教学课程资源库 更多>>

关键词： Machine learning   Mathematics and computing   Technology   Computer science  

摘要： Deceptive videos and images created using generative AI could sway elections, crash stock markets and ruin reputations. Researchers are developing methods to limit their harm.

关键词： Autism disorder   Mental health   Social media mining   Multi-view learning   Transformer learning  

摘要： The detection of mental disorders through social media has received significant attention. With the growing prevalence of Autism Spectrum Disorder (ASD) and the inherent difficulties in diagnosing adults, researchers have attempted to identify undiagnosed adults. Previous studies have primarily concentrated on analyzing ASD characteristics rather than directly detecting ASD. The current study aims to propose a novel framework to assist in identifying the "lost generation"of ASD adults using their social media posts. Combining traditional and deep learning methods makes it possible to model complex aspects of ASD diagnostic characteristics, which have been relatively overlooked in previous studies. To accomplish this, specific formalizations for users' patterns of interest as a main ASD diagnostic characteristic are proposed first. The latent linguistic and semantic features of ASD users' postings are then modeled using deep and transformer-based language models. Finally, all these different aspects are considered together to train a detection model by employing the multi-view learning approach. The experiments show that the feature of idiosyncratic interests has more discriminative power than limited and repetitive interests. The results also indicate that the early fusion of interest-related features along with deep linguistic features outperforms the other examined feature combinations. Additionally, the proposed 'if - iuf' fusion model demonstrates improved performance in capturing patterns of interests, compared to baselines. These findings suggest the potential application of the proposed framework towards indirectly identifying ASD users on social media, as evidenced by achieving precision and recall rates of 85% and 82% respectively on the used sampled dataset. & COPY;2023 Elsevier B.V. All rights reserved.

关键词： Machine learning   Policy   Computer science   Government  

摘要： Large language models and other artificial-intelligence systems could be excellent at synthesizing scientific evidence for policymakers - but only with appropriate safeguards and humans in the loop. Large language models and other artificial-intelligence systems could be excellent at synthesizing scientific evidence for policymakers - but only with appropriate safeguards and humans in the loop.

关键词： Students  

摘要： This study introduces an integrated curriculum designed to empower underrepresented students by combining environmental literacy, data literacy, and computer science. The framework promotes environmental awareness, data literacy, and civic engagement using a culturally sustaining approach. This integrated curriculum is embedded with resources to support language development, technology skills, and coding skills to accommodate the diverse needs of students. To evaluate the effectiveness of this curriculum, we conducted a pilot study in a 5th-grade special education classroom with multilingual Latinx students. During the pilot, students utilized Scratch, a block-based coding language, to create interactive projects that showcased locally collected data, which they used to communicate environmental challenges and propose solutions to community leaders. This approach allowed students to engage with environmental literacy at a deeper level, harnessing their creativity and community knowledge in the digital learning environment. Moreover, this curriculum equipped students with the skills to critically analyze political and socio-cultural factors impacting environmental sustainability. Students not only gained knowledge within the classroom but also applied their learning to address real environmental issues within their community. The results of the pilot study underscore the efficacy of this integrated approach. © 2023, CC BY.

关键词： intelligent assistive technology   stroke patients   caregivers   technology acceptance   human-centric design  

摘要： ObjectivesThe motor disability due to stroke compromises the autonomy of patients and caregivers. To support autonomy and other personal and social needs, trustworthy, multifunctional, adaptive, and interactive assistive devices represent optimal solutions. To fulfill this aim, an artificial intelligence system named MAIA would aim to interpret users' intentions and translate them into actions performed by assistive devices. Analyzing their perspectives is essential to develop the MAIA system operating in harmony with patients' and caregivers' needs as much as ***-stroke patients and caregivers were interviewed to explore the impact of motor disability on their lives, previous experiences with assistive technologies, opinions, and attitudes about MAIA and their needs. Interview transcripts were analyzed using inductive thematic *** interviews were conducted with 12 post-stroke patients and four caregivers. Three themes emerged: (1) Needs to be satisfied, (2) MAIA technology acceptance, and (3) Perceived trustfulness. Overall, patients are seeking rehabilitative technology, contrary to caregivers needing assistive technology to help them daily. An easy-to-use and ergonomic technology is preferable. However, a few participants trust a system based on artificial *** interactive artificial intelligence technology could help post-stroke patients and their caregivers to restore motor autonomy. The insights from participants to develop the system depends on their motor ability and the role of patients or caregiver. Although technology grows exponentially, more efforts are needed to strengthen people's trust in advanced technology.

摘要： In 1972, ten members of the machine intelligence research community travelled to Lake Como, Italy, for a conference on the ‘social implications of machine intelligence research’. This paper explores their varied and contradictory approaches to this topic. Researchers, including John McCarthy, Donald Michie and Richard Gregory, raised ‘ethical’ questions surrounding their research and actively predicted risks of machine intelligence. At the same time, they delayed any action to mitigate these risks to an uncertain future where technical capabilities were greater. I argue that conference participants’ claims that 1972 was ‘too early’ to speculate on societal impacts of their research were disingenuous, motivated both by threats to funding and by researchers’ own politically informed speculation on the future.

摘要： Interdisciplinarity has over the recent years have gained tremendous importance and has become one of the key ways of doing cutting edge research‡. In this paper we attempt to model the citation flow across three different fields - Physics (PHY), Mathematics (MA) and Computer Science (CS). For instance, is there a specific pattern in which these fields cite one another? We carry out experiments on a dataset comprising more than 1.2 million articles taken from these three fields. We quantify the citation interactions among these three fields through temporal bucket signatures. We present numerical models based on variants of the recently proposed relay-linking framework to explain the citation dynamics across the three disciplines. These models make a modest attempt to unfold the underlying principles of how citation links could have been formed across the three fields over time. Copyright © 2023, The Authors. All rights reserved.

关键词： Computer science   Artificial intelligence   Artificial intelligence applications  

摘要： Severe weather conditions pose a significant challenge for computer vision algorithms in autonomous driving applications, particularly regarding robust-ness. Image rain-removal algorithms have emerged as a potential solution by leveraging the power of neural networks to restore rain-free backgrounds in images. However, existing research overlooks the vulnerability concerns in neural networks, which exposes a potential threat to the intelligent perception of autonomous vehicles in rainy conditions. This paper proposes a universal rain-removal attack (URA) that exploits the vulnerability of image rain-removal algorithms. By generating a non-additive spatial perturbation, URA significantly diminishes scene restoration similarity and image quality. The imperceptible and generic perturbation employed by URA makes it a crucial tool for vulnera-bility detection in image rain-removal algorithms and a potential real-world AI attack method. Experimental results demonstrate that URA can reduce scene repair capability by 39.5% and image generation quality by 26.4%, effectively targeting state-of-the-art rain-removal algorithms.

关键词： Contracts   Servers   Internet of Things   Computer science   Resource management   Streaming media   Device-to-device communication   Augmented reality (AR)   computational caching   contract theory   virtual reality (VR)  

摘要： The proliferation of novel infotainment services, such as virtual reality (VR)-based services, has fundamentally changed the existing mobile networks. These bandwidth-hungry services expanded at a tremendously rapid pace, thus, generating a burden of data traffic in the mobile networks. To cope with this issue, one can use multiaccess edge computing (MEC) to bring the resource to the edge. By doing so, we can release the burden of the core network by taking the communication, computation, and caching resources nearby the end users (UEs). Nevertheless, due to the vast adoption of VR-enabled devices, MEC resources might be insufficient in peak times or dense settings. To overcome these challenges, we propose a system model where the service provider (SP) might rent unmanned area vehicles (UAVs) from UAV SPs (USPs) to serve as micro-base stations (UBSs) that expand the service area and improve the spectrum efficiency. In which, UAV can precached certain sets of VR-based contents and serve UEs via air-to-ground (A2G) communication. Furthermore, future intelligent devices are capable of 5G and B5G communication interfaces, and thus, they can communicate with UAVs via A2G links. By doing so, we can significantly reduce a considerable amount of data traffic in mobile networks. In order to successfully enable such kinds of services, an attractive incentive mechanism is required. Therefore, we propose a contract theory-based incentive mechanism for UAV-assisted MEC in VR-based infotainment services, in which the MEC offers an amount reward to a UAV for serving as a UBS in a specific location for certain time slots. We then derive an optimal contract-based scheme with individual rationality and incentive compatibility conditions. The numerical findings show that our proposed approach outperforms the linear pricing (LP) technique and is close to the optimal solution in terms of social welfare. Additionally, our proposed scheme significantly enhanced the fairness of utility for

摘要： Forest degradation is a serious environmental issue that has significant implications for ecological stability, biodiversity, and human well-being. Identifying the extent and severity of forest degradation is crucial for effective management and conservation of forest ecosystems. The objective of this study was to assess the ecological vulnerability of the forest in the Dadabad region using spatial analysis and landscape metrics. The land cover map of the area was divided into 13 sub-basins to quantify landscape metrics, and the severity of human activities, degradation level, and ecological vulnerability were calculated for each sub-basin. Each sub-basin was evaluated as a single landscape to determine the extent of degradation, and landscape zoning was performed based on the degradation coefficients. The study found that sub-basins 2 and 4 had the highest levels of degradation, while sub-basins 3, 7, 8, 11, and 12 were the least degraded. Over half of the Dadabad region, 37.8% for protection and 32.25% for rehabilitation, was recommended for conservation planning. The research highlights the importance of using spatial analysis of landscape metrics to assist managers and planners in protecting and conserving natural areas.