Search

Image denoising methods are of fundamental importance in image processing and artificial intelligence systems. In this review, we analyze the traditional and state of the art mathematical models for computational color image denoising. These algorithms are divided into methods that are based on the partial differential equations, low rank, sparse representation and recent developments based on deep learning models. These algorithms also compared in terms of image quality measures. Our analysis and review of the computational color image denoising filters indicate that the convolutional neural networks from the deep learning domain obtain high quality restorations in terms of image quality despite the higher computational complexity.

Social media has become one of the most popular sources of information. People communicate with each other and share their ideas, commenting on global issues and events in a multilingual environment. While social media has been popular for several years, recently, it has given an exponential rise in online data volumes because of the increasing popularity of local languages on the web. This allows researchers of the NLP community to exploit the richness of different languages while overcoming the challenges posed by these languages. Urdu is also one of the most used local languages being used on social media. In this paper, we presented the first-ever event detection approach for Urdu language text. Multiclass event classification is performed by popular deep learning (DL) models, i.e.,Convolution Neural Network (CNN), Recurrence Neural Network (RNN), and Deep Neural Network (DNN). The one-hot-encoding, word embedding, and term-frequency inverse document frequency- (TF-IDF-) based feature vectors are used to evaluate the Deep Learning(DL) models. The dataset that is used for experimental work consists of more than 0.15 million (103965) labeled sentences. DNN classifier has achieved a promising accuracy of 84% in extracting and classifying the events in the Urdu language script.

In this article, an innovative encryption technique is developed by getting the inspiration from the natural up-down water wave’s phenomena that changes a reflection on pond’s surface. The plain image is considered as water pond and stones are throwing on the pond to diffuse the pixels. The direction of diffusion follows the pattern of natural water waves in 360 degrees. The distance traveled by the waves depend upon the weight of the stone i.e. heavier is the stone, longer will be the distance. Each layer of pixels in image represents Crest (Up) and Troughs (Down) around the hitting point of stone. The number of Crest and Troughs generated by a stone in radius are measured and are categorized into 1 to 6 or six levels (Layers). The concept of Crest and Trough in encryption are achieved by addition and subtraction of pseudo-random numbers in the pixel’s intensity. The pseudo random numbers are generated from Logistic map and transformed into stones of different weights ranges from 0-255. Before substitution, the pixels are shuffled in 1-dimensional vector using the index values of random numbers. The hash value is used for modification of initial seeds of the Logistic map. The initial seeds of the Logistic map are modified by the output of 256-bit hash function. Finally, the simulated results are compiled which ascertains that the projected algorithm achieves the required security standard with large pool of secret keys.

With the progress in technology innovations, business organizations have preferred usage of online trading instead of traditional ways of trading. Online stores let businessmen offer more variety of products without the need of having big warehouses. At the same time, online shopping also saves time of customers and let them enjoy buying-at-home experience. They have the facility of looking at different qualities and prices of the same products offered by different vendors and buy the most suitable one. Online shopping business has especially got lot of attention after emergence of online social media. There are lot of self-made entrepreneurs as well as business giants with their Facebook pages available for online shopping. With this mode of online shopping getting very popular among masses, there are some inherent problems attached with this mode of online shopping. One of the most common problem on online shopping Facebook pages is question-answering on each post. For each product post published on Facebook page, customers ask lots of questions in the form of comments and then Facebook page admin has to reply each question one by one. This can be a very cumbersome job in case that page has a significant number of customers. In case someone is not replied, goodwill of the company is affected which can in turn affect sales. In this paper, we propose several semantic approaches to tackle with this very important problem of online shopping and compare their results. We propose a simple but effective approach for question extraction from comments on a post and we provide a huge data collection for this formulated task. Results show that word embeddings based approach outperform proposed baseline and other semantic approaches.

The objective of this study was to observe the potential of machine vision (MV) approach for the classification of eight citrus varieties. The leaf images of eight citrus varieties that were grapefruit, Moussami, Malta, Lemon, Kinow, Local lemon, Fuetrells, and Malta Shakri. These were acquired by a digital camera in an open environment without any complex laboratory setup. The acquired digital images dataset was transformed into the multi-feature dataset that was the combination of binary, histogram, texture, spectral, rotational, scalability and translational (RST) invariant features. For each citrus leaf image, total 57 multi-features were acquired on every non-overlapping region of interest (ROI), i.e. (32x32), (64x64), (128x128), and (256x256). Furthermore, the optimized 15 features using the supervised correlation-based feature selection (CFS) technique were acquired. The optimized multi-features dataset to different MV classifiers namely Multilayer Perceptron (MLP), Random Forest (RF), J48 and Naïve Bayes using10-fold cross-validation method were plugged-in. The results produced by MLP presented an average overall accuracy of 98.14% on ROIs (256x256) outperforming the other classifiers. The classification accuracy values by MLP on the eight citrus leaf varieties, namely; Grapefruit, Moussami, Malta, Lemon, Kinow, Local lemon, Fuetrells, and Malta Shakri were observed 98%, 98.75%, 99.25%, 97.5%, 97%, 95.87%, 95.5%, and 99.37% respectively.

In this paper, we make use of the 2-dimensional data obtained through t-Stochastic Neighborhood Embedding (t-SNE) when applied on high-dimensional data of Urdu handwritten characters and numerals. The instances of the dataset used for experimental work are classified in multiple classes depending on the shape similarity. We performed three tasks in a disciplined order; namely, (i) we generated a state-of-the-art dataset of both the Urdu handwritten characters and numerals by inviting a number of native Urdu participants from different social and academic groups, since there is no publicly available dataset of such type till date, then (ii) applied classical approaches of dimensionality reduction and data visualization like Principal Component Analysis (PCA), Autoencoders (AE) in comparison with t-Stochastic Neighborhood Embedding (t-SNE), and (iii) used the reduced dimensions obtained through PCA, AE, and t-SNE for recognition of Urdu handwritten characters and numerals using a deep network like Convolution Neural Network (CNN). The accuracy achieved in recognition of Urdu characters and numerals among the approaches for the same task is found to be much better. The novelty lies in the fact that the resulting reduced dimensions are used for the first time for the recognition of Urdu handwritten text at the character level instead of using the whole multidimensional data. This results in consuming less computation time with the same accuracy when compared with processing time consumed by recognition approaches applied to other datasets for the same task using the whole data.

BACKGROUND Dengue is an acute pyretic disease spread by the mosquito-borne dengue virus. It is a self-limiting illness, characterized by fever, myalgia, headache, and rash, and its severe forms are hemorrhagic fever and shock syndrome may lead to multisystem participation and death. The dengue was originated in animals specifically in the monkeys that further overturned into human beings about 500 years ago. Initially, this virus was observed in the subcontinents of Africa and Southeast Asia in mid of 20th century. The dengue viruses in viremic individuals and the Aedes aegypti mosquito (yellow fever mosquito) were the main factors involved in spreading this virus throughout tropical Southeast Asia via maritime shipments. A number of experiments were performed in the last two decades for the remedy of this disease that needs to be arranged in some manageable form for extracting research-oriented information. OBJECTIVE The bibliometric analysis is one of the popular approaches to analyzing the literature review that helps in the mapping of research and development (R&D) activities. We implement this analysis model in illustrating and quantifying the scientific scenario related to dengue research worldwide. While performing the bibliometric analysis we can produce scalable results from an individual to an international level by depicting the collaboration of each author, the role of the impact factor of highly active journals, etc. METHODS In order to perform the above-mentioned task, the Web of Science (WoS) and Scopus databases were selected as the repository of the noteworthy research work done in various tasks related to the dengue virus. In total, 18607 publications were considered within the period 1872-2019. Among these, a total of 9664 and 30604 documents were retrieved from WoS and Scopus databases respectively. After merging the data and eliminating the duplicates, the total number of publications was 32150. Furthermore, on the basis of the titles and abstracts, a total of 18607 studies were retrieved related to dengue virus research excluding the studies related to other diseases and viruses. The retrieved documents include articles, books, conference papers, data papers, editorials, erratum, letters, meeting abstracts, news items, notes, proceeding papers, reprint, review, and short survey papers. The metadata of the retrieved publications contains the information including the date of publication, authors, affiliation, digital object identifier (DOI), the title, abstract, name of the journal, and keywords, among other key aspects that were managed in Excel. For visualization and analysis purposes, state-of-art tools like Mendeley, Microsoft Excel, Biblioshiny, and VOS-viewer (version 1.6.15) were used. RESULTS After performing a careful analysis of the retrieved 18607 publications, it was observed that about 79.00% (14625) of the total articles were the original research papers, 5.99% (1115) were review and survey articles, 4.72% (878) were the editorial letters and remaining 3.41% (635) were the conference proceedings. Furthermore, it was also witnessed that 90.57% (16844) of the collected research articles were published in English and the remaining 9.47% (1763) are published in other languages. Among the journals that published these articles, the international journal “American Journal of Tropical Medicine and Hygiene” stood first having the highest number of papers (698) published in this journal. The research group of academic institutes of Mahidol University, University of Malaya, and the National University of Singapore contributed more than the other universities. The average citation of the top 15 articles was found to be 1,213. The paper having the title “The Global Distribution and Burden of Dengue” was the most cited (3833) as compared with other papers. The network visualization maps conclude that the most frequent terms that appeared in the papers were dengue, dengue virus, antibodies, female, aedes, mosquito, virus replication, epidemic, dengue vaccine. CONCLUSIONS The bibliometric analysis concluded that there is a strong bonding between the authors and institutions for instance Mr. HARRIS E from The University of California, USA is found to be the most productive author with 158 published articles. In general, this study not only demonstrates a full understanding of global dengue virus research but also can contribute to forthcoming further research in this field.

Work on the problem of handwritten text recognition in Urdu script has been an active research area. A significant progress is made in this interesting and challenging field in the last few years. In this study, the authors presented a comprehensive survey for a number of offline and online handwritten text recognition systems for Urdu script written in Nastaliq font style from 2004 to 2019. Following features make their contribution worthwhile and unique among the reviews of a similar kind: (i) their review classifies the existing studies based on types of recognition systems used for Urdu handwritten text, (ii) it covers a very different outlook of the recognition process of the Urdu handwritten text at different granularity levels (e.g. character, word, ligature, or sentence level), (iii) this review article also presents each of surveyed articles in following dimensions: the task performed, its granularity level, dataset used, results obtained, and future dimensions, and (iv) lastly it gives the summary of the surveyed articles according to the granularity levels, publishing years, related tasks or subtasks, and types of classifiers used. In the end, major challenges and tasks related to Urdu handwritten text recognition approaches are also discussed in detail.

Our study is a scientometric analysis of research publications of science and social science disciplines in Pakistan during 2009–2018. The study examines 2000 published articles belonging to 50 research scholars of different disciplines. This analysis is conducted on three different levels: researcher level, field level and domain level. In this paper we discuss readability scores, title formats, single and multiple authorships of articles, citation rates, publication rates over time, the research contribution of both genders and the impact of PhD institution of authors in research publications. The IR features like number of words, sentence length and readability scores are extracted. The results indicate that more research is being conducted in science disciplines as compared to social sciences. It also appears that the readability scores of authors changed over time, and Science articles have higher readability scores compared to Social Science articles. Moreover, title formats are observed to effect citation rates. Titles tend to use more colons over time; and the use of simple sentences as titles is more than 50%, while use of question marks is below 3%, the rest are titles with colons. The citation rates also appear to increase due to co-authorship. Male researchers contribute more to research activities in science disciplines while in social science the ratio is almost equal while PhD institutes appear to influence the performance of researcher slightly. Finally, it is observed that the publication rates of Science disciplines are much higher than Social Science articles, depicting that the growth of Science disciplines is more rapid in Pakistan.

The authors wish to make the following corrections to their paper [...]

The real-time availability of the Internet has engaged millions of users around the world. The usage of regional languages is being preferred for effective and ease of communication that is causing multilingual data on social networks and news channels. People share ideas, opinions, and events that are happening globally i.e., sports, inflation, protest, explosion, and sexual assault, etc. in regional (local) languages on social media. Extraction and classification of events from multilingual data have become bottlenecks because of resource lacking. In this research paper, we presented the event classification task for the Urdu language text existing on social media and the news channels by using machine learning classifiers. The dataset contains more than 0.1 million (102,962) labeled instances of twelve (12) different types of events. The title, its length, and the last four words of a sentence are used as features to classify the events. The Term Frequency-Inverse Document Frequency (tf-idf) showed the best results as a feature vector to evaluate the performance of the six popular machine learning classifiers. Random Forest (RF) and K-Nearest Neighbor (KNN) are among the classifiers that out-performed among other classifiers by achieving 98.00% and 99.00% accuracy, respectively. The novelty lies in the fact that the features aforementioned are not applied, up to the best of our knowledge, in the event extraction of the text written in the Urdu language.

Agriculture plays a vital role in the economy of Pakistan. Issues concerning irrigation have been always encumbering the development of the country. Water scarcity is becoming a big issue because of climate change, insufficient services and rising population. Farmers are not receiving the supply of equitable water efficiently due to current methods of irrigation, such as inequitable water distribution, manual reporting of mogha discharge by OFWM, change of water turn at late night and no need of water at his allocated time, tail-end user problems like either too much of water supply or no availability of water as per need of farmers. One solution to this problem is a smart irrigation system in which the system uses internet of things (IoT) based sensors to monitor water levels and communicates the water situation to the user. In this research, we elaborate on the applicability of the Internet of Things (IOT) in the irrigation system and propose an architecture of IoT based water irrigation system using a wireless sensor network to solve the problems of farmers. The IoT based smart irrigation system is based on the raspberry pi to improve the productivity of water and keep costs down. Farmer is informed about fields while there is any deviance from the expected water situation by a text message.

In the area of pattern recognition and pattern matching, the methods based on deep learning models have recently attracted several researchers by achieving magnificent performance. In this paper, we propose the use of the convolutional neural network to recognize the multifont offline Urdu handwritten characters in an unconstrained environment. We also propose a novel dataset of Urdu handwritten characters since there is no publicly-available dataset of this kind. A series of experiments are performed on our proposed dataset. The accuracy achieved for character recognition is among the best while comparing with the ones reported in the literature for the same task.

The first-order fuzzy differential equation has two possible solutions depending on the definition of differentiability. The definition of differentiability changes as the product of the function and its first derivative changes its sign. This switching of the derivative&rsquo, s definition is handled with the application of min, max operators. In this paper, a numerical technique for solving fuzzy initial value problems is extended to solving higher-order fuzzy differential equations. Fuzzy Taylor series is used to develop the fuzzy differential transformation method for solving this problem. This leads to a single solution for higher-order differential equations.

Cadmium (Cd) phytoremediation potential and its accumulation in edible and nonedible plant tissues is the function of various biochemical processes taking place inside plants. This study assessed the impact of organic ligands on Cd phyto uptake and different biophysiochemical processes of Spinacia oleracea L., and associated health hazards. Plants were exposed to Cd alone and chelated with citric acid (CA) and ethylenediaminetetraacetic acid (EDTA). Results revealed that the effect of Cd on lipid peroxidation, H2O2 production and pigment contents varied greatly with its applied level and the type of organic ligand. Moreover, the effect was more prominent in root tissues than leaf tissues and for high concentrations of Cd and organic ligands. Cadmium accumulation increased by 90 and 74% in roots and leaves, respectively, with increasing Cd levels (25–100 µM). Cadmium exposure at high levels caused lipid peroxidation in roots only. Application of both CA and EDTA slightly diminished Cd toxicity with respect to pigment contents, lipid peroxidation and hydrogen peroxide (H2O2) contents. Hazard quotient (HQ) of Cd was

We applied t-distributed stochastic neighbor embedding (t-SNE) to visualize Urdu handwritten numerals (or digits). The data set used consists of 28 &times, 28 images of handwritten Urdu numerals. The data set was created by inviting authors from different categories of native Urdu speakers. One of the challenging and critical issues for the correct visualization of Urdu numerals is shape similarity between some of the digits. This issue was resolved using t-SNE, by exploiting local and global structures of the large data set at different scales. The global structure consists of geometrical features and local structure is the pixel-based information for each class of Urdu digits. We introduce a novel approach that allows the fusion of these two independent spaces using Euclidean pairwise distances in a highly organized and principled way. The fusion matrix embedded with t-SNE helps to locate each data point in a two (or three-) dimensional map in a very different way. Furthermore, our proposed approach focuses on preserving the local structure of the high-dimensional data while mapping to a low-dimensional plane. The visualizations produced by t-SNE outperformed other classical techniques like principal component analysis (PCA) and auto-encoders (AE) on our handwritten Urdu numeral dataset.

Today, many organizations are transforming their traditional telephone services into Voice over Internet Protocol (VoIP) systems. These services are simple to implement, but they are often vulnerable to attacks because they are packet-switched IP networks to support the circuit-switched used for voice communication. SIP is widely used as a signaling protocol to facilitate video and voice communication, as well as for more multimedia applications. However, it is not protected against various types of attacks because of its open nature and lack of a clear line of defense against the growing number of security threats. Among these risks, registration hijacking assaults, known by its harmful effect, attack both the User Agent Server (UAS) and the User Agent Client (UAC). In particular, the REGISTER message is evaluated as one of the main reasons of registration hijacking assaults in SIP. An attacker who deactivates the SIP registration of a valid user and replaces it with the logical address of the hacker. This allows the hacker to block incoming calls as well as redirect, replay or end calls at will. In this survey, we present a complete study of the registration attack against SIP, communicating its different alternatives and analyzing its consequences. We have also categorized current solutions based on the different registration hijacking attack approaches they face, their types, and their targets. In addition, We conduct an in-depth review of the robustness and inefficiency of these solutions, as well as an in-depth analysis of each one’s basic assumptions to better understand their limitations. Finally, we recommend protecting the UAC registration method against registration-hijacking by using the Media Access Control (MAC) address to improve the efficiency of the studied solutions.

The diabetic retinopathy is the main reason of vision loss in people. Medical experts recognize some clinical, geometrical and haemodynamic features of diabetic retinopathy. These features include the blood vessel area, exudates, microaneurysm, hemorrhages and neovascularization, etc. In Computer Aided Diagnosis (CAD) systems, these features are detected in fundus images using computer vision techniques. In this paper, we review the methods of low, middle and high level vision for automatic detection and classification of diabetic retinopathy.We give a detailed review of 79 algorithms for detecting different features of diabetic retinopathy during the last eight years.

Computers and artificial intelligence affect every field of life nowadays. In medical image interpretation automatic decision making using algorithms are used increasingly in every sub-field and computer aided diagnosis (CAD) is one of the main tools available to medical science today. CAD systems are used as an augmented option for both the medical practitioner and the patients, with image analysis and interpretation being of primary importance. In particular, spatial relations are used in knowledge representation, and these relations can be used for effective medical image interpretation. In this paper, we put forth an algorithm for defining non-small cells lungs cancer (NSCLC) stages in lungs images interpretation using topological spatial relations. We show an application case study in event motion predictions for lung cancer staging scoring - tumor, nodes and metastasis (TNM) - with combined topological and directional relations.

Health information technology revolutionized the world with its great expansion and widespread in the domain of health care system. Most of the developed countries adopted advanced technology in their vaccination systems. Vaccination systems of many developing countries still lack the use of technology eventually causing mismanagement and corruption to occur in vaccination campaigns. Issues like mismanagement and corruption not only affect vaccination campaigns but also cause further diffusion of a disease. Pakistan is also one of such countries where vaccination system is prone to these and many other issues and hence it does not help in disease eradication. For example, polio remains alive in Pakistan because Pakistan’s Polio vaccination system is faced with many problems and the biggest one is security of vaccination teams. Corruption, mismanagement, unawareness among public and life-threat to vaccination teams are the main problems of current polio vaccination system of Pakistan. To overcome these flaws and to make an idyllic system with the new advanced technology, we propose technology oriented secure polio vaccination system. The proposed system is more secure and removes flaws in the current system. We model our proposed system using Colored Petri Nets (CPNs) which is a state-of-the-art tool for formal modeling.

The nature of World Wide Web (www) has evolved over the passage of time. Easier and faster availability of Internet has given rise to huge volumes of data available online. Another cause of huge volumes of data is the emergence of online social networks (like Facebook, Twitter, etc.) which has actually changed the role of data consumers to data generators. Increasing popularity of these online social networks has also changed the way different web services used to be used. For example, Facebook messaging has some impact on usage of emails; twitter usage affects (positively or negatively) online newspaper readings. Both of these platforms are heavily used for information searching. In this paper, we evaluate the role of Facebook and Twitter for academic queries and compare the findings with Google search engines to find out if there is a chance that these online social networks will replace Google sooner. A query set selected from the standard AOL dataset is used for experimentation. Academic related queries are selected and classified by expert users. Findings of Google, Facebook and Twitter are compared against these queries using Mean Average Precision (MAP), as a metrics for evaluation. Results conclude that Google has the dominating factor with a better MAP than Facebook and Twitter.

It is the age of the social web, where people express themselves by giving their opinions about various issues, from their personal life to the world&rsquo, s political issues. This process generates a lot of opinion data on the web that can be processed for valuable information, and therefore, semantic annotation of opinions becomes an important task. Unfortunately, existing opinion annotation schemes have failed to satisfy annotation challenges and cannot even adhere to the basic definition of opinion. Opinion holders, topical features and temporal expressions are major components of an opinion that remain ignored in existing annotation schemes. In this work, we propose OpinionML, a new Markup Language, that aims to compensate for the issues that existing typical opinion markup languages fail to resolve. We present a detailed discussion about existing annotation schemes and their associated problems. We argue that OpinionML is more robust, flexible and easier for annotating opinion data. Its modular approach while implementing a logical model provides us with a flexible and easier model of annotation. OpinionML can be considered a step towards &ldquo, information symmetry&rdquo, It is an effort for consistent sentiment annotations across the research community. We perform experiments to prove robustness of the proposed OpinionML and the results demonstrate its capability of retrieving significant components of opinion segments. We also propose OpinionML ontology in an effort to make OpinionML more inter-operable. The ontology proposed is more complete than existing opinion ontologies like Marl and Onyx. A comprehensive comparison of the proposed ontology with existing sentiment ontologies Marl and Onyx proves its worth.

Spams are becoming a serious threat for the users of online social networks especially for the ones like of twitter. twitter’s structural features make it more volatile to spam attacks. In this paper, we propose a spam detection approach for twitter based on sentimental features. We perform our experiments on a data collection of 29K tweets with 1K tweets for 29 trending topics of 2012 on twitter. We evaluate the usefulness of our approach by using five classifiers i.e. BayesNet, Naive Bayes, Random Forest, Support Vector Machine (SVM) and J48. Naive Bayes, Random Forest, J48 and SVM spam detections performance improved with our all proposed features combination. The results demonstrate that proposed features provide better classification accuracy when combined with content and user-oriented features.

In the last decade, there has been an exponential growth in use of mobile phones among people. Smart phone invention has digitized life of a common man especially after introduction of 3G/4G technology. People are used to use Internet on the move because of this advancement in technology. This advancement has also motivated usability design researchers to propose more usable designs for both smart phones and web sites. This work focuses on evaluation of web usability of mobile phones as well as usability of university web sites. Evaluation is performed on the most popular mobile phones required by the most common mobile users. Selection of the most popular mobile devices, the most common mobile users and their web usage is done by conducting a very detailed survey in the local market. Survey concludes that students and labors are the most common buyers of mobile phones and we choose three mobiles phones from the category of most popular phones that are iPhone (iPhone 4 precisely), Q-Mobile (Q Mobile A35) and Windows phone (Lumia 535). Six participants (three male and three females) are selected for fully detailed and rigorous task-based usability testing with “think aloud” technique. Task scenarios are defined to evaluate the usability of both i.e. smart phones and chosen university web sites. From results of usability testing, we find out that iPhone has better usability design as far as its response time is concerned while Q Mobile ranks second and Microsoft Windows phone takes last position in this ranking. Usability evaluation of university web sites on these mobile phones concludes that web site of Islamia university of Bahawalpur (I.U.B, Bahawalpur) has better mobile usability design and Bahauddin Zakariya university (BZU, Multan) and NFC Institute of Engineering and Technology NFCIET, Multan) second and third respectively and while web site of Institute of Southern Punjab (ISP, Multan) comes last when measured in terms of task completion time. All tests are performed on wireless network when internet download speed is between 3MBPS to 3.2MBPS.

Predicting gender by names is one of the most interesting problems in the domain of Information Retrieval and expert finding task. In this research paper, we propose a machine learning approach for gender prediction task. We propose a new feature, that is, combination of letters in names which gives 86.54% accuracy. Our data collection consists of 3000 Urdu language names written using English Alphabets. This technique can be used to extract names from email addresses and hence is also valid for emails. To the best of our knowledge, it is the first- ever attempt for predicting gender from Pakistani (Urdu) names written using English alphabets.

On Twitter, hashtags are used to summarize topics of the tweet content and to help search tweets. However, hashtags are created in a free style and thus heterogeneous, increasing difficulty of their usage. Therefore, it is important to evaluate that if they really represent the content they are attached with? In this work, we perform detailed experiments to find answer for this question. In addition to this, we compare different semantic relatedness measures to find this similarity between hashtags and tweets. Experiments are performed using ten different measures and Adapted Lesk is found to be the best.

The role of critical system-of-systems have become considerably software-intensive. A critical system-of-system has to satisfy correctness properties of liveness and safety. As critical system-of-systems have to operate in open environments in which they interact and collaborate with other systems, satisfy action of the requirements through traditional offline top-down engineering no longer suffice. Most of the critical software-intensive system-of-systems have no fixed boundaries and services provided by other systems will come and go in unpredictable ways; in these systems assuring correctness is a challenging issue. These systems need to tolerate faults in the face of change; they need a resilient architecture. An approach has been proposed for the analysis, design, formal specification and verification of critical Software-intensive System-of-Systems.

International audience; Opinion mining is one of the most challenging tasks of the field of information retrieval. Research community has been publishing a number of articles on this topic but a significant increase in interest has been observed during the past decade especially after the launch of several online social networks. In this paper, we provide a very detailed overview of the related work of opinion mining. Following features of our review make it stand unique among the works of similar kind: (1) it presents a very different perspective of the opinion mining field by discussing the work on different granularity levels (like word, sentences, and document levels) which is very unique and much required, (2) discussion of the related work in terms of challenges of the field of opinion mining, (3) document level discussion of the related work gives an overview of opinion mining task in blogosphere, one of most popular online social network, and (4) highlights the importance of online social networks for opinion mining task and other related sub-tasks.

This article describes approaches for searching opinionated documents for a given query from a standard data collection. To detect if a text is opinionated (i.e., contain subjective information) or not, we propose two methods: the first method is based on lexicons of subjective words (i.e., SentiWordNet) supported by the assumption that more a document contains the subjective terms more it has the tendency of being an opinionated document while the second method is based on probabilistic model supporting the idea that given a document having a strong similarity with a reference opinionated text is more likely to be opinionated. In the second method, we take support of language modeling approach to compute this similarity. Experiments are conducted with TREC Blog06 as the test collection and the IMDB data collection as being the reference data collection. The experimental results report effectiveness of both methods.

Retrieving entities instead of just documents has become an important task for search engines. In this paper we study entity retrieval for news applications, and in particular the importance of the news trail history (i.e., past related articles) in determining the relevant entities in current articles. This is an important problem in applications that display retrieved entities to the user, together with the news article. We analyze and discuss some statistics about entities in news trails, unveiling some unknown findings such as the persistence of relevance over time. We focus on the task of query dependent entity retrieval over time. For this task we evaluate several features, and show that their combinations significantly improves performance.

In this paper we study the problem of entity retrieval for news applications and the importance of the news trail history (i.e. past related articles) to determine the relevant entities in current articles. We construct a novel entity-labeled corpus with temporal information out of the TREC 2004 Novelty collection. We develop and evaluate several features, and show that an article's history can be exploited to improve its summarization.

In this work, we evaluate the importance of Passages in blogs especially when we are dealing with the task of Opinion Detection. We argue that passages are basic building blocks of blogs. Therefore, we use Passage-Based Language Modeling approach as our approach for Opinion Finding in Blogs. Our decision to use Language Modeling (LM) in this work is totally based on the performance LM has given in various Opinion Detection Approaches. In addition to this, we propose a novel method for bi-dimensional Query Expansion with relevant and opinionated terms using Wikipedia and Relevance-Feedback mechanism respectively. We also compare the impacts of two different query terms weighting (and ranking) approaches on final results. Besides all this, we also compare the performance of three Passage-based document ranking functions (Linear, Avg, Max). For evaluation purposes, we use the data collection of TREC Blog06 with 50 topics of TREC 2006 over TREC provided best baseline with opinion finding MAP of 0.3022. Our approach gives a MAP improvement of almost 9.29% over best TREC provided baseline (baseline4).

The Opinion Detection from blogs has always been a challenge for researchers. However with the introduction of Blog track in TREC 2006, a considerable improvement has been seen in this field at document level. But now it is the time when researchers are thinking to shift their orientation from opinion finding at document level to opinion finding at sentence or passage level. In this paper, we investigate the challenges the researchers might face with sentence-level opinion detection and have tried to demonstrate them with few examples. Our work also includes annotation of a small set of opinionated sentences by two annotators. These Annotators annotate the sentences by labels Positive or Negative. The results of annotation prove that task of opinion detection on sentence-level is more challenging task than opinion detection on document level. In addition, we also discuss the importance of sentence-level opinion detection. Our work can give a new direction to researchers to think and work on.

The World Wide Web has taken the form of a social network and if analyzed carefully, we can extract various communities from this network based on different parameters such as culture, trust, behavior, relationships, etc. The Small World Effect is a kind of behavior that has been discovered in entity networks of many natural phenomena. The set of nodes in a network showing Small World Effect form a local network within the major network highlighting the properties of a Small World Network. This work analyzes three different web networks, i.e. Term-Term similarity network, Document-Document similarity network, and Hyperlinks network, to check whether they show Small World Network behavior or not. We define a criterion and then compare these network graphs against that criterion. The network graph which fulfills that criterion is declared to be a Small World Network.