Delhi Technological University

About: Delhi Technological University is a education organization based out in New Delhi, India. It is known for research contribution in the topics: Computer science & Control theory. The organization has 4427 authors who have published 6761 publications receiving 71035 citations. The organization is also known as: Delhi College of Engineering & DTU.

Effectual recommendations using artificial algae algorithm and fuzzy c-mean

Abstract: Recommender systems play a significant role in e-commerce applications. The primary motive of a recommender system is to recommend some items or products to the users based on their previous ratings of other products in the online environment. In this article, we presented a hybrid collaborative filtering based recommender system that improved the accuracy of the recommendations. In our work, we adopted fuzzy c-mean (FCM) and a recent bio-inspired approach, which is artificial algae algorithm (AAA). We have used advanced multilevel Pearson correlation coefficient (PCC) to find the similarity between two users. Moreover, we discovered the rating which the user will most likely give to the movies which he has not given any ratings yet. By applying above-mentioned procedures, the quality of the recommendations is improved significantly. The proposed system succeeded to provide recommendations of better quality and accuracy when compared to other alternatives. We have experimented and evaluated our proposed recommender system on four real data sets: Movielens 100,000, Movielens 1 million, Jester and Epinion. We concluded that our proposed recommender system delivered better recommendations for all four datasets. The efficiency of the system was estimated by evaluation metrics such as mean absolute error (MAE), precision and recall and showed impressive results. This proposed system delivered best results as compared to our previous work (Katarya and Verma, 2016) [1].

Human Activity Recognition in Video Benchmarks: A Survey

Abstract: Vision-based Human activity recognition is becoming a trendy area of research due to its broad application such as security and surveillance, human–computer interactions, patients monitoring system, and robotics. For the recognition of human activity various approaches have been developed and to test the performance on these video datasets. Hence, the objective of this survey paper is to outline the different video datasets and highlights their merits and demerits under practical considerations. We have categorized these datasets into two part. The first part consists two-dimensional (2D-RGB) datasets and the second part has three-dimensional (3D-RGB) datasets. The most prominent challenges involved in these datasets are occlusions, illumination variation, view variation, annotation, and fusion of modalities. The key specification of these datasets are resolutions, frame rate, actions/actors, background, and application domain. All specifications, challenges involved, and the comparison made in tabular form. We have also presented the state-of-the-art algorithms that give the highest accuracy on these datasets.

Multiferroic properties of BiFeO3/BaTiO3 multilayered thin films

Abstract: Multilayered structures of multiferroic BiFeO 3 (BFO) and ferroelectric BaTiO 3 (BTO) have been fabricated using pulsed laser deposition (PLD). Ferromagnetic and ferroelectric properties of the multilayered system (BFO/BTO) have been investigated. It could be inferred that the magnetization increases with the incorporation of BTO buffer layer, which indicates a coupling between the ferroelectric and ferromagnetic orders. Vibrating sample magnetometer (VSM) measurements performed on the prepared multiferroic samples show that the magnetization is significantly increased ( M s =56.88 emu/cm 3 ) for the multilayer system with more number of layers (four) keeping the total thickness of the multilayered system constant (350 nm) meanwhile maintaining the sufficiently enhanced ferroelectric properties ( P r =29.68 µC/cm 2 ).

Multimodal Multi-Task Financial Risk Forecasting

Abstract: Stock price movement and volatility prediction aim to predict stocks' future trends to help investors make sound investment decisions and model financial risk. Companies' earnings calls are a rich, underexplored source of multimodal information for financial forecasting. However, existing fintech solutions are not optimized towards harnessing the interplay between the multimodal verbal and vocal cues in earnings calls. In this work, we present a multi-task solution that utilizes domain specialized textual features and audio attentive alignment for predictive financial risk and price modeling. Our method advances existing solutions in two aspects: 1) tailoring a deep multimodal text-audio attention model, 2) optimizing volatility, and price movement prediction in a multi-task ensemble formulation. Through quantitative and qualitative analyses, we show the effectiveness of our deep multimodal approach.

Computer Vision and Radiology for COVID-19 Detection

Abstract: COVID-19 is spreading rapidly throughout the world. As of 14 April 2020, 128,000 people died of COVID-19, while 1.99 million cases in 210 countries and territories were reported in 219.747 cases. As the virus spreads at a very high rate, there is a huge shortage of medical testing kits all over the world. The respiratory system is the part of the human body most affected by the virus, so the use of X-rays of the chest may prove to be a more efficient way than the thermal screening of the human body. In this paper, we are trying to develop a method that uses radiology, i.e. X-rays for detecting the novel coronavirus. Along with the paper, we also release a dataset for the research community and further development extracted from various medical research hospital facilities treating COVID-19 patients.