National Institute of Technology, Meghalaya

About: National Institute of Technology, Meghalaya is a education organization based out in Shillong, India. It is known for research contribution in the topics: Control theory & Electric power system. The organization has 503 authors who have published 1062 publications receiving 6818 citations. The organization is also known as: NIT Meghalaya & NITM.

Automated Detection and Classification of Breast Cancer Tumour Cells using Machine Learning and Deep Learning on Histopathological Images

Abstract: Cancer is the result of abnormal growth of cells in a specific body part. It can outspread to other body parts rapidly if not diagnosed in a timely manner. Breast cancer is caused due to development of cancer cells in the breast tissue of women. Breast Cancer is the most frequent cause of death in women after lung cancer. If detected at primary stages, the breast cancer can be cured and the chances of survival drastically increases. Advances in screening and treatment for breast cancer have improved survival rates dramatically since 1989[1]. In this paper we have applied machine learning for image classification and further segmentation algorithms is applied for detection of the tumorous cells. The designing of the model began with classification of histopathological image dataset into Cancerous and Non - cancerous classes using Support Vector Machine (SVM) and Convolutional Neural Network (CNN) algorithms. Both the classifiers are examined on the basis of sensitivity, specificity, accuracy, precision, fl-score parameters. The resulting image i.e., Cancerous obtained from the classification algorithms are further used as an input for Image segmentation models. Genetic Algorithm (GA) and K-Means are used for the segmentation of the histopathological images. Experimental results showed that CNN for image classification in combination with GA for image segmentation gave more precise results with accuracy 99%.

A Novel SSA-NLLSF Approach for Denoising NQR Signals

Abstract: Nuclear quadrupole resonance (NQR) spectroscopy is used to identify narcotics and explosive materials. Detection of NQR signal generated by $${14}^{{N}}$$ isotope in an open environment is a challenging task due to the presence of external random noise and RF interference. Unlike the existing wavelet-based and other frequency-domain approaches that use averaged data, the present work exploits raw data by saving the acquisition time. In this context, a novel singular spectral analysis (SSA) and non-linear least square fit (NLLSF) algorithms are proposed to denoise the NQR signal and obtain the required parameters for detection of the NQR signal. Considering signal to noise ratio (SNR), segmental SNR (SSNR), and Pink noise as the performance parameters, the proposed algorithms are tested under various noise conditions by passing synthesized NQR signal and observed 35.7 dB gain SSNR. Furthermore, tests are carried out on NQR spectroscopy data acquired from the $$\hbox {NaNO}_{2}$$ sample, and an improvement in terms of signal quality and acquisition time are noticed.

Simultaneous Solving of Batched Linear Programs on a GPU

Abstract: Linear Programs (LPs) appear in a large number of applications and offloading them to a GPU is viable to gain performance. Existing work on offloading and solving an LP on a GPU suggests that there is performance gain generally on large sized LPs (typically 500 constraints, 500 variables and above). In order to gain performance from a GPU, for applications involving small to medium sized LPs, we propose batched solving of a large number of LPs in parallel. In this paper, we present the design and implementation of a batched LP solver in CUDA, keeping memory coalescent access, low CPU-GPU memory transfer latency and load balancing as the goals. The performance of the batched LP solver is compared against sequential solving in the CPU using the open source solver GLPK (GNU Linear Programming Kit) and the CPLEX solver from IBM. The evaluation on selected LP benchmarks from the Netlib repository displays a maximum speed-up of 95x and 5x with respect to CPLEX and GLPK solver respectively, for a batch of 1e5 LPs. We demonstrate the application of our batched LP solver to enhance performance in the domain of state-space exploration of mathematical models of control systems design.

Dynamic model of infected population due to spreading of pandemic COVID-19 considering both intra and inter zone mobilization factors with rate of detection.

Abstract: Most of the widely populated countries across the globe have been observing vicious spread and detrimental effects of pandemic COVID-19 since its inception on December 19. Therefore to restrict the spreading of pandemic COVID-19, various researches are going on in both medical and administrative sectors. The focus has been given in this research keeping an administrative point of view in mind. In this paper a dynamic model of infected population due to spreading of pandemic COVID-19 considering both intra and inter zone mobilization factors with rate of detection has been proposed. Few factors related to intra zone mobilization; inter zone mobilization and rate of detection are the key points in the proposed model. Various remedial steps are taken into consideration in the form of operating procedures. Further such operating procedures are applied over the model in standalone or hybridized mode and responses are reported in this paper in a case-studies manner. Further zone-wise increase in infected population due to the spreading of pandemic COVID-19 has been studied and reported in this paper. Also the proposed model has been applied over the real world data considering three states of India and the predicted responses are compared with real data and reported with bar chart representation in this paper.

Dynamic Power Management Controller to the Self-Sustained Wind-Solar DC Microgridin the Transport Applications

Abstract: The exhaustion of petroleum fuels day-by-day imposes the use of renewable energy sources in the transportation sector. The wind and solar generations are the well-established technologies in the field of renewable generation. Nevertheless, these sources suffer from the sporadic nature of electricity generation. Therefore, wind-solar sources are assisted by the energy storage systems (ESS) (i.e., battery and supercapacitor bank). In recent years, thebrushless DC (BLDC) motor became popular in the transport applications due to its reliable and efficient behaviour. To achieve the best-operating conditionsandgood efficiency in the DC microgrid, the high gain converters are used in this paper. Also, a power management algorithm is implemented to manage the proper power sharing among the DC microgrid partakers. Finally, Hardware-in-Loop validation of the proposedpower management control will be carried out using Virtex-7 FPGA kit co-simulated using Xilinx system generator.