Muhammad Diyan

ORCID: 0000-0001-5862-4498
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • IoT and Edge/Fog Computing
  • Hearing Loss and Rehabilitation
  • Mobile Ad Hoc Networks
  • Opportunistic and Delay-Tolerant Networks
  • Speech and Audio Processing
  • Vehicular Ad Hoc Networks (VANETs)
  • Smart Grid Energy Management
  • Green IT and Sustainability
  • Human Mobility and Location-Based Analysis
  • Digital Media Forensic Detection
  • Acoustic Wave Phenomena Research
  • Energy Efficient Wireless Sensor Networks
  • Advanced Steganography and Watermarking Techniques
  • Chaos-based Image/Signal Encryption
  • Caching and Content Delivery
  • Context-Aware Activity Recognition Systems
  • Energy Load and Power Forecasting
  • Advanced Malware Detection Techniques
  • Smart Cities and Technologies
  • IoT-based Smart Home Systems
  • Sleep and Work-Related Fatigue
  • Data Stream Mining Techniques
  • Misinformation and Its Impacts
  • Power System Reliability and Maintenance
  • Cloud Computing and Resource Management

Teesside University
2024

University of Dundee
2024

Edinburgh Napier University
2022

University of Glasgow
2022

Kyungpook National University
2018-2021

The Internet of Things (IoT), inspired by the tremendous growth connected heterogeneous devices, has pioneered notion smart city. Various components, i.e., transportation, community, healthcare, grid, etc. which are integrated within city architecture aims to enrich quality life (QoL) urban citizens. However, real-time processing requirements and exponential data withhold realization. Therefore, herein we propose a Big Data analytics (BDA)-embedded experimental for cities. Two major aspects...

10.3390/s18092994 article EN cc-by Sensors 2018-09-07

Abstract Abnormalities in the heart's rhythm, known as arrhythmias, pose a significant threat to global health, often leading severe cardiac conditions and sudden deaths. Therefore, early accurate detection of arrhythmias is crucial for timely intervention potentially life‐saving treatment. Artificial Intelligence, particularly deep learning, has revolutionised diagnosis various health conditions, including arrhythmias. A unique hybrid architecture, ECG‐TransCovNet, that combines...

10.1049/cit2.12293 article EN cc-by-nc CAAI Transactions on Intelligence Technology 2024-02-12

Maintaining a fair use of energy consumption in smart homes with many household appliances requires sophisticated algorithms working together real time. Similarly, choosing proper schedule for operation can be used to reduce inappropriate consumption. However, scheduling always depend on the behavior home user. Thus, modeling human interaction is needed design an efficient algorithm real-time support. In this regard, we propose based using reinforcement learning (RL). The proposed divides...

10.3390/s20123450 article EN cc-by Sensors 2020-06-18

<abstract><p>The Internet of Things (IoT) is a paradigm that connects range physical smart devices to provide ubiquitous services individuals and automate their daily tasks. IoT collect data from the surrounding environment communicate with other using different communication protocols such as CoAP, MQTT, DDS, etc. Study shows these are vulnerable attack prove significant threat telemetry data. Within network, interdependent, behaviour one device depends on coming another device....

10.3934/mbe.2022493 article EN cc-by Mathematical Biosciences & Engineering 2022-01-01

Abstract The requisition for electrical energy, smart grid, and renewable energy paradigm extend a new space Electrical Energy Data Management Processing Systems (EEDMS), in such way that can mitigate the consumption of energy. Similarly, implementation maintenance EEDMS is challenging task. Moreover, heterogeneous data generated from residential commercial sector are leading challenges standard Internet Things (IoT) architecture. This contributes enormous preprocessing analyzing solutions...

10.1002/ett.3919 article EN Transactions on Emerging Telecommunications Technologies 2020-03-04

A smart home provides a facilitated environment for the detection of human activity with appropriate Deep Learning algorithms to manipulate data collected from numerous sensors attached various things in environment. Human activities comprise expected and unexpected behavior events; therefore, detecting these events consisting mutual dependent poses key challenge paradigm. Besides, battery-powered sensor ubiquitously extensively monitors activities, disputes, energy depletion. Therefore,...

10.3390/s20195498 article EN cc-by Sensors 2020-09-25

Emergence of smart things has matured the Internet Thing (IoT) notion. Extensive attention drawn towards IoT inspired concept Smart homes. However, actual implementation home architecture is highly challenged by heterogeneity devices, platform incompatibilities, and energy management demands. Web Things (WoT) a common solution platform, which exposes these heterogeneous services in an effective transparent manner. Hence, this paper, we propose WoT that occupies representational state...

10.1109/icnc47757.2020.9049774 article EN 2016 International Conference on Computing, Networking and Communications (ICNC) 2020-02-01

Current deep learning (DL) based approaches to speech intelligibility enhancement in noisy environments are often trained minimise the feature distance between noise-free and enhanced signals. Despite improving quality, such do not deliver required levels of everyday environments. Intelligibility-oriented (I-O) loss functions have recently been developed train DL for robust enhancement. Here, we formulate, first time, a novel canonical correlation I-O function more effectively algorithms....

10.1109/embc48229.2022.9871113 article EN 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) 2022-07-11

The smart city notion facilitate interoperation among multiple disciplines to improve the Quality of Life (QoL) urban citizens. Unceasingly growing networks has significantly increased data processing complexity. In consequence, real-time and analysis become a major concern in modern designing implementation. Considering challenges existing cities, this work we propose architecture embedded with Big Data Analytics (BDA). utmost goal proposed scheme is enhance quality decision-making through...

10.1109/icspcs.2018.8631726 article EN 2018-12-01

Vehicular ad hoc network (VANET) is a special form of mobile (MANET), which plays key role in the intelligent transportation system (ITS). Though many outstanding geographic routing protocols are designed for VANETs, majority them use parameters that only affect performance. In this article, we propose an intersection based on fuzzy multi-factor decision (IRFMFD), utilizes several features. The scheme divided into two parts, namely vehicular management and management. component, candidate...

10.3390/app10186613 article EN cc-by Applied Sciences 2020-09-22

Vehicular ad hoc network (VANET) is a special form of Mobile Ad Network (MANET), which plays key role in the Intelligent Transportation System (ITS). Though many outstanding geographic routing protocols are designed for VANETs, Most existing proposals only consider single factor, makes link easy to break. In this research, we propose Routing Protocol Based on Multi-factor Decision (RMFD), utilizes several features. The scheme divided into two parts, namely vehicular decision management and...

10.1109/icce-asia49877.2020.9277478 article EN 2022 IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia) 2020-11-01

Vehicles are highly mobile nodes; therefore, they frequently change their topology. To maintain a stable connection with the server in high-speed vehicular networks, handover process is restarted again to satisfy content requests. requested content, vehicular-content-centric network (VCCN) proposed. The proposed scheme adopts in-network caching instead of destination-based routing In this regard, various protocols have been increase communication efficiency VCCN. Despite disruptive links due...

10.3390/electronics10182270 article EN Electronics 2021-09-15

Multimodal hearing aids (HAs) aim to deliver more intelligible audio in noisy environments by contextually sensing and processing data the form of not only but also visual information (e.g. lip reading). Machine learning techniques can play a pivotal role for contextual multimodal data, however, due low computational power HA devices, must be processed either on edge or cloud which, turn, poses privacy concerns users' sensitive data. Existing literature proposes several encryption their...

10.1109/dsc54232.2022.9888823 article EN 2022-06-22

Load balancing and energy conservation techniques are one of the significant constraints in design wireless sensor network. Usually, clustering method helps networks utilization that results enhancing network lifetime. Moreover, various nodes multi-hop is near to base station drain their battery very quickly thus lead creating hot spot problem a To overcome such constraints, this paper proposes multilayer architecture for selection forwarding node, rotation cluster head, inter intra-cluster...

10.1145/3167132.3167459 article EN 2018-04-09

Internet of Things (IoT) notion gained a tremendous growth with the evolution smart things. Benefits IoT and expert attention has inspired various applications including home, city, etc. Although homes are widely accepted, still face challenges arise from platform incompatibilities heterogeneity devices. Consequently, Web (WoT) came into play as universal that exposes heterogeneous services devices via Web. Therefore, in this article, we propose WoT energy aware home management system...

10.1109/cse/euc.2019.00012 article EN 2019-08-01

Multimodal hearing aids (HAs) aim to deliver more intelligible audio in noisy environments by contextually sensing and processing data the form of not only but also visual information (e.g. lip reading). Machine learning techniques can play a pivotal role for multimodal data. However, since computational power HA devices is low, therefore this must be processed either on edge or cloud which, turn, poses privacy concerns sensitive user Existing literature proposes several encryption their...

10.48550/arxiv.2202.05662 preprint EN other-oa arXiv (Cornell University) 2022-01-01
Coming Soon ...