Throughout history, maps have been used as a tool to explore cities. They visualize a city's urban fabric through its streets, buildings, and points of interest. Besides purely navigation purposes, street names also reflect a city's culture through its commemorative practices. Therefore, cultural maps that unveil socio-cultural characteristics encoded in street names could potentially raise citizens' historical awareness. But designing effective cultural maps is challenging, not only due to data scarcity but also due to the lack of effective approaches to engage citizens with data exploration. To address these challenges, we collected a dataset of 5,000 streets across the cities of Paris, Vienna, London, and New York, and built their cultural maps grounded on cartographic storytelling techniques. Through data exploration scenarios, we demonstrated how cultural maps engage users and allow them to discover distinct patterns in the ways these cities are gender-biased, celebrate various professions, and embrace foreign cultures.
相關內容
We address the problem of visual storytelling, i.e., generating a story for a given sequence of images. While each sentence of the story should describe a corresponding image, a coherent story also needs to be consistent and relate to both future and past images. To achieve this we develop ordered image attention (OIA). OIA models interactions between the sentence-corresponding image and important regions in other images of the sequence. To highlight the important objects, a message-passing-like algorithm collects representations of those objects in an order-aware manner. To generate the story's sentences, we then highlight important image attention vectors with an Image-Sentence Attention (ISA). Further, to alleviate common linguistic mistakes like repetitiveness, we introduce an adaptive prior. The obtained results improve the METEOR score on the VIST dataset by 1%. In addition, an extensive human study verifies coherency improvements and shows that OIA and ISA generated stories are more focused, shareable, and image-grounded.
With the rapid increase in digital technologies, most fields of study include recognition of human activity and intention recognition, which are essential in smart environments. In this study, we equipped the activity recognition system with the ability to recognize intentions by affecting the pace of movement of individuals in the representation of images. Using this technology in various environments such as elevators and automatic doors will lead to identifying those who intend to pass the automatic door from those who are passing by. This system, if applied in elevators and automatic doors, will save energy and increase efficiency. For this study, data preparation is applied to combine the spatial and temporal features with the help of digital image processing principles. Nevertheless, unlike previous studies, only one AlexNet neural network is used instead of two-stream convolutional neural networks. Our embedded system was implemented with an accuracy of 98.78% on our intention recognition dataset. We also examined our data representation approach on other datasets, including HMDB-51, KTH, and Weizmann, and obtained accuracy of 78.48%, 97.95%, and 100%, respectively. The image recognition and neural network models were simulated and implemented using Xilinx simulators for the Xilinx ZCU102 board. The operating frequency of this embedded system is 333 MHz, and it works in real-time with 120 frames per second (fps).
Amidst the climate crisis, the massive introduction of renewable energy sources has brought tremendous challenges to both the power grid and its surrounding markets. As datacenters have become ever-larger and more powerful, they play an increasingly significant role in the energy arena. With their unique characteristics, datacenters have been proved to be well-suited for regulating the power grid yet currently provide little, if any, such active response. This problem is due to issues such as unsuitability of the market design, high complexity of the currently proposed solutions, as well as the potential risks thereof. This work aims to provide individual datacenters with insights on the feasibility and profitability of directly participating in the energy market. By modelling the power system of datacenters, and by conducting simulations on real-world datacenter traces, we demonstrate the substantial financial incentive for individual datacenters to directly participate in both the day-ahead and the balancing markets. In turn, we suggest a new short-term, direct scheme of market participation for individual datacenters in place of the current long-term, inactive participation. Furthermore, we develop a novel proactive DVFS scheduling algorithm that can both reduce energy consumption and save energy costs during the market participation of datacenters. Also, in developing this scheduler, we propose an innovative combination of machine learning methods and the DVFS technology that can provide the power grid with indirect demand response (DR). Our experimental results strongly support that individual datacenters can and should directly participate in the energy market both to save their energy costs and to curb their energy consumption, whilst providing the power grid with indirect DR.
Depleting lake ice can serve as an indicator for climate change, just like sea level rise or glacial retreat. Several Lake Ice Phenological (LIP) events serve as sentinels to understand the regional and global climate change. Hence, it is useful to monitor long-term lake freezing and thawing patterns. In this paper we report a case study for the Oberengadin region of Switzerland, where there are several small- and medium-sized mountain lakes. We observe the LIP events, such as freeze-up, break-up and ice cover duration, across two decades (2000-2020) from optical satellite images. We analyse time-series of MODIS imagery by estimating spatially resolved maps of lake ice for these Alpine lakes with supervised machine learning (and additionally cross-check with VIIRS data when available). To train the classifier we rely on reference data annotated manually based on webcam images. From the ice maps we derive long-term LIP trends. Since the webcam data is only available for two winters, we also validate our results against the operational MODIS and VIIRS snow products. We find a change in complete freeze duration of -0.76 and -0.89 days per annum for lakes Sils and Silvaplana, respectively. Furthermore, we observe plausible correlations of the LIP trends with climate data measured at nearby meteorological stations. We notice that mean winter air temperature has negative correlation with the freeze duration and break-up events, and positive correlation with the freeze-up events. Additionally, we observe strong negative correlation of sunshine during the winter months with the freeze duration and break-up events.
Robotics and automation have the potential to significantly improve quality of life for people with assistive needs and their carers. Adoption of such technologies at this point in time is far from widespread. This paper presents a novel approach to the design of highly customisable robotic concepts, embracing modularity and a co-design process to increase the involvement of end-users in the development life cycle. We discuss this process within the context of an elderly care use case. Using design methodology and additive manufacturing, we outline how key stakeholders can be involved from initial conception through to integration of the final product within their environments. In future work, we will apply this process to demonstrate the effectiveness of our approach for improving long-term acceptance and trust of robotic technology in care contexts.
It is well-known that there exist rigid frameworks whose physical models can snap between different realizations due to non-destructive elastic deformations of material. We present a method to measure this snapping capability based on the total elastic strain energy density of the framework by using the physical concept of Green-Lagrange strain. As this so-called snappability only depends on the intrinsic framework geometry, it enables a fair comparison of pin-jointed body-bar frameworks, thus it can serve engineers as a criterion within the design process of multistable mechanisms. Moreover, it turns out that the value obtained from this intrinsic pseudometric also gives the distance to the closest shaky configuration in the case of isostatic frameworks. Therefore it is suited for the computation of these singularity-distances for diverse mechanical devices. In more detail we study this problem for parallel manipulators of Stewart-Gough type.
Originating in the Renaissance and burgeoning in the digital era, tablatures are a commonly used music notation system which provides explicit representations of instrument fingerings rather than pitches. GuitarPro has established itself as a widely used tablature format and software enabling musicians to edit and share songs for musical practice, learning, and composition. In this work, we present DadaGP, a new symbolic music dataset comprising 26,181 song scores in the GuitarPro format covering 739 musical genres, along with an accompanying tokenized format well-suited for generative sequence models such as the Transformer. The tokenized format is inspired by event-based MIDI encodings, often used in symbolic music generation models. The dataset is released with an encoder/decoder which converts GuitarPro files to tokens and back. We present results of a use case in which DadaGP is used to train a Transformer-based model to generate new songs in GuitarPro format. We discuss other relevant use cases for the dataset (guitar-bass transcription, music style transfer and artist/genre classification) as well as ethical implications. DadaGP opens up the possibility to train GuitarPro score generators, fine-tune models on custom data, create new styles of music, AI-powered songwriting apps, and human-AI improvisation.
LoRaWAN has garnered tremendous attention owing to the low power consumption of end nodes, long range, high resistance to multipath, low cost, and use of license-free sub-GHz bands. Consequently, LoRaWAN is gradually replacing Wi-Fi and Bluetooth in sundry IoT applications including utility metering, smart cities, and localization. Localization, in particular, has already witnessed a surge of alternatives to Global Navigation Satellite System (GNSS), based on Wi-Fi, Bluetooth, Ultra Wide Band, 5G, etc. in indoor and low power domains due to the poor indoor coverage and high power consumption of GNSS. With the need for localization only shooting up with dense IoT deployments, LoRaWAN is seen as a promising solution in this context. Indeed, many attempts employing various techniques such as Time of Arrival (ToA), Time Difference of Arrival (TDoA), and Received Signal Strength Index (RSSI) have been made to achieve localization using LoRaWAN. However, a significant drawback in this scenario is the lack of extensive data on path loss and signal propagation modeling, particularly in Indian cityscapes. Another demerit is the use of GNSS at some stage primarily for time synchronization of gateways. In this work, we attempt to nullify these two disadvantages of LoRaWAN based localization. The first part of this work presents experimental data of LoRaWAN transmissions inside a typical city building to study signal propagation and path loss. The latter part proposes a standalone GNSS-free localization approach using LoRaWAN that is achieved by applying a collaborative, TDoA-based methodology. An additional stationary node is introduced into the network to allow the synchronization of gateways without GNSS. Finally, the distribution of localization error in a triangle of gateways and the effect of timing resolution, time-on-air, and duty cycle constraints on it are investigated.
Deep learning has penetrated all aspects of our lives and brought us great convenience. However, the process of building a high-quality deep learning system for a specific task is not only time-consuming but also requires lots of resources and relies on human expertise, which hinders the development of deep learning in both industry and academia. To alleviate this problem, a growing number of research projects focus on automated machine learning (AutoML). In this paper, we provide a comprehensive and up-to-date study on the state-of-the-art AutoML. First, we introduce the AutoML techniques in details according to the machine learning pipeline. Then we summarize existing Neural Architecture Search (NAS) research, which is one of the most popular topics in AutoML. We also compare the models generated by NAS algorithms with those human-designed models. Finally, we present several open problems for future research.
Recommender systems rely on large datasets of historical data and entail serious privacy risks. A server offering recommendations as a service to a client might leak more information than necessary regarding its recommendation model and training dataset. At the same time, the disclosure of the client's preferences to the server is also a matter of concern. Providing recommendations while preserving privacy in both senses is a difficult task, which often comes into conflict with the utility of the system in terms of its recommendation-accuracy and efficiency. Widely-purposed cryptographic primitives such as secure multi-party computation and homomorphic encryption offer strong security guarantees, but in conjunction with state-of-the-art recommender systems yield far-from-practical solutions. We precisely define the above notion of security and propose CryptoRec, a novel recommendations-as-a-service protocol, which encompasses a crypto-friendly recommender system. This model possesses two interesting properties: (1) It models user-item interactions in a user-free latent feature space in which it captures personalized user features by an aggregation of item features. This means that a server with a pre-trained model can provide recommendations for a client without having to re-train the model with the client's preferences. Nevertheless, re-training the model still improves accuracy. (2) It only uses addition and multiplication operations, making the model straightforwardly compatible with homomorphic encryption schemes.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191