Abstract

The ability of intelligent agents to play games in human-like fashion is popularly considered a benchmark of progress in Artificial Intelligence. In our work, we introduce the first computational model aimed at Pictionary, the popular word-guessing social game. We first introduce Sketch-QA, a guessing task. Styled after Pictionary, Sketch-QA uses incrementally accumulated sketchstroke sequences as visual data. Sketch-QA involves asking a fixed question (“What object is being drawn?”) and gathering open-ended guess-words from human guessers. We analyze the resulting dataset and present many interesting findings therein. Tomimic Pictionary-style guessing, we propose a deep neural model which generates guess-words in response to temporally evolving human-drawn object sketches. Our model even makes human-like mistakes while guessing, thus amplifying the human mimicry factor.We evaluate our model on the large-scale guess-word dataset generated via Sketch-QA task and compare with various baselines. Wealso conduct a Visual Turing Test to obtain human impressions of the guess-words generated by humans and our model. Experimental results demonstrate the promise of our approach for Pictionary and similarly themed games.

Abstract

As the communications among the vehicles, theRoad-Side Units(RSU)and the Edge Servers(ES)take placevia wireless communication and the Internet, an adversary maytake the opportunity to tamper with the data communicatedamong various entities in an Internet of Vehicles (IoV) envi-ronment. Therefore, it demands secure communication amongthe involved entities in an IoV-based Intelligent TransportationSystem (ITS) deployment. In this work, we design a newblockchain-enabled certificate-based authentication scheme forvehicle accident detection and notification in ITS, called BCAS-VADN. In BCAS-VADN, through the authentication process, eachvehicle can securely notify accident related transactions to itsnearby Cluster Head(CH), if an accident is detected on roadseither by its own or neighbor vehicle(s). TheCHthen securelysends the transactions received from the vehicles to itsRSUand subsequently, these transactions are also received secretlyby theESs. TheESis responsible for preparing partial blockcontaining transactions and Merkle tree root, and a digital signa-ture on those information, and then forwarding to its associatedCloud Server(CS)in the Blockchain Center(BC)for completeblock creation, verification and addition of the block using thedesigned consensus process. Due to blockchain technology usage,it is shown that BCAS-VADN is not only secure against variouspotential attacks, but also maintains transparency, immutabilityand decentralization of the information. Furthermore, a compre-hensive comparative analysis reveals that BCAS-VADN achievesbetter security and more functionality attributes, and has lowcommunication and computational overheads as compared toother competitive authentication schemes in IoV. In addition,the practical demonstration using the blockchain technology hasbeen also provided.

Abstract

Agriculture is a vital area for the sustenance ofmankind engulfing manufacturing, security, traceability, andsustainable resource management. With the resources recedingexpeditiously, it is of utmost significance to innovate techniquesthat help in the subsistence of agriculture. The growth of Internetof Things (IoT) and Blockchain technology as two rapidlyemerging fields can ameliorate the state of food chain today. Thispaper provides a rigorous literature review to inspect the state-of-the-art development of the schemes that provide informationsecurity using blockchain technology. After identifying the corerequirements in smart agriculture, a generalized blockchain-based security architecture has been proposed. A detailed costanalysis has been conducted on the studied schemes. A meticu-lous comparative analysis uncovered the drawbacks in existingresearch. Furthermore, detailed analysis of the literature has alsorevealed the security goals towards which the research has beendirected and helped to identify new avenues for future researchusing artificial intelligence.

Abstract

Recent technological evolution in the Internet ofThings (IoT) age supports better solutions to magnify themanagement of the power quality and reliability concerns, andimposes the measures of a smart grid. In smart grid environment,a smart meter needs to securely access the services from a serviceprovider via insecure channel. However, since the communicationis via public channel, it imposes various security threats byan adversary. To deal to this, in this article we design a newanonymous signature-based authenticated key exchange schemefor IoT-enabled smart grid environment, called AAS-IoTSG.The dynamic smart meter addition phase is also permissiblein AAS-IoTSG after initial deployment. The security of AAS-IoTSG has been tested rigorously using formal security analysisunder the Real-Or-Random (ROR) model which is one of thebroadly-accepted standard random oracle models, formal secu-rity verification under the broadly-used Automated Validationof Internet Security Protocols and Applications (AVISPA) tooland also using informal security analysis. Finally, an exhaustivecomparative study unveils that AAS-IoTSG supports bettersecurity & functionality features and requires less communication& computation overheads as compared to the existing state-of-artauthentication mechanisms in smart grid systems

Abstract

The modern day traffic continues to evolve in termsof scale, autonomy and access to information. Every vehiclegathers information and contributes its decisions to the globalvehicular network every second. With the advent of 5G equippeddigital communication and sophisticated algorithms are in placefor the vehicles to communicate with each other in a closelymonitored, yet decentralized network, there is a need to ensurethat no form of incorrect data be propagated without priorvalidation. There is also a requirement of maintaining cache sincethere is no centralized network where all vehicles report theiractivities and gather information from, at a required speed. Thedistribution of cache is a major hurdle both in terms of validationand propagation. Cache poisoning can occur if a malicious vehicleor a compromised vehicle intentionally or unintentionally putsincorrect data and other vehicles use that data to skew their ownfuture decisions. In this paper, we explore different methodologiesto address and combat the cache poisoning scenarios and suggestan efficient and secure scheme for validation and distribution ofcache using the Directed Acyclic Graph (DAG) based ledger,which is based on Tangle™.

Abstract

The periodic opening and closing of the vibrating vocal foldschanges the production system continuously during the pro-duction of voiced speech. The subglottal and supraglottalcavities have distinct structure and impedance. A couplingand decoupling of these cavities affects effective length of thevocal tract which in turn affects its impedance. This can bestudied based on the shift in the location of dominant reso-nant frequencies (DRFs) of the instantaneous system responseobtained using zero time windowing (ZTW) method. Thechange in the impedance of the vocal tract is reflected in thebandwidth of spectral resonances. Bandwidth values esti-mated using the group delay function at dominant resonancelocations, approximated by the Hilbert envelope of the nu-merator of group delay (HNGD) function. An estimate ofthis change is made by comparing the bandwidths in closedglottal phase of the glottal cycle for the oral and nasal tracts.A study of the relative difference in the bandwidth of vowelsand nasals in speech is attempted to compare the impedanceof the respective tracts. The study examines VC/CV segmentsin English for speakers in the TIMIT database. The resultsshow that the nasal segments exhibit higher bandwidth valuescompared to vowels

Abstract

Residential energy (electricity) use in India is expected to grow four-fold by 2030, yet there is paucity of data that is essential for developing energy policy or programme. This paper undertakes a meta-study of residential energy studies in India to characterise their scope, data collection methods and findings. An in-depth review of literature was undertaken using Google Scholar, Web of Science, Scopus and ScienceDirect to identify relevant journal publications, conference papers and reports. A series of expert workshops were held to identify any data gaps and stakeholders’ needs. The identified studies were characterised using a meta-data framework that included criteria such as climate, dwelling form, income group, methods and study duration. An online searchable platform (REACT) was created to make the identified studies more accessible using the meta-data criteria. Of the 29 studies identified, only 16 were published in peer-reviewed publications (10 in journals and 6 in conferences proceedings). About 11 studies focussed on dwelling-level energy use, while the remaining used econometric data and statistical modelling at a macro-scale. To develop evidence based energy policies, it is vital to gather empirical data on residential energy in different climatic zones. Robust data sharing policies should be implemented to avoid duplication of effort.

Abstract

Personalized Comfort Systems (PCS) have been seen as an effective alternative to provide thermal comfort along with reducing energy consumption. This paper contains the methodology and results of a study conducted in a laboratory environment that aims to evaluate Thermally Activated Furniture (TAF) panels. These panels mounted in front and on the side of a workstation as space partition panels, can provide thermal comfort and have the potential to save energy. The experiments were carried out in a controlled thermal comfort chamber using a thermal mannequin having 22 body segments and TAF. A total of 15 cases were examined against a reference case with an aim to understand the impact of TAF on the change in PMV, Skin Temperature (Tskin) and Heat Flux (U) of 22 individual body segments and change in the energy consumption. The combinations of three Room Air Temperatures (Tair) i.e. 26
C, 28
C and 30
C were tested with a combination of four surface temperature (Tsur) ranging from the difference between Tair and Tsur 2 to 8
C. For the entire study, Relative Humidity (RH) was maintained at 50%. The results indicate a change in PMV by about 0.15 votes towards the cooler side when the difference between Tair and Tsur was D2
C for the three Tair cases. The PMV changed by about 0.5 votes in the case of the D8
C difference between Tair and Tsur. The increase in DT values was found to increase the cooling thermal energy consumption relative to the baseline case without having PCS in operation, whereas the increase in Tair caused a decrease in the cooling thermal energy consumption

Abstract

Rapid urbanization and associated land-use changes in cities cause an increase in the demand for electricity by altering the local climate. The present study aims to examine the variations in total energy and cooling energy demand in a calibrated building energy model, caused by urban heat island formation over Delhi. The study used Sentinel-2A multispectral imagery for land use and land cover (LULC) of mapping of Delhi, and Moderate Resolution Imaging Spectroradiometer (MODIS) imagery for land surface temperature (LST) mapping during March 2018. It was observed that regions with dense built-up areas (i.e., with built-up area greater than 90%) had a higher annual land surface temperature (LST), i.e., 293.5 K and urban heat island intensity (UHII) ranging from 0.9 K–5.9 K. In contrast, lower annual values of LST (290K) and UHII (0.0–0.4 K) were observed in regions with high vegetation cover (53%). Statistical analysis reveals that a negative correlation exists between vegetation and nighttime LST, which is further confirmed by linear regression analysis. Energy simulations were performed on a calibrated building model placed at three different sites, identified on the basis of land use and land cover percentage and annual LST. Simulation results showed that the site located in the central part of Delhi displayed higher annual energy consumption (255.21 MWh/y) compared to the site located in the rural periphery (235.69 MWh/y). For all the three sites, the maximum electricity consumption was observed in the summer season, while the minimum was seen in the winter season. The study indicates that UHI formation leads to increased energy consumption in buildings, and thus UHI mitigation measures hold great potential for energy saving in a large city like Delhi.

Abstract

This study aimed to estimate water quality–based minimum environmental flow (Eflow) of a river under the impact of different plausible scenarios. The water quality model QUAL2K was deployed to simulate levels of dissolved oxygen (DO) and biochemical oxygen demand (BOD) in a river during the dry season. Hypothetical scenarios of pollution were generated by varying BOD in contributing drains, and climate change scenarios were generated by altering air temperature over the study region. DO and BOD levels were simulated under the impact of various scenarios. Corresponding to each scenario, minimum Eflow throughout the river stretch—that is, the headwaters flow (quantity and quality) meeting desirable river water quality standards (as proposed by the Indian Central Pollution Control Board)— was explored. Water quality charts were developed for direct and user-friendly estimation of Eflows. The proposed approach was applied to the Yamuna and Bhadra rivers in India. The results reveal the inefficiency of existing river flow conditions in maintaining permissible water quality standards. Adverse effects of pollution load, upstream diversions, and climate change are highlighted. DOI: 10.1061/(ASCE) HE.1943-5584.0001780. © 2019 American Society of Civil Engineer