Abstract

This paper presents the application of computer vision and machine learning to autonomous approach and landing and taxiing for an air vehicle. Recently, there has been growing interest in developing unmanned aircraft systems (UAS). We present a system and method that uses pattern recognition which aids the landing of a UAS and enhances the human-crewed air vehicle landing. Auto-landing systems based on the Instrument Landing System (ILS) have already proven their importance through decades. The auto-land systems work in conjunction with a radio altimeter, ILS, MLS, or GNSS. Closer to the runway, both under VFR and IFR, pilots are expected to rely on visual references for landing. Modern systems like HUD or CVS allow a trained pilot to manually fly the aircraft using guidance cues from the flight guidance system. Notwithstanding the type of landing and instruments used, typically, Pilots are expected to have the runway threshold markings, aiming point, displacement arrows, and touch down markings/lights insight before Minimum Decision Altitude (MDA). Imaging sensors are the essential standard equipment in crewed and crewless aerial vehicles that are widely used during the landing maneuver. In this method, a dataset of visual objects from satellite images is subjected to pattern recognition training. This trained system learns and

Abstract

We, the people’ is the most popular phrase from the constitutions. In spite of the fact that the number of countries including preamble as part of their constitution has been on the rise, preambles have received scant attention in academia. The importance of preambles has been established in multiple studies yet preambles have been looked at in isolation from socio-economic-environmental contexts. Our article attempts to present a unique insight by correlating preambles with the socio-economicenvironmental and infrastructural context within which they exist. It explores whether these correlations exist and if they do with which features and to what extent and the possibility of a causal link. We pursue a statistical study between various indicators that reflect the growth of a country and the presence or absence of various elements in preambles across the world. Our study finds that correlations exist between the economic-social-environmental and infrastructural context of a nation-state and different elements in their preambles. Our study rigorously engages with patterns in development indicators across years to provide correlational insights into the role of preambles not just as a dormant reference but as active fragments of the socio-political-economic reality of a nation-state. We hope our article establishes grounds for a further study of the manner in which preambles and the nonpolitical aspects of a nation-state can engage with each other.

Abstract

Individual device loads and energy consumption feedback is one of the important approaches for pursuing users to save energy in residences. This can help in identifying faulty devices and wasted energy by devices when left On unused. The main challenge is to identity and estimate the energy consumption of individual devices without intrusive sensors on each device. Non-intrusive load monitoring (NILM) or energy disaggregation, is a blind source separation problem which requires a system to estimate the electricity usage of individual appliances from the aggregated household energy consumption. In this paper, we propose a novel deep neural network-based approach for performing load disaggregation on low frequency power data obtained from residential households. We combine a series of one-dimensional Convolutional Neural Networks and Long Short Term Memory (1D CNN-LSTM) to extract features that can identify active appliances and retrieve their power consumption given the aggregated household power value. We used CNNs to extract features from main readings in a given time frame and then used those features to classify if a given appliance is active at that time period or not. Following that, the extracted features are used to model a generation problem using LSTM. We train the LSTM to generate the disaggregated energy consumption of a particular appliance. Our neural network is capable of generating detailed feedback of demandside, providing vital insights to the end-user about their electricity consumption. The algorithm was designed for low power offline devices such as ESP32. Empirical calculations show that our model outperforms the state-of-the-art on the Reference Energy Disaggregation Dataset (REDD)

Abstract

The radiant systems consume less energy and provide better thermal comfort as compared to the conventional system, but the main drawback of radiant technology is inability to cater the latent load and condensation. This problem has engaged researchers to push their emphasis on Personalized Conditioning System (PCS). It forms a micro-climate region near the occupant. This study is aimed at PCS combined with a radiant conditioning system, which evaluates the performance of the PCS and compares it with different radiant cooling systems. A radiant cubicle was used to investigate the performance of the PCS for both heating & cooling modes. For heating mode, the Standard Effective Temperature (SET) was calculated with the help of thermal comfort surveys which were in a range of 23.4°C to 27.3°C. For cooling mode, four different cases compared the performance of the system which are: Conventional Air Conditioning System (CACS), Radiant Cooled Ceiling System (RCCS), Personalized Radiant Conditioning System (PRCS), and both PRCS-RCCS coupled. It was observed that PRCS alone reaches the thermal comfort criteria with low energy consumption. The energy-saving of RCCS-PRCS was achieved 38% when compared with CACS. It can be concluded that PRCS is a new step in the field of thermal comfort.

Abstract

Standard accuracy metrics have shown that Math Word Problem (MWP) solvers have achieved high performance on benchmark datasets. However, the extent to which existing MWP solvers truly understand language and its relation with numbers is still unclear. In this paper, we generate adversarial attacks to evaluate the robustness of state-of-the-art MWP solvers. We propose two methods Question Reordering and Sentence Paraphrasing to generate adversarial attacks. We conduct experiments across three neural MWP solvers over two benchmark datasets. On average, our attack method is able to reduce the accuracy of MWP solvers by over 40 percentage points on these datasets. Our results demonstrate that existing MWP solvers are sensitive to linguistic variations in the problem text. We verify the validity and quality of generated adversarial examples through human evaluation.

Abstract

Existing black box search methods have achieved high success rate in generating adversarial attacks against NLP models. However, such search methods are inefficient as they do not consider the amount of queries required to generate adversarial attacks. Also, prior attacks do not maintain a consistent search space while comparing different search methods. In this paper, we propose a query efficient attack strategy to generate plausible adversarial examples on text classification and entailment tasks. Our attack jointly leverages attention mechanism and locality sensitive hashing (LSH) to reduce the query count. We demonstrate the efficacy of our approach by comparing our attack with four baselines across three different search spaces. Further, we benchmark our results across the same search space used in prior attacks. In comparison to attacks proposed, on an average, we are able to reduce the query count by 75% across all datasets and target models. We also demonstrate that our attack achieves a higher success rate when compared to prior attacks in a limited query setting.

Abstract

We study an important and challenging task of attacking natural language processing models in a hard label black box setting. We propose a decision-based attack strategy that crafts high quality adversarial examples on text classification and entailment tasks. Our proposed attack strategy leverages population-based optimization algorithm to craft plausible and semantically similar adversarial examples by observing only the top label predicted by the target model. At each iteration, the optimization procedure allow word replacements that maximizes the overall semantic similarity between the original and the adversarial text. Further, our approach does not rely on using substitute models or any kind of training data. We demonstrate the efficacy of our proposed approach through extensive experimentation and ablation studies on five state-of-the-art target models across seven benchmark datasets. In comparison to attacks proposed in prior literature, we are able to achieve a higher success rate with lower word perturbation percentage that too in a highly restricted setting.

Abstract

The growing need for localization has created an array of alternative approaches to GNSS, based on Wi-Fi, Bluetooth, Ultra-Wideband, etc. Long Range Wide Area Network (LoRaWAN) is one such technology that has garnered tremendous attention due to its low power and long-range capabilities. Many attempts to achieve localization using LoRaWAN have been made till now, based on a variety of techniques such as Angle of Arrival (AoA), Time Difference of Arrival (TDoA), Received Signal Strength Index (RSSI). In this paper, we present a novel, standalone localization approach by developing a collaborative, TDoA-based methodology using LoRaWAN. The server determines the target node location by means of TDoA measurements from the target node to the gateways. The introduction of an additional stationary node allows the synchronization of the gateways without utilizing GNSS, either inbuilt or external. The cooperation between target node, synchronization node and server, is the innovative feature which makes this approach attractive for GNSS-free localization. Further, we explore the effects of timing resolution, time-on-air, and duty cycle constraints on the localization error. Finally, the distribution of error in a triangle of gateways situated approximately 8.6 kilometers apart is simulated in ideal Line of Sight (LoS) conditions, showing the maximum error to be around 23 meters

Abstract

Methods and apparatus for modulating light using a tunable light modulation device . The tunable light modulation devices comprises an elastomer structure including at least one elastomer layer , a compliant electrode network of con ducting fibers arranged on a first surface of the at least one elastomer layer , a patterned electric conductor arranged on a second surface of the at least one elastomer layer opposite the first surface . The patterned electric conductor includes a plurality of individually - addressable sections , and the com pliant electrode network is configured to compress the at least one elastomer layer in the presence of an electric field between the compliant electrode network and one or more of the individually - addressable sections of the patterned elec tric conductor to produce a voltage - dependent roughening of the at least one elastomer layer .

Abstract

Muscle weakening is a common consequence of stroke and can result in a reduction in physical activity of the affected body part. Therapy includes a range of physical exercises that will help the patients restore and build physical strength, endurance, flexibility, balance, and stability. In order to analyze and recognize the activity and movement of hands while performing these exercises, we have developed a 4 × 4 flexible pressure sensor matrix to quantize the performance and progress of a patient undergoing physiotherapy. We have also developed an artificial intelligence (AI) based algorithm to determine the accuracy of positioning by the patients. Experimental results demonstrate that the algorithm gives a mean error of 0.103 cm in detecting the position of load, compared to a mean error of 0.704 cm using mathematical analysis. With this system, a patient can be asked to move a weight to a particular location (as part of regular physiotherapy) and the pressure sensor matrix can be used to calculate error in positioning along with the time taken to complete the task. Advantages of the proposed pressure sensor matrix are cost effectiveness, facile fabrication, high sensitivity, robustness and flexibility