Three-layer Architecture Research Articles

A Distributed Algorithm for Task Offloading in Vehicular Networks With Hybrid Fog/Cloud Computing

Fog computing has been an effective paradigm of real-time applications in the IoT area, which enables task offloading at network edge devices. Particularly, many emerging vehicular applications require real-time interaction between the terminal users and computation servers, which can be implemented in fog-based architecture. However, it is still challenging to apply fog computing in vehicular networks due to high mobility of vehicles and uneven distribution of vehicle density, which may result in performance degradation, such as unbalanced workload and unexpected task failure. In this article, we investigate a new service scenario of task offloading under a three-layer service architecture, where the resources of vehicular fog (VF), fog server (FS), and central cloud (CC) are utilized in a cooperative way. On this basis, we formulate the probabilistic task offloading (PTO) problem by synthesizing task transmission, computation, and result retrieval, as well as characterizing the heterogeneity of computation servers. The objective of the PTO is to minimize the weighted sum of execution delay, energy consumption, and payment cost. To resolve the PTO problem, we propose a comprehensive task offloading algorithm by combining the alternating direction method of multipliers (ADMMs) and particle swarm optimization (PSO), called ADMM-PSO. The basic idea of the ADMM-PSO is to divide the PTO problem into multiple unconstrained subproblems and achieve the optimal solution in the form of an iterative coordination process. For each iteration, the solution is achieved by solving each subproblem with the PSO and updated based on a designed rule, which is able to converge to the optimal solution when the stop criterion is satisfied. Finally, we build the simulation model and implement the proposed algorithm for performance evaluation. The simulation results demonstrate the superiority of the proposed algorithm under a wide range of service scenarios.

Graph deep network for optic disc and optic cup segmentation for glaucoma disease using retinal imaging.

The fundus imaging method of eye screening detects eye diseases by segmenting the optic disc (OD) and optic cup (OC). OD and OC are still challenging to segment accurately. This work proposes three-layer graph-based deep architecture with an enhanced fusion method for OD and OC segmentation. CNN encoder-decoder architecture, extended graph network, and approximation via fusion-based rule are explored for connecting local and global information. A graph-based model is developed for combining local and overall knowledge. By extending feature masking, regularization of repetitive features with fusion for combining channels has been done. The performance of the proposed network is evaluated through the analysis of different metric parameters such as dice similarity coefficient (DSC), intersection of union (IOU), accuracy, specificity, sensitivity. Experimental verification of this methodology has been done using the four benchmarks publicly available datasets DRISHTI-GS, RIM-ONE for OD, and OC segmentation. In addition, DRIONS-DB and HRF fundus imaging datasets were analyzed for optimizing the model's performance based on OD segmentation. DSC metric of methodology achieved 0.97 and 0.96 for DRISHTI-GS and RIM-ONE, respectively. Similarly, IOU measures for DRISHTI-GS and RIM-ONE datasets were 0.96 and 0.93, respectively, for OD measurement. For OC segmentation, DSC and IOU were measured as 0.93 and 0.90 respectively for DRISHTI-GS and 0.83 and 0.82 for RIM-ONE data. The proposed technique improved value of metrics with most of the existing methods in terms of DSC and IOU of the results metric of the experiments for OD and OC segmentation.

A secure and efficient data deduplication framework for the internet of things via edge computing and blockchain

Data deduplication can solve the problem of resource wastage caused by duplicated data. However, due to the limited resources of Internet of Things (IoT) devices, applying data deduplication to IoT scenarios is challenging. Existing data deduplication frameworks for the IoT are prone to inefficiency or trust crises due to the random allocation of edge computing nodes. Furthermore, side-channel attacks remain a risk. In addition, after IoT devices store data in the cloud through data deduplication, they cannot share their data efficiently. In this paper, we propose a secure and efficient data deduplication framework for the IoT based on edge computing and blockchain technologies. In this scheme, we propose a model based on parallel use of three-layer and two-layer architectures and introduce the RAndom REsponse (RARE) scheme to resist side-channel attacks. We also design a label tree to realise one-to-many data-sharing, which improves efficiency and meets the needs of the IoT. In addition, we use blockchain to resist collusion attacks. Experiments were conducted to demonstrate that our framework has advantages over similar schemes in terms of communication cost, security and efficiency.

Predicting bus travel time using machine learning methods with three-layer architecture

The increase in population and the crowding of cities bring along transportation problems. Thus, people are directed to public transportation to reduce the burden on transportation. Being informed correctly about the arrival time at the stops attracts passengers. In this study, machine learning methods with three-layer architecture were used to predict bus arrival time. The first layer processes the measured data and gives the prediction results of actual data. In the second layer, the residuals are predicted at the specified depth. In the third layer, the results of the previous two layers are integrated with three different approaches to calculate the final prediction. The case study was carried out on the data obtained from Istanbul public transportation and various machine learning methods were applied to the data using the traditional and the three-layer architecture. The experimental results showed that the three-layer architecture provided successful results with approximately 2.552 MAPE.

A Deep Learning-Based Diagnosis System for COVID-19 Detection and Pneumonia Screening Using CT Imaging

Background: Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) is a global threat impacting the lives of millions of people worldwide. Automated detection of lung infections from Computed Tomography scans represents an excellent alternative; however, segmenting infected regions from CT slices encounters many challenges. Objective: Developing a diagnosis system based on deep learning techniques to detect and quantify COVID-19 infection and pneumonia screening using CT imaging. Method: Contrast Limited Adaptive Histogram Equalization pre-processing method was used to remove the noise and intensity in homogeneity. Black slices were also removed to crop only the region of interest containing the lungs. A U-net architecture, based on CNN encoder and CNN decoder approaches, is then introduced for a fast and precise image segmentation to obtain the lung and infection segmentation models. For better estimation of skill on unseen data, a fourfold cross-validation as a resampling procedure has been used. A three-layered CNN architecture, with additional fully connected layers followed by a Softmax layer, was used for classification. Lung and infection volumes have been reconstructed to allow volume ratio computing and obtain infection rate. Results: Starting with the 20 CT scan cases, data has been divided into 70% for the training dataset and 30% for the validation dataset. Experimental results demonstrated that the proposed system achieves a dice score of 0.98 and 0.91 for the lung and infection segmentation tasks, respectively, and an accuracy of 0.98 for the classification task. Conclusions: The proposed workflow aimed at obtaining good performances for the different system’s components, and at the same time, dealing with reduced datasets used for training.

FAHP-Based Reliability Evaluation of Distributed IoT Devices in a Distribution Power Grid

Reliable operation of distributed internet of things (IoT) devices is essential for supporting two-way interaction between energy flow and information flow in a distribution power grid. Traditional reliability evaluation methods suffer from several challenges including complex evaluation indicator selection and inadaptability of fixed weights with actual reliability requirements. In this paper, we first establish a multilevel reliability evaluation indicator system, where the indicators are selected through joint consideration of comprehensiveness and effectiveness. Then, we propose a fuzzy analytic hierarchy process- (FAHP-) based reliability evaluation method, where a three-layer reliability evaluation architecture is established. Specifically, a 0.1-0.9 scaling method is adopted to establish the fuzzy judgment matrix and scale the important relationship among state-layer elements, which can be dynamically adjusted to generate the weights adapting with actual operation state. The scores of distributed IoT devices and corresponding reliability levels can be obtained through the weighted summation of the scores of each layer. Simulation results verify the effectiveness and accuracy of the proposed method through comparing with actual reliability value and two existing evaluation methods.

Adaptive cell-based evacuation systems for leader-follower crowd evacuation

The challenge of controlling crowd movement at large events expands not only to the realm of emergency evacuations but also to improving non-critical conditions related to operational efficiency and comfort. In both cases, it becomes necessary to develop adaptive crowd motion control systems. In particular, adaptive cell-based crowd evacuation systems dynamically generate exit-choice recommendations favoring a coordinated group dynamic that improves safety and evacuation time. We investigate the viability of using this mechanism to develop a “leader-follower” evacuation system in which a trained evacuation staff guides evacuees safely to the exit gates. To validate the proposal, we use a simulation–optimization framework integrating microscopic simulation. Evacuees’ behavior has been modeled using a three-layered architecture that includes eligibility, exit-choice changing, and exit-choice models, calibrated with hypothetical-choice experiments. As a significant contribution of this work, the proposed behavior models capture the influence of leaders on evacuees, which is translated into exit-choice decisions and the adaptation of speed. This influence can be easily modulated to evaluate the evacuation efficiency under different evacuation scenarios and evacuees’ behavior profiles. When measuring the efficiency of the evacuation processes, particular attention has been paid to safety by using pedestrian Macroscopic Fundamental Diagrams (p-MFD), which model the crowd movement dynamics from a macroscopic perspective. The spatiotemporal view of the evacuation performance in the form of crowd-pressure vs. density values allowed us to evaluate and compare safety in different evacuation scenarios reasonably and consistently. Experimental results confirm the viability of using adaptive cell-based crowd evacuation systems as a guidance tool to be used by evacuation staff to guide evacuees. Interestingly, we found that evacuation staff motion speed plays a crucial role in balancing egress time and safety. Thus, it is expected that by instructing evacuation staff to move at a predefined speed, we can reach the desired balance between evacuation time, accident probability, and comfort.

Perturb more, trap more: Understanding behaviors of graph neural networks

While graph neural networks (GNNs) have shown great potential in various graph-related tasks, their lack of transparency has hindered our understanding of how they arrive at their predictions. The fidelity to the local decision boundary of the original model, indicating how well the explainer fits the original model around the instance to be explained, is neglected by existing GNN explainers. In this paper, we first propose a novel post hoc framework based on local fidelity for any trained GNNs, called TraP2, which can generate a high-fidelity explanation. Considering that both the relevant graph structure and important features inside each node must be highlighted, a three-layer architecture in TraP2 is designed: i) the interpretation domain is defined by the Translation layer in advance; ii) the local predictive behaviors of the GNNs being explained are probed and monitored by the Perturbation layer, in which multiple perturbations for graph structure and feature level are conducted in the interpretation domain; and iii) highly faithful explanations are generated by fitting the local decision boundary of GNNs being explained through the Paraphrase layer. We evaluated TraP2 on several benchmark datasets under the four metrics of accuracy, area under receiver operating characteristic curve, fidelity, and contrastivity, and the results prove that it significantly outperforms state-of-the-art methods.

Web-Based Ideological and Political Education System Design and Application

Ideological and political education in colleges and universities is an important way to enhance students’ ideological and political quality and promote their all-around education. It plays an important and positive role in personnel training. To improve the effectiveness of online ideological and political education, this study builds a web-based ideological and political education system and adopts a three-layer system architecture including a data layer, an interface layer, and an application layer. In addition, the system is designed with multiple modules to guarantee the active operation of the complete system and combines algorithms to implement system resource recommendation and practical student-teaching functions. Finally, a control experiment is designed to examine the performance of the proposed web-based ideological and political education system. Results show that the system constructed in this study has certain practical effects. The proposed system can be used to strengthen the work of ideological and political education, truly achieve the correct guidance of ideological, political, and moral aspects, and improve the teaching quality of ideological and political education as much as possible.

A Fog-Centric Secure Cloud Storage Scheme

Cloud computing is now being utilized as a prospective alternative for catering storage service. Security issues of cloud storage are a potential deterrent in its widespread adoption. Privacy breach, malicious modification, and data loss are emerging cyber threats against cloud storage. Recently, a fog server based three-layer architecture has been presented for secure storage employing multiple clouds. The underlying techniques used are Hash-Solomon code and customized hash algorithm in order to attain the goal. However, it resulted in loss of smaller portion of data to cloud servers and failed to provide better modification detection and data recoverability. This paper proposes a novel fog-centric secure cloud storage scheme to protect data against unauthorized access, modification, and destruction. To prevent illegitimate access, the proposed scheme employs a new technique <inline-formula><tex-math notation="LaTeX">$Xor - Combination$</tex-math></inline-formula> to conceal data. Moreover, <inline-formula><tex-math notation="LaTeX">$Block - Management$</tex-math></inline-formula> outsources the outcomes of <inline-formula><tex-math notation="LaTeX">$Xor - Combination$</tex-math></inline-formula> to prevent malicious retrieval and to ensure better recoverability in case of data loss. Simultaneously, we propose a technique based on hash algorithm in order to facilitate modification detection with higher probability. We demonstrate robustness of the proposed scheme through security analysis. Experimental results validate performance supremacy of the proposed scheme compared to contemporary solutions in terms of data processing time.

Research on Dynamic Design of Ideological and Political Education Based on Intelligent Algorithm

The digital civilization of human-computer coexistence has become a reality, thanks to the intelligent era. The widespread application of artificial intelligence technology in education has paved a new road for the collaborative and innovative development of ideological and political science teachers in universities and schools. In response to the problems of irregular, unprofessional, and unified resource sharing channels, duplicated, inverted, and disconnected teaching contents, and uncoordinated, insufficient, and unbalanced scientific research linkages in the integration process of university and college civics courses, the B/S three-layer architecture framework is used to build a university and college civics course teachers’ collaborative innovation platform that supports both PC and cell phone use by using jQuery, my structured query language (MySQL), hypertext preprocessor (PHP), juvenile sex offender assessment protocol (J-SOAP) crawlers, and other technologies. Teachers of civics courses can use the platform as a collaborative innovation tool. The goal of integrating resources, teaching, and scientific research of university and college civics courses is achieved, and the collaborative innovation development of university and college Civics teachers is promoted from theory to practice, thanks to the development of three major functions of the platform, namely, resource sharing, scientific research exchange, and teaching mutual assistance.

A Federated Learning Based Privacy-Preserving Smart Healthcare System

The rapid development of the smart healthcare system makes the early-stage detection of dementia disease more user-friendly and affordable. However, the main concern is the potential serious privacy leakage of the system. In this article, we take Alzheimer's disease (AD) as an example and design a convenient and privacy-preserving system named <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ADDetector</small> with the assistance of Internet of Things (IoT) devices and security mechanisms. Particularly, to achieve effective AD detection, <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ADDetector</small> only collects user's audio by IoT devices widely deployed in the smart home environment and utilizes novel topic-based linguistic features to improve the detection accuracy. For the privacy breach existing in data, feature, and model levels, <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ADDetector</small> achieves privacy-preserving by employing a unique three-layer (i.e., user, client, cloud, etc.) architecture. Moreover, <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ADDetector</small> exploits <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">federated learning (FL) based scheme</i> to ensure the user owns the integrity of raw data and secure the confidentiality of the classification model and implement <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">differential privacy (DP) mechanism</i> to enhance the privacy level of the feature. Furthermore, to secure the model aggregation process between clients and cloud in FL-based scheme, a novel <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">asynchronous privacy-preserving aggregation framework</i> is designed. We evaluate <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ADDetector</small> on 1010 AD detection trials from 99 health and AD users. The experimental results show that <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ADDetector</small> achieves high accuracy of 81.9% and low time overhead of 0.7 s when implementing all privacy-preserving mechanisms (i.e., FL, DP, and cryptography-based aggregation).

IoT-Based Human Fall Detection System

Human falls are an issue that especially affects elderly people, resulting in permanent disabilities or even in the person’s death. Preventing human falls is a social desire, but it is almost impossible to achieve because it is not possible to ensure full prevention. A possible solution is the detection of human falls in near real-time so that help can quickly be provided. This has the potential to greatly reduce the severity of the fall in long-term health consequences. This work proposes a solution based on the internet of things devices installed in people’s homes. The proposed non-wearable solution is non-intrusive and can be deployed not only in homes but also in hospitals, rehabilitation facilities, and elderly homes. The solution uses a three-layered computation architecture composed of edge, fog, and cloud. A mathematical model using the Morlet wavelet and an artificial intelligence model using artificial neural networks are used for human fall classification; both approaches are compared. The results showed that the combination of both models is possible and brings benefits to the system, achieving an accuracy of 92.5% without false negatives.

Human-computer interaction based interface design of intelligent health detection using PCANet and multi-sensor information fusion

Background and Objective: At present, because health monitoring using human-computer interaction (HCI) has become a demand in society, an intelligent health detector with HCI characteristics is urgently needed. Our device and software framework can provide natural human-machine interaction and facilitate the use of effective, efficient and safe electronic equipment for health detection. This paper integrates the research results of human subjects testing with analysis of our computational algorithms to build the proposed interaction platform.Methods: We collected the pulse signals of normal and sub-health people and used them as pre-processed signals. Then, we input them into the Principal Componcent Analysis Network (PCANet) layer by layer, and extracted the corresponding mapping features in each layer. The extracted features are hash coded, and histogram blocks are used as the feature matrix. Next, the accuracy obtained by the classical classifier is compared with the classification results of other feature extraction methods. The HCI integrated intelligent health detector based on PCANet neural network and multi-sensor information fusion has significantly improved the accuracy of human health detection.Results: The experimental results show that the proposed method achieves high accuracy for sub-health state recognition. Compared with the traditional feature extraction method, our PCANet method improves the recognition rate by more than 10%, which proves the effectiveness of PCANet model in the field of sub-health pulse signal detection. Because the PCANet is a multi-layer architecture model, in order to verify the influence of the number of extended network layers on the experimental results, experiments are carried out on the three-layer architectures represented by PCANet-1, PCANet-2 and PCANet-3 respectively. The Experimental results show that PCANet-3 model is 2.4% higher than PCANet-1, but only 0.6% higher than PCANet-2. The running time is about 2 times and 1.6 times higher than that of PCANet-1 and PCANet-2; Compared with traditional feature extraction algorithms such as MP and Gabor transform, the accuracy of pcanet model in pulse signal sub-health detection is significantly improved. Therefore, this product can effectively distinguish between the health and sub-health states.Conclusion: Our research shows that the intelligent health detector is efficient and convenient to use, and has higher accuracy for health detection. The HCI integrated platform provides a new reference basis for the detection of sub-health state.

A Model For risk-Based adaptive security controls

Security controls and countermeasures have shifted from static desktop-based and corporate network environments to heterogeneous, distributed and dynamic environments (e.g., cloud and mobile computing or Internet of Things). Due to this paradigm shift, adaptive and risk-based approaches have gained significant importance. These approaches allow security managers to perform context-aware decision making, adapting controls’ deployment, configuration or use to every specific situation, depending on the current value of risk indicators or scores and on the level of risk tolerated by the organisation at any given time. This paper proposes a model to automatically adapt security controls to different risk scenarios in almost real-time (if required). This model is based on a three-layer architecture and a three-step flow (measurement-decision-adaptation), relying on a scalable policies&rules framework capable of integrating with different kinds of controls. Furthermore, the proposed model is validated and evaluated with an actual use case.

A light-activated TiO2@In2Se3@Ag3PO4 cathode for high-performance Zn-Air batteries

Zn-air batteries (ZABs) require a small discharging voltage and large charging voltage. In this work, mesoporous hollow nanospheres of titanium dioxide@indium selenide@silver phosphate (TiO2@In2Se3@Ag3PO4) are designed and synthesized. The three-layer structure consists of TiO2 as the inner layer, In2Se3 as the middle layer, and Ag3PO4 as the outer layer. When TiO2@In2Se3@Ag3PO4 is irradiated with light, In2Se3 serves as the sensitizer to enhance light absorption and in the three-layer architecture, the photogenerated electrons and holes migrate in opposite direction in the near surface to minimize recombination. Hence, the three monomeric materials produce synergistic effects upon light illumination. The excited electrons are mainly concentrated in the conduction band (CB) of In2Se3 to promote the oxygen reduction reaction (ORR) and also increase the output voltage during discharging. On the other hand, holes are primarily concentrated in the valence band (VB) of Ag3PO4 to promote the oxygen evolution reaction (OER) and decrease the input voltage during charging. During light illumination, the discharging and charging voltages of the ZABs are 1.82 V and 0.64 V, respectively. The novel materials design reveals an effective strategy to harvest photo energy for electrochemical storage devices.

A Blockchain Application Prototype for the Internet of Things

The emergence of the Internet of things (IoT), associated with the explosion in the number of connected objects, and the growth in user needs, makes the Internet network very complex. IoT objects are diverse and heterogeneous, which requires establishing interoperability and efficient identity management on the one hand. On the other hand, centralized architectures such as cloud-based ones can have overhead and high latency, with a potential risk of failure. Facing these challenges, Blockchain technology, with its decentralized architecture based on a distributed peer-to-peer network, offers a new infrastructure that allows IoT objects to interact reliably and securely. In this paper, a new approach is proposed with a three-layer architecture: layer of sensing and collection of data made up of the IoT network, layer of processing and saving of data exchanges at the Blockchain level, and access and visualization layer via a web interface. The prototype implemented in this study allows all transactions (data exchanges) generated by IoT devices to be recorded and stored on a dedicated Blockchain, assuring the security of IoT objects' communications. This prototype also enables access to and visualization of all data and information, thus enhancing the IoT network's transparency.

Message Scheduling in Blockchain Based IoT Environment With Additional Fog Broker Layer

Recently researchers and companies have shown significant interest in merging blockchain and the Internet of Things (IoT) to create a safe, reliable, and resilient communication platform. However, determining the proper role of blockchain in existing IoT contexts with minimum implications is a challenge. This work suggests a message schedule for a blockchain-based architecture with two access-level setting filters for incoming messages: critical and non-critical. The proposed work of the researchers divides the fog layer into two parts: action clusters and blockchain fog clusters. Similar to the three-layered IoT architecture, the action cluster and the main cloud data center work together for critical message requests. The blockchain fog cluster is dedicated to only the blockchain application’s requirements. In the fog layer, a fog broker is used to schedule critical and non-critical messages in the action and blockchain fog clusters, respectively. The proposed technique is compared to the existing Dual Fog-IoT architecture. The solution is also tested for fog and cloud computing resource utilization. The findings demonstrate that this architecture is feasible for varying percentages of receiving critical and non-critical messages. In addition to the inherent benefits of blockchain, the suggested paradigm reduces the system loss rate and offloads the cloud data center with minimal changes to the existing IoT ecosystem.

Revisiting Aspect-Sentiment-Opinion Triplet Extraction: Detailed Analyses Towards a Simple and Effective Span-Based Model

Aspect-based sentiment information extraction has attracted increasing attention in the research community of natural language processing. Various methods, such as sequence tagging, sequence-to-sequence generation and span-based extraction, have been proposed, which own different advantages and disadvantages. In this article, we revisit the span-based method for aspect-sentiment-opinion triplet extraction, by designing and analyzing a simple yet effective Span-based Model, called SMTFASTE. Our model leverages a tidily three-layer architecture, including a BERT-based encoding layer, a span representation layer and an aspect-sentiment-opinion prediction layer. In the experiments of two widely-used benchmarks (ASTE-V2 and ASOTE-V2), we find that our model outperforms a number of complicated state-of-the-art models in most evaluation metrics. Therefore, we conduct detailed analyses for our model, such as ablation studies of the core components of our model and the benefit of explicitly using context information, and obtain some insightful findings and conclusion. Through this study, we show that a simple span-based model is able to achieve competitive results without much feature and architecture engineering. Our model is easy to follow and we have opened our code to facilitate related research.

Reliable and Resilient AI and IoT-Based Personalised Healthcare Services: A Survey

Recent technological and economic developments have transformed the healthcare sector towards more personalized and IoT-based healthcare services. These services are realized through control and monitoring applications that are typically developed using artificial intelligence/machine learning-based algorithms, which play a significant role in highlighting the efficiency of traditional healthcare systems. Current personalized healthcare services are dedicated to a specific environment to support technological personalization. However, they are unable to consider different interrelated health conditions, leading to inappropriate diagnoses and affecting sustainability and the long-term health of patients. To this end, current Healthcare 5.0 technology has evolved that supersede previous healthcare technologies. The goal of healthcare 5.0 is to achieve an autonomous healthcare service, that takes into account the interdependent effect of different health conditions of a patient. This paper conducts a comprehensive survey on personalized healthcare services. In particular, we first present an overview of key requirements of comprehensive personalized healthcare services in modern healthcare Internet of Things (HIoT), including the definition of personalization and an example use case scenario as a representative for modern HIoT. Second, we explored a fundamental three-layer architecture for IoT-based healthcare systems using AI and non-AI-based approaches, considering key requirements for CPHS followed by their strengths and weaknesses in the frame of personalized healthcare services. Third, we highlighted different security threats against each layer of IoT architecture along with the possible AI and non-AI-based solutions. Finally, we propose a methodology to develop reliable, resilient, and personalized healthcare services that address the identified weaknesses of existing approaches.