Local Clients Research Articles

Speech Assistant System With Local Client and Server Devices to Guarantee Data Privacy

Users of speech assistant systems have reservations about the distributed approach of these systems. They have concerns that people might get access to the transmitted speech data or that somebody is able to access their microphone from outside. Therefore, we investigate the concept of a setup with local client and server systems. This comes along with the requirement of cost-efficient realizations of client and server. We examined a number of different cost-efficient server solutions depending on the required recognition capability of specific applications. A fairly cost-efficient solution is the use of a small computing device for recognizing a few dozens of words with a GMM-HMM based recognition. To perform a DNN-HMM based recognition, we looked at small computing devices with an integrated additional graphical processor unit (GPU). Furthermore, we investigated the use of low-cost PCs for implementing real-time versions of the Kaldi framework to allow the recognition of large vocabularies. We investigated the control of a smart home by speech as an exemplary application. For this, we designed compact client systems that can be integrated at certain places inside a room, e.g., in a standard outlet socket. Besides activating a client by a sensor that detects approaching people, the recognition of a spoken wake-up word is the usual way for activation. We developed a keyword recognition algorithm that can be implemented in the client despite its limited computing resources. The control of the whole dialogue has been integrated in our client, so that no further server is needed. In a separate study, we examined the approach of an extremely energy-efficient realization of the client system without the need of an external power supply. The approach is based on using a special microphone with an additional low-power operating mode detecting the exceeding of a preset sound level threshold only. This detection can be used to wake up the client's microcontroller and to make the microphone switch to normal operating mode. In the listening mode, the energy consumption of the microphone is so low that a client system can be active for months with an energy supply from standard batteries only.

Robust Aggregation for Federated Learning by Minimum γ-Divergence Estimation.

Federated learning is a framework for multiple devices or institutions, called local clients, to collaboratively train a global model without sharing their data. For federated learning with a central server, an aggregation algorithm integrates model information sent from local clients to update the parameters for a global model. Sample mean is the simplest and most commonly used aggregation method. However, it is not robust for data with outliers or under the Byzantine problem, where Byzantine clients send malicious messages to interfere with the learning process. Some robust aggregation methods were introduced in literature including marginal median, geometric median and trimmed-mean. In this article, we propose an alternative robust aggregation method, named -mean, which is the minimum divergence estimation based on a robust density power divergence. This -mean aggregation mitigates the influence of Byzantine clients by assigning fewer weights. This weighting scheme is data-driven and controlled by the value. Robustness from the viewpoint of the influence function is discussed and some numerical results are presented.

A Fairness-Aware Peer-to-Peer Decentralized Learning Framework with Heterogeneous Devices

Distributed machine learning paradigms have benefited from the concurrent advancement of deep learning and the Internet of Things (IoT), among which federated learning is one of the most promising frameworks, where a central server collaborates with local learners to train a global model. The inherent heterogeneity of IoT devices, i.e., non-independent and identically distributed (non-i.i.d.) data, and the inconsistent communication network environment results in the bottleneck of a degraded learning performance and slow convergence. Moreover, most weight averaging-based model aggregation schemes raise learning fairness concerns. In this paper, we propose a peer-to-peer decentralized learning framework to tackle the above issues. Particularly, each local client iteratively finds a learning pair to exchange the local learning model. By doing this, multiple learning objectives are optimized to advocate for learning fairness while avoiding small-group domination. The proposed fairness-aware approach allows local clients to adaptively aggregate the received model based on the local learning performance. The experimental results demonstrate that the proposed approach is capable of significantly improving the efficacy of federated learning and outperforms the state-of-the-art schemes under real-world scenarios, including balanced-i.i.d., unbalanced-i.i.d., balanced-non.i.i.d., and unbalanced-non.i.i.d. environments.

Trusted quantum remote sensing based on self-testing of entangled states

In a typical scenario of quantum remote sensing, a server at the remote site sends the sensing information to the local site, so that the client there can make a diagnosis about the sensed field. In practice, the reliability of the sensing information may be undermined by kinds of errors, e.g., the imperfections of measurement devices or the attacks from a malicious eavesdropper. An alternative way to circumvent this problem is to encode the sensing information into entangled states, of which the form can be inferred in a device-independent manner, namely, self-testing. In this paper, we propose a protocol to make secure sensing of a parameter at the remote side. Upon receiving the remote sensing data, the local client can figure out the parameter range by inspecting the joint probabilities. In stark contrast, a malicious eavesdropper who is allowed to access all the remote data cannot either acquire the information of the parameter or cheat the client by replacing returned data with fake ones. We apply this protocol to a magnetic sensing scenario, and we show that the client can reliably estimate the strength range of the magnetic field, which could be intimately related to various mineral resources. Consequently, the client should not overslip any mineral resources by identifying the upper bound of magnetic strength. We also show that our protocol is valid even if the entangled states are mildly noisy.

Federated Learning for Automatic Modulation Classification Under Class Imbalance and Varying Noise Condition

Automatic modulation classification (AMC) is a promising technology for identifying modulation types, and deep learning (DL)-based AMC is one of its main research directions. Conventional DL-based AMC methods are centralized solutions (i.e., CentAMC), which are trained on abundant data collected from local clients and stored in the server and generally have advanced performance, but their major problem is the risk of data leakage. Besides, if DL-based AMC is only trained with the data from their corresponding clients, it may exhibit weak performance. Thus, a federated learning (FL)-based AMC (FedeAMC) is proposed under the condition of class imbalance and noise varying. Its advantage is low risk of data leakage without severe performance loss, because data and training are in each local client, while only knowledge (i.e., gradient or model weight), rather than data, is shared with the server. In addition, there is generally class imbalance problem in each local client, and balanced cross entropy is introduced as loss function for solving this problem. Simulation results demonstrated that average accuracy gap between FedeAMC and CentAMC is less than 2%.

Empires of Antiquities: Modernity and the Rediscovery of the Ancient Near East, 1914–1950

Empires of Antiquities: Modernity and the Rediscovery of the Ancient Near East, 1914–1950

Mobile AR Contents Production Technique for Long Distance Collaboration

This study proposes that mobile AR users with different physical spaces can use one collaboration coordinate by synchronizing each other's coordinates. When each user uses mobile AR remote contents from a distance, it is difficult to maintain the same working environment depending on their physical environment. In order for physical spaces to maintain the same working environment in different situations, the coordinates of the virtual object must be matched to the direction of each client. To solve this problem, this paper proposes a coordinate synchronization technology using a shared coordinate flag. Through this technique, the interaction of all subsequent objects can be performed based on the shared coordinate system of the local client. The user installs a coordinate synchronization flag on a map formed based on each physical space. Through this flag, the location of the virtual object may be synchronized based on each client to perform collaboration. To verify the proposed technology, the mobile AR remote technology was implemented as a painting contents application. Three users synchronized the coordinate system together on three Android mobile devices to verify the feasibility of the technology proposed in this paper.

A Secure Federated Deep Learning-Based Approach for Heating Load Demand Forecasting in Building Environment

Recently, with the establishment of new thermal regulation, the energy efficiency of buildings has increased significantly, and various deep learning-based methods have been presented to accurately forecast the heating load demand of buildings. However, all of these methods are executed on a dataset with specific distribution and do not have the property of global forecasting, and have no guarantee of data privacy against cyber-attacks. This paper presents a novel approach to heating load demand forecasting based on Cyber-Secure Federated Deep Learning (CSFDL). The suggested CSFDL provides a global super-model for forecasting heating load demand of different local clients without knowing their location and, most importantly, without revealing their privacy. In this study, a CSFDL global server is trained and tested considering the heating load demand of 10 different clients in their building environment. The presented results, including a comparative study, prove the viability and accuracy of the proposed procedure.

Application of Federated Learning Algorithm Based on K-Means in Electric Power Data

Accurate electricity forecasting is the key basis for guiding the power sector to arrange operation plans and guaranteeing the profitability of electric power companies. However, with the increasing demand of enterprises and departments for data security, the phenomenon of “Isolated Data Island” becomes more and more serious, resulting in the accuracy loss of the traditional electricity prediction model. Federated learning, as an emerging artificial intelligence technology, is designed to ensure data privacy while carrying out efficient machine learning, which provides a new way to solve the problem of “Isolated Data Island” in terms of electricity forecasting. Nonetheless, due to the popularity of smart meters, the collected electricity data presents the characteristics of uneven distribution and huge data volume, so it is difficult to apply the electric quantity prediction model generated only by federated learning in practice. To solve this problem, a clustering federated learning method (C-FL) is proposed to protect data privacy while improving the accuracy of power prediction. Firstly, C-FL uses K-means algorithm to cluster power data locally in power enterprises, and then builds accurate power forecasting models for each class of power data combined with other local clients through federated learning. A large number of experimental results show that the clustering federated learning method proposed in this paper is superior to the existing federated learning models in terms of the accuracy of electric power forecasting.

Paving the Way for Distributed Artificial Intelligence Over the Air

Distributed Artificial Intelligence (DAI) is one of the most promising techniques to provide intelligent services under strict privacy protection regulations for multiple clients. By applying DAI, training on raw data is carried out locally. At the same time, the trained outputs, e.g., model parameters from multiple local clients, are sent back to a central server for aggregation. DAI is recently studied in conjunction with wireless communication networks to achieve better practicality, incorporating various random effects brought by wireless channels. However, because of wireless channels’ complex and case-dependent nature, a generic simulator for applying DAI in wireless communication networks is still lacking. To accelerate the development of DAI in wireless communication networks, we propose a generic system design in this paper and an associated simulator that can be set according to wireless channels and system-level configurations. Details of the system design and analysis of the impacts of wireless environments are provided to facilitate further implementations and updates. We employ a series of experiments to verify the effectiveness and efficiency of the proposed system design and reveal its superior scalability.

Patientperspectives from the multi-disciplinary chronic pain clinic: a qualitative study.

Aim: The chronic pain clinic (CPC) is a multi-disciplinary program that incorporates pharmacological and non-pharmacological methods, including First Nations healing strategies, to manage pain, improve functioningand reduce opioid misuse among patients with chronic pain in Regina, Canada. Materials & methods: The care experiences of ten current clients were explored using a narrative interview approach. Results: The CPC provides high-quality and safe care for effective chronic pain management. Clients noted pain reduction and improvements in sleep, mobility, functionality, and mood. First Nation clients emphasized the importance of traditional healing strategies. Conclusion: This unique comprehensive multi-modal approach which incorporates First Nations healing strategies is effective in supporting the unique needs of local clients.

Ethnomedical Specialists and their Supernatural Theories of Disease

Religious healing specialists such as shamans often use magic. Evolutionary theories that seek to explain why laypersons find these specialists convincing focus on the origins of magical cognition and belief in the supernatural. In two studies, we reframe the problem by investigating relationships among ethnomedical specialists, who possess extensive theories of disease that can often appear “supernatural,” and religious healing specialists. In study 1, we coded and analyzed cross-cultural descriptions of ethnomedical specialists in 47 cultures, finding 24% were also religious leaders and 74% used supernatural theories of disease. We identified correlates of the use of supernatural concepts among ethnomedical specialists; incentives and disincentives to patronize ethnomedical specialists; and distinct clusters of ethnomedical specialists that we label prestigious teachers, feared diviners, and efficacious healers. In study 2, we interviewed 84 Maasai pastoralists and their traditional religious and non-religious healing specialists. We found that laypersons relied on medicinal services based on combinations of efficacy, religious identity, and interpersonal trust. Further, laypersons and specialists largely used abstract concepts that were not conspicuously supernatural to describe how local medicines work. We conclude that religious healers in traditional societies often fulfill a practical and specialized service to local clients, and argue that supernatural theories of disease often reflect abstract cognition about rare phenomena whose causes are unobservable (e.g., infection, mental illness) instead of a separate “religious” style of thinking.

Personalized Federated Learning for ECG Classification Based on Feature Alignment

Electrocardiogram (ECG) data classification is a hot research area for its application in medical information processing. However, insufficient data, privacy preserve, and local deployment are still challenging difficulties. To address these problems, a novel personalized federated learning method for ECG classification is proposed in this paper. First, a global model is trained with federated learning framework on multiple local data clients. Then, we use the global model and private data to train the local model. To reduce the feature inconsistency between global and private local data and for better fitting the private local data, a novel ”feature alignment” module is devised to guarantee the uniformity, which contains two parts, global alignment and local alignment, respectively. For global alignment, the graph metric of batch data is used to constrain the dissimilarity between features generated by the global model and local model. For local alignment, triplet loss is adopted to increase discriminative ability for local private data. Comprehensive experiments on our collected dataset are evaluated. The results show that the proposed method can be better adapted to local data and exhibit superior ability of generalization.

Federated Learning and Wireless Communications

Federated learning becomes increasingly attractive in the areas of wireless communications and machine learning due to its powerful learning ability and potential applications. In contrast to other machine learning techniques that require no communication resources, federated learning exploits communications between the central server and the distributed local clients to train and optimize a model. Therefore, how to efficiently assign limited communication resources to train a federated learning model becomes critical to performance optimization. On the other hand, federated learning, as a brand-new tool, can potentially enhance the intelligence of wireless networks. In this article, we provide a comprehensive overview of the relationship between federated learning and wireless communications, including basic principles of federated learning, efficient communications for training a federated learning model, and federated learning for intelligent wireless applications. We also identify some research challenges and directions at the end of this article.

Interpreting in Tanzania from the perspective of Tanzanian interpreters

Abstract The study overviews the role of interpreting services in Tanzania, presenting mainly the experience of practicing freelance interpreters. The two official languages of Tanzania – English and Swahili – have separate roles in the country. Although most Tanzanians accept English as a necessary medium of intercultural communication, Swahili is perceived as an important part of Tanzanian national identity. It is the country’s lingua franca. On the one hand, Tanzania aims to preserve communication in Swahili; on the other hand, there is an inevitable need for intercultural communication with the rest of the world that grows especially in the context of globalization. The paper focuses on the role, status, education, working languages, conditions of Tanzanian interpreters, and the requirements of local and international clients. The study also creates a broader context that mentions crucial historical moments that have influenced the country’s current character of intercultural communication.

Navigating with logics: Care for women with hypertensive disorders of pregnancy in a tertiary hospital in Ghana

This paper explores how care for women with hypertensive disorders of pregnancy (HDP) is practiced in a tertiary hospital in Ghana. Partly in response to the persistently high maternal and neonatal mortality rates in Low- and Middle-income countries, efforts to improve quality of maternity care have increased. Quality improvement initiatives are shaped by the underlying conceptualisation of quality of care, often driven by global (WHO) standards and protocols. However, there are tensions between global standards of care and local clients' and providers' understandings of care practices and quality of care. Implementation of standards is further complicated by structural and organisational restrictions that influence providers' possibilities and priorities. Based on ethnographic fieldwork, we explore how clinical guidelines and professionals' and patients' perspectives converge and, more importantly, diverge. We illuminate local, situated care practices and show how professionals creatively deal with tensions that arise on the ground. In this middle-income setting, caring for women with HDP involves tinkering and navigating in contexts of uncertainty, scarcity, varying responsibilities and conflicting interests. We unravelled a complex web of, at times, contradictory logics, from which various forms of care arise and in which different notions of good care co-exist. While practitioners navigated through and with these varying logics of care, the logic of survival permeated all practices. This study provides important initial insights into how professionals might implement and innovatively adapt the latest quality of maternity care guidelines which seek to marry clinical standards and patients’ needs, preferences and experiences.

Do PCAOB Inspections of Foreign Auditors Affect Global Financial Reporting Comparability?*

ABSTRACTThis study investigates whether PCAOB inspections of foreign auditors affect global financial reporting comparability. Foreign auditors may adjust audit methodologies to address PCAOB inspection findings, which could affect financial reporting of local clients. Exploiting both within‐ and cross‐country variation in PCAOB inspections, we predict and find that non‐US‐listed foreign companies' financial reporting becomes more comparable to their US and non‐US industry peers after their auditors undergo an initial inspection. However, there is a decrease in comparability compared to local peers whose auditors have not been inspected. Subsample tests suggest that the improvement in comparability is driven by (i) auditors that satisfactorily address deficiencies and (ii) auditors that do not publicly push back against deficiencies. The effects are dampened after local audit regulators begin inspection programs. Overall, our evidence suggests that the PCAOB international inspection program affects audit methodologies of inspected auditors in a consistent way, improving comparability across jurisdictions. The improved comparability implies that the PCAOB international inspection program may unintentionally help meet accounting regulators' goals of cross‐country financial reporting convergence, which potentially promotes efficient cross‐country capital allocation.

Considerations for Social Needs Screening in a Local Public Health Agency.

The social determinants of health impact the health outcomes of local public health agency clients. This report shows how the Florida Department of Health in Hillsborough County (DOH) sought to address this for its clients. This midstream intervention identified individual DOH client needs and navigated clients to community resources to address these social needs. During the 2019 program, 768 DOH clients were screened, with 77% reporting having 1 or more social needs. Staff and clients identified various challenges clients faced navigating resources on their own, and the value in having resource navigators within the local public health agency. Program findings demonstrated alignment with priorities in the Community Health Assessment, leading to engagement of specific partners and planning for population-level policy interventions. Social needs screenings present a unique opportunity for local public health agencies to improve the circumstances of clients and implement health equity approaches in their communities.

The Impact of Of COVID-19 on the Sri Lankan Economy

The recently identified coronavirus causes COVID-19, an infectious disease. Before the eruption in Wuhan, China in December 2019, no one had heard of this new virus (WHO, 2020). All affected nations have taken steps to protect themselves and several countries have already specialized in obtaining the coronavirus vaccine but have been unable to control the problem due to lack of knowledge and management. Although more than six months have passed since the epidemic, Sri Lanka has made significant progress in curbing the spread of COVID-19; However, the threat persists after the third wave of COVID-19 attacks. This article focuses on identifying the impact of the country's major income sectors, especially tourism, apparel and textile industry, small and medium enterprises, agriculture and food, on the Sri Lankan economy. Tea export earnings fell to the US $ 270.1 million. Revenue from other sectors such as fruit and vegetable production and coconut production in March 2020 was significantly lower than in March 2019. Tourism earnings from January to June 2019 were 1,901. USD This was due to restrictions imposed on airport routes and the revocation of visas. Delays or cancellations of orders from local and international clients reduced sales by more than 80% in small and medium enterprises. The impact of Kovid-19 on all these major revenue-generating sectors in the country, however, led to a GDP growth of 3.6%, which could harm the overall economy of the epidemic and lead to appropriate recommendations. It is being implemented to achieve economic growth despite the epidemic in the country.

Scalable Orchestration of Service Function Chains in NFV-Enabled Networks: A Federated Reinforcement Learning Approach

Network function virtualization (NFV) is critical to the scalability and flexibility of various network services in the form of service function chains (SFCs), which refer to a set of Virtual Network Functions (VNFs) chained in a specific order. However, the NFV performance is hard to fulfill the ever-increasing requirements of network services mainly due to the static orchestrations of SFCs. To tackle this issue, a novel Scalable SFC Orchestration (SSCO) scheme is proposed in this paper for NFV-enabled networks via federated reinforcement learning. SSCO has three remarkable characteristics distinguishing from the previous work: (1) A federated-learning-based framework is designed to train a global learning model, with time-variant local model explorations, for scalable SFC orchestration, while avoiding data sharing among stakeholders; (2) SSCO allows for parameter update among local clients and the cloud server just at the first and last epochs of each episode to ensure that distributed clients can make model optimization at a low communication cost; (3) SSCO introduces an efficient deep reinforcement learning (DRL) approach, with the local learning knowledge of available resources and instantiation cost, to map VNFs into networks flexibly. Furthermore, a loss-weight-based mechanism is proposed to generate and exploit reference samples in replay buffers for future training, avoiding the strong relevance of samples. Simulation results obtained from different working scenarios demonstrate that SSCO can significantly reduce placement errors and improve resource utilization ratio to place time-variant VNFs compared with the state-of-the-art mechanisms. Furthermore, the results show that the proposed approach can achieve desirable scalability.