• Dublin, Uttar Pradesh, India
Recent publications
Refactorings constitute the most direct and comprehensible approach for addressing software quality issues, stemming directly from identified code smells. Nevertheless, despite their popularity in both the research and industrial communities: (a) the effect of a refactoring is not guaranteed to be successful; and (b) the plethora of available refactoring opportunities does not allow their comprehensive application. Thus, there is a need of guidance, on when to apply a refactoring opportunity, and when the development team shall postpone it. The notion of interest, forms one of the major pillars of the Technical Debt metaphor expressing the additional maintenance effort that will be required because of the accumulated debt. To assess the benefits of refactorings and guide when a refac-toring should take place, we first present the results of an empirical study assessing and quantifying the impact of various refactorings on Technical Debt Interest (building a real-world training set) and use machine learning approaches for guiding the application of future refactorings. To estimate interest, we rely on the FITTED framework, which for each object-oriented class assesses its distance from the best-quality peer; whereas the refactorings that are applied throughout the history of a software project are extracted with the RefactoringMiner tool. The dataset of this study involves 4,166 refactorings applied accriss 26,058 revisions of 10 Apache projects. The results suggest that the majority of refactorings reduce Technical Debt interest; however, considering all refactoring applications , it cannot be claimed that the mean impact differs from zero, confirming the results of previous studies highlighting mixed effects from the application of refactorings. To alleviate this problem, we have built an adequately accurate (~70%) model for the prediction of whether or not a refactoring should take place, in order to reduce Technical Debt interest.
Illegal movement or the flow of drugs in the supply chain has always been the root cause of various criminal activities involving pharmaceutical products. One such concern is the black-marketing of drugs by erasing the record of the drug from the registered supply chain and selling it on various channels for many times the price with an alteration made to the drug itself. To counteract such methods, we have proposed a solution using one of the most prominent characteristics, i.e., traceability, using which we can back-trace the route taken in the supply chain for the targeted drug on which the medical prescription is made.KeywordsBlockchainTraceabilityPharmaceuticalDrug traceabilityTracing medical prescriptionDecentralized applicationBlockchain traceability systemDecentralized tracking system
The cutting-edge technology, namely Cloud of Things (CoT) has shaped the existing business process into a new orientation in terms of performance, usability, and reliability. Among different business processes, online education is one of the prime areas where CoT can be used to make it more agile in the context of performance and usability. In this endeavor, a novel methodology has been proposed for an online higher education framework based on CoT. The proposed framework is made agile using Service Oriented Architecture (SOA). Furthermore, in order to make the proposed framework more reliable, a Zero Knowledge Proof (ZKPF) system has been introduced here. The proposed ZKPF algorithm is based on the Hadamard matrix. Experimental results have shown to lay bare the effectiveness of the proposed algorithms.
In recent years, task-oriented virtual assistants have gained huge popularity and demand in both research and industry communities. The primary aim of a task-oriented dialogue agent is to assist end-users in accomplishing a task successfully and satisfactorily. Existing virtual agents have acquired proficiency in assisting users in solving simple tasks such as restaurant bookings. However, they operate under the deterministic presumption that end-users will have a servable task objective, which makes them inadequate under adversarial situations such as goal unavailability. On the other hand, human agents accomplish users’ tasks even in many goal unavailability scenarios by persuading them towards a similar goal to the user’s proposed task. Motivated by the limitation, the current work proposes and builds a novel transformer-based context-aware personalized persuasive virtual assistant (CoPersUasive VA), which also serves end-users in task unavailability situations. The proposed CoPersUasive VA recognizes goal conflicts through user sentiment and identifies an appropriate persuasion strategy using ongoing dialogue context and user personality. Depending on users’ proposed goals, it finds a similar servable goal and persuades them with the identified persuasion strategy. The obtained experimental results and detailed post-analysis firmly establish that the proposed model effectively enhances the capability of task-oriented virtual assistants to deal with the task failures caused by goal unavailability. The obtained findings also suggest the crucial role of dialogue context in identifying an appropriate and appealing persuasion strategy. The proposed CoPersUasive model could easily be adapted to any other domain by fine-tuning the model on an underlying task. Furthermore, we developed a personalized persuasive multi-intent conversational dialogue corpus annotated with intent, slot, sentiment, and dialogue act for electronic domain.
Healthcare is one of the emerging application fields in the Internet of Things (IoT). Stress is a heightened psycho-physiological condition of the human that occurs in response to major objects or events. Stress factors are environmental elements that lead to stress. A person’s emotional well-being can be negatively impacted by long-term exposure to several stresses affecting at the same time, which can cause chronic health issues. To avoid strain problems, it is vital to recognize them in their early stages, which can only be done through regular stress monitoring. Wearable gadgets offer constant and real information collecting, which aids in experiencing an increase. An investigation of stress discovery using detecting devices and deep learning-based is implemented in this work. This proposed work investigates stress detection techniques that are utilized with detecting hardware, for example, electroencephalography (EEG), photoplethysmography (PPG), and the Galvanic skin reaction (GSR) as well as in various conditions including traveling and learning. A genetic algorithm is utilized to separate the features, and the ECNN-LSTM is utilized to classify the given information by utilizing the DEAP dataset. Before that, preprocessing strategies are proposed for eliminating artifacts in the signal. Then, the stress that is beyond the threshold value is reached the emergency/alert state; in that case, an expert who predicts the mental stress sends the report to the patient/doctor through the Internet. Finally, the performance is evaluated and compared with the traditional approaches in terms of accuracy, f1-score, precision, and recall.
One of the most prevalent diseases that can be initially identified by visual inspection and further identified with the use of dermoscopic examination and other testing is skin cancer. Since eye observation provides the earliest opportunity for artificial intelligence to intercept various skin images, some skin lesion classification algorithms based on deep learning and annotated skin photos display improved outcomes. The researcher used a variety of strategies and methods to identify and stop diseases earlier. All of them yield positive results for identifying and categorizing diseases, but proper disease categorization is still lacking. Computer-aided diagnosis is one of the most crucial methods for more accurate disease detection, although it is rarely used in dermatology. For Feature Extraction, we introduced Spectral Centroid Magnitude (SCM). The given dataset is classified using an enhanced convolutional neural network; the first stage of preprocessing uses a median filter, and the final stage compares the accuracy results to the current method.
In a mobile network, nodes are placed in infrequent manner, which are moved along network in abruptly. Communication flaw between sender node and accepting node in path, the node having restricted energy and restricted transmission rate. It does not provide perfect route for communication among mobile nodes. It increases the packet drop rate and minimizes the lifetime of network. This work has proposed enhanced path routing with buffer allocation (IPBA) scheme which is implemented to obtain better communication; it protects the node from packet loss, and the buffer is used to maintain the temporary details of nodes and data packets that are ready to broadcast and receive. The coupling node selection algorithm is constructed to offer the path which frequently communicates data packets in normal case; the two efficient nodes are coupled with each other, and this type of nodes is selected to perform communication. It reduces the packet loss rate and increases network lifetime. End-to-end delay, communication overhead, throughput, network lifetime, packet loss, and energy consumption are the parameters considered for performance evaluations.
Outcome prediction for individual patient groups is of paramount importance in terms of selection of appropriate therapeutic options, risk communication to patients and families, and allocating resource through optimum triage. This has become even more necessary in the context of the current COVID-19 pandemic. Widening the spectrum of predictor variables by including radiological parameters alongside the usually utilized demographic, clinical and biochemical ones can facilitate building a comprehensive prediction model. Automation has the potential to build such models with applications to time-critical environments so that a clinician will be able to utilize the model outcomes in real-time decision making at bedside. We show that amalgamation of computed tomogram (CT) data with clinical parameters (CP) in generating a Machine Learning model from 302 COVID-19 patients presenting to an acute care hospital in India could prognosticate the need for invasive mechanical ventilation. Models developed from CP alone, CP and radiologist derived CT severity score and CP with automated lesion-to-lung ratio had AUC of 0.87 (95% CI 0.85–0.88), 0.89 (95% CI 0.87–0.91), and 0.91 (95% CI 0.89–0.93), respectively. We show that an operating point on the ROC can be chosen to aid clinicians in risk characterization according to the resource availability and ethical considerations. This approach can be deployed in more general settings, with appropriate calibrations, to predict outcomes of severe COVID-19 patients effectively.
This study explores the experience of displacement from the perspective of women who have been or are about to be moved from their homes and sources of livelihood, to make way for the expansion of a wildlife reserve in India. We conducted this in the Nayi Basti (Nb) and Umravan (U) areas of the tribal belt around the Panna Tiger Reserve in Madhya Pradesh state of India. Availability of common property resources significantly contributed to a better position for women in tribal society, despite their lack of access to modern health care and education. Displacement to plains and non-forest areas with no access to familiar means of livelihood, however, makes such communities vulnerable to psychosocial trauma and decline in social status. We conducted in-depth interviews with women respondents and key informants for this study to assess the levels of distress of women after they were displaced and obtained their perspectives, in particular, about the key psychosocial issues they faced after moving.
Formaldehyde is a carcinogenic indoor air pollutant emitted from common wood-based materials. Low-cost sensing of formaldehyde is difficult due to inaccuracies in measuring low concentrations and susceptibility of sensors to changing indoor environmental conditions. Currently gas sensors are calibrated by manufacturers using simplistic models which fail to capture their complex behaviour. We evaluated different low-cost gas sensors to ascertain a suitable component to create a mobile sensing node and built a calibration algorithm to correct it. We compared the performance of 2 electrochemical sensors and 3 metal oxide sensors in a controlled chamber against a photo-acoustic reference device. In the chamber the formaldehyde concentrations, temperature and humidity were varied to assess the sensors in diverse environments. Pre-calibration, the electrochemical sensors (mean absolute error (MAE) = 70.8 ppb) outperformed the best performing metal oxide sensor (MAE = 335 ppb). A two-stage calibration model was built, using linear regression followed by random forest, where the residual of the first stage acted as a input for the second. Post-calibration, the metal oxide sensors (MAE = 154 ppb) improved compared to their electrochemical counterparts (MAE = 78.8 ppb). Nevertheless, the uncalibrated electrochemical sensor showed overall superior performance hence was selected for the mobile sensing node.
Institution pages aggregate content on ResearchGate related to an institution. The members listed on this page have self-identified as being affiliated with this institution. Publications listed on this page were identified by our algorithms as relating to this institution. This page was not created or approved by the institution. If you represent an institution and have questions about these pages or wish to report inaccurate content, you can contact us here.
3,068 members
Bhushan Jagyasi
  • Artificial Intelligence
Anil Choudhary
  • Institute for High Performance
Sherman D Quan
  • Strategy and Consulting
Ullas Nambiar
  • Applied Intelligence
Address, Yogendra Park, INSIDE SATISH PARK,Modinagar,, 201201, Dublin, Uttar Pradesh, India