Fairness in deep learning has attracted tremendous attention recently, as deep learning is increasingly being used in high-stake decision making applications that affect individual lives. We provide ...a review covering recent progresses to tackle algorithmic fairness problems of deep learning from the computational perspective. Specifically, we show that interpretability can serve as a useful ingredient to diagnose the reasons that lead to algorithmic discrimination. We also discuss fairness mitigation approaches categorized according to three stages of deep learning life-cycle, aiming to push forward the area of fairness in deep learning and build genuinely fair and reliable deep learning systems.
In the digital era, the proliferation of new media, facilitated by digital platforms, has positioned new media marketing as a predominant marketing strategy. This study introduces a novel node ...ranking algorithm, leveraging the principles of PageRank, and proposes the UIEM-CMR influence assessment model derived from it. Utilizing data extracted from microblogging platforms and Facebook, this model evaluates the influence of various new media marketing nodes. Subsequently, the ten most influential nodes within the microblogging dataset were analyzed to examine the correlation between node influence in new media marketing and both the thematic distribution of new media marketing and the community distribution of followers. The findings reveal that the MR value of node influence, as calculated by the model, is impacted by the combined effects of AR and BR values, with these values alone identified as pivotal. The influence ranking, when solely based on AR and BR values, tends to diverge significantly from real-world scenarios. Nodes ranked highly under popular new media marketing topics exhibit a substantially greater probability of distribution compared to lower-ranked or randomly chosen nodes. Conversely, the distribution probabilities among influential nodes under less popular (cold) new media marketing topics show no significant disparity. Nodes with high influence ratings tend to attract followers from at least two distinct communities. The UIEM-CMR model, as developed in this study, proves to be an effective tool for assessing the influence of new media marketing strategies.
Display omitted
•The vision of intelligent public information and warning is identified.•Social media contributes to three functions of public information and warning.•Studies on communication ...phenomena and social media informatics are reviewed.•A research roadmap is proposed to address the challenges of achieving the vision.
Social media offers participatory and collaborative structure and collective knowledge building capacity to the public information and warning approaches. Therefore, the author envisions the intelligent public information and warning in disaster based on social media, which has three functions: (1) efficiently and effectively acquiring disaster situational awareness information, (2) supporting self-organized peer-to-peer help activities, and (3) enabling the disaster management agencies to hear from the public. To achieve this vision, authors of this study examined 304 studies conducted 2008 through 2018 to systemically evaluate the current literature in understanding the phenomena of communication on social media and the state-of-the-art studies on social media informatics in disasters. This review then identified the challenges of existing studies and proposed a research roadmap to address the challenges of achieving the vision. This review could serve as a bridge for researchers working on social media in disasters to understand the state-of-the-art of this problem in other related domains. The findings of this review highlight the value of certain research areas, e.g., (1) a fine-grained disaster social media ontology with semantic interoperability, (2) network pattern of trending information and emerging influential users, (3) fine-grained assessment of societal impacts due to infrastructure disruptions, and (4) best practices for social media usage during disasters.
Electricity is the commonest commodity for most businesses in our world today. The use of electricity has been a breakthrough for the discovery of new technologies and has become the main driving ...force behind several innovations. With the introduction of smart grid systems, there have been improvements in how utility companies interact with their customers with regards to electricity use. However, since the readings are done via the Internet, there is the tendency for the data to be compromised when it gets into the hands of the wrong people. Moreover, customers mostly do not know why they pay huge amounts and which appliances use more electricity, since they are not privy to the readings. The sovereign blockchain technology, which provides transparency and provenance, is utilized in this paper to mitigate these above mentioned problems. A smart contract, which executes laid down procedures to provide a trust-based system between participants on the network is also implemented. Our system proves very efficient as the user can monitor how the electricity is used, and it also provides a platform where there is no manipulation from either party.
•Patients who are infected by SARS-Cov-2 and HIV tend to have a longer disease course and slower generation of specific antibodies•For suspected cases of COVID-19, nucleic acid detection, gene ...sequencing and antibody detection can confirm the diagnosis, respectively•SARS-Cov-2 may damage lymphocytes, especially T-lymphocytes, and the immune system is impaired during the period of disease
The ongoing outbreak of COVID-19 that began in Wuhan, China, become an emergency of international concern when thousands of people were infected around the world. This study reports a case simultaneously infected by SARS-Cov-2 and HIV, which showed a longer disease course and slower generation of specific antibodies. This case highlights that a co-infection of SARS-Cov-2 and HIV may severely impair the immune system.
The goal of intelligent transport systems (ITSs) is to enhance the network performance of vehicular ad hoc networks (VANETs). Even though it presents new opportunities to the Internet of Vehicles ...(IoV) environment, there are some security concerns including the need to establish trust among the connected peers. The fifth-generation (5G) communication system, which provides reliable and low-latency communication services, is seen as the technology to cater for the challenges in VANETs. The incorporation of software-defined networks (SDNs) also ensures an effective network management. However, there should be monitoring and reporting services provided in the IoV. Blockchain, which has decentralization, transparency, and immutability as some of its properties, is designed to ensure trust in networking platforms. In that regard, this article analyzes the combination of blockchain and SDN for the effective operation of the VANET systems in 5G and fog computing paradigms. With managerial responsibilities shared between the blockchain and the SDN, it helps to relieve the pressure off the controller due to the ubiquitous processing that occurs. A trust-based model that curbs malicious activities in the network is also presented. The simulation results substantially guarantee an efficient network performance, while also ensuring that there is trust among the entities.
Eco-pharmacovigilance (EPV) is a practical and powerful approach to minimize the potential risks posed by pharmaceutical residues in environment. However, it is impracticable to practise rigorous and ...unitary EPV process for all the existing and new pharmaceuticals. Here, we focused on non-steroidal anti-inflammatory drugs (NSAIDs), and discussed the necessity and potential opportunities of practising EPV of NSAIDs. We found that the consumption of NSAIDs is huge and ubiquitous across the globe. NSAIDs were worldwidely reported as one of the most dominant and frequently detected groups in environmental matrices including wastewater, surface water, suspended solids, sediments, groundwater, even drinking water. Besides, there is definitive evidence for the adverse impacts of NSAID residues on scavenging birds and aquatic species. These data suggested the necessity of implementing EPV of NSAIDs. From the perspective of drug administration, we identified some things that can be done as management practice options for EPV implementation on NSAIDs: ●Improving knowledge and perceptions of pharmacy/health care practitioners about EPV of NSAIDs.●Emphasizing the control of NSAIDs pollution sources, including preventing unnecessary consumption and unrational use of NSAIDs; promoting the safe disposal of medicines among the general public; controlling the manufacturing-related releases.●Identifying high-risk areas of NSAIDs pollution and associated risk factors.●Identifying high priority NSAIDs to be monitored in environment.●Lifting the world-wide ban on the production and sale of veterinary diclofenac in support of meloxicam, the only NSAID currently considered safe for vultures.●Designing and constituting a multidisciplinary framework for EPV of NSAIDs.
Display omitted
•EPV should target individual pharmaceuticals on a prioritised basis.•The huge consumption, serious environmental pollution and high potential risks suggest the necessity of EPV of NSAIDs.•Some advice and management practice options for EPV of NSAIDs were proposed.
Objective: The purpose of this paper is to propose a novel algorithm for joint optic disc and cup segmentation, which aids the glaucoma detection. Methods: By assuming the shapes of cup and disc ...regions to be elliptical, we proposed an end-to-end region-based convolutional neural network for joint optic disc and cup segmentation (referred to as JointRCNN). Atrous convolution is introduced to boost the performance of feature extraction module. In JointRCNN, disc proposal network (DPN) and cup proposal network (CPN) are proposed to generate bounding box proposals for the optic disc and cup, respectively. Given the prior knowledge that the optic cup is located in the optic disc, disc attention module is proposed to connect DPN and CPN, where a suitable bounding box of the optic disc is first selected and then continued to be propagated forward as the basis for optic cup detection in our proposed network. After obtaining the disc and cup regions, which are the inscribed ellipses of the corresponding detected bounding boxes, the vertical cup-to-disc ratio is computed and used as an indicator for glaucoma detection. Results: Comprehensive experiments clearly show that our JointRCNN model outperforms state-of-the-art methods for optic disc and cup segmentation task and glaucoma detection task. Conclusion: Joint optic disc and cup segmentation, which utilizes the connection between optic disc and cup, could improve the performance of optic disc and cup segmentation. Significance: The proposed method improves the accuracy of glaucoma detection. It is promising to be used for glaucoma screening.
PDF
