Batch-based Method Research Articles

Bubbling up in a Lab-on-a-Chip: A gravity-driven approach to the formation of polyelectrolyte multilayer capsules and foams

The generation of multi-functional capsules often requires the sequential deposition of different components on the surface of bubbles or drops. Batch-based methods lack fine control over the capsule sizes, including risk of fusion, and cannot ensure identical environments for each capsule. To overcome these issues, different micro/milli-fluidic methods have been developed in the past. However, a major challenge remains in combining an explicit and flexible control over the capsule generation and their residence time in the different solutions within the same device. Using for the first time the example of bubbles covered by layers of oppositely charged polyelectrolytes (PSS/PAH), we introduce an original millifluidic Lab-on-a-Chip device with two novel functions: (1) Size and separation of the bubbles are tuned at constant flow conditions via gas injection through a movible, circular dispense tip into the cross-flow of a rectangular channel. We provide a detailed exploration of the bubbling parameters together with physical justification of the observations. (2) The device exploits gravity to make the generated bubbles rise between horizontally stacked millifluidic chips containing each the controlled flow of a specific polyelectrolyte solution. In analogy with electric circuits, we show how the flow resistance of each chip can be adapted such that bubbles move smoothly between them while avoiding undesired mixing of the solutions. We show first examples of obtained multilayer capsules and discuss their peculiar features, in particular, their outstanding stability with respect to coalescence and dissolution. While our methods use polyelectrolyte assembly on bubbles, they can be readily transferred to other types of solutions or even to drops and particles.

P-Ride: A Shareability Prediction Based Framework in Ridesharing

Ridesharing services aim to reduce travel costs for users and optimize revenue for drivers and platforms by sharing available seats. Existing works can be roughly classified into two types, i.e., online-based and batch-based methods. The former mainly focuses on responding quickly to the requests, and the latter focuses on meticulously enumerating request combinations to improve service quality. However, online-based methods perform poorly in service quality due to the neglect of the sharing relationship between requests, while batch-based methods fail in terms of efficiency. To obtain better service quality more efficiently, we propose a shareability prediction-based framework P-Ride. Specifically, we first introduce the k-clique listing strategy in graph theory based on the shareability graph to reduce the infeasible request combinations. Moreover, we extend the shareability graph to the hypergraph structure to represent the higher-order shareable relationships among requests. Furthermore, we devise a shareability prediction model that supports the prediction of sharable relationships for request combinations of an arbitrary size, which helps further filtering of candidate request combinations with GPU devices acceleration. The extensive experimental results demonstrate the efficiency and effectiveness of our proposed P-Ride framework.

E-Ride: An Adaptive Event-Driven Windowed Matching Framework in Ridesharing

Ridesharing services aim at reducing the users’ travel cost and optimizing the drivers’ routes to satisfy passengers’ expected maximum matching times in practice request dispatching. Existing works can be roughly classified into two types, i.e., online-based and batch-based methods, in which the former mainly focus on responding quickly to the requests and the latter focuses on enumerating request combinations meticulously to improve the service quality. However, online-based methods perform poorly in terms of service quality due to the neglect of the sharing relationship between requests, while batch-based methods fail on efficiency. None of these works can smoothly balance the service quality and matching time cost since the matching window is not sufficiently explored or even neglected. To cope with this problem, we propose a novel framework <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mathcal {E}$ </tex-math></inline-formula> -Ride, which comprehensively leverages the matching time window based on the event model. Specifically, an adaptive windowed matching algorithm is proposed to adaptively consider personalized matching time and provide a matching solution with higher service rates at lower latencies. Besides, we maintain the request groups through a mixed graph and further integrate the subsequent arrival requests to optimize the matching results, which can scale to or satisfy online use demands. The extensive experimental results demonstrate the efficiency and effectiveness of our proposed method.

Lifelong Learning Augmented Short Text Stream Clustering Method

Depending on the scanning mode, existing short text stream clustering methods can be divided into the following two kinds of methods: one-pass-based and batch-based. The one-pass-based method handles each text only one time, but cannot deal with the sparseness problem very well. The batch-based method obtains better results by allowing multiple iterations of each batch, but the efficiency is relatively low. To overcome these problems, this paper presents Lifelong learning Augmented Short Text stream clustering method (LAST), which incorporates the episodic memory module and sparse experience replay module of lifelong learning into the clustering process. Specifically, LAST processes each text one time, but at a certain interval it randomly samples some previously seen texts of the episodic memory to update cluster features by performing sparse experience replay. Empirical studies on two public datasets demonstrate that the performance of the LAST-based method is on a par with the batch-based method, and runs close to the speed of the one-pass-based method.

Online Adaptive Supervised Hashing for Large-Scale Cross-Modal Retrieval

In recent years, with the continuous growth of multimedia data on the Internet, multimodal hashing has attracted increasing attention for its efficiency in large-scale cross-modal retrieval. Typically, most existing multimodal hashing methods are batch-based methods that cannot deal with the growing streaming data. Online multimodal hashing adopts online learning strategy to learn hash models incrementally, which can process large-scale streaming data. However, existing supervised online multimodal hashing methods still suffer from several limitations: (1) most methods cannot update hash codes of old data when hash model changes, which will hinder the retrieval accuracy. (2) the discrete optimizations of most methods for learning binary hash codes are less efficient or less effective. To address the above limitations, an efficient supervised online multimodal hashing method termed Online Adaptive Supervised Hashing (OASH) is proposed in this paper. OASH regresses class labels and training data to binary hash codes to learn discrete hash codes and hash functions with an efficient online optimization scheme. It learns hash functions incrementally with newly arriving data and updates hash codes with the latest hash model. By adaptively updating hash functions and hash codes with new data rather than accessing to old data, it gains much performance enhancement and computation savings. Extensive experiments on three benchmark data sets validate the superiority of OASH over state-of-the-art methods in both accuracy and efficiency.

Improving Online Clustering of Chinese Technology Web News With Bag-of-Near-Synonyms

In the Internet era, online clustering of technology web news can help discover scientific breakthroughs and grasp technology trends. To do that automatically, the news documents to be clustered must be represented appropriately with numerical vectors. However, traditional representations such as Term Frequency-Inverse Document Frequency (TF-IDF) cannot distinguish near-synonyms and may cause “dimension disaster.” To overcome these problems, this article proposes the Bag-of-Near-Synonyms (BoNS) model based on the idea to construct near-synonym sets using word embeddings and agglomerative clustering, and then to represent a document with a Set Frequency-Inverse Document Frequency (SF-IDF) vector in which each dimension corresponds to a near-synonym set rather than a single word. To speed up computation, we further propose the hashed version of SF-IDF and name it hSF-IDF, which employs a hash function to map each near-synonym set to a unique number as the key and hence reduces the computation of SF to linear time. In addition, we apply hSF-IDF to online clustering of Chinese technology web news and propose an improved batch-based method. Extensive experiments have been conducted on a real-world dataset. The results show that our model outperforms some strong baselines including TF-IDF, average pooling of word or character embeddings, Latent Dirichlet Allocation (LDA), and bag-of-concepts in terms of both accuracy and efficiency.

On Training Deep Neural Networks Using a Streaming Approach

Abstract In recent years, many deep learning methods, allowed for a significant improvement of systems based on artificial intelligence methods. Their effectiveness results from an ability to analyze large labeled datasets. The price for such high accuracy is the long training time, necessary to process such large amounts of data. On the other hand, along with the increase in the number of collected data, the field of data stream analysis was developed. It enables to process data immediately, with no need to store them. In this work, we decided to take advantage of the benefits of data streaming in order to accelerate the training of deep neural networks. The work includes an analysis of two approaches to network learning, presented on the background of traditional stochastic and batch-based methods.

UniCNN: A Pipelined Accelerator Towards Uniformed Computing for CNNs

Convolutional neural networks (CNNs) have been widely applied for image recognition, face detection, and video analysis because of their ability to achieve accuracy close to or even better than human level perception. However, different features of convolution layers and fully connected layers have brought many challenges to the implementation of CNN on FPGA platforms, because different accelerator units must be designed to process the whole networks. In order to overcome this problem, this work proposes a pipelined accelerator towards uniformed computing for convolutional neural networks. For the convolution layer, the accelerator first repositions the input features into matrix on-the-fly when they are stored to FPGA on-chip buffers, thus the computation of convolution layer can be completed through matrix multiplication. For the fully connected layer, the batch-based method is used to reduce the required memory bandwidth, which also can be completed through matrix multiplication. Then a pipelined computation method for matrix multiplication is proposed to increase the throughput and also reduce the buffer requirement. The experiment results show that the proposed accelerator surpasses CPUs and GPUs platform in terms of energy efficiency. The proposed accelerator can achieve the throughput of 49.31 GFLOPS, which is done using only 198 DSP modules. Compared to the state-of-the-art implementatuion, our accelerator has better hardware utilization efficiency.

Incremental structural modeling on sparse visual SLAM

This paper presents an incremental structural modeling approach that improves the precision and the stability of existing batch-based ones for sparse and noisy point clouds from visual simultaneous localization and mapping (SLAM). The main idea is to use the generating process of point clouds on SLAM effectively. First, a batch-based method is applied to point clouds that are incrementally generated from SLAM. Then, the temporal history of reconstructed geometric primitives is statistically analyzed to suppress incorrect reconstruction. The evaluation shows that both precision and stability are improved compared to an existing batch-based method, and the proposed method is suitable for real-time structural modeling.

Robust Brain-Machine Interface Design Using Optimal Feedback Control Modeling and Adaptive Point Process Filtering.

Much progress has been made in brain-machine interfaces (BMI) using decoders such as Kalman filters and finding their parameters with closed-loop decoder adaptation (CLDA). However, current decoders do not model the spikes directly, and hence may limit the processing time-scale of BMI control and adaptation. Moreover, while specialized CLDA techniques for intention estimation and assisted training exist, a unified and systematic CLDA framework that generalizes across different setups is lacking. Here we develop a novel closed-loop BMI training architecture that allows for processing, control, and adaptation using spike events, enables robust control and extends to various tasks. Moreover, we develop a unified control-theoretic CLDA framework within which intention estimation, assisted training, and adaptation are performed. The architecture incorporates an infinite-horizon optimal feedback-control (OFC) model of the brain’s behavior in closed-loop BMI control, and a point process model of spikes. The OFC model infers the user’s motor intention during CLDA—a process termed intention estimation. OFC is also used to design an autonomous and dynamic assisted training technique. The point process model allows for neural processing, control and decoder adaptation with every spike event and at a faster time-scale than current decoders; it also enables dynamic spike-event-based parameter adaptation unlike current CLDA methods that use batch-based adaptation on much slower adaptation time-scales. We conducted closed-loop experiments in a non-human primate over tens of days to dissociate the effects of these novel CLDA components. The OFC intention estimation improved BMI performance compared with current intention estimation techniques. OFC assisted training allowed the subject to consistently achieve proficient control. Spike-event-based adaptation resulted in faster and more consistent performance convergence compared with batch-based methods, and was robust to parameter initialization. Finally, the architecture extended control to tasks beyond those used for CLDA training. These results have significant implications towards the development of clinically-viable neuroprosthetics.

Incrementally Detecting Moving Objects in Video with Sparsity and Connectivity

Moving object detection is crucial for cognitive vision-based robot tasks. However, due to noise, dynamic background, variations in illumination, and high frame rate, it is a challenging task to robustly and efficiently detect moving objects in video using the clue of motion. State-of-the-art batch-based methods view a sequence of images as a whole and then model the background and foreground together with the constraints of foreground sparsity and connectivity (smoothness) in a unified framework. But the efficiency of the batch-based methods is very low. State-of-the-art incremental methods model the background by a subspace whose bases are updated frame by frame. However, such incremental methods do not make full use of the foreground sparsity and connectivity. In this paper, we develop an incremental method for detecting moving objects in video. Compared to existing methods, the proposed method not only incrementally models the subspace for background reconstruction but also takes into account the sparsity and connectivity of the foreground. The optimization of the model is very efficient. Experimental results on nine public videos demonstrate that the proposed method is much efficient than the state-of-the-art batch methods and has higher F1-score than the state-of-the-art incremental methods.