Abstract

Surface normal estimation is an essential component of several computer and robot vision pipelines. While this problem has been extensively studied, most approaches are geared towards indoor scenes and often rely on multiple modalities (depth, multiple views) for accurate estimation of normal maps. Outdoor scenes pose a greater challenge as they exhibit significant lighting variation, often contain occluders, and structures like building facades are often ridden with numerous windows and protrusions. Conventional supervised learning schemes excel in indoor scenes, but do not exhibit competitive performance when trained and deployed in outdoor environments. Furthermore, they involve complex network architectures and require many more trainable parameters. To tackle these challenges, we present an adversarial learning scheme that regularizes the output normal maps from a neural network to appear more realistic, by using a small number of precisely annotated examples. Our method presents a lightweight and simpler architecture, while improving performance by at least 1.5x across most metrics. We evaluate our approaches against the state-of-the-art on normal map estimation, on a synthetic and a real outdoor dataset, and observe significant performance enhancements.

Abstract

Explainable AI aims to build systems that not only give high performance but also are able to provide insights that drive the decision making. However, deriving this explanation is often dependent on fully annotated (class label and local annotation) data, which are not readily available in the medical domain. Approach: This paper addresses the above-mentioned aspects and presents an innovative approach to classifying a lung nodule in a CT volume as malignant or benign, and generating a morphologically meaningful explanation for the decision in the form of attributes such as nodule margin, sphericity, and spiculation. A deep learning architecture that is trained using a multi-phase training regime is proposed. The nodule class label (benign/malignant) is learned with full supervision and is guided by semantic attributes that are learned in a weakly supervised manner. Results: Results of an extensive evaluation of the proposed system on the LIDC-IDRI dataset show good performance compared with state-of-the-art, fully supervised methods. The proposed model is able to label nodules (after full supervision) with an accuracy of 89.1% and an area under curve of 0.91 and to provide eight attributes scores as an explanation, which is learned from a much smaller training set. The proposed system's potential to be integrated with a sub-optimal nodule detection system was also tested, and our system handled 95% of false positive or random regions in the input well by labeling them as benign, which underscores its robustness. Conclusions: The proposed approach offers a way to address computer-aided diagnosis system design under the constraint of sparse availability of fully annotated images.

Abstract

Skin is one of the very important and largest organs of the human body that helps in regulating the body temperature and is responsible for sensations such as feel, touch, hot and cold. These days, skin problems are very common in day-to-day life. There may be many reasons for skin diseases: unbalanced and impure diet, several types of pollutions, or maybe family heredity. However, if skin disease after a long treatment does not show any sign of improvement or the skin cells grow abnormally, this may lead to skin cancer. There are many forms of skin cancer. For early and timely diagnosis of skin cancer, an efficient technique is required at utmost importance. Many people across the globe lost their lives due to the late diagnosis. Therefore, a technique that is cost-effective, quicker, and easily accessible needs a higher demand. These days for the classification of images, machine learning, and deep learning techniques proved to be the most efficient approach. In this paper, the dataset of several images of a benign and malignant tumor was taken and pre-processed. Once all the images were pre-processed, they are ready to fed in several CNN models. These models extract the features and pass the images to several machine learning classifiers for the classification of moles as benign or malignant. The results verify by using the classification approach it becomes very much easy for the dermatologist to easily detect the lesions and provide the appropriate treatment to the patient to save the life.

Abstract

The newly detected virus also called coronavirus spreads the disease Covid19. World Health Organization (WHO) confirmed this virus as a worldwide pandemic as it has infected millions of people and has taken away many lives across the globe. An infection caused by Covid19 disease majorly destroys the respiratory tract of human beings that ends with multiple organ failures or death in the worst case. In the present work, chest radiographs were provided as input to various deep learning CNN architectures for the purpose of feature extraction. After extracting the features, the images were provided as the input to various machine learning classifiers that classify the chest radiographs as Covid-19 positive, pneumonia infection, or healthy scans.

Abstract

We develop a theory of linear witnesses for detecting non-Markovianity, based on the geometric structure of the set of Choi states for all Markovian evolutions having Lindblad-type generators. We show that the set of all such Markovian Choi states form a convex and compact set under the small time interval approximation. Invoking geometric Hahn–Banach theorem, we construct linear witnesses to separate a given non-Markovian Choi state from the set of Markovian Choi states. We present examples of such witnesses for dephasing channel and Pauli channel in case of qubits. Furthermore, we have devised another method of detection NM of various qubit channels, by using projective measurements in the Bell basis. This can be done without the knowledge of what specific kind of channel we are dealing with. This gives us a huge operational advantage for NM detection. We further investigate the geometric structure of the Markovian Choi states to find that they do not form a polytope. This presents a platform to consider nonlinear improvement of non-Markovianity witnesses.

Abstract

Radars with mmWave frequency modulated continuous wave (FMCW) technology accu- rately estimate the range and velocity of targets in their field of view (FoV). The targeted angle of arrival (AoA) estimation can be improved by increasing receiving antennas or by using multiple- input multiple-output (MIMO). However, obtaining target features such as target type remains challenging. In this paper, we present a novel target classification method based on machine learning and features extracted from a range fast Fourier transform (FFT) profile by using mmWave FMCW Radars operating in the frequency range of 77–81 GHz. The measurements are carried out in a variety of realistic situations, including pedestrian, automotive, and unmanned aerial vehicle (UAV) (also known as drone). Peak, width, area, variance, and range are collected from range FFT profile peaks and fed into a machine learning model. In order to evaluate the performance, various light weight classification machine learning models such as logistic regression, Naive Bayes, support vector machine (SVM), and lightweight gradient boosting machine (GBM) are used. We demonstrate our findings by using outdoor measurements and achieve a classification accuracy of 95.6% by using LightGBM. The proposed method will be extremely useful in a wide range of applications, including cost-effective and dependable ground station traffic management and control systems for autonomous operations, and advanced driver-assistance systems (ADAS). The presented classifi- cation technique extends the potential of mmWave FMCW Radar beyond the detection of range, velocity, and AoA to classification. mmWave FMCW Radars will be more robust in computer vision, visual perception, and fully autonomous ground control and traffic management cyber-physical systems as a result of the added new feature.

Abstract

The paper presents a sub-nW bandgap reference (BGR) that exploits the temperature variation of gate-leakage current in thin oxide devices operating in the accumulation region to generate the reference voltage. The incorporation of gateleakage transistors scales down the power consumption of the BGR to pico-watt level without using any large physical resistors or sophisticated techniques, thereby making it suitable for IoT applications. The BGR is designed in TSMC 65nm technology and occupies an area of 0.009mm 2 . Post layout simulation results show nominal and worst-case accuracies of 23ppm/°C and 44ppm/°C respectively in the temperature range of -40°C to 100°C. Without any trimming, an inaccuracy (±3σ) of 3% is observed for the reference voltage, showing its resilience to process variations. It also exhibits a typical line sensitivity of 0.063%/V in a supply range of 1.5V-3.8V and a PSRR of -65dB at DC and 1.8V supply. The power consumption is observed to be 443pW at 1.5V supply and nominal temperature

Abstract

The COVID-19 pandemic has disrupted people's lives driving them to act in fear, anxiety, and anger, leading to worldwide racist events in the physical world and online social networks. Though there are works focusing on Sinophobia during the COVID-19 pandemic, less attention has been given to the recent surge in Islamophobia. A large number of positive cases arising out of the religious Tablighi Jamaat gathering has driven people towards forming anti-Muslim communities around hashtags like #coronajihad, #tablighijamaatvirus on Twitter. In addition to the online spaces, the rise in Islamophobia has also resulted in increased hate crimes in the real world. Hence, an investigation is required to create interventions. To the best of our knowledge, we present the first large-scale quantitative study linking

Abstract

Nasalization of vowels is a phenomenon where the oral and nasal tracts participate simultaneously in the production of speech. Acoustic coupling of the oral and nasal tracts, together with the glottal activity, results in a complex dynamic production system. The extent of coupling determines the degree of nasalization in vowels. Changes in the instantaneous response of the vocal tract system are used to study the effects of co-articulatory load of nasals on vowels. Dominant resonance frequency (DRF) contour is extracted from the instantaneous response of the system to determine the duration of the vowel nasalization. The extent of coupling determines the relative dominance of the oral and nasal resonances during the open and closed phases of a glottal cycle. Larger coupling leads to more decay of the energy of the oral resonances, and hence the vowel spectra exhibit predominantly the nasal resonances characteristics. Comparison with the existing measures show the effectiveness of the proposed measures for determining vowel nasalization. Segments of vowels in the context of nasal consonants from utterances of both male and female speakers of English are used to illustrate different aspects of this study on vowel nasalization.

Abstract

Pattern mining is an important task of data mining and involves the extraction of interesting associations from large transactional databases. Typically, a given transactional database D gets updated due to the addition and deletion of transactions. Consequently, some of the previously discovered patterns may become invalid, while some new patterns may emerge. This has motivated significant research efforts in the area of incremental mining. The goal of incremental mining is to efficiently mine patterns when D gets updated with additions and/or deletions of transactions as opposed to mining all of the patterns from scratch. Incidentally, active research efforts are being made to develop incremental pattern mining algorithms for extracting frequent patterns, sequential patterns and utility patterns. Another important type of pattern is the coverage pattern (CP), which has significant applications in areas such as banner advertising, search engine advertising and visibility mining. However, none of the existing works address the issue of incremental mining for extracting CPs. In this regard, the main contributions of this work are twofold. First, we introduce the problem of incremental mining of CPs. Second, we propose an approach, designated as Comprehensive Coverage Pattern Mining, for efficiently extracting CPs under the incremental paradigm. We have also performed extensive experiments using two real click-stream datasets and one synthetic dataset to demonstrate the overall effectiveness of our proposed approach.