Region-based image retrieval using region of interest (ROI) according to incremental frame and clustering color image

Content-based image retrieval involves the extraction of global feature images for their retrieval performance in large image databases. Extraction of global features image cause problem of the semantic gap between the high-level meaning and low-level visual features images. In this study RBIR, Region of Interest Based (ROI) Image Retrieval Using Incremental Frame of Color Image was proposed. It combines several methods, including filtering process, image partitioning using clustering and incremental frame formation, complementation law of theory set to generate ROI, NROI, or ER of the region. The concept of weighting as well as a significant query is also incorporated as a query strategy. Extensive experiments were also conducted on the Wang database and the color model selected was the CIE lab. Experimental results show the proposed method is efficient in image retrieval. The performance of the proposed method shows a better average IPR value of 3.51% compared to RGB and 22.92% with the HSV color model. Meanwhile, it also performs better by 36%, 5%, and 24% compared to methods CH (8,2,2), CH (8,3,3), and CH (16,4,4).

Adaptive Data Screening for Multi-Angle Polarimetric Aerosol and Ocean Color Remote Sensing Accelerated by Deep Learning

Remote sensing measurements from multi-angle polarimeters (MAPs) contain rich aerosol microphysical property information, and these sensors have been used to perform retrievals in optically complex atmosphere and ocean systems. Previous studies have concluded that, generally, five moderately separated viewing angles in each spectral band provide sufficient accuracy for aerosol property retrievals, with performance gradually saturating as angles are added above that threshold. The Hyper-Angular Rainbow Polarimeter (HARP) instruments provide high angular sampling with a total of 90–120 unique angles across four bands, a capability developed mainly for liquid cloud retrievals. In practice, not all view angles are optimal for aerosol retrievals due to impacts of clouds, sunglint, and other impediments. The many viewing angles of HARP can provide resilience to these effects, if the impacted views are screened from the dataset, as the remaining views may be sufficient for successful analysis. In this study, we discuss how the number of available viewing angles impacts aerosol and ocean color retrieval uncertainties, as applied to two versions of the HARP instrument. AirHARP is an airborne prototype that was deployed in the ACEPOL field campaign, while HARP2 is an instrument in development for the upcoming NASA Plankton, Aerosol, Cloud, ocean Ecosystem (PACE) mission. Based on synthetic data, we find that a total of 20–30 angles across all bands (i.e., five to eight viewing angles per band) are sufficient to achieve good retrieval performance. Following from this result, we develop an adaptive multi-angle polarimetric data screening (MAPDS) approach to evaluate data quality by comparing measurements with their best-fitted forward model. The FastMAPOL retrieval algorithm is used to retrieve scene geophysical values, by matching an efficient, deep learning-based, radiative transfer emulator to observations. The data screening method effectively identifies and removes viewing angles affected by thin cirrus clouds and other anomalies, improving retrieval performance. This was tested with AirHARP data, and we found agreement with the High Spectral Resolution Lidar-2 (HSRL-2) aerosol data. The data screening approach can be applied to modern satellite remote sensing missions, such as PACE, where a large amount of multi-angle, hyperspectral, polarimetric measurements will be collected.

How to Retrieve Music using Mood Tags in a Folksonomy

A folksonomy is a classification system in which volunteers collaboratively create and manage tags to annotate and categorize content. The folksonomy has several problems in retrieving music using tags, including problems related to synonyms, different tagging levels, and neologisms. To solve the problem posed by synonyms, we introduced a mood vector with 12 possible moods, each represented by a numeric value, as an internal tag. This allows moods in music pieces and mood tags to be represented internally by numeric values, which can be used to retrieve music pieces. To determine the mood vector of a music piece, 12 regressors predicting the possibility of each mood based on acoustic features were built using Support Vector Regression. To map a tag to its mood vector, the relationship between moods in a piece of music and mood tags was investigated based on tagging data retrieved from Last.fm, a website that allows users to search for and stream music. To evaluate retrieval performance, music pieces on Last.fm annotated with at least one mood tag were used as a test set. When calculating precision and recall, music pieces annotated with synonyms of a given query tag were treated as relevant. These experiments on a real-world data set illustrate the utility of the internal tagging of music. Our approach offers a practical solution to the problem caused by synonyms.

Elegant Unsupervised Cross-Modal Hashing

<div><p>Unsupervised cross-modal retrieval has received increasing attention recently, because of the extreme difficulty of labeling the explosive multimedia data. The core challenge of it is how to measure the similarities between multi-modal data without label information. In previous works, various distance metrics are selected for measuring the similarities and predicting whether samples belong to the same class. However, these predictions are not always right. Unfortunately, even a few wrong predictions can undermine the final retrieval performance. To address this problem, in this paper, we categorize predictions as solid and soft ones based on their confidence. We further categorize samples as solid and soft ones based on the predictions. We propose that these two kinds of predictions and samples should be treated differently. Besides, we find that the absolute values of similarities can represent not only the similarity but also the confidence of the predictions. Thus, we first design an elegant dot product fusion strategy to obtain effective inter-modal similarities. Subsequently, utilizing these similarities, we propose a generalized and flexible weighted loss function where larger weights are assigned to solid samples to increase the retrieval performance, and smaller weights are assigned to soft samples to decrease the disturbance of wrong predictions. Despite less information is used, empirical studies show that the proposed approach achieves the state-of-the-art retrieval performance.</p><br></div>

Elegant Unsupervised Cross-Modal Hashing

<div><p>Unsupervised cross-modal retrieval has received increasing attention recently, because of the extreme difficulty of labeling the explosive multimedia data. The core challenge of it is how to measure the similarities between multi-modal data without label information. In previous works, various distance metrics are selected for measuring the similarities and predicting whether samples belong to the same class. However, these predictions are not always right. Unfortunately, even a few wrong predictions can undermine the final retrieval performance. To address this problem, in this paper, we categorize predictions as solid and soft ones based on their confidence. We further categorize samples as solid and soft ones based on the predictions. We propose that these two kinds of predictions and samples should be treated differently. Besides, we find that the absolute values of similarities can represent not only the similarity but also the confidence of the predictions. Thus, we first design an elegant dot product fusion strategy to obtain effective inter-modal similarities. Subsequently, utilizing these similarities, we propose a generalized and flexible weighted loss function where larger weights are assigned to solid samples to increase the retrieval performance, and smaller weights are assigned to soft samples to decrease the disturbance of wrong predictions. Despite less information is used, empirical studies show that the proposed approach achieves the state-of-the-art retrieval performance.</p><br></div>

An Intelligent Question Answering Platform for Graduate Enrollment

To enhance the competitiveness of colleges and universities in the graduate enrollment and reduce the pressure on candidates for examination and consultation, it is necessary and practically significant to develop an intelligent Q&A platform, which can understand and analyze users' semantics and accurately return the information they need. However, there are problems such as the low volume and low quality of the corpus in the graduate enrollment, this paper develops a question answering platform based on a novel retrieval model including density-based logistic regression and the combination of convolutional neural networks and bidirectional long short-term memory. The experimental results show that the proposed model can effectively alleviate the problem of data sparseness and greatly improve the accuracy of the retrieval performance for the graduate enrollment.

NLP-based personal learning assistant for school education

Computer-based knowledge and computation systems are becoming major sources of leverage for multiple industry segments. Hence, educational systems and learning processes across the world are on the cusp of a major digital transformation. This paper seeks to explore the concept of an artificial intelligence and natural language processing (NLP) based intelligent tutoring system (ITS) in the context of computer education in primary and secondary schools. One of the components of an ITS is a learning assistant, which can enable students to seek assistance as and when they need, wherever they are. As part of this research, a pilot prototype chatbot was developed, to serve as a learning assistant for the subject Scratch (Scratch is a graphical utility used to teach school children the concepts of programming). By the use of an open source natural language understanding (NLU) or NLP library, and a slackbased UI, student queries were input to the chatbot, to get the sought explanation as the answer. Through a two-stage testing process, the chatbot’s NLP extraction and information retrieval performance were evaluated. The testing results showed that the ontology modelling for such a learning assistant was done relatively accurately, and shows its potential to be pursued as a cloud-based solution in future.