Search

In this paper, we propose a Hierarchical Multimodal Variational Encoder-Decoder (HMMVED) to predict the popularity of micro-videos by comprehensively leveraging the user information and micro-video content in a hierarchical fashion. In particular, the multimodal variational encoder-decoder framework encodes the input modalities to a lower dimensional stochastic variable, from which the popularity of micro-videos can be decoded. Considering the important role of users social influence in social media for information dissemination, a user encoderdecoder is designed to learn the user Gaussian embedding from the user information, which is informative about the coarsegrained popularity for the micro-videos uploaded by the user. The learned user embedding then acts as the prior of the micro-video latent embeddings in the micro-video encoder-decoder, where the refined posterior embedding of the micro-video is obtained by taking the multimodal content into consideration. The finegrained popularity of each micro-video is generated from the posterior embedding of the micro-video. Based on the multimodal extension of variational information bottleneck theory, we show that the learned latent embeddings of micro-videos are maximally expressive about the popularity whilst maximally compressing the information from input modalities. Extensive experiments conducted on two real-world datasets demonstrate the effectiveness of the proposed method. Codes and datasets are available at: https://github.com/JennyXieJiayi/HMMVED.

With the help of inter-vehicle communication (IVC), autonomous vehicles (AVs) can drive cooperatively, thus significantly improve road safety, traffic efficiency, and environmental sustainability. While substantial research has been conducted to investigate the efficiency of AVs in transportation systems, few attempts have been carried out to explore the lane-changing operations of AVs in multi-lane freeways, especially the dynamics of AVs at lane-drop bottlenecks. To this end, this paper aims to develop a cooperative space distribution method (CSDM) not only to increase the lane-drop bottleneck's throughput but also to equally distribute the AVs in the dropped lane to other lanes by efficiently coordinating the dynamics of AVs upstream of the bottleneck in a multi-lane freeway. More specifically, we propose a novel framework where the freeway (region of interest) is divided into three segments: i) platoon segment, ii) acceleration segment, and iii) merging segment. In the first segment, AVs travel together in the platoon to guarantee their safety; they will then speed up to attain the maximum velocity and reach the determined position in the second segment. Finally, these AVs change lanes in the last segment and pass through the bottleneck with maximum velocity and minimum gap (i.e., gap distance). Simulation results are tested to demonstrate the performance of the proposed method, where we show that the proposed framework can significantly decrease the average travel time of all vehicles.

Multiview clustering (MVC) has recently been the focus of much attention due to its ability to partition data from multiple views via view correlations. However, most MVC methods only learn either interfeature correlations or intercluster correlations, which may lead to unsatisfactory clustering performance. To address this issue, we propose a novel dual-correlated multivariate information bottleneck (DMIB) method for MVC. DMIB is able to explore both interfeature correlations (the relationship among multiple distinct feature representations from different views) and intercluster correlations (the close agreement among clustering results obtained from individual views). For the former, we integrate both view-shared feature correlations discovered by learning a shared discriminative feature subspace and view-specific feature information to fully explore the interfeature correlation. This allows us to attain multiple reliable local clustering results of different views. Following this, we explore the intercluster correlations by learning the shared mutual information over different local clusterings for an improved global partition. By integrating both correlations, we formulate the problem as a unified information maximization function and further design a two-step method for optimization. Moreover, we theoretically prove the convergence of the proposed algorithm, and discuss the relationships between our method and several existing clustering paradigms. The experimental results on multiple datasets demonstrate the superiority of DMIB compared to several state-of-the-art clustering methods.

The pattern recognition of surface electromyography (sEMG) signal is an important application in the realization of human-machine interface. However, due to the disturbance of human body, sensors and environment, sEMG signal usually contains lots of noise, which brings great challenges to the high-accuracy sEMG pattern recognition. In addition, embedded human wearable devices are becoming more and more popular nowadays. How to realize the sEMG recognition method with low power consumption and high noise immunity has also become a difficult and very meaningful research topic. In this paper, a spiking neural network (SNN) classification method based on second-order information bottleneck training is proposed. Firstly, the training loss function for classification neural networks is constructed based on the proposed second-order information bottleneck. The method is used to train the conventional continuous-valued neural network and convert it into an SNN model with equivalent structure and connection weights. Then, the converted SNN is used to classify the sEMG signal patterns. Through a series of theoretical analysis and experimental results, it is proved that this method has significant advantages in terms of generalization of network determination and computational efficiency. The experimental code can be accessed from https://github.com/anvien/2OIB-for-sEMG-Recognition.

This paper develops a bottleneck model in which the capacity of the bottleneck is assumed to be stochastic and follow a general distribution that has a positive upper bound. The user equilibrium principle in terms of mean trip cost is adopted to formulate commuters’ departure time choice in the stochastic bottleneck. We find that there exist five possible equilibrium departure patterns, which depend on both commuters’ unit costs of travel time, schedule delay early and late, and the uncertainty of the stochastic capacity of the bottleneck. All possible equilibrium departure patterns are analytically derived. Both the analytical and numerical results show that increasing the uncertainty of the capacity of the bottleneck leads to an increase of commuters’ individual mean trip cost. In addition, both a time-varying toll scheme and a single-step coarse toll scheme are designed within the proposed stochastic bottleneck model. We provide an analytical method to determine the detailed toll-charging schemes for both toll strategies. The numerical results show that the proposed toll schemes can indeed improve the efficiency of the stochastic bottleneck in terms of decreasing mean total social cost, and the time-varying toll scheme is more efficient than the single-step coarse toll scheme. However, as the uncertainty of the capacity of the bottleneck increases, the efficiency of the time-varying toll scheme decreases, whereas the efficiency of the single-step coarse toll scheme fluctuates slightly.

Deep neural networks are a key component of behavior prediction and motion generation for self-driving cars. One of their main drawbacks is a lack of transparency: they should provide easy to interpret rationales for what triggers certain behaviors. We propose an architecture called Attentional Bottleneck with the goal of improving transparency. Our key idea is to combine visual attention, which identifies what aspects of the input the model is using, with an information bottleneck that enables the model to only use aspects of the input which are important. This not only provides sparse and interpretable attention maps (e.g. focusing only on specific vehicles in the scene), but it adds this transparency at no cost to model accuracy. In fact, we find improvements in accuracy when applying Attentional Bottleneck to the ChauffeurNet model, whereas we find that the accuracy deteriorates with a traditional visual attention model.

Cloud computing applications have grown rapidly in the last decade, where many organizations are migrating their applications to cloud data center as they expected high performance, reliability, and the best quality of service. Data centers deploy a variety of technologies, such as software-defined networks (SDN), to effectively manage their resources. The SDN approach is a highly flexible network architecture that automates network configuration using a centralized controller to overcome traditional network limitations. This paper proposes an SDN-based monitoring algorithm to detect the performance anomaly and identify the bottleneck of the distributed application in the cloud data center using the support vector machine algorithm. It collects the data from the network devices and calculates the performance metrics for the distributed application components that are used to train the SVM algorithm and build a baseline model of the normal behavior of the distributed application. The SVM model detects performance anomaly behavior and identifies the root cause of bottlenecks using one-class support vector machine (OCSVM) and multi-class support vector machine (MCSVM) algorithms. The proposed method does not require any knowledge about the running applications or depends on static threshold values for performance measurements. Simulation results show that the proposed method can detect and locate the failure occurrences efficiently with high precision and low overhead compared to statistical methods, Naive Bayes Classifier and the decision tree machine learning method.

This paper proposes a bottleneck model for managing the ship lock congestion in an inland waterway caused by the uneven temporal distribution of ship traffic demand. Due to safety checks and regular maintenance, the lock only works within a specified time window during a day. A bottleneck model with a service time window is presented to describe the dynamic scheduling process of the ships passing through the lock. The properties of the proposed model are investigated. To alleviate ships' delays at the lock area, two congestion tolling schemes (i.e., first-best and second-best) and a novel administrative scheme of moving the service time window (MST) are explored together with a combined scheme of tolling and MST. The results show that the ship's preferred departure time and the value of time for schedule delay matter in the choice of the counter-measures against ship traffic congestion. MST alone can be an effective substitute for the tolling schemes in most cases and it even outperforms the first-best tolling under certain conditions. This finding is appealing given the academic debate and public controversy raised by congestion tolling. Besides, combining MST with either tolling scheme can always yield higher efficiency. However, the benefits of MST can be marginal or even zero when the difference between the ship's preferred departure time and lock's initial service start time is around a certain value. In such cases, the authority should be cautious about combining any tolling scheme with MST since the implementation costs might outweigh the additional benefits brought by MST.

In production systems, the bottleneck is typically understood as the operation that affects the system performance in the strongest manner. Identification and mitigation of bottleneck are among the most important problems in production systems research and practice. The current literature offers numerous methods for the identification of production bottlenecks. Most of these methods focus on steady-state system behavior under constant parameters, and the corresponding mitigation approach is typically to prioritize the improvement of that particular operation. This applies when the improvement cannot be dynamically reallocated to other operations in the system, and the improvement is to be fixed to an operation for a long period of time. In this article, we attempt to study the bottleneck problem in a dynamic environment. Especially, we consider serial production lines with finite capacity buffers and the Bernoulli reliability machines and use a control-theoretic approach to formulate the bottleneck identification and mitigation problem as a state-based feedback control problem with the objective being the maximization of steady-state throughput. Computation formulas and procedures are developed to calculate the performance metrics of such systems with dynamic bottleneck control. Properties of the optimal control policies are investigated, and a computationally efficient algorithm is developed to obtain an effective real-time bottleneck indicator. Numerical experiments are used to demonstrate the efficacy of the proposed method, and a case study is presented to illustrate its application. Note to Practitioners —It is very common in manufacturing practice that operators, engineers, and managers need to make decisions on-the-fly to ensure efficient production operations. One of the key tasks involved is to identify real-time bottleneck (RTBN). This is typically carried out based on the practitioners’ intuition and experience. With the advances in sensing, computing, and communication technologies emerging in the Industry 4.0 era, manufacturers now have the capability to collect, process, and visualize an enormous amount of data in real time. This provides a foundation for more rigorous real-time production management and control. The research described in this article is intended to provide such a tool for RTBN identification in production lines and, thus, guide timely decision-making on the factory floor for smarter production activities.

Consider the following setup: Through a joint design, multiple observations of a remote data source shall be locally compressed before getting transmitted via several error-prone , rate-limited forward links to a (distant) processing unit. For addressing this specific instance of multiterminal Joint Source-Channel Coding problem, in this article, the foundational principle of the Information Bottleneck method is fully extended to obtain purely statistical design approaches, enjoying the Mutual Information as their fidelity criterion. Specifically, the forms of stationary points for two types of distributed compression schemes are characterized here. Subsequently, those acquired solutions are utilized as the centerpiece of the proposed generic, iterative algorithm, termed the Multiterminal Forward-Aware Vector Information Bottleneck (M-FAVIB) , for addressing the design optimizations. Leveraging an unfolding trick, it will be proven that both distributed compression schemes fall into the category of Successive Upper-Bound Minimization , ensuring their convergence to a stationary point. Eventually, the effectiveness of the proposed compression schemes will be substantiated as well by means of numerical investigations over some typical transmission scenarios.

Deep metric learning aims to learn a non-linear function that maps raw-data to a discriminative lower-dimensional embedding space, where semantically similar samples have larger similarity than dissimilar ones. Most existing approaches process each raw-data in two steps, by mapping the raw-data to a higher-dimensional feature space via a fixed backbone, followed by mapping the higher-dimensional feature space to a lower-dimensional embedding space via a linear layer. This paradigm, however, inevitably leads to a Generalization Bottleneck (GB) problem. Specifically, GB refers to a limitation that the generalization capacity of lower-dimensional embedding space is inferior to the higher-dimensional feature space in the test stage. To mitigate the capacity gap between feature space and embedding space, we propose to introduce a fully-learnable module, dubbed Relational Knowledge Preserving (RKP), that improves the generalization capacity of lower-dimensional embedding space by transferring the mutual similarity of instances. Our proposed RKP module can be integrated into a general deep metric learning approach. And, experiments conducted on different benchmarks show that it can significantly improve the performance of original model.

Human Activity Recognition (HAR) in videos using convolution neural network become the preferred choice for researcher due to the tremendous success of deep learning models for visual recognition applications. After the invention of the low-cost depth sensor, multiple modalities based activity recognition systems were successfully developed in the past decade. Although it is always challenging to recognize the complex human activities in videos. In this work, we proposed a deep bottleneck multimodal feature fusion (D-BMFF) framework that fused three different modalities of RGB, RGB-D(depth) and 3D coordinates information for activity classification. It helps to better recognize and make full use of information available simultaneously from a depth sensor. During the training process RGB and depth, frames are fed at regular intervals for an activity video while 3D coordinates are first converted into single RGB skeleton motion history image (RGB-SklMHI). We have extracted the features from multimodal data inputs using the latest deep pre-trained network architecture. The multimodal feature obtained from bottleneck layers before the top layer is fused by using multiset discriminant correlation analysis (M-DCA), which allows for robust visual action modeling. Finally, using a linear multiclass support vector machine (SVM) method, the fused features are categorized. The proposed approach is evaluated over four standard RGB-D datasets: UT-Kinect, CAD-60, Florence 3D and SBU Interaction. Our framework produces outstanding results and outperformed the state-of-the-art methods.

Freeway bottleneck identification is an essential component in the process of deploying mitigation strategies to reduce congestion at freeway bottlenecks. Most previous studies on bottleneck identification focus on recurrent bottlenecks, and limited work has been conducted to identify the locations of non-recurrent bottlenecks. Therefore, in this study, we propose a new travel time reliability (TTR) measurement and develop a freeway bottleneck identification method based on this measurement, which can identify with high probability not only recurrent bottlenecks but also the locations of non-recurrent bottlenecks. The TTR measurement is developed based on statistical distance between travel time distributions. Three statistical distance measurements, Jensen–Shannon divergence, Wasserstein distance, and Hellinger distance, are applied in the TTR measurement. The bottleneck identification method is evaluated in a case study on I-15 freeway corridor in Salt Lake City, Utah. The three statistical distance measurements show good consistency in ranking locations by the impacts of recurrent and non-recurrent congestion, especially for extreme cases with very high or low variation between travel time distributions. The recurrent bottlenecks identified in this study show their clustering characteristics, which is similar to the generating and dismissing process of recurrent congestion. The locations with high probability of non-recurrent bottlenecks scatter both spatially and temporally, which agrees with the random characteristic of non-recurrent congestion.

Identifying, and eventually eliminating throughput bottlenecks, is a key means to increase throughput and productivity in production systems. In the real world, however, eliminating throughput bottlenecks is a challenge. This is due to the landscape of complex factory dynamics, with several hundred machines operating at any given time. Academic researchers have tried to develop tools to help identify and eliminate throughput bottlenecks. Historically, research efforts have focused on developing analytical and discrete event simulation modelling approaches to identify throughput bottlenecks in production systems. However, with the rise of industrial digitalisation and artificial intelligence (AI), academic researchers explored different ways in which AI might be used to eliminate throughput bottlenecks, based on the vast amounts of digital shop floor data. By conducting a systematic literature review, this paper aims to present state-of-the-art research efforts into the use of AI for throughput bottleneck analysis. To make the work of the academic AI solutions more accessible to practitioners, the research efforts are classified into four categories: (1) identify, (2) diagnose, (3) predict and (4) prescribe. This was inspired by real-world throughput bottleneck management practice. The categories, identify and diagnose focus on analysing historical throughput bottlenecks, whereas predict and prescribe focus on analysing future throughput bottlenecks. This paper also provides future research topics and practical recommendations which may help to further push the boundaries of the theoretical and practical use of AI in throughput bottleneck analysis.

The growing rate of technology improvements has caused dramatic advances in processor performances, causing significant speed-up of processor working frequency and increased amount of instructions which can be processed in parallel. The given development of processor's technology has brought performance improvements in computer systems, but not for all the types of applications. The reason for this resides in the well known Von-Neumann bottleneck problem which occurs during the communication between the processor and the main memory into a standard processor-centric system. This problem has been reviewed by many scientists, which proposed different approaches for improving the memory bandwidth and latency. This paper provides a brief review of these techniques and also gives a deep analysis of various memory- centric systems that implement different approaches of merging or placing the memory near to the processing elements. Within this analysis we discuss the advantages, disadvantages and the application (purpose) of several well-known memory-centric systems.

As an important branch of reinforcement learning, Apprenticeship learning studies how an agent learns good behavioral decisions by observing an expert policy from the environment. It has made many encouraging breakthroughs in real-world applications. State abstraction is typically used to compress the state space of the environment to eliminate redundant information, thereby improving learning efficiency. However, excessive compression results in poor decision performance. Therefore, it is important to balance the compression degree and decision performance. Deterministic Information Bottleneck for State abstraction (DIBS) attempts to solve this problem. Specifically, DIBS uses the information rate to represent the compression degree at first. Then, decision performance after compression is measured using the Kullback-Leibler (KL) divergence of distributions between the policy after state compression and the expert policy. However, if the two distributions do not have exactly overlapping support sets, then the KL divergence is usually infinity, which leads to poor decision performance under the low information rate. In this paper, we propose the Wasserstein DIBS (WDIBS) algorithm to optimize the trade-off between the compression degree and decision performance. Specifically, we use the Wasserstein distance to calculate the difference of the distributions between the policy after state compression and the expert policy. Even if the two distributions do not have precisely overlapping support sets, the Wasserstein distance can still reflect their actual difference, thereby ensuring that WDIBS has good decision performance under the low information rate. Theoretical analyses and experiments demonstrate that our method provides a better trade-off between the compression degree and decision performance than DIBS.

We experimentally investigated the flow of luggage-carrying pedestrians through a bottleneck in both normal and emergency situations. Based on trajectories, we analysed the temporal and spatial fea...

International audience; This article designs an optimal observer-based output feedback control for traffic breakdown to dissolve traffic congestion using the backstepping method and optimization. The linearized Aw–Rascle–Zhang model is used to represent the congested traffic dynamics resulting from traffic breakdown. Based on the factors leading to traffic breakdown, we take into account the boundary conditions consisting of a boundary with a constant density and a speed drop at the upstream inlet of a bottleneck, and a boundary with a disturbance of inflow (high traffic demand) at the inlet of the road segment under consideration. To dissolve traffic congestion, a dynamic feedback controller is designed at the upstream boundary. By using the backstepping approach, an observer-based output feedback controller is computed to guarantee the integral input-to-state stability of the closed-loop system. By establishing an optimization problem and solving it, the optimal value of the considered class controller is obtained. The performance of the output feedback controller is also validated by numerical simulations.

Polar code is one of the channel codes and is used in the 5th generation of mobile communication system (5G). This encoding scheme is based on the operation of channel polarization, and it is possible to achieve the capacity of arbitrary binary-input symmetric discrete memoryless channels. Compared with Turbo codes and LDPC (Low-Density Parity-Check) codes, the implementation of the encoder and decoder is easier. BP (Belief Propagation) decoding, one of the decoding methods of the polar codes, can be performed at high speed because it can decode in parallel. However, the disadvantages of the BP decoding are the hardware and computational complexities. The technique of quantization can be used to reduce complexities of hardware and calculation. One of the quantization methods is the information bottleneck method, which allows an observation variable to compressed one while trying to preserve the mutual information shared with a relevant variable. As a novel approach, the information bottleneck method is used in the design of quantizers for the BP decoding of LDPC codes. In this paper, we propose a discrete BP polar decoder that can use only unsigned integers in the decoding process by using the information bottleneck method. Thus, we can replace complex calculations of BP decoding with simple lookup tables. We also investigate the minimum bit width for quantization with negligible degradation and the suboptimal Eb/N0 for designing lookup tables, where Eb and N0 denote energy per bit and noise power density, respectively. The simulation results show that the proposed method can achieve almost the same error correcting capability compared with the BP decoding without compression in the range of low Eb/N0. Besides, we show that the proposed decoder can compress both channel outputs and BP messages with small loss compared with the uniform quantization decoder.

The uneven workload distribution and working time utilisation create a bottleneck, leading to inefficient utilisation of capacity and increased costs. A bottleneck is a limiting and risk factor for any business entity. In the case of a distribution warehouse, the bottleneck limits its ability to meet the requirements for sending an order within the required time limit. Delays at any phase of a distribution process may result in non-compliance with customer requirements. In solving capacity problems and bottlenecks elimination, computer simulations and optimisation are often used. The article presents a basic simulation analysis of workload distribution and work times, useful for logistics companies, thus for the area of human and financial resources. In the article, the use of simulations in the ExtendSim9 program to eliminate the bottleneck is discussed. The bottleneck is solved by experiments on a simulation model when optimal workers assignment to individual workplaces of the warehouse is sought. The two final proposals for workers allocation, with the current and increased number of workers, are compared in workforce utilisation and system stability. The simulation method allows verification of the proposals' impacts in advance and practically with no financial costs.

Battery-free wireless sensor networks (BF-WSNs) have captured the interest of research community in recent years. Compared with traditional battery-powered WSNs (BP-WSNs), BF-WSNs can prolong the lifetime of the network by exploiting ambient energy. Many-to-many communication is widely used in many applications of WSNs and the problem of minimum-latency many-to-many communication scheduling in BF-WSNs is of great significance. However, this problem has not been studied yet. The existing algorithms for BP-WSNs and BF-WSNs are not suitable for minimum-latency many-to-many scheduling problem in BF-WSNs. Also, different from BP-WSNs, energy-bottleneck nodes with low recharge rate and high workload in BF-WSNs make the problem more challenging. To address these issues, in this article, we first study the problem of many-to-many scheduling in BF-WSNs with the purpose of minimizing communication latency. The problem is formally defined and proved to be NP-hard. The energy-adaptive and bottleneck-aware scheduling algorithm for many to many in BF-WSNs is proposed. The correctness and average latency of the proposed algorithm are carefully analyzed. Extensive simulations show that our algorithm has high performance, in terms of communication latency and energy usage ratio. Furthermore, we also extend the proposed algorithm to other network models.

Most complex traits evolved in the ancestors of all modern humans and have been under negative or balancing selection to maintain the distribution of phenotypes observed today. Yet all large studies mapping genomes to complex traits occur in populations that have experienced the Out-of-Africa bottleneck. Does this bottleneck affect the way we characterise complex traits? We demonstrate using the 1000 Genomes dataset and hypothetical complex traits that genetic drift can strongly affect the joint distribution of effect size and SNP frequency, and that the bias can be positive or negative depending on subtle details. Characterisations that rely on this distribution therefore conflate genetic drift and selection. We provide a model to identify the underlying selection parameter in the presence of drift, and demonstrate that a simple sensitivity analysis may be enough to validate existing characterisations. We conclude that biobanks characterising more worldwide diversity would benefit studies of complex traits.

Valuing travel time reliability is an important element of travel choice modeling. In this paper, we introduce the notion of variation cost in the utility function, capturing the variations in both...

Car drivers have been suffering from road bottlenecks due to the constant increase in the number of vehicles that are not matched by the growth of the road network. Obstacles on a road or a road na...

As an advanced warning system, resource buffer can notify the use of resources and provide added protection to critical chain activities. However, most of the existing studies in the literature focus on locating actual time buffers at various locations. In this study, we locate bottleneck resource buffers along the critical chain and determines optimal time windows for the first time. Drawing on the theory of constraints, we take into account factors such as bottleneck resource sensitivity, the idle cost, the start time flexibility and the work flow on the critical chain, and develop a quantitative model for the optimal time window determination of resource buffer. The proposed method is tested and compared with the currently widely adopted buffer management method. Results of the computational experiment of the proposed method demonstrates its relative dominance over the predominant buffer management approach in terms of overall completion time, project cost, the probability of delay and the average buffer consumption ratio.

This paper investigates an event-triggered adaptive control strategy for multiple high-speed trains (MHSTs) with deception attacks in bottleneck sections. Firstly, the high-speed trains in the bottleneck section are mapped onto the same railway line. Then, the effect of deception attacks and the state information transmitted from leader train subject to deception attacks are introduced. In order to maintain safety operation, the position and speed limitations of high-speed trains are established as state constraints. An event-triggered adaptive control strategy consisting of adaptive controller, adaption laws, and event-triggered condition is designed to realize the cooperative control for MHSTs subject to deception attacks, state and input constraints. The stability and string stability of the proposed multi-train system is proved by applying the Lyapunov function method. Finally, a simulation example is given to show the effectiveness of the proposed method.

This paper considers two variants of the bottleneck Tower of Hanoi problems with n (≥1) discs and the bottleneck size b (≥2), which allows violation of the “divine rule” (at most) once. Denoting by MB3(n, b) the minimum number of moves required to solve the new variant of the bottleneck Tower of Hanoi problem, an explicit form of MB3(n, b) is found. Also, MB4(n, b) denotes the minimum number of moves required to solve the new variant of the bottleneck Reve’s puzzle, a closed-form expression of MB4(n, b) is derived. Journal of Bangladesh Academy of Sciences, Vol. 44, No. 2, 197-200, 2020

Recently, the introduction of Convolutional Neural Network (CNNs) has advanced the way of solving image segmentation tasks. Semantic image segmentation has considerably benefited from employing various CNN models. The most widely used network in this field is U-Net and its different variations. However, these models require significant number of trainable parameters, floating-point operations per second, and great computational power to be trained. These factors make real-time semantic segmentation in low powered devices very hard. Therefore, in the present paper, we aim to modify particular aspects of the U-Net model to improve its performance through developing a fast U-Net (FU-Net) relying on bottleneck convolution layers in the contraction and expansion paths of the model. The proposed model can be utilized in semantic segmentation applications even on the devices with limited computational power and memory by ensuring the state-of-the-art performance. The amount of memory required by the proposed model is reduced by 23 times when compared with the original U-Net. Moreover, the modifications allowed achieving better performance. In conducted experiments, we assessed the performance of the proposed model on two biomedical image segmentation datasets, namely 2018 Data Science Bowl and ICIS 2018: Skin Lesion Analysis Towards Melanoma Detection. FU-Net demonstrated the state-of-the-art results in biomedical image segmentation, requiring the number of trainable parameters reduced by eight times compared with the original U-Net model. In addition, using bottleneck layers decreased the number of computations, resulting in nearly 30% speed-up at the training, validation and test stages. Furthermore, despite relying on fewer parameters FU-Net achieved a slight improvement of the performance in terms of pixel accuracy, Jaccard index, and dice coefficient evaluation metrics.

With the arrival of the industrial big data era, it offers unprecedented opportunities for machine learning to intelligently uncover hidden tasks and restore the entire underlying process for business process modelling. While recent studies, e.g., process mining and ontologies, have advanced the research agenda of business process modelling and management, identifying a bottleneck task automatically needs more in-depth research. In this paper, a text mining-based bottleneck task identification approach is proposed. Firstly, to extract tasks from documents in different lengths, a dynamic sliding window is introduced to the biterm topic model. The sliding window size is adjusted according to document length during biterm selection process to ensure the two words in biterm comes from a context. Secondly, a fusion-based clustering algorithm is studied to uncover business tasks. The improved biterm topic model and the Doc2vec model are used to train two document vectors and then calculate two distances. The linear fusion of these two distances is used as the metric of clustering. Thirdly, the temporal frequency of each task at different periods is calculated to show the timeline and abnormal occurrence of tasks to identify bottleneck tasks. The proposed approach is evaluated using a data set containing the execution of a multi-year multidisciplinary student design project. The experiment results show the approach can effectively identify bottleneck tasks without manual intervention.

Carpooling as one of demand management measures is effective in reducing highway congestion. Recent studies have shown that an appropriate spatial allocation of bottleneck capacity between carpool lane and general-purpose lane can lead to peak-spread of the morning commuters' departure time and reduce the system's total trip cost. What is not clear however is whether temporal allocation of bottleneck capacity can also be effective and if so, what the impact would be, and furthermore what the combined effects of temporal-spatial allocation of bottleneck capacity would be. This paper investigates the impacts of a temporal allocation of bottleneck capacity, when carpool lane is available only within a reserved time window, and a joint temporal-spatial capacity allocation, on morning commute patterns. User equilibrium commute patterns are derived for both the temporal-only and the joint temporal-spatial capacity allocation schemes, along a highway corridor with two driving modes: solo driving and carpooling. The extra costs associated with carpooling are considered alongside of travel time and schedule delay costs. We identify three different cases representing the relative barriers and attractions of carpooling to commuters, and we show that the optimal capacity allocations are sensitive to the accurate estimation of the commuters' extra carpool cost. To assist in evaluating the difference between a non-optimal and the optimal temporal-spatial allocation schemes, we derive analytically the upper bounds on the efficiency loss and present numerical illustrations on how the upper bounds vary with the different operational and behavioral variables.

Operational bottlenecks are commonly observed in power systems and lead to severe system security issues, which may be caused by the fluctuating and uncertain nature of renewable energy. This paper presents an approach to define, identify and eliminate such bottlenecks in the scope of system balance for renewable energy integrated bulk power systems, so as to quantify the requirement of energy storage. A mixed-integer linear programming (MILP) formulation for system operational bottleneck identification is proposed given renewable generation profile, in order to obtain operational restriction indices to assess the adequacy of power adjustment margin and power ramp rate. Cosine similarity based density-based spatial clustering of applications with noise (DBSCAN) method is used to cluster a large number of scenarios by operational restriction indices, then scenarios with bottlenecks are attributed to corresponding clusters. Finally, various bottleneck elimination options, including energy storage with different technologies, are compared for each cluster. Case studies of an eight-bus test system and a practical Chinese power system are presented to verify the proposed approach, the numerical results indicate energy storage is the most effective option to eliminate bottlenecks identified in power downward adjustment margin and ramp rate dominated clusters aforementioned.

Aiming at improving the performance of Multipath TCP (MPTCP) in heterogeneous wireless network environments, in this paper, by taking the advantages Bottleneck Bandwidth and Round-trip propagation time (BBR) and considering bottleneck fairness, we propose BBR-based Congestion Control and Packet Scheduling scheme, called BCCPS. The proposed BCCPS first considers a BBR-based congestion control algorithm, MPTCP-BBR, for MPTCP by adaptively adjusting the sending rate of each subflow according to the real probing rate rather than the loss information to enhance the goodput while keeping bottleneck fairness with regular TCP. Then, considering that the different sending rates of the subflows in heterogeneous wireless networks will result in the problem of out-of-order (OFO) delivery, a fine-grained packet scheduling scheme is proposed to keep in-order delivery and so as to reduce the application layer completion time. The performance of the proposed scheme is evaluated via both NS-3 and real network scenarios. Experimental results show that our proposed scheme far outperforms existing MPTCP schemes in heterogeneous wireless environment.

Regulative and social changes towards sustainability are promoting a significant growth of the electromobility sector. Lithium-ion batteries play a major role in this context; however its complex and energy-intensive process chain is responsible for a large part of cradle-to-gate impacts of electric vehicles. Therefore, this work discusses the influence of bottleneck reduction on the energy demand to foster energy efficiency in battery manufacturing. Based on data from the Battery LabFactory Braunschweig, a discrete event simulation is applied to identify bottlenecks and different scenarios for bottleneck reduction are analyzed. Next to improving existing process chain, the results may support the planning of new energy efficient installations.

Highlights • Provide a 50th anniversary bibliometric review of the bottleneck model research;. • Identify influential papers, top contributing authors and leading topics;. • Review the studies in terms of travel behavior, demand-side and supply-side strategies;. • Discuss potential directions for further studies., The bottleneck model introduced by Vickrey in 1969 has been recognized as a benchmark representation of the peak-period traffic congestion due to its ability to capture the essence of congestion dynamics in a simple and tractable way. This paper aims to provide a 50th anniversary review of the bottleneck model research since its inception. A bibliometric analysis approach is adopted for identifying the distribution of all journal publications, influential papers, top contributing authors, and leading topics in the past half century. The literature is classified according to recurring themes into travel behavior analysis, demand-side strategies, supply-side strategies, and joint strategies of demand and supply sides. For each theme, typical extended models developed to date are surveyed. Some potential directions for further studies are discussed.

For TOC (Theory of Constraints) implementation in a production system, the determination of the system's bottleneck is a crucial step. Effective bottleneck identification allows setting priorities for the improvement of a production system. The article deals with a significant problem for the manufacturing industry related to the location of a bottleneck. The article aims for a detailed analysis of methods for bottleneck identification based on a comprehensive literature review and the design of a generalised methodology for bottleneck identification in the production system. The article uses two research methods, first, the combination of a narrative and scoping literature review, and second, the logical design. Several methods for bottleneck identification are reviewed and compared, finding some being similar, and others giving new insights into the evaluated production system. A methodology for bottleneck identification is proposed. It contains several detailed methods arranged in coherent steps, which are suggested to be followed when aiming for the recognition of a production system's bottleneck. The proposed methodology is expected to be helpful in the practical TOC implementation. The presented methodology for the identification of bottlenecks in a production system is a practical tool for managers and experts dealing with TOC. However, it is still a conceptual proposal that needs to be tested empirically. The proposed methodology for bottleneck identification is an original concept based on the current literature output. It contributes to the production management theory as a practical managerial tool.

Recently, there are several studies focusing on the bottleneck optimization objective in Spatial Crowdsourcing (SC). However, these studies usually do not consider the deadline constraint. Different from these studies, we take deadlines into consideration and identify the Fully Online Bottleneck Matching with Deadlines (FOBMD) problem in SC. Because of the deadlines, consideration must be given to both the bottleneck cost and the cardinality, which makes the FOBMD problem more challenging, and no online algorithm without actively refusing tasks can achieve a constant competitive ratio of the bottleneck cost for the FOBMD problem. To settle the FOBMD problem, we consider three baseline algorithms and propose an online algorithm, namely Local Isolated Point Greedy (LIPG). Finally, we validate the effectiveness and efficiency of our proposed algorithm via extensive experiments on both synthetic and real world datasets.

Uncertainty, a critical factor of causing congestion and extra travel costs in the commute, can be mitigated by providing information. This paper studies the welfare effects of accurate pre-trip information on departure time and route choices in the morning commute under binary stochastic bottleneck capacity. We consider a classical two-route network. Each route has a single bottleneck where congestion occurs during the rush hours. The two routes' bottleneck capacities vary from day-to-day due to events such as bad weather, accidents, and temporary road closures. We derive all equilibrium solutions in consideration of the differences between routes in free-flow travel time, the shadow value of travel time, the severity of bottleneck capacity reductions, and the degree of correlation between two routes in travel conditions. Furthermore, we investigate the benefit changes from zero-information to full-information and prove that accurate pre-trip information about the bottleneck conditions is strictly welfare-improving. Finally, these theoretical results are supplemented by case studies that show examples of benefit gains from pre-trip information.

With the development of lean manufacturing and economic globalization, supply networks increasingly become complex and large-scale, within which thousands of firms inter-depend with each other. Due to these increasing inter-dependencies, disruption of a quite few critical suppliers, namely bottleneck suppliers, can induce high loss to a supply network and even make the whole network dysfunction. Identification of bottleneck suppliers is significantly important for supply network risk management. Thus, in this article, a method based on a memetic algorithm with local neighborhood search (MALNS) is proposed to identify bottleneck suppliers in a two-stage supply network. Firstly, a model based on multipartite network is designed to describe the product supply-demand relations between multiple manufacturers and suppliers, which considers the different roles of manufacturer and supplier and differentiates the products that suppliers supply. To assess the loss caused by supplier disruptions, two performance metrics of supply networks, average product availability rate and manufacturer functioning rate, are presented. Then, a MALNS-based method is proposed to identify bottleneck suppliers, i.e., suppliers whose disruption will decrease both performance metrics most greatly. Finally, a case study based on a real automobile supply network is presented to validate the applicability and effectiveness of the proposed method.

The Bottleneck Hypothesis argues that properties of inflectional morphology explain why second-language learners may face persistent difficulties in articulating meaning in target-language forms. I...

Traditional tracking algorithms reply on manually extracted features while deep learning algorithms can automatically extract features, which is of great importance for single target tracking in the complex underwater environment that is characterized by poor visibility, low contrasts, and occlusion. The convolutional neural network SiamRPN++ is an advanced deep learning algorithm whose backbone network structure is. However, this algorithm is difficult to be implemented in an underwater platform due to its large amount of computation and high requirement for the computing power of the hardware. To solve this problem, a new backbone network structure NewNet-62 characterized by inverted residual bottleneck block and the SiamRPN++ algorithm are proposed. The depth-wise separable convolution in NewNet-62 simplifies the computation so that the SiamRPN++ algorithm can realize fast and accurate tracking of underwater single targets. The video set in VOT2016 was used to test the algorithm. The results show that the SiamRPN++ algorithm using NewNet-62 as the main network has the great performance. Compared with the algorithms using ResNet-50, the accuracy of the SiamRPN++ algorithm increased to 0.524 and its EAO increased to 0.303. And its tracking speed increased to 73.74. The network complexity reduced to 3.013 billion and the network parameters reduced to 12.538 million, which significantly reduces network complexity and number of network parameters.

Time delay estimation (TDE) is of great importance in reconnaissance and passive localization. Though TDE could leverage compressive sensing (CS) kernel to enjoy the advantage of sub-Nyquist samples, the estimation accuracy and robustness are inclined to be reduced by jamming or noise. To address the issue, this letter proposes a scheme of defensive compressive time delay estimation (DCTDE) with a novel sensing kernel optimization method and a defense augmentation strategy for the kernel. Inspired by the information bottleneck (IB) theory, we deduce a new analytic principle to enhance the estimation capability of the kernel, which focuses on the fidelity to the non-compressive scheme and the relevant information provided for TDE task. The strategy adopts an adversarial idea for the anti-spoofing design of kernel. Via simulations, the proposed scheme shows promising estimation accuracy, robustness, and high adaptability in both Gaussian noise and jamming environments, and more competitiveness than the Nyquist scheme.

The paper gives an optimization model named multiple bottleneck traveling salesmen problem (MBTSP), which can model the optimization problems where there are multiple salesmen and tasks. In intelligent transport systems and multiple tasks cooperation, some real-world problems can be modeled by MBTSP, the scale of constructed model usually tends to multiple scales, therefore it is significant to study multiple scales MBTSP and its solving algorithms. The relevant literatures have proved that genetic algorithm and its versions can show good performance for the variants of TSP, thus this paper proposes a novel hybrid genetic algorithm (VNSGA) with variable neighborhood search (VNS) for multi-scale MBTSP. For VNSGA, the feasible solutions are constructed by dual-chromosome coding, then they are updated by the crossover operator, mutation operator and variable neighborhood search. During this process, the VNS can be carried out by the deleting and reinserting operator of the cities for optimization. The experiments show that VNSGA can demonstrate better solution quality than the state-of-the-art algorithms for MBTSP problem.

We characterize a class of systems for which the H-infinity optimal control problem can be simplified in a way that enables sparse solutions and efficient computation. For a subclass of the systems, an optimal controller can be explicitly expressed in terms of the matrices of the system's state-space representation. In many applications, the controller given by this formula, which is static, can be implemented in a decentralized or distributed fashion. Examples are temperature dynamics in buildings, water irrigation and electrical networks.

The main focus will be on the indirect Joint Source-Channel Coding problem in which a noisy observation of the source has to be quantized ahead of transmission over an error-prone forward link to a remote processing unit. To that end, we present here a complete extension to the preliminary Information Bottleneck method by providing the formal optimal solution to this newly established Variational Principle , together with an algorithm, the Forward-Aware Vector Information Bottleneck (FAVIB) , to pragmatically tackle its underlying non-convex design optimization. FAVIB extends the current state-of-the-art approaches via capacitating a full sweep over the entire gamut of the trade-off parameter. Consequently, the trajectory of all achievable points in the Information-Compression plane becomes traversable via soft mappings. It will be shown that, by enjoying an inherent error protection, this novel compression scheme can obviate the call for separate channel coding on the forward path.

Traffic bottleneck refers to the road section or node that often causes the propagation or spread of traffic congestion in the road network, which is the source of the whole road network congestion. In this paper, the author analyzes the bottleneck prediction of urban road network based on improved PSO algorithms and fuzzy control. This paper analyzes the factors and characteristics of the main road of the system, proposes the traffic coordination control of the main road based on the delay model, and carries on the statistical simulation to the actual traffic data, develops the basic theory of the traffic coordination control which is more effective than the traditional timing control strategy. Compared with the traditional model, the algorithm considers the waiting time of the red light at the intersection. For the congested road section, it can better calculate the travel time of the vehicle, making the results more accurate and more applicable. The results of this study can provide a strong theoretical basis and prediction scheme for the traffic management and control of the road network in the target area.

We present an algorithm to insert a train path in an existing railway timetable close to operation, when we want to affect the existing (passenger) traffic as little as possible. Thus, we consider all other trains as fixed, and aim for a resulting train path that maximizes the bottleneck robustness, that is, a train path that maximizes the temporal distance to neighboring trains in the timetable. Our algorithm is based on a graph formulation of the problem and uses a variant of Dijkstra’s algorithm. We present an extensive experimental evaluation of our algorithm for the Swedish railway stretch from Malmö to Hallsberg. Moreover, we analyze the size of our constructed graph. Funding agency: Linköping University Shift2Rail