Search

The popularity of egocentric cameras and their always-on nature has lead to the abundance of day long first-person videos. The highly redundant nature of these videos and extreme camera-shakes make them difficult to watch from beginning to end. These videos require efficient summarization tools for consumption. However, traditional summarization techniques developed for static surveillance videos or highly curated sports videos and movies are either not suitable or simply do not scale for such hours long videos in the wild. On the other hand, specialized summarization techniques developed for egocentric videos limit their focus to important objects and people. This paper presents a novel unsupervised reinforcement learning framework to summarize egocentric videos both in terms of length and the content. The proposed framework facilitates incorporating various prior preferences such as faces, places, or scene diversity and interactive user choice in terms of including or excluding the particular type of content. This approach can also be adapted to generate summaries of various lengths, making it possible to view even 1-minute summaries of one's entire day. When using the facial saliency-based reward, we show that our approach generates summaries focusing on social interactions, similar to the current state-of-the-art (SOTA). The quantitative comparisons on the benchmark Disney dataset show that our method achieves significant improvement in Relaxed F-Score (RFS) (29.60 compared to 19.21 from SOTA), BLEU score (0.68 compared to 0.67 from SOTA), Average Human Ranking (AHR), and unique events covered. Finally, we show that our technique can be applied to summarize traditional, short, hand-held videos as well, where we improve the SOTA F-score on benchmark SumMe and TVSum datasets from 41.4 to 46.40 and 57.6 to 58.3 respectively. We also provide a Pytorch implementation and a web demo at https://pravin74.github.io/Int-sum/index.html.

Text entry for smartwatches is a useful service for many applications like sending text messages and replying emails. Traditional touchscreen-based approaches are two-handed text entry methods, that could be cumbersome when the user is performing other tasks with one hand. Therefore, we propose AirText, the first one-handed text entry method which achieves accurate and practical handwriting in the air for commercial smartwatches. By analyzing the inertial readings from the smartwatch worn on the wrist, AirText is able to accurately recognize the in-air handwritten characters. However, the wrist movements, which produce the inertial readings, are harmful to the user to focus on the screen. In order to address this challenge, AirText uses a novel cross-modal supervision design to achieve accurate character recognition from the small wrist movements. AirText further includes a novel word recommendation method to speed up the text entry. We implement AirText on five smartwatches and evaluate its performance extensively with eight volunteers and more than 25,000 in-air handwritten characters. Results show that AirText outperforms two baselines methods and achieves comparable text entry speed as two-handed approaches.

The goal of personalized search is to tailor the document ranking list to meet user's individual needs. Previous studies showed users usually look for the information that has been searched before. This is called re-finding behavior which is widely explored in existing personalized search approaches. However, most existing methods for identifying re-finding behavior focus on simple lexical similarities between queries. In this paper, we propose a personalized framework based on hierarchical memory networks (MN) to enhance the identification of the potential re-finding behavior. Specifically, we explore the potential re-finding behaviors of users from two dimensions. (1) Granularity dimension. The framework carries out re-finding identification with external memories from word, sentence, and session levels. (2) Query intent dimension. Query-based re-finding and document-based re-finding are taken into account to cover user's different query intents. To enhance the interaction between different memory slots, we optimize the $READ$ operation of MN with two strategies that utilize the information in memory in a multi-hop way. Endowed with these memory networks, we can enhance user's potential re-finding behaviors and build a fine-grained user model dynamically. Experimental results on two datasets have a significant improvement over baselines, and the optimized $READ$ operation shows better performance.

China has become a workshop for the world, and manufacturing in the country is increasingly moving beyond labor-intensive, low value-added products. As a result, companies in different industries around the world are facing increasing competition. Taiwan's bicycle industry is a good example. Taiwan's A-Team aims to establish standardization to achieve the functions of an industrial platform in the bicycle industry. Taiwan's A-Team forms an innovation ecosystem through the participation of domestic and foreign complementary companies and suppliers. The companies of Taiwan's A-Team focus on high value-added products in the global bicycle industry by competing and cooperating with each other in the innovation ecosystem. A study of Taiwan's A-Team provides a number of insights into how this goal is achieved.

With the continued proliferation of mobile Internet and geo-locating technologies, carpooling as a green transport mode is widely accepted and becoming tremendously popular worldwide. In this paper, we focus on a popular carpooling service called ride hitching, which is typically implemented using a publish/subscribe approach. In a ride hitching service, drivers subscribe ride orders published by riders and continuously receive matching ride orders until one is picked. The current systems (e.g., Didi Hitch) adopt a threshold-based approach to filter out ride orders. That is, a new ride order will be sent to all subscribing drivers whose planned trips can match the ride order within a pre-defined detour threshold. A limitation of this approach is that it is difficult for drivers to specify a reasonable detour threshold in practice. In addressing this problem, we propose a novel top-k subscription query called Top-k Ride Subscription (TkRS) query, which continuously returns the best k ride orders that match drivers' trip plans to them. We propose two efficient algorithms to enable the top-k results maintenance. We also design a novel hybrid index and a two-level buffer to efficiently track the top- $k$ results. Finally, extensive experiments on real-life datasets suggest that our algorithms can achieve desirable performance in practical settings.

Although quite natural for human beings to communicate based on their own personality in daily life, it is rather challenging for neural dialog systems to do the same. This is because the general dialog systems are difficult to generate diverse responses while at the same time maintaining consistent persona information. Existing methods basically focus on merely one of them, ignoring either of them will reduce the quality of dialog. In this work, we propose a two-stage generation framework to promote the persona-consistency and diversity of responses. In the first stage, we propose a persona-guided conditional variational autoencoder (persona-guided CVAE) to generate diverse responses, and the main difference when compared with general CVAE-based model is that we use additional dialog attribute to assist the latent variables to encode the effective information in the response and further use it as a guiding vector for response generation. In the second stage, we employ persona-consistency checking module and the response rewriting module to mask the inconsistent word in the generated response prototype and rewrite it to more consistent. Automatic evaluation results demonstrate that the proposed model is able to generate diverse and persona-consistent responses.

Molecular imaging & biology : MIB 25(1), 3-17 (2023). doi:10.1007/s11307-021-01665-2 special issue: "Special Issue: Optical Surgical Navigation: The Future of Fluorescence Guided Surgery / Issue editors: Summer L. Gibbs & Edward J. Delikatny", Published by Springer Nature Switzerland, Cham

Communication is the basic need of humans to interact with their surroundings. BCI acts as a great tool for providing the means of basic communication to people with locked-in syndrome. For such patients, these basic things matter most and give them a sense of independence. Communication through BCI can be done using various paradigms, P300 speller is one of these paradigms in which the user is instructed to focus their attention on the desired character and able to produce negative and positive slow cortical potential changes which is then interpreted by the BCI system. Although P300 based BCI was introduced over twenty years ago, the past few years have seen a rapid increase in P300 based BCI research. In this paper, we overview the current status of P300 BCI technology and also discussed and compare different approaches using Random Forest, Support Vector Machine (SVM), and Extreme Gradient Boosting (XgBoost) classification algorithm.

The field of information security, in general, has seen shifts a traditional approach to an intelligence system. Moreover, an increasing of researchers to focus on propose intelligence systems and framework based on the forensic case studies because of the limitations of traditional methods such as analysis intensive data manually, intelligence visualization to make the evidence more understandable and intelligence system for store data. However, most of these intelligence systems are still facing different limitations. Furthermore, the primary goal of this work analysis popular intelligence system that was used based on forensic. Moreover, propose new algorithms and hybrid model which it's achieved good results in dif-ferent other fields to develop the forensic systems in the future.

In recent days the entire world moving towards autonomous driving vehicle. For the last decades, the world started more research on Autonomous or Auto-pilot vehicle. It faces lot of challenges to design such a system. In recent, Google and tesla designs an autonomous vehicle in the name of waymo. The main aim of this research work is to provide healthy transportation with high safety and security. This waymo vehicle is now under testing with conditional and unconditional environment. In this paper it is focused on a controller part to take care of the vehicle in critical and non-critical environmental situation. In this perception, this research gives the overview of the various controllers with its merits and demerits. The controller is to imitate like a human driver. Normally the human eye focus on mobile and immobile objects, road sign, pedestrian etc., the controller need to focus the road condition, optimal steering control with less tracking error and cruise control.

Until very recently, the major focus of research in the field of consumer behavior has been on the selection of products, brands and decision choices primarily in the sphere of marketing. The purpose of this paper was to modify a model developed to measure market share to account for the variables that enter into the selection of a political candidate and predict voting behavior.

Estimating the depth of virtual content has proven to be a challenging task in Augmented Reality (AR) applications. Existing studies have shown that the visual system makes use of multiple depth cues to infer the distance of objects, occlusion being one of the most important ones. The ability to generate appropriate occlusions becomes particularly important for AR applications that require the visualization of augmented objects placed below a real surface. Examples of these applications are medical scenarios in which the visualization of anatomical information needs to be observed within the patient's body. In this regard, existing works have proposed several focus and context (F+C) approaches to aid users in visualizing this content using Video See-Through (VST) Head-Mounted Displays (HMDs). However, the implementation of these approaches in Optical See-Through (OST) HMDs remains an open question due to the additive characteristics of the display technology. In this article, we, for the first time, design and conduct a user study that compares depth estimation between VST and OST HMDs using existing in-situ visualization methods. Our results show that these visualizations cannot be directly transferred to OST displays without increasing error in depth perception tasks. To tackle this gap, we perform a structured decomposition of the visual properties of AR F+C methods to find best-performing combinations. We propose the use of chromatic shadows and hatching approaches transferred from computer graphics. In a second study, we perform a factorized analysis of these combinations, showing that varying the shading type and using colored shadows can lead to better depth estimation when using OST HMDs.

Platform owners face multiple challenges such as onboarding and orchestrating app developers as well as providing resources to enable the development of complementary apps. Information systems research considers digital platform governance as key to address these challenges. Thereby, the focus lies on the relationship of a platform owner and app developers. However, while there is evidence how app developers acquire skills through these interactions, there is limited knowledge of how platform owners benefit from interacting with app developers to improve their digital platforms. To address this gap, in this article, we study the emergence of a digital platform for automotive onboard apps within the BMW Group. Our results are grounded in 30 expert interviews that we conducted during a period of two years and are enriched by extensive secondary data. We identify transfer of perspective, transfer of knowledge, and transfer of artifacts as basic mechanisms that enable a platform owner to enhance its digital platform. The inherent improvements of the digital platform facilitate the app development. Our work extends the existing theory on platform emergence and provides insights into the learning process of an inexperienced platform owner. Our findings reveal valuable recommendations for organizations that are struggling to establish digital platforms.

In recent years, we have witnessed the proliferation of mobile devices such as smart phones, tablets, smart watches, etc., the majority of which are based on the Android operating system. However, because these Android-based mobile devices are becoming increasingly popular, they are now the primary target of mobile malware, which could cause both privacy leakage and property loss. To address the rapidly deteriorating security issues caused by mobile malware, various research efforts have been made to develop novel and effective detection mechanisms to identify and battle them. Nevertheless, in order to avoid being caught by these malware detection mechanisms, malware authors are inclined to launch adversarial example attacks by tampering with mobile applications. In this paper, several types of adversarial example attacks are investigated and a feasible approach is proposed to fight against them. First, we look at adversarial example attacks on the Android system and prior solutions that have been proposed to address these attacks. Then, we specifically focus on the data poisoning attack and evasion attack models, which may mutate various application features, such as API calls, permissions and the class label, to produce adversarial examples. Then, we propose and design a malware detection approach which is resistant to the adversarial examples. To observe and investigate how the malware detection system is impacted by the adversarial example attacks, we conduct experiments on some real Android application datasets which are composed of both malware and benign applications. Experimental results clearly indicate that the performance of Android malware detection is severely degraded when facing the adversarial example attacks.

Functional and nonfunctional characteristics of software systems are defined by their architecture. Therefore, research streams such as Internet-of-Things (IoT) or component-based software engineering provide researchers and practitioners with construction guidelines for selected architectural characteristics. Current systems can be categorized in delivering services to the user and being engineered in a smart way. For example, services being provided by IoT-Systems must fulfill users’ goals in a highly dynamic and ad-hoc way. Consequently, this survey aims at answering various research questions regarding the methodical composition of system components and services. Furthermore, new research opportunities are sketched that should be tackled to make the scientific progress available to practitioners. Based on a systematic literature review from a software architecture point of view, in this paper we identify 75 primary studies for domain-specific IoT component composition approaches and architectures. Initial results show that current integration approaches mainly focus on performance evaluation of their integration solutions, which may be too narrow for fulfilling user goals by utilizing of IoT architectures.

Mobile Crowdsensing (MCS) has attained much attention for gathering distributed mobile users to complete large-scale sensing tasks. To ensure the task completion, enough users should be motivated to perform tasks. Thus, many existing works in MCS focus on proposing incentive mechanism in the offline scenario, where the information of all users is available to the platform. However, we argue that the actual MCS is usually an online scenario, where the platform does not know the user's information until they establish connections with the platform. Meanwhile, users connect to the platform randomly and will cut off the connection at any time. Hence, when accessed by a user, the platform needs to make an irrevocable decision instantly about whether to select the user or not, and decides a remuneration for the user without knowing future information. In this paper, we first propose a reverse-auction framework to model the interaction between the platform and users. Then, we present an online truthful incentive mechanism (OTIM) to motivate users, including online winner selection and remuneration determination strategies. Finally, massive simulations are conducted based on three real traces and the results illustrate that OTIM achieves truthfulness, individual rationality, computational efficiency and an approximately full budget utilization.

The analysis of large-scale multimodal data has become very popular recently. Image captioning, whose goal is to describe the content of image with natural language automatically, is an essential and challenging task in artificial intelligence. Commonly, most existing image caption methods utilize the mixture of Convolutional Neural Network and Recurrent Neural Network framework. These methods either pay attention to global representation at the image level or only focus on the specific concepts, such as regions and objects. To make the most of characteristics about a given image, in this study, we present a novel model named Multilevel Attention Networks and Policy Reinforcement Learning for image caption generation. Specifically, our model is composed of a multilevel attention network module and a policy reinforcement learning module. In the multilevel attention network, the object-attention network aims to capture global and local details about objects, whereas the region-attention network obtains global and local features about regions. After that, a policy reinforcement learning algorithm is adopted to overcome the exposure bias problem in the training phase and solve the loss-evaluation mismatching problem at the caption generation stage. With the attention network and policy algorithm, our model can automatically generate accurate and natural sentences for any particular image. We carry out extensive experiments on the MSCOCO and Flickr30k data sets, demonstrating that our model is superior to other competitive methods.

Fake news detection attracts many researchers' attention due to the negative impacts on the society. Most existing fake news detection approaches mainly focus on semantic analysis of news' contents. However, the detection performance will dramatically decrease when the content of news is short. In this paper, we propose a novel $fake news detection multi-task learning (FDML)$ model based on the following observations: 1) some certain topics have higher percentages of fake news; and 2) some certain news authors have higher intentions to publish fake news. FDML model investigates the impact of topic labels for the fake news and introduce contextual information of news at the same time to boost the detection performance on the short fake news. Specifically, the FDML model consists of representation learning and multi-task learning parts to train the fake news detection task and the news topic classification task, simultaneously. As far as we know, this is the first fake news detection work that integrates the above two tasks. The experiment results show that the FDML model outperforms state-of-the-art methods on real-world fake news dataset.

Ongoing smart contract attack events have seriously impeded the practical application of blockchain. Although lots of researches have been conducted, they mostly focus on off-chain vulnerability detection. However, smart contract cannot be modified once they have been deployed on chain, and thus existing techniques cannot protect those deployed contracts from being attacked. To mitigate this problem, we propose Aroc, a general repairer that can automatically patch vulnerable deployed smart contracts. The core insight of Aroc is to generate a patch contract leveraging static analysis techniques to verify whether transactions obey secure states of the vulnerable contracts, and then abort those deviated transactions in advance. Take the three most serious bug types (i.e., reentrancy, arithmetic bugs, and unchecked low-level checks) as examples, we present how Aroc is able to automatically repairs them on chain. Experimental results show that Aroc can automatically repair 84.95% of the vulnerable contracts with an average correctness ratio of 91.43%. Meanwhile, Aroc introduces acceptable additional overheads to smart contract users and blockchain miners.

As one of most successful industrial realizations of Internet of Things, a smart grid is a smart IoT system that deploys widespread smart meters to capture fine-grained data on residential power usage. It suffers diverse privacy attacks, which seriously increases the risk of violating the privacy of customers. Although some solutions have been proposed to address this privacy issue, most of them mainly rely on a trusted party and focus on the sanitization of metering masurements. However, these solutions are vulnerable to advanced attacks. In this paper, we propose a decentralized mechanism for privacy-preserving computation in smart grid called DDP, which leaverages the differential privacy and extends the data sanitization from the value domain to the time domain. Specifically, we inject Laplace noise to the measurements at the end of each customer in a distributed manner, and then use a random permutation algorithm to shuffle the power measurement sequence, thereby enforcing differential privacy after aggregation and preventing the sensitive power usage mode informaton of the customers from being inferred by other parties. Extensive experiments demonstrate that DDP shows an outstanding performance in terms of privacy from the non-intrusive load monitoring (NILM) attacks and utility by using two different error analysis.

The Internet of Things (IoT) has been growing over the past few years due to its flexibility and ease of use in real-time applications. The IoT’s foremost task is ensuring that there is proper communication between different types of applications and devices, and that the application layer protocols fulfill this necessity. However, as the number of applications grows, it is necessary to modify or enhance the application layer protocols according to specific IoT applications, allowing specific issues to be addressed, such as dynamic adaption to network conditions and interoperability. Recently, several IoT application layer protocols have been enhanced and modified according to application requirements. However, no existing survey articles have focused on these protocols. In this article, we survey traditional and recent advances in IoT application layer protocols, as well as relevant real-time applications and their adapted application layer protocols for improving performance. As changing the nature of protocols for each application is unrealistic, machine learning offers means of making protocols intelligent and able to adapt dynamically. In this context, we focus on providing open challenges to drive IoT application layer protocols in such a direction.

Numerous state-of-the-art recommendation frameworks employ deep neural networks in Collaborative Filtering (CF). In this paper, we propose a cross feature fusion neural network (CFFNN) for the enhancement of CF. Existing studies overlook either user preferences for various item features or the relationship between item features and user features. To solve this problem, we construct a cross feature fusion network to enable the fusion of user features and item features as well as a self-attention network to determine users' preferences for items. Specifically, we design a feature extraction layer with multiple MLP (Multilayer Perceptrons) modules to extract both user features and item features. Then, we introduce a cross feature fusion mechanism for an accurate determination of the relationship between different user-item interactions. The features of users and items are crossly embedded and then fed into a prediction network. The attention mechanism enables the model to focus on more effective features. The effectiveness of CFFNN model is demonstrated through extensive experiments on four real-world datasets. The experimental results indicate that CFFNN significantly outperforms the existing state-of-the-art models, with a relative improvement of 3.0\% to 12.1\% on hit ratio (HR) and normalized discounted cumulative gain (NDCG) compared with the baselines.

In social networks, one of the most significant challenges is how to estimate the tweet popularity. Prior studies focus on leveraging different aspects of just a single tweet, while ignoring the impact of historical tweets. In this paper, we propose to leverage such historical information and rethink the problem of tweet popularity estimation. From historical information, there are two important factors that can be extracted: (1) user reputation feature, which can represent coarse-grained level of tweet popularity; (2) tweet related features, which can represent fine-grained level of tweet popularity. To incorporate these two factors from historical information, we design a novel deep neural architecture, a Bi-layered LSTM for tweet popUlarity Estimation, called DeepBlue. Specifically, we first propose a user-reputation aware mechanism to combine coarse-grained and fine-grained level estimation into a united LSTM model. We also design a content attention mechanism to consider different impacts of historical tweets in terms of content similarity. We then propose a time aware mechanism to address the time interval irregularity issue. Finally, we apply the Poisson regression model to obtain the overall loss for tweet popularity estimation. Extensive experiments demonstrate the superiority of our proposed approach to other state-of-the-arts in terms of MAE and SRC.

Current robotic studies are focused on the performance of specific tasks. However, such tasks cannot be generalized, and some special tasks, such as compliant and precise manipulation, fast and flexible response, and deep collaboration between humans and robots, cannot be realized. Brain-inspired intelligent robots imitate humans and animals, from inner mechanisms to external structures, through an integration of visual cognition, decision making, motion control, and musculoskeletal systems. This kind of robot is more likely to realize the functions that current robots cannot realize and become human friends. With the focus on the development of brain-inspired intelligent robots, this article reviews cutting-edge research in the areas of brain-inspired visual cognition, decision making, musculoskeletal robots, motion control, and their integration. It aims to provide greater insight into brain-inspired intelligent robots and attracts more attention to this field from the global research community.

The Internet of Things (IoT), which describes the equipment of physical objects with sensors, actuators, computing logic, and connectivity, has attracted much attention. Although many facets of the IoT have already been explored, existing works either treat smart things as black box or focus on their technical characteristics. From an engineering management perspective, however, also a profound understanding of nontechnical smart thing characteristics is key. Hence, in this article, we develop and evaluate a corresponding multilayer taxonomy based on the latest IoT literature and a deliberately broad sample of 200 smart things, which covers the diversity of smart things available on the market. Based on 11 dimensions, the taxonomy enables classifying smart things according to the layers of established IoT architectures. Based on our sample, we infer five clusters, each covering a typical combination of nontechnical smart thing characteristics occurring in practice. These results extend our understanding of the IoT by structuring nontechnical characteristics of smart things and by abstracting the diversity of smart things into artefacts with manageable complexity. Our results inspire future research on the adoption, affordances, and design of smart things. Moreover, engineering managers can use our results in early phases of product development and process reengineering projects.

Abstract. A number of authors consider that exploring the interconnections between social representations and emotions is essential. However, both empirical and theoretical contributions have focused on specific aspects of these concepts and thus offer a narrow view of their articulation. Moreover, these are published in different languages, making it difficult to provide an overview of the current knowledge on the subject. Consequently, this article adopts a broader approach through a literature review articulating social representations and emotions. This is based on a search of various databases, conducted between March and April 2020 and using the terms “social representation” and “emotion” (or affect, mood, or feeling) in their singular and plural forms, both in French and in English. As a result, 41 references explicitly mentioned both terms and were published in English, French, Portuguese, and Spanish were collected. This brought to light two lines of inquiry that structure this field of research: the first focuses on the role of emotions in the emergence, dynamics, and functioning of social representations, while the second explores how social representations determine emotions or emotional processes. These perspectives will be discussed from both a theoretical and methodological standpoint with the aim of highlighting new avenues for research.

The Next Generation NCLEX® requires higher levels of understanding for new registered nurses to practice safely. Team-based learning (TBL) offers a rigorous but pragmatic approach to achieve that aim. TBL employs collaborative strategies for structured problem-solving, a key focus of contemporary nurse educators. In this prospective study, a faculty team at a second-degree, accelerated baccalaureate nursing program within the southeast United States evaluated student perspectives of TBL. Overall findings revealed positive student experiences (n = 30, with three students on an alternate plan of study) in all aspects of the method.

COVID-19 pandemic has a catastrophic consequence globally since its first case was detected in December 2019, with an aggressive spread. Currently an exponential growth is expected. If not diagnosed at the proper time, COVID-19 may lead to death of the infected individuals. Thus, continuous screening, early diagnosis and prompt actions are crucial to control the spread and reduce the mortality. In this paper we focus on developing a Medical Diagnosis Humanoid (MDH) which is a cost effective, safety critical mobile robotic system that provides a complete diagnostic test to check whether an individual is infected by Covid-19 or not. This paper highlights the development of a system based on Artificial Intelligence for Medical Science, where humanoids can navigate through desired destinations, diagnose an individual for Covid-19 through various parameters and make a survey of a locality for the same. The humanoid uses the concept of real time data sensing and processing through machine learning produced by various sensors used in the context.

Bus priority signal control can reduce bus delay at intersections and improve bus operation efficiency. The existing research focus mainly on bus priority control methods at isolated intersections, as well as urban arterial corridors. Rarely existing works consider a network-level bus priority control. Treating regional-wide intersections can be challenging, given that more traffic directions and large multi-modal traffic volume should be considered. The conventional transit signal priority (TSP) research focus on the delay of buses and social vehicles and neglect the delay of pedestrians. To fill these gaps, this paper proposes a regional coordinated bus priority signal control (RCBPSC) method, which is a network-level bus priority control method considering pedestrian and passenger delays. This method is divided into two stages. The first stage is the regional coordinated signal control to obtain the basic signal timing schemes. The second stage is the bus priority signal control. At this stage, the timing schemes at each intersection will be adjusted according to the bus arrival time and the delays. In order to verify the effectiveness of this method, we choose four intersections in Chengdu to study. The results show that the total delay of the proposed method at the first stage (control case 1) can be reduced by 602s (2.3%) and 606s (3.7%) comparing with the conventional timing method in the peak and non-peak period. At the second stage, the proposed method can reduce more pedestrian delay than the conventional TSP method in both scenario 1 and scenario 2.

Card fraud is an important issue and incurs a considerable cost for both cardholders and issuing banks. Contemporary methods apply machine learning-based approaches to detect fraudulent behavior from transaction records. But manually generating features needs domain knowledge and may lay behind the modus operandi of fraud, which means we need to automatically focus on the most relevant fraudulent behavior patterns in the online detection system. Therefore, in this work, we propose a spatial-temporal attention-based graph network (STAGN) for credit card fraud detection. In particular, we learn the temporal and location-based transaction graph features by a graph neural network first. Afterwards, we employ the spatial-temporal attention on top of learned tensor representations, which are then fed into a 3D convolution network. The attentional weights are jointly learned in an end-to-end manner with 3D convolution and detection networks. After that, we conduct extensive experiments on the real-word card transaction dataset. The result shows that STAGN performs better than other state-of-the-art baselines in both AUC and precision-recall curves. Moreover, we conduct empirical studies with domain experts on the proposed method for fraud detection and knowledge discovery; the result demonstrates its superiority in detecting suspicious transactions, mining spatial and temporal fraud hotspots, and uncover fraud patterns. The effectiveness of the proposed method in other user behavior-based tasks is also demonstrated. Finally, in order to tackle the challenges of big data, we integrate our proposed STAGN into the fraud detection system as the predictive model and present the implementation detail of each module in the system.

3-D printing is an additive manufacturing process, which enables products to be custom designed. Obtaining the evolution trend and identifying the potential RD model acquisition, extrusion devices, rotary printing, and denture are the key topics of technological evolution that are difficult to overcome; laser focusing, print head, color printing, recyclable, feeding, control panel, and denture will become the focus of R&D in the near future. Finally, a comparison and experiments are given to demonstrate the plausibility of our method.

Accurate climate predictions help policymakers mitigate the negative effects of climate change and prioritize environmental issues based on scientific evidence. These predictions rely heavily on the outputs of GCMs (General Circulation Models), but the large number of GCMs and their different outputs in each region confuses researchers in their selection. In this paper, we analyzed the performance of a CMIP6 (Climate Model Intercomparison Project Phase 6) multi-model ensemble for precipitation data over Northern Europe. We first evaluated the overall performance of 12 CMIP6 models from GCMs in thirty years of 1985-2014. In addition, future projections were analyzed between 2071 and 2100 using SSP1-2.6 and SSP5-8.5 (Shared Socioeconomic Pathways). Then, simulations were statistically improved using an ensemble method to correct the systematic error of the CMIP6 models and then the capacity of postprocessed data to reproduce historical trends of climate events was investigated. Finally, the possible spatio-temporal changes of future precipitation data were explored in Tana River Basin. The results of this study show that different CMIP6 models do not have the same accuracy in estimating precipitation in the study area. However, the ensemble method can be effective in increasing the accuracy of the predictions. In addition, this study projected a change in the monthly precipitation data over Tana River Basin by 2.46% and 2.06% from 2071 to 2100 compared to the historical period, based on SSP1-2.6 and SSP5-8.5, respectively.

The current study analyzes the use of click sounds in Peninsular Spanish with a focus on those that occur when speakers are searching for what to say and signaling a particular stance. The data corpus consists of interviews with 18 speakers from Spain who produce a total of 281 clicks. We consider clicks to be a non-lexical discourse marker that conveys information to the listener regarding how an utterance should be interpreted. By applying a discourse-pragmatic approach from both quantitative and qualitative perspectives, we examine contextual and co-textual factors that co-occur with the click and contribute to a multimodal display consisting of pauses, fillers, repetitions, prolongations, gestures and object of search. The quantitative results indicate some statistically significant differences with regard to how clicks interact with the linguistic and extralinguistic environments. Qualitatively, we show evidence supporting the idea that clicks are part of a larger multimodal communicative activity.

Showing material objects by bringing them to the camera or turning the camera toward them are pervasive practices in domestic and recreational video-mediated communication (VMC). We here discuss a set of specific showing practices characteristic of digitally embedded video-mediated settings, which may be called ‘digital showings’. These involve participants’ collaboration to retrieve a digital object so as to ensure a shared perceptual experience on screen of said object. We draw on data from multiparty Google Hangouts On Air (HOAs) to show that while digital and material showings share an overall sequential organization, the former display the emergence of unique collaborative practices that at times become collective performances of computer literacy. We focus on three instances of digital showings: (a) screenshares of pictures – showing an image by sharing one’s screen; (b) screenshares of videos – showing a running video by sharing one’s screen; and (c) link-share showings – showing by sharing the link to a showable content that may be independently retrieved while experienced jointly.

This study explores the phenomenon of multiactivity during recreational video-mediated communication (VMC) through the analysis of competing engagements. From a data corpus of naturally occurring interactions in public Google Hangouts, we focus on instances of competing engagements triggered by the co-presence of unratified participants in broadcasters’ physical environments. As users are immersed in their everyday spaces, interferences from their domestic sphere are common occurrences that break the participatory framework established in the digital sphere. Following a conversation analytic approach, we intend to show that these interferences lead to competing engagements that can be exploited rather than simply dealt with. Drawing on literature on multiactivity, we argue that participants at times organize and coordinate these multiple engagements to add playfulness and advance their interactions. In sum, this study aims to highlight how situated competing streams of action are coordinated and the purpose they may serve in recreational VMC.

This case study explores concepts and methodologies in user interface (UI) and user experience (UX) design with a view to increasing information retention and memorisation through the inclusion of human-centred design principles. It focuses on the participants’ individual context, mental state and abilities. In emergencies, visual perception and situation awareness may be restricted due to the impact of sensory symptoms (panic, tunnel vision or limited motor skills), thus calling for a linear course of action. This applied research project, ‘Floodscape’, is a mobile application designed to educate its user about possible inundation zones resulting from a tsunami. Ongoing user engagement through interactive simulation is the prime focus of the initial (dormant) state of the app. In case of an actual tsunami the app registers the event and adapts its UI accordingly. Crucial life-saving wayfinding information will then be displayed in a contextual manner considering contrast, typography, limited user attention and ease of use.

Code review is a powerful technique to ensure high quality software and spread knowledge of best coding practices between engineers. Unfortunately, code reviewers may have biases about authors of the code they are reviewing, which can lead to inequitable experiences and outcomes. In principle, anonymous author code review can reduce the impact of such biases by withholding an author's identity from a reviewer. In this paper, to understand the engineering effects of using author anonymous code review in a practical setting, we applied the technique to 5217 code reviews performed by 300 software engineers at Google. Our results suggest that during anonymous author code review, reviewers can frequently guess authors identities; that focus is reduced on reviewer-author power dynamics; and that the practice poses a barrier to offline, high-bandwidth conversations. Based on our findings, we recommend that those who choose to implement anonymous author code review should reveal the time zone of the author by default, have a break-the-glass option for revealing author identity, and reveal author identity directly after the review.

An efficient transportation system can substantially benefit our society, but road intersections have always been among the major traffic bottlenecks leading to traffic congestion. Appropriate traffic signal timing adapted to real-time traffic may help mitigate such traffic congestion. However, most existing traffic signal control methods require a huge amount of road information, such as vehicle positions. In this paper, we focus on a particular road intersection and aim to minimize the average waiting time. We propose a traffic signal control (TSC) system based on an end-to-end off-policy deep reinforcement learning (deep RL) agent with background removal residual networks. The agent takes real-time images at the road intersection as input. Upon sufficient training, the agent can perform (near-) optimal traffic signaling based on real-time traffic conditions. We conduct experiments on different intersection scenarios and compare various TSC methods. The experimental results show that our end-to-end deep RL approach can adapt to the dynamic traffic based on the traffic images and outperforms other TSC methods.

In intelligent transportation systems (ITS), the vehicular ad-hoc network (VANET) is an enabling technology that can provide information exchange services among connected and autonomous vehicles (CAVs). Video streaming over VANETs is a potential application to ensure the safety of drivers and passengers and improve infotainment services. However, owing to the dynamic network topology, video transmission in VANETs is very challenging in terms of latency, reliability, and security. Therefore, a comprehensive summary of the state-of-art video streaming over VANETs is surveyed in this work. Firstly, related works and background knowledge are introduced. Then, a systematic survey on resource allocation (RA) scheme for video streaming in VANETs is provided, and some prevailing and feasible optimization tools are elaborated. Furthermore, enabling technologies of video streaming over VANETs are summarized with a special focus on the integration of video communication, caching, and computing. Finally, we give some challenges and future research directions.

Classic inventory theories typically focus on the operational trade-offs to optimize inventory decisions. However, managers of public firms who obtain stock-based incentives may alter inventory operations to influence the stock price. We develop a stylized model, which shows that, in the presence of an interest in the stock price, managers over-install inventory when it can either inflate sales or deflate the reported cost of goods sold even if the market anticipates such actions. We analyze the joint and marginal effects of the stock-based incentives and the cost of using inventory to manage earnings, which may provide useful implications for the detection of inventory distortion and the design of management incentive plans. We then conduct an empirical analysis based on the financial data of U.S. publicly listed retailers and manufacturers. We find positive (negative) correlation between firms’ abnormal excess inventory and the stock-based incentives of their top executives (the inventory manipulation cost). Moreover, the marginal effect of the stock-based incentives on the abnormal excess inventory is the strongest when the inventory manipulation cost is intermediate. Our empirical analysis also shows that this effect becomes statistically weaker after the passage of the Sarbanes–Oxley Act. This is in line with the prediction of our analytical model about the effect of the accuracy of financial reporting. This paper was accepted by Vishal Gaur, operations management.

Cloud computing is gaining popularity among small and medium-sized enterprises. The cost of cloud resources plays a significant role for these companies and this is why cloud resource optimization has become a very important issue. Numerous methods have been proposed to optimize cloud computing resources according to actual demand and to reduce the cost of cloud services. Such approaches mostly focus on a single factor (i.e. compute power) optimization, but this can yield unsatisfactory results in real-world cloud workloads which are multi-factor, dynamic and irregular. This paper presents a novel approach which uses anomaly detection, machine learning and particle swarm optimization to achieve a cost-optimal cloud resource configuration. It is a complete solution which works in a closed loop without the need for external supervision or initialization, builds knowledge about the usage patterns of the system being optimized and filters out anomalous situations on the fly. Our solution can adapt to changes in both system load and the cloud provider's pricing plan. It was tested in Microsoft's cloud environment Azure using data collected from a real-life system. Experiments demonstrate that over a period of 10 months, a cost reduction of 85% was achieved.

In this study, preservice teachers viewed clips from three documentary films that presented multiple experiences of contemporary immigrants and refugees. Our focus in the study was how preservice teachers analyzed the three films. Specifically, we examined how elementary, middle grades, and secondary preservice teachers analyzed, both from a cognitive and affective stance, clips of documentary films about the difficult topic of contemporary immigration.

The aim of this article is to describe one aspect of an on-line writing tool designed to help students and researchers with scientific writing: the use of the students’ and researchers’ initial drafts and the corrected versions in order to highlight errors and focus on the corrections and modifications. An example of a letter is given and we comment upon the typical errors and the corrections. It is hypothesized that feedback given on such errors raises learners’ awareness and leads to improved drafts. L’objectif de cet article est de décrire un aspect d’un outil d’aide à la rédaction conçu pour assister étudiants et chercheurs dans la rédaction scientifique : l’utilisation des premiers jets des étudiants et chercheurs et les versions corrigées pour attirer l’attention sur les erreurs et les corrections. Nous donnons l’exemple d’une lettre et commentons les erreurs commises et modifications effectuées. Le but est d’attirer l’attention sur des erreurs plus ou moins fréquemment commises et d’aider d’autres apprenants à améliorer leurs propres écrits.

Cyber-threats are continually evolving and growing in numbers and extreme complexities with the increasing connectivity of the Internet of Things (IoT). Existing cyber-defense tools seem not to deter the number of successful cyber-attacks reported worldwide. If defense tools are not seldom, why does the cyber-chase trend favor bad actors? Although cyber-defense tools monitor and try to diffuse intrusion attempts, research shows the required agility speed against evolving threats is way too slow. One of the reasons is that many intrusion detection tools focus on anomaly alerts’ accuracy, assuming that pre-observed attacks and subsequent security patches are adequate. Well, that is not the case. In fact, there is a need for techniques that go beyond intrusion accuracy against specific vulnerabilities to the prediction of cyber-defense performance for improved proactivity. This paper proposes a combination of cyber-attack projection and cyber-defense agility estimation to dynamically but reliably augur intrusion detection performance. Since cyber-security is buffeted with many unknown parameters and rapidly changing trends, we apply a machine learning (ML) based hidden markov model (HMM) to predict intrusion detection agility. HMM is best known for robust prediction of temporal relationships mid noise and training brevity corroborating our high prediction accuracy on three major open-source network intrusion detection systems, namely Zeek, OSSEC, and Suricata. Specifically, we present a novel approach for combined projection, prediction, and cyber-visualization to enable precise agility analysis of cyber defense. We also evaluate the performance of the developed approach using numerical results.

Social Internet of Things (SIoT) incorporates social relationship into Internet of Things, and compositive relationship between persons, devices and persons to devices is utilized for providing better services. This paper proposes a novel type of search, namely top-k social spatial keyword search (SSKS) in SIoT networks to discover relevant users or data objects according to social, spatial and textual preferences. Existing works mainly focus on two of these preferences at the same time, and efficiently processing top-k SSKS remains challenging. To this end, we propose two algorithms to evaluate top-k SSKS in SIoT networks. The first algorithm is a forward search based algorithm, which spreads the search from the vertex of the querying user. An effective pruning strategy is established by recognizing an early termination condition according to the threefold preference. The forward search based algorithm is efficient when textual objects are dense. The second algorithm is based on index searching. We present an index namely 2HL-GIL to support spatial and textual pruning while providing fast computation of social distances in the SIoT. Then an index-based search algorithm is proposed for top-k SSKS, and it is efficient especially when textual objects are sparse. Our proposed algorithms are evaluated over two real-life social networks attached with synthetic locations and textual data. Evaluation results illustrate the effectiveness and efficiency of our proposed forward search based algorithm and index-based search algorithm.

Soft gripping provides the potential for high performance in challenging tasks through morphological computing; however, design explorations are limited by a combination of a difficulty in generating useful models and use of laborious fabrication techniques. We focus on a class of grippers based on granular jamming that are particularly difficult to model and introduce a "one shot" technique that exploits multimaterial three-dimensional (3D) printing to create entire grippers, including membrane and grains, in a single print run. This technique fully supports the de facto physical generate-and-test methodology used for this class of grippers, as entire design iterations can be fitted onto a single print bed and fabricated from Computer-Aided Design (CAD) files in a matter of hours. Initial results demonstrate the approach by rapidly prototyping in materio solutions for two challenging problems in unconventional design spaces; a twisting gripper that uses programmed deformations to reliably pick a coin, and a multifunctional legged robot paw that offers the ability for compliant locomotion over rough terrains, as well as being able to pick objects in cluttered natural environments. The technique also allows us to easily characterize the design space of multimaterial printed jamming grippers and provide some useful design rules. The simplicity of our technique encourages and facilitates creativity and innovation. As such, we see our approach as an enabling tool to make informed principled forays into unconventional design spaces and support the creation of a new breed of novel soft actuators.

Recent evidence from well-controlled efficacy studies suggests that diffusing treatment focus across multiple concerns is associated with poorer clinical outcomes. However, research regarding treatment focus diffusion (TFD) in public mental health care (PMHC) settings, broadly or in implemented evidence-based treatments (EBT), is scarce, despite therapists in such settings often reporting more complex cases. Using multilevel modeling, this study examined TFD differences between two in-home PMHC services: (a) Multisystemic Therapy (MST; n = 911 youths, 109 therapists), an implemented EBT, and (b) a less structured service more characteristic of treatment as usual (n = 2362 youth, 457 therapists). The relationship between TFD and monthly therapeutic progress within and across these two service formats was also examined. Treatment focus diffusion occurred less in the implemented EBT. Overall, receiving services through the less structured service format and more diffused treatment focus predicted less and slower progress over the course of treatment. The relationship between TFD and less clinical progress was stronger in the MST format. These findings held when accounting for indicators of case complexity including initial level of impairment and number of diagnoses. EBTs appear to maintain a narrower treatment focus even when implemented in a public mental health system. However, even in EBTs, TFD predicts poorer clinical progress. Maintaining a narrow treatment focus, even in complex cases typical of PMHC, might improve clinical outcomes.