School of Engineering & Technology

Permanent URI for this collection

http://10.10.25.38:4000/handle/123456789/659

Browse

Browsing School of Engineering & Technology by Title

Now showing 1 - 20 of 99
  • Thumbnail Image
    Item
    An Amended Crow Search Algorithm for Hybrid Active Power Filter Design
    (2023-08) Ali, S; Bhargava, A; Saxena, A
    Hybrid Active Power Filter (HAPF) imbibes the advantages of both passive and active power filters. These filters are considered one of the important technologies for mitigating harmonic pollution in electrical systems. Accurate estimation of filter parameters is a key component to reduce harmonic pollution effectively. In recent years, several optimization approaches have been reported to solve this estimation problem; still, this area is worthy of further investigation. This paper is a proposal for an estimator that can estimate the parameter of HAPF configuration accurately. For evolving this estimator, first, an objective function that mathematically embeds filter parameters and harmonic pollution is presented. For handling the optimization process, an Amended Crow Search Algorithm (ACSA) is proposed. ACSA employs a local search algorithm (in the form of a pattern search) for obtaining optimal results. The analysis of the estimation process is carried out on two HAPF configurations. Various analyses that include harmonic pollution statistical analysis along with fitness function value analysis reveal that the proposed algorithm acquires optimal results as compared with other recently published and reported algorithms. Further, the proposed filter configurations are tested with the existing filter. The results prove that the proposed filter shows promising results.
  • Thumbnail Image
    Item
    An Amended Crow Search Algorithm for Hybrid Active Power Filter Design
    (2023-08) Ali, S; Bhargava, A; Saxena, A
    Hybrid Active Power Filter (HAPF) imbibes the advantages of both passive and active power filters. These filters are considered one of the important technologies for mitigating harmonic pollution in electrical systems. Accurate estimation of filter parameters is a key component to reduce harmonic pollution effectively. In recent years, several optimization approaches have been reported to solve this estimation problem; still, this area is worthy of further investigation. This paper is a proposal for an estimator that can estimate the parameter of HAPF configuration accurately. For evolving this estimator, first, an objective function that mathematically embeds filter parameters and harmonic pollution is presented. For handling the optimization process, an Amended Crow Search Algorithm (ACSA) is proposed. ACSA employs a local search algorithm (in the form of a pattern search) for obtaining optimal results. The analysis of the estimation process is carried out on two HAPF configurations. Various analyses that include harmonic pollution statistical analysis along with fitness function value analysis reveal that the proposed algorithm acquires optimal results as compared with other recently published and reported algorithms. Further, the proposed filter configurations are tested with the existing filter. The results prove that the proposed filter shows promising results.
  • Thumbnail Image
    Item
  • Thumbnail Image
    Item
    Areservoir computing approach for forecasting and regenerating both dynamical andtime-delay controlled financial system behavior
    (2021-02) Budhiraja, R; Kumar, M
    Significant research in reservoir computing over the past two decades has revived interest in recurrent neural networks. Owing to its ingrained capability of performing high-speed and low-cost computations this has become a panacea for multi-variate complex systems hav ing non-linearity within their relationships. Modelling economic and financial trends has always been achallenging task owing to their volatile nature and no linear dependence on associated influencers. Prior studies aimed at effectively forecasting such financial systems, but, always left a visible room for optimization in terms of cost, speed and modelling com plexities. Our work employs a reservoir computing approach complying to echo-state net work principles, along with varying strengths of time-delayed feedback to model a complex financial system. The derived model is demonstrated to act robustly towards influence of trends and other fluctuating parameters by effectively forecasting long-term system behav ior. Moreover, it also re-generates the financial system unknowns with a high degree of accuracy when only limited future data is available, thereby, becoming a reliable feeder for any long-term decision making or policy formulations.
  • Thumbnail Image
    Item
    Assessing risks and cloud readiness in PaaS environments
    (International Journal of Recent Technology and Engineering, 2019) Malik, Vinita; Singh, Sukhdip
    The cloud computing has utilization of pervasive or distributed models on demand access to highly configurable computing devices for fast provision and less management efforts. The complex architecture, multitenant and virtual environment in cloud infrastructure asks for risks identification and mitigation. The cloud computing model business needs reassurances so it’s prime consideration for testing the cloud services. This research primarily identifies various risks, threats, testing models and vulnerabilities in cloud computing environment. This research has implemented the risk assessment and cloud readiness for PaaS environment by scanning its code with a software vendor. The research makes an emphasis on risk minimization strategies and trust evaluation in cloud computing environment.
  • Thumbnail Image
    Item
    Asymmetric double-image encryption using twin decomposition in fractional Hartley domain
    (2022) Kumar, J; Singh, P; Yadav, AK
    Twin decomposition, consisting of equal and random modulus decompositions, not only makes a cryptosystem asymmetric but also resists special attack. A new double-image asymmetric crypto system using twin decomposition in fractional Hartley domain is proposed. An input grayscale image, bonded with another grayscale image as its phase mask, is transformed via fractional Hartley transform. Equal modulus decomposition is applied on the resulting image, giving us two inter mediate images. One of them is subjected to another fractional Hartley transform followed by ran dom modulus decomposition, whereas the other serves as the first private key. The application of random modulus decomposition also results in two images: encrypted image and the second private key. During the process of decryption, firstly the encrypted image is combined with second private key and thereafter it is subjected to inverse fractional Hartley transform. The resulting image is then combined with the first private key, and followed by another inverse fractional Hartley trans form, thus recovering the two original images. The proposed cryptosystem is validated for pairs of grayscale images.
  • Thumbnail Image
    Item
    Behavioral study of self-compacting concrete with wollastonite microfiber as part replacement of sand for pavement quality concrete (PQC)
    (2019-07) Jindal, A; Ransinchung R.N., G.D; Kumar, P
    The fact that self-compacting concrete (SCC) does not require any supplementary com paction to fill in every nook and corner of the structure without compromising with strength and durability makes it much more futuristic and desirable over conventional concrete. Present study highlights the behavioural changes in SCC for PQC applications at macro and micro levels with the incorporations of wollastonite micro-fiber; proposed to be used for restoration of deteriorated pavement quality concrete slab. Wollastonite micro-fiber was incorporated as part replacement of fine aggregates in proportions of 10–50% with an offset of 10%. Different properties of SCC mixes such as flow-ability, seg regation resistance and filling ability were investigated in fresh state while mechanical properties including compressive strength, flexural strength and hardened density were studied in hardened states. The SCC mixes were also investigated for estimating effect of incorporating wollastonite micro-fiber in hydrated states of cement mortar. Inclusions of wollastonite micro-fiber in SCC enhanced the cohesiveness of the mix thereby improving the density and reducing its water absorption. SCC mixes with wollastonite micro-fiber showed higher flexural and comparable compressive strength parameters than those of conventional SCC mix. SCC mix with 30% wollastonite micro-fiber as a replacement of fine aggregates provides similar strength and better repair prospects as compared to conven tional SCC or normal concrete mix.
  • Thumbnail Image
    Item
    Biogeography-based optimization of artificial neural network (BBO-ANN) for solar radiation forecasting
    (Applied Artificial Intelligence, 2023) Yahya, Umar; Bansal, Ajay Kumar; Aneja, Nagender; Dadheech, Pankaj; Sangtani, Virendra,Swaroop
    Renewable energy can help India’s economy and society. Solar energy is everywhere and can be used anywhere, making it popular. Solar energy’s drawbacks are weather and environmental dependencies and solar radiation variations. Solar Radiation Forecasting (SRF) reduces this drawback. SRF eliminates solar power generation variations, grid overvoltage, reverse current, and islanding. Short-term solar radiation forecasts improve photovoltaic (PV) power generation and grid connection. Previous promising SRF studies often fail to generalize to new data. A biogeography-based optimization artificial neural network (BBO-ANN) model for SRF is proposed in this work. 5-year and 6-year data are used to train and validate the model. The data was collected from India’s Jaipur Rajasthan weather station from 2014 to 2019. This work used biogeography- based optimization (BBO) to optimize and adjust the inertia weight of artificial neural networks (ANN) during training. The BBO-ANN model developed in this study had a Mean Absolute Percentage Error (MAPE) of 3.55%, which is promising compared to previous SRF studies. The BBO-ANN SRF model introduced in this work can generalize well to new data because it was able to produce equally accurate autumn and winter forecasts despite the great climatic variation that occurs during the summer and spring.
  • Thumbnail Image
    Item
  • Thumbnail Image
    Item
    CAQoE: A Novel No-Reference Context-aware Speech Quality Prediction Metric
    (2023-01) JAISWAL, RK; DUBEY, RK
    The quality of speech degrades while communicating over Voice over Internet Protocol applications, for exam ple, Google Meet, Microsoft Skype, and Apple FaceTime, due to different types of background noise present in the surroundings. It reduces human perceived Quality of Experience (QoE). Along this line, this article proposes a novel speech quality prediction metric that can meet human’s desired QoE level. Our motivation is driven by the lack of evidence showing speech quality metrics that can distinguish different noise degra dations before predicting the quality of speech. The quality of speech in noisy environments is improved by speech enhancement algorithms, and for measuring and monitoring the quality of speech, objective speech quality metrics are used. With the integration of these components, a novel no-reference context-aware QoE prediction metric (CAQoE) is proposed in this article, which initially identifies the context or noise type or degradation type of the input noisy speech signal and then predicts context-specific speech quality for that input speech signal. It will have of great importance in deciding the speech enhancement algorithms if the types of degradations causing poor speech quality are known along with the quality metric. Results demon strate that the proposed CAQoE metric outperforms in different contexts as compared to the metric where contexts are not identified before predicting the quality of speech, even in the presence of limited size speech corpus having different contexts available from the NOIZEUS speech database.
  • Thumbnail Image
    Item
    CAQoE: A Novel No-Reference Context-aware Speech Quality Prediction Metric
    (2023-01) JAISWAL, R; DUBEY, R
    The quality of speech degrades while communicating over Voice over Internet Protocol applications, for exam ple, Google Meet, Microsoft Skype, and Apple FaceTime, due to different types of background noise present in the surroundings. It reduces human perceived Quality of Experience (QoE). Along this line, this article proposes a novel speech quality prediction metric that can meet human’s desired QoE level. Our motivation is driven by the lack of evidence showing speech quality metrics that can distinguish different noise degra dations before predicting the quality of speech. The quality of speech in noisy environments is improved by speech enhancement algorithms, and for measuring and monitoring the quality of speech, objective speech quality metrics are used. With the integration of these components, a novel no-reference context-aware QoE prediction metric (CAQoE) is proposed in this article, which initially identifies the context or noise type or degradation type of the input noisy speech signal and then predicts context-specific speech quality for that input speech signal. It will have of great importance in deciding the speech enhancement algorithms if the types of degradations causing poor speech quality are known along with the quality metric. Results demon strate that the proposed CAQoE metric outperforms in different contexts as compared to the metric where contexts are not identified before predicting the quality of speech, even in the presence of limited size speech corpus having different contexts available from the NOIZEUS speech database.
  • Thumbnail Image
    Item
    Combining Forth and Rust: A Robust and Efficient Approach for Low-Level System Programming
    (2023-12) Gupta, P; Rahar, R; Yadav, R; Singh, A; Ramandeep; Kumar, S
    Rust is a modern programming language that addresses the drawbacks of earlier languages by providing features such as memory safety at compilation and high performance. Rust’s memory safety features include ownership and borrowing, which makes it an ideal choice for systems programming, where memory safety is critical. Forth is a stack-based programming language that is widely used for low-level system programming due to its simplicity and ease of use. This research paper aims to explore the combination of Forth and Rust programming languages to create a more robust and efficient solution for low-level system programming. The primary objective is to demonstrate the implementation of essential Forth operations, including addition, subtraction, assignment, comparison, and if-else statements, while demonstrating loops, push operations, and dump operations in Rust. The implementation of these operations in Rust is demonstrated using code from actual implementation. This research paper also discusses the advantages of using Rust for low-level system programming. Rust’s memory safety features, coupled with its high performance, make it an ideal choice for systems programming, where memory safety and performance are critical. The combination of Forth and Rust provides a more efficient and safer solution for low-level system programming, making the implementation more robust. Our implementation tries to leverage these properties of both languages to make a memory-safe and low-level system programming language. This research paper also includes code snippets to provide a practical demonstration of how the Forth operations can be implemented in Rust.
  • Thumbnail Image
    Item
    Combining Forth and Rust: A Robust and Efficient Approach for Low-Level System Programming †
    (2023-12) Gupta, P; Rahar, R; Yadav, R; Singh, A
    Abstract: Rust is a modern programming language that addresses the drawbacks of earlier languages by providing features such as memory safety at compilation and high performance. Rust’s memory safety features include ownership and borrowing, which makes it an ideal choice for systems programming, where memory safety is critical. Forth is a stack-based programming language that is widely used for low-level system programming due to its simplicity and ease of use. This research paper aims to explore the combination of Forth and Rust programming languages to create a more robust and efficient solution for low-level system programming. The primary objective is to demonstrate the implementation of essential Forth operations, including addition, subtraction, assignment, comparison, and if-else statements, while demonstrating loops, push operations, and dump operations in Rust. The implementation of these operations in Rust is demonstrated using code from actual implementation. This research paper also discusses the advantages of using Rust for low-level system programming. Rust’s memory safety features, coupled with its high performance, make it an ideal choice for systems programming, where memory safety and performance are critical. The combination of Forth and Rust provides a more efficient and safer solution for low-level system programming, making the implementation more robust. Our implementation tries to leverage these properties of both languages to make a memory-safe and low-level system programming language. This research paper also includes code snippets to provide a practical demonstration of how the Forth operations can be implemented in Rust.
  • Thumbnail Image
    Item
    A critical review on techno-economic analysis of hybrid renewable energy resources-based microgrids
    (2023) Manas, M; Sharma, S; Reddy, K; Srivastava, A
    Now that the population is growing, the expenditure on basic needs of life is also increasing due to a lack of or less availability of resources. The economy con sumed electricity is reaching peaks as its main fuel, coal, is decreasing day by day. Due to this, 90% of the population who are in the middle class, lower middle class, or rural areas are economically poor and are unable to bear the prices. To overcome the fnancial problems, many researchers have prepared various types of microgrids that generate electricity from various types of fow resources, like hydro, solar, biogas, and air current power stations, whose system is called a compound fow power system. This paper gives a combined review of various research papers that discuss some case studies and some research on various models designed on software like HOMER Pro, how microgrids become economic barriers, optimal power supply solutions with CFPS, distributed and centralized microgrid components, the technical and economic feasibility of EV charging stations, and the analysis of various combina tions of power systems at various locations like Bangladesh, Canada, the Republic of Djibouti, China, Indonesia, Sierra Leone, some rural sites in India, and some devel oping countries. This overview provides a glimpse into the various aspects of CFPS, including fusion approaches, techno-economic analysis, simulation platforms, storage technologies, design specifcations, unit sizing methodologies, and control techniques. Further research and analysis in these areas are needed to explore their applications and advancements in CFPS development. The main reason for the study is to analyze and bring various ideas and models of various researchers together on a common platform and make a combined conceptual framework for further proceedings.
  • Thumbnail Image
    Item
    Cross-Silo, Privacy-Preserving, and Lightweight Federated Multimodal System for the Identification of Major Depressive Disorder Using Audio and Electroencephalogram
    (2023-12) Gupta, C; Khullar, V; Goyal, N; Saini, K; Baniwal, R; Kumar, S; Rastogi, R
    In this day and age, depression is still one of the biggest problems in the world. If left untreated, it can lead to suicidal thoughts and attempts. There is a need for proper diagnoses of Major Depressive Disorder (MDD) and evaluation of the early stages to stop the side effects. Early detection is critical to identify a variety of serious conditions. In order to provide safe and effective protection to MDD patients, it is crucial to automate diagnoses and make decision-making tools widely available. Although there are various classification systems for the diagnosis of MDD, no reliable, secure method that meets these requirements has been established to date. In this paper, a federated deep learning based multimodal system for MDD classification using electroencephalography (EEG) and audio datasets is presented while meeting data privacy requirements. The performance of the federated learning (FL) model was tested on independent and identically distributed (IID) and non-IID data. The study began by extracting features from several pre-trained models and ultimately decided to use bidirectional short-term memory (Bi-LSTM) as the base model, as it had the highest validation accuracy of 91% compared to a convolutional neural network and LSTM with 85% and 89% validation accuracy on audio data, respectively. The Bi-LSTM model also achieved a validation accuracy of 98.9% for EEG data. The FL method was then used to perform experiments on IID and non-IID datasets. The FL-based multimodal model achieved an exceptional training and validation accuracy of 99.9% when trained and evaluated on both IID and non-IIID datasets. These results show that the FL multimodal system performs almost as well as the Bi-LSTM multimodal system and emphasize its suitability for processing IID and non-IIID data. Several clients were found to perform better than conventional pre-trained models in a multimodal framework for federated learning using EEG and audio datasets. The proposed framework stands out from other classification techniques for MDD due to its special features, such as multimodality and data privacy for edge machines with limited resources. Due to these additional features, the framework concept is the most suitable alternative approach for the early classification of MDD patients.
  • Thumbnail Image
    Item
    Cross-Silo, Privacy-Preserving, and Lightweight Federated Multimodal System for the Identification of Major Depressive Disorder Using Audio and Electroencephalogram
    (2023-12) Gupta, C; Khullar, V; Goyal, N
    In this day and age, depression is still one of the biggest problems in the world. If left untreated, it can lead to suicidal thoughts and attempts. There is a need for proper diagnoses of Major Depressive Disorder (MDD) and evaluation of the early stages to stop the side effects. Early detection is critical to identify a variety of serious conditions. In order to provide safe and effective protection to MDD patients, it is crucial to automate diagnoses and make decision-making tools widely available. Although there are various classification systems for the diagnosis of MDD, no reliable, secure method that meets these requirements has been established to date. In this paper, a federated deep learning based multimodal system for MDD classification using electroencephalography (EEG) and audio datasets is presented while meeting data privacy requirements. The performance of the federated learning (FL) model was tested on independent and identically distributed (IID) and non-IID data. The study began by extracting features from several pre-trained models and ultimately decided to use bidirectional short-term memory (Bi-LSTM) as the base model, as it had the highest validation accuracy of 91% compared to a convolutional neural network and LSTM with 85% and 89% validation accuracy on audio data, respectively. The Bi-LSTM model also achieved a validation accuracy of 98.9% for EEG data. The FL method was then used to perform experiments on IID and non-IID datasets. The FL-based multimodal model achieved an exceptional training and validation accuracy of 99.9% when trained and evaluated on both IID and non-IIID datasets. These results show that the FL multimodal system performs almost as well as the Bi-LSTM multimodal system and emphasize its suitability for processing IID and non-IIID data. Several clients were found to perform better than conventional pre-trained models in a multimodal framework for federated learning using EEG and audio datasets. The proposed framework stands out from other classification techniques for MDD due to its special features, such as multimodality and data privacy for edge machines with limited resources. Due to these additional features, the framework concept is the most suitable alternative approach for the early classification of MDD patients.
  • No Thumbnail Available
    Item
    Current trends in microplastic removal using biodegradation approaches and advancement A review
    (2026) Kumar, Dhushyant
    Due to improper disposal and mismanagement of plastic waste, plastic converted into microplastic when exposed to the environment causes tremendous burdens to nature. It becomes the most persistent pollutant in air, water, and land environments due to the inert property of plastic. It enters the environment from various sources, such as industrial, household, and agricultural waste, affecting the lives of humans, other living beings, and the entire ecosystem. Much research and experimentation have been conducted to eliminate microplastics from the envi ronment with the help of conventional methods, such as physical, chemical, and biological, which remove microplastics but are inefficient in eliminating them from the environment. Some processes are good for nature and the environment, as they can cause secondary pollution. Therefore, there is a need for some scientifically proven new methods to achieve the required level of results and be environmentally friendly. Bioremediation is a sound technique used to degrade plastic with the help of bacteria, fungi, algae, and insects. However, some studies reveal that the pretreatment (UV, thermal, chemical, and physical) can change the inert property of plastic, making it more available to the microbes and increasing the biodegradation process without affecting the microbes’ life. Such a treatment gives hope for removing plastic from the environment in an efficient way.
  • No Thumbnail Available
    Item
    Deep learning approaches to address cold start and long tail challenges in recommendation systems: a systematic review
    (2025) Jangid, Manisha
    Recommendation systems (RS) have become prevalent across different domains includ ing music, e-commerce, e-learning, entertainment, and social media to address the issue of information overload. While traditional RS approaches have achieved significant success in delivering recommendations, they still face issues including sparse data, diversity, cold start, and long tail problem. The emergence of deep learning as a prominent and exten sively studied topic has shown significant potential in addressing these challenges in RS. Deep learning captures intricate patterns of interaction and precisely reflects user prefer ences, allowing for encoding complex abstractions in data representation and enhancing information processing capabilities. This paper provides an extensive survey of the existing literature on recommendation systems. We will begin by providing a foundational under standing of the core concepts and terminology of recommendation systems and signifi cance of deep learning. Secondly, we talk about the original studies being conducted on deep learning methods and solutions to address “Cold start and long tail” challenges in recommendation. Thirdly, we examine the potential future directions of research pertain ing to deep learning-based recommender systems (DLRS). Our review provides valuable insights for both researchers and practitioners in using deep learning to address challenges in recommendation and in developing effective and efficient recommendation systems.
  • No Thumbnail Available
    Item
    Deep Learning for Monitoring and Managing Oil Spill in Underwater Sensor Networks: Enabling Technologies
    (2026) Goyal, Nitin
    Environmental problems can significantly impact people’s lives and must be addressed. The oil spill is one of the biggest applications of underwater wireless sensor networks (UWSNs) that threaten aquatic life, so it is essential to focus on it. Oil spill count has risen in recent years because of the rise in shipping and marine transportation industries. Timely and accurate detection of oil spills can improve the response process and get the necessary resources to the affected areas more efficiently. This work was motivated by the fact that oil spill detection is critical to maritime protection. Since oil spill detection is a complex process, it faces various challenges. One of the biggest challenges is similar visual appearance which makes it difficult to identify an oil spill and a similar oil slick in synthetic aperture radar (SAR) imagery. Various radar images are frequently utilized for this purpose. Despite being widely used for earth observation, SAR images have noisy and illegible image quality, which makes classification challenging. Previously, detecting and classifying SAR images required manual involvement, which made the process time consuming. Therefore, researchers focused on automating such tasks by incorporating deep learning (DL) techniques. Numerous papers proposed the applications of DL in various radar images for oil spill monitoring but faced multiple problems. This study aims to thoroughly investigate oil spills and their detection techniques, utilizing DL techniques applied to various radar images. These studies have originated in diverse nations with distinct environments. However, compared to other types of radar images, synthetic aperture radar (SAR) images are more effective in pinpointing the location of oil spills. However, they are also rather complex.
  • Thumbnail Image
    Item
    Design and Performance Analysis of ISFET using various Oxide Materials for Biosensing Applications
    (2024) Majji, S; Dash, C; Rani, D; Bhukya, M; Panigrahy, A
    The healthcare industry is always changing because of technological breakthroughs that spur new methods of diagnosing and treating illnesses. This study investigates the development of Ion Sensitive Field Effect Transistor (ISFET) sensors for DNA based blood cancer diagnosis. This work presents the design of a two-dimensional ion-sensitive field-effect transistor. Concentration fluctuations and transfer characteristics with different oxides are studied using blood from two electrolyte solutions. It is possible to evaluate how the modeled device can be utilized as a pH sensor or a biosensor in healthcare applications by looking at how the pH changes for different oxides. Additionally, several oxides were examined in the simulated ISFET devices' output characteristics. Blood is used as the electrolyte to study the device's sensitivity for different oxides. When pH 7.4 is considered, SiO2 oxide is significantly more sensitive than other oxides. The resulting 2D-ISFET exhibits remarkable blood electrolyte sensitivity and holds potential as a quick detection tool for blood cancer. The results show that the ISFET possesses drain-induced barrier lowering (DIBL), greater ON-current (ION) and switching ratio (ION/IOFF), and decreased subthreshold swing (SS). The pH sensor's sensitivity and the suggested equipment can detect up to 30 fg/mL of blood cancer biomarkers. An important development in technology-driven healthcare is the emergence of DNA-based blood cancer detection utilizing ISFET sensors. This opens up new avenues for improving cancer diagnosis and patient outcomes.