Convolution neural networks (CNNs) have shown great success in various applications. However, the computational complexity and memory storage of CNNs is a bottleneck for their deployment on resource-constrained devices. Recent efforts towards reducing the computation cost and the memory overhead of CNNs involve similarity-based passive filter pruning methods. Similarity-based passive filter pruning methods compute a pairwise similarity matrix for the filters and eliminate a few similar filters to obtain a small pruned CNN. However, the computational complexity of computing the pairwise similarity matrix is high, particularly when a convolutional layer has many filters. To reduce the computational complexity in obtaining the pairwise similarity matrix, we propose to use an efficient method where the complete pairwise similarity matrix is approximated from only a few of its columns by using a Nyström approximation method. The proposed efficient similarity-based passive filter pruning method is 3 times faster and gives same accuracy at the same reduction in computations for CNNs compared to that of the similarity-based pruning method that computes a complete pairwise similarity matrix. Apart from this, the proposed efficient similarity-based pruning method performs similarly or better than the existing norm-based pruning methods. The efficacy of the proposed pruning method is evaluated on CNNs such as DCASE 2021 Task 1A baseline network and a VGGish network designed for acoustic scene classification.

Productivity in software development is a complex, multi-faceted concept expressed as a combination of effectiveness and efficiency. From a quantitative lens, productivity is often interpreted from a collection of activities and metrics such as the number of commits, lines of code added and removed, and the number of issues closed. Software development team managers often seek to track developers’ activity and productivity for short-term planning and medium-term team performance measurement. Existing tools and platforms analyze and visualize individual aspects of developers’ activity, productivity, or quality. However, a tool that fuses multiple information streams representing productivity and quality aspects is missing. The proposed tool QConnect fills the gap by mining, analyzing, and fusing information from software development-relevant streams. QConnect, on the one hand, mines the repository and issue tracking metadata from GitHub and Jira issue tracking system; on the other hand, it gathers information related to code quality using external tools Designite and RefactoringMiner. By tying-in productivity measures with code quality information, stakeholders can assess not only how fast but also how well the project is progressing.Demo: tool website and demo video.

We present a method to develop low-complexity convolutional neural networks (CNNs) for acoustic scene classification (ASC).The large size and high computational complexity of typical CNNs is a bottleneck for their deployment on resourceconstrained devices.We propose a passive filter pruning framework, where a few convolutional filters from the CNNs are eliminated to yield compressed CNNs.Our hypothesis is that similar filters produce similar responses and give redundant information allowing such filters to be eliminated from the network.To identify similar filters, a cosine distance based greedy algorithm is proposed.A fine-tuning process is then performed to regain much of the performance lost due to filter elimination.To perform efficient fine-tuning, we analyze how the performance varies as the number of fine-tuning training examples changes.An experimental evaluation of the proposed framework is performed on the publicly available DCASE 2021 Task 1A baseline network trained for ASC.The proposed method is simple, reduces computations per inference by 27%, with 25% fewer parameters, with less than 1% drop in accuracy.

Given a stream of food orders and available delivery vehicles, how should orders be assigned to vehicles so that the delivery time is minimized? For a successful assignment strategy, two key decisions need to be made: (1) assignment of orders to vehicles, (2) grouping orders into batches to cope with limited vehicle availability. We show that the minimization problem is not only NP-hard but inapproximable in polynomial time. To mitigate this computational bottleneck, we develop an algorithm called FOODMATCH, which maps the vehicle assignment problem to that of minimum weight perfect matching on a bipartite graph. The solution quality is further enhanced by reducing batching to a graph clustering problem. Extensive experiments on food-delivery data from large metropolitan cities establish that FOODMATCH is substantially better than baseline strategies on a number of metrics.

In this paper, we propose a statistical framework to prune feature maps in 1-D deep convolutional networks. SoundNet is a pre-trained deep convolutional network that accepts raw audio samples as input. The feature maps generated at various layers of SoundNet have redundancy, which can be identified by statistical analysis. These redundant feature maps can be pruned from the network with a very minor reduction in the capability of the network. The advantage of pruning feature maps, is that computational complexity can be reduced in the context of using an ensemble of classifiers on the layers of SoundNet. Our experiments on acoustic scene classification demonstrate that ignoring 89% of feature maps reduces the performance by less than 3% with 18% reduction in computational complexity.

Classifying and counting vehicles in road traffic has numerous applications in the transportation engineering domain. However, the wide variety of vehicles (two-wheelers, three-wheelers, cars, buses, trucks etc.) plying on roads of developing regions without any lane discipline, makes vehicle classification and counting a hard problem to automate. In this paper, we use state of the art Convolutional Neural Network (CNN) based object detection models and train them for multiple vehicle classes using data from Delhi roads. We get upto 75% MAP on an 80-20 train-test split using 5562 video frames from four different locations. As robust network connectivity is scarce in developing regions for continuous video transmissions from the road to cloud servers, we also evaluate the latency, energy and hardware cost of embedded implementations of our CNN model based inferences.