Directing research on Alzheimer’s disease toward only early prediction and accuracy cannot be considered a feasible approach toward tackling a ubiquitous degenerative disease today. Applying deep learning (DL), Explainable artificial intelligence, and advancing toward the human-computer interface (HCI) model can be a leap forward in medical research. This research aims to propose a robust explainable HCI model using SHAPley additive explanation, local interpretable model-agnostic explanations, and DL algorithms. The use of DL algorithms—logistic regression (80.87%), support vector machine (85.8%), k -nearest neighbor (87.24%), multilayer perceptron (91.94%), and decision tree (100%)—and explainability can help in exploring untapped avenues for research in medical sciences that can mold the future of HCI models. The presented model’s results show improved prediction accuracy by incorporating a user-friendly computer interface into decision-making, implying a high significance level in the context of biomedical and clinical research.

This paper introduces a simple Wireless Sensor Network (WSN)-based framework that uses Proteus sensors of Libelium Smart Water Xtreme IoT platform to detect e-Coli in wastewater, uses an efficient priority-based routing protocol for timely notification of the detection e-Coli at the COVID-19 detection lab to identify the existence of SARS-CoV-2, the virus that currently causes the COVID-19 pandemic. These sensors use fluorescence to monitor coli forms in real-time, determining if the water is polluted and contaminated with SARS-CoV-2 once tested at the lab. The framework also includes an efficient Packet Priority Routing Protocol (PPRP) that prioritizes data packets transmission related to detecting COVID-19 over other data packets for timely and emergency measures. Simulation results show that the proposed PPRP routing protocol is more efficient in terms of end-to-end data transmission delay and network energy consumption than existing LEACH and CPWS protocols.

Computational Linguistics (CL) associated with the Internet of Multimedia Things (IoMT)-enabled multimedia computing applications brings several research challenges, such as real-time speech understanding, deep fake video detection, emotion recognition, home automation, and so on. Due to the emergence of machine translation, CL solutions have increased tremendously for different natural language processing (NLP) applications. Nowadays, NLP-enabled IoMT is essential for its success. Sarcasm detection, a recently emerging artificial intelligence (AI) and NLP task, aims at discovering sarcastic, ironic, and metaphoric information implied in texts that are generated in the IoMT. It has drawn much attention from the AI and IoMT research community. The advance of sarcasm detection and NLP techniques will provide a cost-effective, intelligent way to work together with machine devices and high-level human-to-device interactions. However, existing sarcasm detection approaches neglect the hidden stance behind texts, thus insufficient to exploit the full potential of the task. Indeed, the stance, i.e., whether the author of a text is in favor of, against, or neutral toward the proposition or target talked in the text, largely determines the text’s actual sarcasm orientation. To fill the gap, in this research, we propose a new task: stance-level sarcasm detection (SLSD), where the goal is to uncover the author’s latent stance and based on it to identify the sarcasm polarity expressed in the text. We then propose an integral framework, which consists of Bidirectional Encoder Representations from Transformers (BERT) and a novel stance-centered graph attention networks (SCGAT). Specifically, BERT is used to capture the sentence representation, and SCGAT is designed to capture the stance information on specific target. Extensive experiments are conducted on a Chinese sarcasm sentiment dataset we created and the SemEval-2018 Task 3 English sarcasm dataset. The experimental results prove the effectiveness of the SCGAT framework over state-of-the-art baselines by a large margin.

The industrial healthcaresystem has enabled the possibility of realizing advanced real-time monitoring of patients and enriched the quality of medical services through data sharing among intelligent wearable devices and sensors. However, this connectivity brings the intrinsic vulnerabilities related to security and privacy due to the need of continuous communication and monitoring over public network (insecure channel). Motivated from the aforementioned discussions, we integrate permissioned blockchain and smart contract with deep learning (DL) techniques to design a novel secure and efficient data sharing framework named PBDL. Specifically, PBDL first has a blockchain scheme to register, verify (using zero-knowledge proof), and validate the communicating entities using the smart contract-based consensus mechanism. Second, the authenticated data are used to propose a novel DL scheme that combines stacked sparse variational autoencoder (SSVAE) with self-attention-based bidirectional long short term memory (SA-BiLSTM). In this scheme, SSVAE encodes or transforms the healthcare data into new format, and SA-BiLSTM identifies and improves the attack detection process. The security analysis and experimental results using IoT-Botnet and ToN-IoT datasets confirm the superiority of the PBDL framework over existing state-of-the-art techniques.

Intelligent Manufacturing 5.0 of multipulse rectifier systems requires them to be optimized for a variety of use in transportation and factories producing hearty touch technology. The research presented in this article show advances of using heuristic models to set 12-pulse and 24-pulse rectifiers to work under low- and high-voltage load. As a result of heuristic optimization electric systems increase efficiency and reduce energy consumption by efficiency benefits in adopting artificial intelligence. Applied heuristic models helped in computer simulations to optimize system settings in a short time. Results show that optimized models are more efficient and our proposed approach is reducing voltage pulsation. As a result optimized system improves electromagnetic compatibility for beneficial use in modern industry and sensible human–machine cooperation.

Wireless body area network (WBAN) suffers secure challenges, especially the eavesdropping attack, due to constraint resources. In this article, deep reinforcement learning (DRL) and mobile edge computing (MEC) technology are adopted to formulate a DRL-MEC-based jamming-aided anti-eavesdropping (DMEC-JAE) scheme to resist the eavesdropping attack without considering the channel state information. In this scheme, a MEC sensor is chosen to send artificial jamming signals to improve the secrecy rate of the system. Power control technique is utilized to optimize the transmission power of both the source sensor and the MEC sensor to save energy. The remaining energy of the MEC sensor is concerned to ensure routine data transmission and jamming signal transmission. Additionally, the DMEC-JAE scheme integrates with transfer learning for a higher learning rate. The performance bounds of the scheme concerning the secrecy rate, energy consumption, and the utility are evaluated. Simulation results show that the DMEC-JAE scheme can approach the performance bounds with high learning speed, which outperforms the benchmark schemes.

Green IoT primarily focuses on increasing IoT sustainability by reducing the large amount of energy required by IoT devices. Whether increasing the efficiency of these devices or conserving energy, predictive analytics is the cornerstone for creating value and insight from large IoT data. This work aims at providing predictive models driven by data collected from various sensors to model the energy usage of appliances in an IoT-based smart home environment. Specifically, we address the prediction problem from two perspectives. Firstly, an overall energy consumption model is developed using both linear and non-linear regression techniques to identify the most relevant features in predicting the energy consumption of appliances. The performances of the proposed models are assessed using a publicly available dataset comprising historical measurements from various humidity and temperature sensors, along with total energy consumption data from appliances in an IoT-based smart home setup. The prediction results comparison show that LSTM regression outperforms other linear and ensemble regression models by showing high variability ( R 2 ) with the training (96.2%) and test (96.1%) data for selected features. Secondly, we develop a multi-step time-series model using the auto regressive integrated moving average (ARIMA) technique to effectively forecast future energy consumption based on past energy usage history. Overall, the proposed predictive models will enable consumers to minimize the energy usage of home appliances and the energy providers to better plan and forecast future energy demand to facilitate green urban development.

Experts and crowds can work together to generate high-quality datasets, but such collaboration is limited to a large-scale pool of data. In other words, training on a large-scale dataset depends more on crowdsourced datasets with aggregated labels than expert intensively checked labels. However, the limited amount of high-quality dataset can be used as an objective test dataset to build a connection between disagreement and aggregated labels. In this paper, we claim that the disagreement behind an aggregated label indicates more semantics (e.g. ambiguity or difficulty) of an instance than just spam or error assessment. We attempt to take advantage of the informativeness of disagreement to assist learning neural networks by computing a series of disagreement measurements and incorporating disagreement with distinct mechanisms. Experiments on two datasets demonstrate that the consideration of disagreement, treating training instances differently, can promisingly result in improved performance.

Recently, deep learning-based models are being extensively utilized for steganalysis. However, deep learning models suffer from overfitting and hyperparameter tuning issues. Therefore, in this paper, an efficient θ -nondominated sorting genetic algorithm- ( θ NSGA-) III based densely connected convolutional neural network (DCNN) model is proposed for image steganalysis. θ NSGA-III is utilized to tune the initial parameters of DCNN model. It can control the accuracy and f-measure of the DCNN model by utilizing them as the multiobjective fitness function. Extensive experiments are drawn on STEGRT1 dataset. Comparison of the proposed model is also drawn with the competitive steganalysis model. Performance analyses reveal that the proposed model outperforms the existing steganalysis models in terms of various performance metrics.

Diabetic retinopathy (DR) is one of the most common causes of vision loss in people who have diabetes for a prolonged period. Convolutional neural networks (CNNs) have become increasingly popular for computer-aided DR diagnosis using retinal fundus images. While these CNNs are highly reliable, their lack of sufficient explainability prevents them from being widely used in medical practice. In this article, we propose a novel explainable deep learning ensemble model where weights from different models are fused into a single model to extract salient features from various retinal lesions found on fundus images. The extracted features are then fed to a custom classifier for the final diagnosis of DR severity level. The model is trained on an APTOS dataset containing retinal fundus images of various DR grades using a cyclical learning rates strategy with an automatic learning rate finder for decaying the learning rate to improve model accuracy. We develop an explainability approach by leveraging gradient-weighted class activation mapping and shapely adaptive explanations to highlight the areas of fundus images that are most indicative of different DR stages. This allows ophthalmologists to view our model's decision in a way that they can understand. Evaluation results using three different datasets (APTOS, MESSIDOR, IDRiD) show the effectiveness of our model, achieving superior classification rates with a high degree of precision (0.970), sensitivity (0.980), and AUC (0.978). We believe that the proposed model, which jointly offers state-of-the-art diagnosis performance and explainability, will address the black-box nature of deep CNN models in robust detection of DR grading.

Detection of cyber attacks in the Internet of Things (IoT) networks has lately been a growing concern. Due to the extensive use of IoT infrastructures in numerous domains, these malicious attacks are also increasing continuously and changing over time. Moreover, devices connected in IoT networks are operated without any human intervention for longer times. Hence, intelligent network-based security solutions are very important to provide timely detection of these attacks to protect an IoT system from potential failure. Different machine learning based techniques have already been proposed to provide effective solution to discover and counteract network intrusion aiming to ensure security in the network. In the context of IoT networks, little attention has been paid to the identification of malicious attacks. To this end, we propose an effective intrusion detection system (IDS) to detect unforeseen IoT cyberattacks by using various bagging and boosting ensemble methods and feed forward artificial neural network. We have used a recently published dataset, UNSW-NB15, containing simulated IoT sensor data to estimate the performance of the proposed models through 5-fold cross validation technique. The performance results show the effectiveness of the models with a small set of automatically selected optimal features from the dataset.

Malaria is a contagious disease that affects millions of lives every year. Traditional diagnosis of malaria in laboratory requires an experienced person and careful inspection to discriminate healthy and infected red blood cells (RBCs). It is also very time-consuming and may produce inaccurate reports due to human errors. Cognitive computing and deep learning algorithms simulate human intelligence to make better human decisions in applications like sentiment analysis, speech recognition, face detection, disease detection, and prediction. Due to the advancement of cognitive computing and machine learning techniques, they are now widely used to detect and predict early disease symptoms in healthcare field. With the early prediction results, healthcare professionals can provide better decisions for patient diagnosis and treatment. Machine learning algorithms also aid the humans to process huge and complex medical datasets and then analyze them into clinical insights. This paper looks for leveraging deep learning algorithms for detecting a deadly disease, malaria, for mobile healthcare solution of patients building an effective mobile system. The objective of this paper is to show how deep learning architecture such as convolutional neural network (CNN) which can be useful in real-time malaria detection effectively and accurately from input images and to reduce manual labor with a mobile application. To this end, we evaluate the performance of a custom CNN model using a cyclical stochastic gradient descent (SGD) optimizer with an automatic learning rate finder and obtain an accuracy of 97.30% in classifying healthy and infected cell images with a high degree of precision and sensitivity. This outcome of the paper will facilitate microscopy diagnosis of malaria to a mobile application so that reliability of the treatment and lack of medical expertise can be solved.

Cloud computing infrastructures capable of providing scalable storage and computing resources can efficiently be used for big data storage and processing. There are growing trends in developing data-intensive (big data) applications in this computing environment that need to access massive datasets. Hence, effective data management such as data availability and efficient accesses has become critical requirements in these applications. This can be achieved by using data replication, which offers reduced data access latency, higher data availability and improved system load balancing. Moreover, different applications may have different quality-of-service (QoS) requirements. To continuously support the QoS requirement of an application, we propose a highly distributed QoS-aware replication technique that computes the optimal data center locations for the replicas so that the overall replication cost is minimized. Further, the replication strategy aims at maximizing QoS satisfaction to improve data availability and reduce access latency. The problem is formulated using dynamic programming. Finally, simulation experiments are performed using widely observed data access patterns to demonstrate the effectiveness of the proposed technique.

Data Grids provide services and infrastructure for distributed data-intensive applications accessing massive geographically distributed datasets. An important technique to speed access in Data Grids is replication, which provides nearby data access. Much of the work on the replica placement problem has focused on average system performance and ignored quality assurance issues. In a data grid environment, resource availability, network latency, and users' requests may change. Moreover, different sites may have different service quality requirements. In this paper, we introduce a new highly distributed and decentralized replica placement algorithm for hierarchical Data Grids that determines the positions of a minimum number of replicas expected to satisfy certain quality requirements. Our placement algorithm exploits the data access history for popular data files and computes replica locations by minimizing overall replication cost (read and update) while maximizing QoS satisfaction for a given traffic pattern. The problem is formulated using dynamic programming. We assess our algorithm using OptorSim. A comparison between our algorithm and its QoS-unconstrained counterpart shows that our algorithm can shorten job execution time greatly while consuming moderate bandwidth for data transfer.

Data grids support distributed data-intensive applications that need to access massive datasets stored around the world. Ensuring efficient access to such datasets is hindered by the high latencies of wide-area networks. To speed up access, files can be replicated so a user can access a nearby replica. Replication also provides improved availability, decreased bandwidth use, increased fault tolerance, and improved scalability. Since a grid environment is dynamic, resource availability, network latency, and user requests may change. To address these issues a dynamic replica placement strategy that adapts to changing behaviour is needed. In this paper, we introduce a highly distributed replica placement algorithm for hierarchical data grids. Our algorithm exploits data access histories to identify popular files and determines optimal replication locations to improve access performance by minimizing replication overhead (access and update) assuming a given traffic pattern. The problem is formulated using dynamic programming. We evaluate our algorithm using the OptorSim simulator and find that it offers shorter execution time and reduced bandwidth consumption compared to other dynamic replica placement methods.

Data grids provide geographically distributed storage for large-scale data-intensive applications. Ensuring efficient access to such large and widely distributed datasets is hindered by high latencies. To speed up data access, data grid systems replicate data in multiple locations so a user can access the data from a nearby site. In addition to reducing data access time, replication also aims to use network and storage resources efficiently. While replication is a well-known technique, the problem of replica placement has not been widely studied for data grid environments. To obtain the best possible gains from replication, strategic placement of the replicas is critical. In a grid environment resource availability, network latency, and userspsila requests can vary. To address these issues a placement strategy is needed that adapts to dynamic behavior. This paper proposes a new dynamic replica placement algorithm for hierarchical data grids based on file ldquopopularityrdquo. Our goal is to place replicas close to the clients to reduce access time while using the network and storage efficiently thereby effectively balancing storage cost and access latency. We evaluate our algorithm using OptorSim which shows that our approach outperforms other techniques in terms of access time and bandwidth used.

Heterogeneity of networks and end systems poses challenges for multicast based collaborative applications. In traditional multicasting, the sender transmits video at the same rate to all receivers independent of their network connection, end system equipment, and users' preferences. This wastes resources and may also result in some receivers having their quality expectations unsatisfied. This problem can be addressed, near the network edge, by applying dynamic, in-network transcoding of video streams. In this paper, we design, implement, and assess a network processor (NP) based video transcoding system using the Intel IXP1200. Experiments suggest that our system can adapt the video rate of MPEG-1 streams to a desired level on a per packet basis for moderate traffic levels.