Abstract

Mining of coverage patterns from transactional databases is one of the data mining tasks. It has applications in banner advertising, search engine advertising and visibility computation. In general, most real-world transactional databases are typically large. Mining of coverage patterns from large transactional databases such as query log transactions on a single computer is challenging and time-consuming. In this paper, we propose Distributed Coverage Pattern Mining (DCPM) approach. In this approach, we employ a notion of the summarized form of Inverse Transactional Database (ITD) and replicate it at every node. We also employ an efficient clustering-based method to distribute the computational load of extracting coverage patterns among the Worker nodes. We performed extensive experiments using two real-world datasets and one synthetic dataset. The results show that the proposed approach significantly improves the performance over the state-of-the-art approaches in terms of execution time and data shuffled.

Abstract

In this paper, we propose beamformed energy detection (BFED) spectrum sensing schemes for a single secondary user (SU) or a cognitive radio to detect a primary user (PU) transmission in the presence of an interferer. In the millimeter wave (mmWave) band, due to high attenuation, there are fewer multipaths, and the channel is sparse, giving rise to fewer directions of arrivals (DoAs). Sensing in only these paths instead of blind energy detection can reap significant benefits. An analog beamforming weight vector is designed such that the beamforming gain in the true DoAs of the PU signal is maximized while minimizing interference from the interferer. To demonstrate the bound on the system performance, the proposed sensing scheme is designed under the knowledge of full channel state information (CSI) at the SU for the PU-SU and Interferer-SU channels. However, as the CSI may not be available at the SU, another BFED sensing scheme is proposed, which only utilizes the estimate the DoAs. To model the estimates of DoAs, perturbations are added to the true DoAs. The distribution of the test statistic for BFED with full CSI schemes is derived under the null hypothesis so that the threshold of the NeymanPearson detector can be found analytically. The performance of both schemes is also compared with the traditional energy detector for multi-antenna systems. Index Terms—Beamforming, direction of arrival (DoA), energy detection, mmWave, spectrum sensing.

Abstract

During the COVID-19 pandemic, India’s complete lockdown was implemented from March 24 to May 3 2020, to minimize the effects of community transfer and control the rapidly growing rate of the virus spread. In this paper, we focus on quantifying the change in air pollution due to Hyderabad’s lockdown, the capital of Telangana State. For this, two datasets are employed. The first dataset is from the Central Pollution Control Board (CPCB) stations in the city. In contrast, the second dataset is the dense IoT network of PM monitors deployed in the educational campus of IIITH in Gachibowli, Hyderabad. An analysis is done on the collected data to understand the effect of lockdown on PM values while considering the yearly and seasonal variations. It has been shown that while there has been a significant drop in PM values. However, through correlation analysis between the temperature and the PM values during the regular times, not all PM values decrease because of the lockdown. Index Terms

Abstract

Codes with locality are a class of codes which minimize the number of nodes accessed to repair a failed node. These codes can be used to handle single and multiple erasures. In an extension, codes with hierarchical locality have been proposed, which offer multiple levels of locality as the number of erasure increase. Given the constraints imposed by locality, maximally recoverable codes (MRC) are a class of codes which allow for recoverability from all information theoretically recoverable erasure patterns. In this work, we consider MRC for the case of codes with hierarchical locality. We derive a field size lower bound on MRC with hierarchical locality. We also give constructions of MRC with hierarchical locality for some parameters, whose field size is smaller than that of earlier known constructions.

Abstract

— Centrality measures on graphs have found applications in a large number of domains including modeling the spread of an infection/disease, social network analysis, and transportation networks. As a result, parallel algorithms for computing various centrality metrics on graphs are gaining significant research attention in recent years. In this paper, we study parallel algorithms for the percolation centrality measure which extends the betweenness-centrality measure by incorporating a time dependent state variable with every node. We present parallel algorithms that compute the source-based and source-destination variants of the percolation centrality values of nodes in a network. Our algorithms extend the algorithm of Brandes, introduce optimizations aimed at exploiting the structural properties of graphs, and extend the algorithmic techniques introduced by Sariyuce et al. [26] in the context of centrality computation. Experimental studies of our algorithms on an Intel Xeon(R) Silver 4116 CPU and an Nvidia Tesla V100 GPU on a collection of 12 real-world graphs indicate that our algorithmic techniques offer a significant speedup.

Abstract

Current aerial robots are increasingly adaptive; they can morph to enable operation in changing conditions to complete diverse missions. Each mission may require the robot to conduct a different task. A conventional learning approach can handle these variations when the system is trained for similar tasks in a representative environment. However, it may result in overfitting to the new data stream or the failure to adapt, leading to degradation or a potential crash. These problems can be mitigated with an excessive amount of data and embedded model, but the computational power and the memory of the aerial robots are limited. In order to address the variations in the model, environment as well as the tasks within onboard computation limitations, we propose a deep neuromorphic controller approach with variable topologies to handle each different condition and the data stream with a feasible computation and memory allocation. The proposed approach is based on a deep neuromorphic (multi and variable layered neural network) controller with dynamic depth and progressive layer adaptation for each new data stream. This adaptive structure is combined with a switching function to form a sliding mode controller. The network parameter update rule guarantees the stability of the closed loop system by the convergence of the error dynamics to the sliding surface. Being the first implementation on an aerial robot in this context, the results illustrate the adaptation capability, stability, computational efficiency as well as the real-time validation.

Abstract

Objective assessment of voice disorders is widely explored as an early diagnosis tool for the classification of voice disorders. Voice disorders affect the pitch, loudness and voice quality, which are perceived at the suprasegmental-level in the speech signal. For the detection and assessment of voice disorders, this study explores the effectiveness of Long Term Average Spectral (LTAS) features using four state-of-the-art filter banks designed with critical-band, constant-Q, gammatone, and singlefrequency filtering approaches. Moreover, the performance of the systems is compared with state-of-the-art statistical-average and openSMILE features. Voice disorder detection experiment was carried out on SVD and HUPA database, while only SVD database is used for assessment task. Assessment task is performed in clinical way, in which four binary classifiers were trained in our study. Voice disorder detection and assessment tasks were carried out using the support vector machine classifier. From the results, it was observed that constant-Q filter bank based LTAS features performed better among all LTAS features with classification accuracy of 78% and 81.4% for voice disorder detection task on SVD and HUPA database, respectively. Further, the combination of LTAS features with OpenSMILE features improved (89.6% and 86.6% for SVD and HUPA database, respectively) the performance.

Abstract

In this paper, a new method to detect disfluencies directly from speech is explored. The method makes use of pre-linguistic automatic syllabification - the process of segmenting input speech signals into perceptually distinct syllable-like regions, to develop syllable-level disfluency detection systems. Statistical prosody features related to fundamental frequency, energy and duration are extracted from each syllable-like region and used to train a DNN classifier for automatic detection of speech disfluencies. Further, complementary information useful for the task of disfluency detection is added to the pipeline with the help of acoustic features. A BiLSTM feature extractor is used to get complex acoustic representation from the baseline MFCC features for each syllable-like region. This acoustic representation is concatenated with the prosody features and used in the proposed system for detecting multiple speech disfluencies. Experiments are conducted for four types of disfluencies in the UCLASS and the IIITH-IED datasets to test the proposed disfluency detection system. Overall, it is found that the proposed system gives a detection accuracy of 88.75% for the disfluencies in the UCLASS dataset, whereas for the IIITH-IED dataset, the accuracy obtained is 91.24%, showing the effectiveness of considering perceptually distinct syllable-like regions as representational units for detecting disfluencies.

Abstract

An Internet of Things (IoT)-based healthcare monitoring system is an amalgamation of smart healthcare devices and applications which connect to the healthcare information system through the internet. It has opened up a world of possibilities in the medical field. Connected smart healthcare devices can collect important healthcare data and provide extra details about the symptoms. That further enables remote care as the patient can consult the appropriate healthcare expert. It generally provides patients more control over their lives and treatment. Moreover, a blockchain-enabled IoT-based healthcare monitoring system (BIoT-HMS) is one step ahead as it can reduce unnecessary hospital visits and the burden on healthcare systems by connecting patients to their healthcare experts and allowing the secure transfer and storage of healthcare data by making use of the blockchain mechanism. Some of the possible applications of BIoT-HMS are “remote health monitoring,” “management of healthcare operations,” “detection and prevention of diseases” and many more. However, IoT-based healthcare monitoring systems have issues related to security breaches and privacy of healthcare data. Therefore, it is essential to design some security protocols for IoT-based healthcare monitoring systems. From time to time researchers propose different protocols to secure the data of IoT-based healthcare monitoring systems. However, most of them are vulnerable to various types of attack like, replay, MiTM, impersonation, secret credentials leakage, unauthorized data update, etc., Therefore, researchers came up with the idea of inclusion of blockchain-enabled security in the IoT-based healthcare monitoring system, which further can be considered as a blockchain-enabled IoT-based healthcare monitoring system (BIoT-HMS). In this chapter, we provide the details of various possible architectures of BIoT-HMS. We also provide the details of various threats and attacks along with the threat model in BIoT-HMS. The security requirements and applications of BIoT-HMS are also discussed. We then provide the summary of various existing security protocols related to BIoT-HMS. The comparison of “security and functionality features” of security protocols related to BIoT-HMS is also provided.

Abstract

We propose a pitch stylization technique in the presence of pitch halving and doubling errors. The technique uses an optimization criterion based on a minimum mean absolute error to make the stylization robust to such pitch estimation errors, particularly under noisy conditions. We obtain segments for the stylization automatically using dynamic programming. Experiments are performed at the frame level and the syllable level. At the frame level, the closeness of stylized pitch is analyzed with the ground truth pitch, which is obtained using a laryngograph signal, considering root mean square error (RMSE) measure. At the syllable level, the effectiveness of perceptual relevant embeddings in the stylized pitch is analyzed by estimating syllabic tones and comparing those with manual tone markings using the Levenshtein distance measure. The proposed approach performs better than a minimum mean squared error criterion based pitch stylization scheme at the frame level and a knowledgebased tone estimation scheme at the syllable level under clean and 20dB, 10dB and 0dB SNR conditions with five noises and four pitch estimation techniques. Among all the combinations of SNR, noise and pitch estimation techniques, the highest absolute RMSE and mean distance improvements are found to be 6.49Hz and 0.23, respectively. Index Terms: Pitch stylization, minimum MAE criterion, dynamic programming based segmentation, noise robustness