Can Defect Prediction Be Useful for Coarse-Level Tasks of Software Testing?

It is popular to use software defect prediction (SDP) techniques to predict bugs in software in the past 20 years. Before conducting software testing (ST), the result of SDP assists on resource allocation for ST. However, DP usually works on fine-level tasks (or white-box testing) instead of coarse-level tasks (or black-box testing). Before ST or without historical execution information, it is difficult to get resource allocated properly. Therefore, a SDP-based approach, named DPAHM, is proposed to assist on arranging resource for coarse-level tasks. The method combines analytic hierarchy process (AHP) and variant incidence matrix. Besides, we apply the proposed DPAHM into a proprietary software, named MC. Besides, we conduct an up-to-down structure, including three layers for MC. Additionally, the performance measure of each layer is calculated based on the SDP result. Therefore, the resource allocation strategy for coarse-level tasks is gained according to the prediction result. The experiment indicates our proposed method is effective for resource allocation of coarse-level tasks before executing ST.

Multilabel Classification for Emotion Analysis of Multilingual Tweets

Emotion Analysis of text targets to detect and recognize types of feelings expressed in text. Emotion analysis is successor of Sentiment analysis. The latter does coarse-level analysis and classify the text into positive and negative categories while former does fine-grain analysis and classify text in specific emotion categories like happy, surprise, angry. Analysis of text at fine-level provides deeper insight compared to coarse-level analysis. In this paper, tweets are classified in discrete eight basic emotions namely joy, trust, fear, surprise, sadness, anticipation, anger, disgust specified in Plutchik’s wheel of emotions [1]. Tweets for three languages collected out of which one is English language and rest two are Indian languages namely Gujarati and Hindi. The collected tweets are related to Indian politics and are annotated manually. Supervised Learning and Hybrid approach are used for classification of tweets. Supervised learning uses tf-idf as features while hybrid approach uses primary and secondary features. Primary features are generated using tf-idf weighting and two different algorithms of feature generation are proposed which generate secondary features using SenticNet resource. Multilabel classification is performed to classify tweets in emotion categories. Results of experiments show effectiveness of hybrid approach.

The Sweet Sounds of Syntax: Music, Language, and the Investigation of Hierarchical Processing

Language and music are uniquely human faculties, defined by a level of sophistication found onlyin our species. The ability to productively combine contrastive units of sound, namely words inlanguage and notes in music, underlies much of the vast communicative and expressive capacities ofthese systems. Though the intrinsic rules of syntax in language and music differ in many regards,they both lead to the construction of complex hierarchies of interconnected, functional units. Muchresearch has examined the overlap, distinction, and general neuropsychological nature of syntaxin language and music but, in comparison to the psycholinguistic study of sentence processing,musical structure has been regarded at a coarse level of detail, especially in terms of hierarchicaldependencies. The current research synthesizes recent ideas from the fields of generative music theory,linguistic syntax, and neurolinguistics to outline a more detailed, hierarchy-based methodology forinvestigating the brain’s processing of structures in music.

Mask Region Based Convolution Neural Network (R-CNN) based Smart System for Anomaly Detection in Pedestrian Walkways

Recently, anomaly detection becomes a fascinating research application which usually raises an alarm in scenarios where the event varies from the actual event. Anomaly detection can be treated as a coarse-level video understanding problem that determines the existence of anomalies from habitual events. This paper introduces a new anomaly detection model by the use of Mask region based convolution neural network (R-CNN). The application of mask in the detection process helps to precisely identify the presence of anomalies in the scene. The effectiveness of the Mask R-CNN based anomaly detection model is validated against UCSD anomaly detection dataset. An extensive quantitative and experimental outcome evidently shows the superior nature of the presented model over the compared methods in a significant manner.

Spatio-Temporal Action Detection in Untrimmed Videos by Using Multimodal Features and Region Proposals

This paper proposes a novel deep neural network model for solving the spatio-temporal-action-detection problem, by localizing all multiple-action regions and classifying the corresponding actions in an untrimmed video. The proposed model uses a spatio-temporal region proposal method to effectively detect multiple-action regions. First, in the temporal region proposal, anchor boxes were generated by targeting regions expected to potentially contain actions. Unlike the conventional temporal region proposal methods, the proposed method uses a complementary two-stage method to effectively detect the temporal regions of the respective actions occurring asynchronously. In addition, to detect a principal agent performing an action among the people appearing in a video, the spatial region proposal process was used. Further, coarse-level features contain comprehensive information of the whole video and have been frequently used in conventional action-detection studies. However, they cannot provide detailed information of each person performing an action in a video. In order to overcome the limitation of coarse-level features, the proposed model additionally learns fine-level features from the proposed action tubes in the video. Various experiments conducted using the LIRIS-HARL and UCF-10 datasets confirm the high performance and effectiveness of the proposed deep neural network model.

The behavior of hydrophobic-core/hydrophilic-shell structured microgels at an interface: from Mickering emulsion to colloidosomes with dual-level controlled permeability

The release of model drug FITC-Dex from colloidosomes was examined in selected media and the controllable release was achieved by adjusting the pH (coarse level) and the ratio of the shell to core in the microgels (fine level).