M. M. Sufyan Beg

Mohd Zeeshan Ansari, M M Sufyan Beg, Tanvir Ahmad et al.

Language identification of social media text has been an interesting problem of study in recent years. Social media messages are predominantly in code mixed in non-English speaking states. Prior knowledge by pre-training contextual embeddings have shown state of the art results for a range of downstream tasks. Recently, models such as BERT have shown that using a large amount of unlabeled data, the pretrained language models are even more beneficial for learning common language representations. Extensive experiments exploiting transfer learning and fine-tuning BERT models to identify language on Twitter are presented in this paper. The work utilizes a data collection of Hindi-English-Urdu codemixed text for language pre-training and Hindi-English codemixed for subsequent word-level language classification. The results show that the representations pre-trained over codemixed data produce better results by their monolingual counterpart.

M Zeeshan Ansari, Tanvir Ahmad, M M Sufyan Beg et al.

The conventional natural language processing approaches are not accustomed to the social media text due to colloquial discourse and non-homogeneous characteristics. Significantly, the language identification in a multilingual document is ascertained to be a preceding subtask in several information extraction applications such as information retrieval, named entity recognition, relation extraction, etc. The problem is often more challenging in code-mixed documents wherein foreign languages words are drawn into base language while framing the text. The word embeddings are powerful language modeling tools for representation of text documents useful in obtaining similarity between words or documents. We present a simple probabilistic approach for building efficient word embedding for code-mixed text and exemplifying it over language identification of Hindi-English short test messages scrapped from Twitter. We examine its efficacy for the classification task using bidirectional LSTMs and SVMs and observe its improved scores over various existing code-mixed embeddings

Asra Aslam, Ekram Khan, Mohammad Samar Ansari et al.

Image segmentation refers to the separation of objects from the background, and has been one of the most challenging aspects of digital image processing. Practically it is impossible to design a segmentation algorithm which has 100% accuracy, and therefore numerous segmentation techniques have been proposed in the literature, each with certain limitations. In this paper, a novel Falling-Ball algorithm is presented, which is a region-based segmentation algorithm, and an alternative to watershed transform (based on waterfall model). The proposed algorithm detects the catchment basins by assuming that a ball falling from hilly terrains will stop in a catchment basin. Once catchment basins are identified, the association of each pixel with one of the catchment basin is obtained using multi-criterion fuzzy logic. Edges are constructed by dividing image into different catchment basins with the help of a membership function. Finally closed contour algorithm is applied to find closed regions and objects within closed regions are segmented using intensity information. The performance of the proposed algorithm is evaluated both objectively as well as subjectively. Simulation results show that the proposed algorithms gives superior performance over conventional Sobel edge detection methods and the watershed segmentation algorithm. For comparative analysis, various comparison methods are used for demonstrating the superiority of proposed methods over existing segmentation methods.

Parvez Mahmood Khan, M. M. Sufyan Beg

Estimation is one of the most critical areas in software project management life cycle, which is still evolving and less matured as compared to many other industries like construction, manufacturing etc. Originally the word estimation, in the context of software projects use to refer to cost and duration estimates only with software-size almost always assumed to be a fixed input. Continued legacy of bad estimates has compelled researchers, practitioners and business organizations to draw their attention towards another dimension of the problem and seriously validate an additional component, viz. size estimation. Recent studies have shown that size is the principal determinant of cost, and therefore an accurate size estimate is crucial to good cost estimation. Improving the accuracy of size estimates is, therefore, instrumental in improving the accuracy of cost and schedule estimates. Moreover, software size and cost estimates have the highest utility at the time of project inception, when most important decisions (e.g. budget allocation, personnel allocation, etc). are taken. The dilemma, however, is that only high-level requirements for a project are available at this stage. Leveraging this high-level information to produce an accurate estimate of software size is an extremely challenging and high risk task. This study acknowledges the presence and effect of risk in any software estimate and offers pragmatic strategies for risk mitigation.

Parvez Mahmood Khan, M. M. Sufyan Beg

It is well known fact that was phrased by famous quality scholar P.B. Crosby that it is always cheaper to do the job right the first time. However, this statement must be reconsidered with respect to software development projects, because the concept of quality and associated costs measurements in software engineering discipline is not as matured as in manufacturing and other fields of the industry. Post delivery defects (i.e. software bugs) are very common and integral part of software industry. While the process of measuring and classifying quality cost components is visible, obvious and institutionalized in manufacturing industry, it is still evolving in software industry. In addition to this, the recommendations of British standard BS-6143-2:1990 for classifying quality-related costs into prevention costs, appraisal costs, and failure costs have been successfully adopted by many industries, by identifying the activities carried out within each of these categories, and measuring the costs connected with them, software industry has a long-way to go to have the same level of adoption and institutionalization of cost of quality measurements and visibility. Cost of Quality for software isn't the price of creating a quality software product or IT-service. It's actually the cost of NOT creating a quality software product or IT-service. The chronic affliction of majority of software development projects that are frequently found bleeding with cost overruns, schedule slippage, scope creep and poor quality of deliverables in the global IT industry, was the trigger for this research work. Lessons learnt from this study offer valuable prescriptive guidance for small and medium software businesses, who can benefit from this study by applying the same for their quality improvement initiatives using CoQ-metric, to enhance the capability and maturity of their SDLC-project performance.

Parvez Mahmood Khan, M M Sufyan Beg, Musheer Ahmad

Growth in the number of PMOs established by the industry over last decade and ever growing body of literature on PMO related research in academia is a clear indication that there is very clear interest of researchers, practitioners and industries across the globe to understand and explore value propositions of PMO. However, there is still a lack of consensus on many critical aspects of PMOs. While there are many PMOs being established, but there are also many being closed and disbanded, which is definitely a matter of concern. In industry environment, a narrow majority of PMOs are well-regarded by their organizations and are seen as contributing business value, many of the others are still struggling to show value for money and some are failing, causing a high mortality rate among PMOs. This paper is the result of a study undertaken to get a deeper understanding of factors that may be causing mortality and failure of PMOs. Post Implementation Reviews of 4-failed & 3-challenged PMOs in IT-Industry were carried out with concerned Project Managers & PMO-staff, using grounded theory research method, with support from the concerned enterprise from IT-Industry.