Abstract

No Results Found

Abstract

In this paper, we investigate the problem of text coherence modeling with a new perspective of learning better distributed sentence representation by incorporating document dependent and document independent features of a sentence. To this end, we propose a datadriven end-to-end novel neural coherence model that captures text coherence by exploiting the semantic and distributional aspects of the sentences in a document. The network is able to capture various document independent and document dependent features of a sentence which is imperative in assessing text coherence. Experiments on the standard Sentence Ordering task indicate that our proposed model shows significant performance gain of 1.7 percent in terms of accuracy score compared with the state-of-the-art baselines.

Abstract

Normalizing flows are an essential alternative to GANs for generative modelling, which can be optimized directly on the maximum likelihood of the dataset. They also allow computation of the exact latent vector corresponding to an image since they are composed of invertible transformations. However, the requirement of invertibility of the transformation prevents standard and expressive neural network models such as CNNs from being directly used. Emergent convolutions were proposed to construct an invertible 3×3 CNN layer using a pair of masked CNN layers, making them inefficient. We study conditions such that 3×3 CNNs are invertible, allowing them to construct expressive normalizing flows. We derive necessary and sufficient conditions on a padded CNN for it to be invertible. Our conditions for invertibility are simple, can easily be maintained during the training process. Since we require only a single CNN layer for every effective invertible CNN layer, our approach is more efficient than emerging convolutions. We also proposed a coupling method, Quad-coupling. We benchmark our approach and show similar performance results to emergent convolutions while improving the model's efficiency

Abstract

Artificial Bee Colony (ABC)method optimization procedure for design of RC moment frames​. Cross-section properties of frame members are optimized considering constraints specified by design codes.​Structural design provisions enunciated in Indian Standards IS456 (2000), IS1893 (2016) and IS13920 (2016) are used as system of design rules, to interact with Finite Element Method of analysis of frames developed for the study. Cross-sectional properties of structural members are chosen from a set of pre-defined sectional properties from the database developed to form design variables compliant with Indian Standards. The optimized design & detailing of frame elements are obtained after the frame structure is analyzed under the action of multiple load combinations ​ ABC method can then be applied, to improve the Nonlinear Response of the frame​

Abstract

The advent of Internet of Things has resulted in new communication protocols such as LoRaWAN and Narrowband IoT slowly rising to be viable and even better alternatives to traditional protocols such as Wi-Fi and Bluetooth. LoRa in particular, has attracted a lot of attention owing to low power consumption of end nodes, low cost and use of license-free sub-GHz bands. Further, high link budgets in LoRaWAN communication allow for fewer gateways to provide network coverage over a large area. However, the success of deployment of LoRaWAN gateways in real world applications depends on meticulous planning. A major drawback in this scenario is the lack of extensive data on loss of signal strength, particularly in cityscapes, where buildings and trees can create significant path loss. In this paper, we investigate the path loss for LoRaWAN signals inside a typical city building (brick walls, reinforced cement concrete ceiling, wooden doors). The RSSI values of transmissions from multiple locations to a stationary gateway have been analysed to find the effect of indoor obstacles such as walls and doors on the propagation of LoRaWAN signals. We report that significant loss of energy can occur, even at relatively close range, because of the structures.

Abstract

No Results Found

Abstract

Quality assessment of agricultural produce is a crucial step in minimizing food stock wastage. However, this is currently done manually and often requires expert supervision, especially in smaller seeds like corn. We propose a novel computer vision-based system for automating this process. We build a novel seed image acquisition setup, which captures both the top and bottom views. Dataset collection for this problem has challenges of data annotation costs/time and class imbalance. We address these challenges by i.) using a Conditional Generative Adversarial Network (CGAN) to generate real-looking images for the classes with lesser images and ii.) annotate a large dataset with minimal expert human intervention by using a Batch Active Learning (BAL) based annotation tool. We benchmark different image classification models on the dataset obtained. We are able to get accuracies of up to 91.6% for testing the physical purity of seed samples.

Abstract

Malaria is a deadly disease caused by the plasmodium parasites. Approximately 210 million people get affected by malaria every year resulting in half a million deaths. Among several species of the parasite, Plasmodium falciparum is the primary cause of severe infection and death. Several drugs are available for malaria treatment in the market but plasmodium parasites have successfully developed resistance against many drugs over the years. This poses a serious threat to efficacy of the treatments and continuing discovery of new drug is necessary to tackle the situation, especially due to failure in designing an effective vaccine. People are now trying to design new drugs for malaria using AI technologies which can substantially reduce the time and cost required in classical drug discovery programs. In this chapter, we provide a comprehensive overview of a road map for several AI based computational techniques which can be implemented in a malaria drugs discovery program. Classical computers has limiting computing power. So, researchers are also trying to harness quantum machine learning to speed up the drug discovery processes.

Abstract

The identification of plant species by looking at their leaves, flowers, and seeds is a crucial component in the conservation of endangered plants. Traditional identification methods are manual and time consuming and require domain knowledge to operate. Owing to an increased interest in the automated plant identification system, we propose one that utilizes modern convolutional neural network architectures. This approach helps in the recognition of leaf images and can be integrated into mobile platforms like smartphones. Such a system can also be employed in aiding plant-related education, promoting ecotourism, and creating a digital heritage for plant species, among many others. Our proposed solution achieves a state-of-the-art performance for plant classification in the wild. An exhaustive set of experiments are performed to classify 112 species of plants from the challenging Indic-Leaf dataset. The best-performing model gives Top 1 precision of 90.08 and Top 5 precision of 96.90. We discuss and elaborate on our crowdsourcing web application that is used to collect and regulate data. We explain how the automated plant identification system can be integrated into a smartphone by detailing the flow of our mobile application.

Abstract

This paper describes a new method for speech activity detection (SAD) based on the recently proposed single frequency filtering (SFF) analysis of speech signals and a neural network model. The SFF analysis gives instantaneous spectrum of the speech signal at each sampling instant. The frequency resolution of the spectrum is decided by the number of frequencies used in the SFF analysis, which in turn depends on the frequency spacing. Using a frequency spacing of 10 Hz and a sampling frequency of 8 kHz, a 401 dimensional spectrum, covering 0–4 kHz, is obtained at each sampling instant. This is used as a feature vector to train an artificial neural network (ANN) model to discriminate (noisy) speech and nonspeech (mostly noise). The output of the trained ANN model for a given test utterance gives speech/nonspeech decision at every sampling instant. Post processing of the decision is used for SAD. The system generated SAD is evaluated on the Apollo corpus for SAD task in terms of detection cost function (DCF). The DCF values of the proposed system on the development and evaluation datasets are 3.1% and 4.6%, respectively, whereas the DCF values of the reported baseline system are 8.6% and 11.7%, respectively.