With the increasing trend of web services over the Internet, developing a robust Quality of Service (QoS) prediction algorithm for recommending services in real-time is becoming a challenge today. Designing an efficient QoS prediction algorithm achieving high accuracy, while supporting faster prediction to enable the algorithm to be integrated into a real-time system, is one of the primary focuses in the domain of Services Computing. The major state-of-the-art QoS prediction methods are yet to efficiently meet both criteria simultaneously, possibly due to the lack of analysis of challenges involved in designing the prediction algorithm. In this paper, we systematically analyze the various challenges associated with the QoS prediction algorithm and propose solution strategies to overcome the challenges, and thereby propose a novel offline framework using deep neural architectures for QoS prediction to achieve our goals. Our framework, on the one hand, handles the sparsity of the dataset, captures the non-linear relationship among data, figures out the correlation between users and services to achieve desirable prediction accuracy. On the other hand, our framework being an offline prediction strategy enables faster responsiveness. We performed extensive experiments on the publicly available WS-DREAM dataset to show the trade-off between prediction performance and prediction time. Furthermore, we observed our framework significantly improved one of the parameters (prediction accuracy or responsiveness) without considerably compromising the other as compared to the state-of-the-art methods.

In this paper, we undertake a task to find named entities directly from unstructured handwritten document images without any intermediate text/character recognition. Here, we do not receive any assistance from natural language processing. Therefore, it becomes more challenging to detect the named entities. We work on Bengali script which brings some additional hurdles due to its own unique script characteristics. Here, we propose a new deep neural network-based architecture to extract the latent features from a text image. The embedding is then fed to a BLSTM (Bidirectional Long Short-Term Memory) layer. After that, the attention mechanism is adapted to an approach for named entity detection. We perform experimentation on two publicly-available offline handwriting repositories containing 420 Bengali handwritten pages in total. The experimental outcome of our system is quite impressive as it attains 95.43% balanced accuracy on overall named entity detection.

Automated handwriting analysis is a popular area of research owing to the variation of writing patterns. In this research area, writer verification is one of the most challenging branches, having direct impact on biometrics and forensics. In this paper, we deal with offline writer verification on complex handwriting patterns. Therefore, we choose a relatively complex script, i.e., Indic Abugida script Bengali (or, Bangla) containing more than 250 compound characters. From a handwritten sample, the probability distribution functions (PDFs) of some handcrafted features are obtained and input to a convolutional neural network (CNN). For such a CNN architecture, we coin the term "PDFCNN", where handcrafted feature PDFs are hybridized with auto-derived CNN features. Such hybrid features are then fed into a Siamese neural network for writer verification. The experiments are performed on a Bengali offline handwritten dataset of 100 writers. Our system achieves encouraging results, which sometimes exceed the results of state-of-the-art techniques on writer verification.

This paper deals with computer-based cognitive analysis towards legibility and aesthetics of a handwritten document. The legible text creates a human perception that the writing can be read effortlessly because of its orthographic clarity. The aesthetic property relates to the beautiful appearance of a handwritten document. In this study, we deal with these properties on offline Bengali handwriting. We formulate both legibility and aesthetic analysis tasks as machine learning problems supervised by the human cognitive system. We employ automatically derived feature-based recurrent neural networks to investigate writing legibility. For aesthetics evaluation, we employ hand-crafted feature-based support vector machines (SVMs). We have collected contemporary Bengali handwritings, on which the subjective legibility and aesthetic scores are provided by human readers. On this corpus containing legibility and aesthetic ground-truth information, we executed our experiments. The experimental results obtained on various handwritings are encouraging.

Named entity recognition is an important topic in the field of natural language processing, whereas in document image processing, such recognition is quite challenging without employing any linguistic knowledge. In this paper we propose an approach to detect named entities (NEs) directly from offline handwritten unstructured document images without explicit character/word recognition, and with very little aid from natural language and script rules. At the preprocessing stage, the document image is binarized, and then the text is segmented into words. The slant/skew/baseline corrections of the words are also performed. After preprocessing, the words are sent for NE recognition. We analyze the structural and positional characteristics of NEs and extract some relevant features from the word image. Then the BLSTM neural network is used for NE recognition. Our system also contains a post-processing stage to reduce the true NE rejection rate. The proposed approach produces encouraging results on both historical and modern document images, including those from an Australian archive, which are reported here for the very first time.

Writer identification is an essential component in computational forensic. In this paper, we attempt to do this job based only on isolated characters and numerals. For that, at first, some points of interest (keypoints) on the image are detected by structural analysis and SIFT based detector. Then we calculate a set of features within a certain neighborhood of the keypoint and employ fusion rule on multiple probabilistic SVM classifiers output for writer identification. For experimental analysis, a database containing 212,300 isolated Bangla orthosyllabic characters and numerals are generated with the help of 100 writers. We obtain fairly good result to identify a writer. We also try to find a small set of highly discriminative characters storing extra information about the writing style of an individual.