overcome the distance problem. In UM-MIMO systems, the impact of mutual coupling among antennas on the system performance is unable to be ignored because of the dense array. In this letter, a channel model of UM-MIMO communication system is developed which considers coupling effect. The effect of mutual coupling in the subarray on the functionality of the system has been investigated through simulation studies, and reliable results have been derived.

Automatic detection of prohibited items is vital in helping security staff be more efficient while improving the public safety index. However, prohibited item detection within X-ray security inspection images is limited by various factors, including the imbalance distribution of categories, diversity of prohibited item scales, and overlap between items. In this paper, we propose to leverage the Poisson blending algorithm with the Canny edge operator to alleviate the imbalance distribution of categories maximally in the X-ray images dataset. Based on this, we improve the cascade network to deal with the other two difficulties. To address the prohibited scale diversity problem, we propose the Re-BiFPN feature fusion method, which includes a coordinate attention atrous spatial pyramid pooling (CA-ASPP) module and a recursive connection. The CA-ASPP module can implicitly extract direction-aware and position-aware information from the feature map. The recursive connection feeds the CA-ASPP module processed multi-scale feature map to the bottom-up backbone layer for further multi-scale feature extraction. In addition, a Rep-CIoU loss function is designed to address the overlapping problem in X-ray images. Extensive experimental results demonstrate that our method can successfully identify ten types of prohibited items, such as Knives, Scissors, Pressure, etc. and achieves 83.4% of mAP, which is 3.8% superior to the original cascade network. Moreover, our method outperforms other mainstream methods by a significant margin.

In this paper, we consider distributed decision-making over directed time-varying multi-agent systems. We consider an adversarial bandit problem in which a group of agents chooses an option from among multiple arms to maximize the total reward. In the proposed method, each agent cooperatively searches for the optimal arm with the highest reward by a consensus-based distributed Exp3 policy. To this end, each agent exchanges the estimation of the reward of each arm and the weight for exploitation with the nearby agents on the network. To unify the explored information of arms, each agent mixes the estimation and the weight of the nearby agents with their own values by a consensus dynamics. Then, each agent updates the probability distribution of arms by combining the Hedge algorithm and the uniform search. We show that the sublinearity of a pseudo-regret can be achieved by appropriately setting the parameters of the distributed Exp3 policy.

Control of complex networks such as gene regulatory networks is one of the fundamental problems in control theory. A Boolean network (BN) is one of the mathematical models in complex networks, and represents the dynamic behavior by Boolean functions. In this paper, a solution method for the finite-time control problem of BNs is proposed using a BDD (binary decision diagram). In this problem, we find all combinations of the initial state and the control input sequence such that a certain control specification is satisfied. The use of BDDs enables us to solve this problem for BNs such that the conventional method cannot be applied. First, after the outline of BNs and BDDs is explained, the problem studied in this paper is given. Next, a solution method using BDDs is proposed. Finally, a numerical example on a 67-node BN is presented.

In interdependent systems, such as electric power systems, entities or components mutually depend on each other. Due to these interdependencies, a small number of initial failures can propagate throughout the system, resulting in catastrophic system failures. This paper addresses the problem of finding the set of entities whose failures will have the worst effects on the system. To this end, a two-phase algorithm is developed. In the first phase, the tight bound on failure propagation steps is computed using a Boolean Satisfiablility (SAT) solver. In the second phase, the problem is formulated as an Integer Linear Programming (ILP) problem using the obtained step bound and solved with an ILP solver. Experimental results show that the algorithm scales to large problem instances and outperforms a single-phase algorithm that uses a loose step bound.

A PBN is well known as a mathematical model of complex network systems such as gene regulatory networks. In Boolean networks, interactions between nodes (e.g., genes) are modeled by Boolean functions. In PBNs, Boolean functions are switched probabilistically. In this paper, for a PBN, a simplified representation that is effective in analysis and control is proposed. First, after a polynomial representation of a PBN is briefly explained, a simplified representation is derived. Here, the steady-state value of the expected value of the state is focused, and is characterized by a minimum feedback vertex set of an interaction graph expressing interactions between nodes. Next, using this representation, input selection and stabilization are discussed. Finally, the proposed method is demonstrated by a biological example.

In cyber-physical systems (CPSs) that interact between physical and information components, there are many sensors that are connected through a communication network. In such cases, the reduction of communication costs is important. Event-triggered control that the control input is updated only when the measured value is widely changed is well known as one of the control methods of CPSs. In this paper, we propose a design method of output feedback controllers with decentralized event-triggering mechanisms, where the notion of uniformly ultimate boundedness is utilized as a control specification. Using this notion, we can guarantee that the state stays within a certain set containing the origin after a certain time, which depends on the initial state. As a result, the number of times that the event occurs can be decreased. First, the design problem is formulated. Next, this problem is reduced to a BMI (bilinear matrix inequality) optimization problem, which can be solved by solving multiple LMI (linear matrix inequality) optimization problems. Finally, the effectiveness of the proposed method is presented by a numerical example.

In this paper, we consider a distributed stochastic nonconvex optimization problem for multiagent systems. We propose a distributed stochastic gradient-tracking method with event-triggered communication. A group of agents cooperatively finds a critical point of the sum of local cost functions, which are smooth but not necessarily convex. We show that the proposed algorithm achieves a sublinear convergence rate by appropriately tuning the step size and the trigger threshold. Moreover, we show that agents can effectively solve a nonconvex optimization problem by the proposed event-triggered algorithm with less communication than by the existing time-triggered gradient-tracking algorithm. We confirm the validity of the proposed method by numerical experiments.

We address a path planning problem for heterogeneous multi-robot systems under specifications consisting of temporal constraints and routing tasks such as package delivery services. The robots are partitioned into several groups based on their dynamics and specifications. We introduce a concise description of such tasks, called a work, and extend counting LTL to represent such specifications. We convert the problem into an ILP problem. We show that the number of variables in the ILP problem is fewer than that of the existing method using cLTL+. By simulation, we show that the computation time of the proposed method is faster than that of the existing method.

A 150 GHz fundamental oscillator employing an inter-stage matching network based on a transmission line is presented in this letter. The proposed oscillator consists of a two-stage common-emitter amplifier loop, whose inter-stage connections are optimized to meet the oscillation condition. The oscillator is designed in a 130-nm SiGe BiCMOS process that offers fT and fMAX of 350 GHz and 450 GHz. According to simulation results, an output power of 3.17 dBm is achieved at 147.6 GHz with phase noise of -115 dBc/Hz at 10 MHz offset and figure-of-merit (FoM) of -180 dBc/Hz.

A wireless sensor terminal module of 5cc size (2.5 cm × 2.5 cm × 0.8 cm) that does not require a battery is proposed by integrating three kinds of circuit technologies. (i) a low-power sensor interface: an FM modulation type CMOS sensor interface circuit that can operate with a typical power consumption of 24.5 μW was fabricated by the 0.7-μm CMOS process technology. (ii) power supply to the sensor interface circuit: a wireless power transmission characteristic to a small-sized PCB spiral coil antenna was clarified and applied to the module. (iii) wireless sensing from the module: backscatter communication technology that modulates the signal from the base terminal equipment with sensor information and reflects it, which is used for the low-power sensing operation. The module fabricated includes a rectifier circuit with the PCB spiral coil antenna that receives wireless power transmitted from base terminal equipment by electromagnetic resonance coupling and converts it into DC power and a sensor interface circuit that operates using the power. The interface circuit modulates the received signal with the sensor information and reflects it back to the base terminal. The module could achieve 100 mm communication distance when 0.4 mW power is feeding to the sensor terminal.