Browse Items (5511 total)
Sort by:
-
A Novel Paradigm for IoT Security: ResNet-GRU Model Revolutionizes Botnet Attack Detection
The rapid proliferation of the Internet of Things (IoT) has engendered substantial security apprehensions, chiefly due to the emergence of botnet attacks. This research study delves into the realm of Intrusion Detection Systems (IDS) by leveraging the IoT23 dataset, with a specific emphasis on the intricate domain of IoT at the network's edge. The evolution of edge computing underscores the exigency for tailored security solutions. An array of statistical methodologies, encompassing ANOVA, Kruskal-Wallis, and Friedman tests, is systematically employed to illuminate the evolving trends across multiple facets of the study. Given the intricacies entailed in feature selection within edge environments, Chi-square analyses, Recursive Feature Elimination (RFE), and Lasso-based techniques are strategically harnessed to unearth meaningful feature subsets. A meticulous evaluation encompassing 19 classifiers, meticulously selected from both machine learning (ML) and deep learning (DL) paradigms, is rigorously conducted. Initial findings underscore the potential of the Gated Recurrent Unit (GRU) model, especially when coupled with intrinsic lasso-based feature selection. This promising outcome catalyzes the formulation of an ensemble approach that harnesses multiple LassoCV models, aimed at amplifying feature selection proficiency. Furthermore, an optimized ResNet-GRU model emerges from the fusion of the GRU and ResNet architectures, with the objective of augmenting classification performance. In response to mounting concerns regarding data privacy at the edge, a resilient federated learning ecosystem is meticulously crafted. The seamless integration of the optimized ResNet-GRU model into this framework facilitates the employment of FedAvg, a widely acclaimed federated learning methodology, to adeptly navigate the intricacies associated with data sharing challenges. A comprehensive performance evaluation is undertaken, wherein the ResNet-GRU model is benchmarked against FedAvg and a diverse array of other federated learning algorithms, including FedProx and Fed+. This extensive comparative analysis encompasses a spectrum of performance metrics and processing time benchmarks, shedding comprehensive light on the capabilities of the model. (2023), (Science and Information Organization). All Rights Reserved. -
LiST: A Lightweight Framework for Continuous Indian Sign Language Translation
Sign language is a natural, structured, and complete form of communication to exchange information. Non-verbal communicators, also referred to as hearing impaired and hard of hearing (HI&HH), consider sign language an elemental mode of communication to convey information. As this language is less familiar among a large percentage of the human population, an automatic sign language translator that can act as an interpreter and remove the language barrier is mandatory. The advent of deep learning has resulted in the availability of several sign language translation (SLT) models. However, SLT models are complex, resulting in increased latency in language translation. Furthermore, SLT models consider only hand gestures for further processing, which might lead to the misinterpretation of ambiguous sign language words. In this paper, we propose a lightweight SLT framework, LiST (Lightweight Sign language Translation), that simultaneously considers multiple modalities, such as hand gestures, facial expressions, and hand orientation, from an Indian sign video. The Inception V3 architecture handles the features associated with different signer modalities, resulting in the generation of a feature map, which is processed by a two-layered (long short-term memory) (LSTM) architecture. This sequence helps in sentence-by-sentence recognition and in the translation of sign language into text and audio. The model was tested with continuous Indian Sign Language (ISL) sentences taken from the INCLUDE dataset. The experimental results show that the LiST framework achieved a high translation accuracy of 91.2% and a prediction accuracy of 95.9% while maintaining a low word-level translation error compared to other existing models. 2023 by the authors. -
A Study on Indian Foriegn Exchange Market Efficiency - Application of Random Walk Hypothesis
International Journal of Research in Computer Application & Management Vol. 2, Issue 10, pp. 138-142, ISSN No. 2231-1009 -
The nexus between demogaphics and investment behaviour /
Asian Journal Management, Vol.8, Issue 2, pp.361-369, ISSN: 2321-5763 (Online) 0976-495X (Print). -
Financial behavior of IT professionals: A case study of Bengaluru city /
Al-Barkaat Journal of Finance & Management, Vol.8, Issue 2, pp.19-31, ISSN: 0974-7281 (Print), 2229-4503 (Online). -
Saving and investment behaviour of information technology professionals - An empirical analysis /
Asian Journal Of Research In Business Economics And Management, Vol.7, Issue 6, pp.71-91, ISSN: 2249-7307. -
An empirical analysis of price discovery in spot and futures market of gold in India /
Pacific Business Review International, Vol.7, Issue 10, pp.80-88 -
Integrating machine learning techniques for Air Quality Index forecasting and insights from pollutant-meteorological dynamics in sustainable urban environments
Air pollution poses a significant environmental and health challenge in Delhi, India. This research focuses on predicting the Air Quality Index (AQI) for Delhi utilizing machine learning techniques. The research methodology encompasses comprehensive steps such as data collection, preprocessing, analysis, and modeling. Data comprising various pollutants and meteorological parameters were gathered from the Central Pollution Control Board (CPCB) spanning from January 1, 2016, to December 30, 2022. Missing values were imputed using the IterativeImputer method with RandomForestRegressor as the estimator. Data normalization and variance reduction were achieved through Box-Cox transformation. Spearman Rank Correlation analysis was employed to explore relationships between features and AQI. Initial evaluation of nine machine learning algorithms identified Random Forest and XGBoost as the top performers based on accuracy. These algorithms were further optimized using 5-fold cross-validation with RandomizedSearchCV. The results demonstrated the efficacy of both algorithms in AQI prediction. Notably, PM2.5 and CO concentrations emerged are most influential features, highlighting the potential for AQI improvement in Delhi through the reduction of these pollutants. This research distinguishes itself through a meticulous examination of the complex interconnections between pollutants and AQI, providing invaluable insights to inform targeted interventions and enduring policies geared towards improving air quality in Delhi. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024. -
pH-indicator based on delignified jute fiber and red cabbage anthocyanins for monitoring fish spoilage using a smartphone application
Halochromic materials that show visible color changes in response to changes in pH are suitable for the real-time monitoring of fish spoilage. In this study, an easy-to-use, simple, inexpensive, and non-toxic fish freshness indicator was fabricated by combining delignified jute (Corchorus olitorius) fibers and anthocyanins (halochromic materials) from red cabbage (DFA: Delignified jute fibers incorporated with anthocyanins). A single-step decolorization/delignification using solar irradiation along with NaOH and H2O2 treatment was used for modifying the jute fibers. This method helps to overcome the self-color, mitigates the lack of affinity of jute fibers towards anthocyanins and preserves the lignin so that the strength of the fiber is not impacted. A smartphone-based color analysis was used for real-time fish quality monitoring using DFA. To the best of our knowledge, there are no reports on the use of jute fibers as substrates to incorporate anthocyanins for food spoilage monitoring. The indicator displayed an observable color response to the pH and varying concentrations of amine compounds. During the storage of fish (mackerel), the colorimetric indicator showed a visible color change from pink (for fresh fish) to blue (for spoiling fish) and then to green (for spoiled fish), corresponding to changes in pH and total volatile basic nitrogen. To offer a straightforward quantitative assessment of color changes, we utilized the freely available Android application Color Grab to measure the color using RGB and L*, a*, and b* indices. The DFA indicator providing naked-eye analysis has the potential to be an effective tool for real-time monitoring of on-site food spoilage by non-specialized personnel in resource-limited areas. 2024 Elsevier B.V. -
Multifunctional electrospun membranes incorporated with metal oxide nanoparticles, cellulose acetate, and polyvinylpyrrolidone for wastewater treatment: Oil/water separation, dye adsorption, and dye degradation
Multifunctional membranes have gained considerable attention as useful materials for the treatment of complex wastewater that contains dye and oil substances. Electrospun nanofiber membranes (ENM) have substantial advantages and potential for complex wastewater remediation, owing to their unique properties. In this study, an environmentally compatible ENM is fabricated by incorporating photocatalytic metal oxide nanoparticles of zinc oxide (ZnO) or silver-zinc Oxide (Ag-ZnO) into cellulose acetate (CA)/polyvinylpyrrolidone (PVP) nanofibers using electrospinning. Composite membranes ZnO/CA/PVP, Ag-ZnO/CA/PVP, ZnO/DCA/PVP (DCA: deacetylated cellulose acetate), and Ag-ZnO/DCA/PVP (deacetylated) were employed for oilwater emulsion separation, owing to their superhydrophilic and underwater superoleophobic nature, photocatalytic dye degradation due to the presence of ZnO or Ag-ZnO, and dye adsorption resulting from their high surface area. The composite membranes showed more than 95% efficiency for oil/water separation, malachite green adsorption, and photocatalytic methylene blue degradation. These membranes displayed simultaneous oilwater and dye separation efficiency, as well as antibacterial properties. The membrane we present here provides a simple and effective platform for wastewater remediation with a low energy consumption. 2024 Elsevier B.V. -
Deep learning based model for computing percentage of fake in user reviews using topic modelling techniques
Sentiment analysis plays a vital role in real time environment for knowing the history of a product or any other specific entity. Due to large number of users in the www, chances are there that many fake users may upload the fake reviews to damage the business for the sake of money. Identifying the fake reviews or percentage of fake content in the review is yet a challenging task. In this paper, an attempt has been made to find the percentage of fake in the review data. Two methodologies are combined to address this issue. Concept of spelling checking, topic modelling and deep learning for context extraction is extensively used to build the effective model. Proposed technique is exhaustively checked for efficiency with many trails of experiments. Also, the training and testing samples were shuffled for experimentation. The results of the models show its goodness. The details of the results can be found at experiments section. 2024 The Author(s) -
Analysis of value and growth styles of investing : A study on nifty 100 index stocks of NSE /
Asian Journal Of Research In Business Economics And Management, Vol.7, Issue 5, pp.165-177, ISSN: 2249-7307. -
Dynamics of Indian stock market integration with global stock markets /
Asian Journal Of Management, Vol.8, Issue 3, pp.559-568, ISSN: 2321-5763 (Online) 0976-9495X (Print). -
Statistical features from frame aggregation and differences for human gait recognition
Human gait recognition, an alternate biometric technique, received significant attention in the last decade. As many gait recognition applications require real-time response, the primary concern is to design efficient and straightforward gait features for human recognition. In this work, two novel gait features are proposed. Both features are designed by exploring the dynamic variations of different body parts during a gait cycle. The first feature set is based on one-against-all gait frame differences for person identification. This novel approach divides each frame in a gait cycle to blocks, compute the block sum, and then find the difference of respective block sum between the first frame and the rest. The second feature set is defined on the first-order statistics of the normalized sum of the frames in a cycle. Two other existing features- Centroid of Silhouette frames and feature values defined on Change Energy Images are also considered. Feature level fusion is realized by considering the different combinations of the four types of features. Experiments carried out with the CASIA Gait Dataset B demonstrated the proposals merit with high recognition accuracy. The outcome of the investigations is promising when compared to recent contributions. 2021, The Author(s), under exclusive licence to Springer Science+Business Media, LLC part of Springer Nature. -
Design, synthesis, single-crystal X-ray and docking studies of imidazopyridine analogues as potent anti-TB agents
With the intent to discover new anti-TB compounds, new imidazopyridine analogues were synthesized through Schiff-base reaction. The newly developed imidazopyridines (I1-I8) were characterized using spectroscopic and elemental analysis. In addition the structure of compound I3 was elucidated by the single crystal X-ray diffraction technique. The global chemical reactivity descriptor parameter was calculated using theoretically DFT-B3LYP-631G(d) basis set which estimated HOMO-LUMO value and results are discussed. All the newly synthesized compounds were screened for their in vitro anti-tubercular activity, while the most active compounds were subjected to a cytotoxicity assay on Vero cell lines. Most of the tested compounds exhibited significant anti-TB activity with MIC in the range 3.12 12.5 ?g/mL. Among the synthesized, compound I2 and I7 were found to be more active than the standard anti-TB drug streptomycin and comparable activity to pyrazinamide. A cytotoxicity study on Vero-cell lines confirmed the nontoxic nature of compound I2 and I7 indicating good safety profile. The molecular docking studies on PDB IB: 4ED4 enzyme of Mycobacterium tuberculosis was conducted to investigate mechanisms of anti-TB activity. The compounds displayed excellent hydrogen binding interactions and docking scores against MTB, which were in accordance with the results and further supported its credibility. 2023 -
Surveillance system based on raspberry pi for monitoring a location through a mobile device /
International Journals of Advanced Multidisciplinary Research, Vol.2, Issue 3, pp.75-79, ISSN No: 2393-8870. -
Relationship Between Socio-Cultural Environment and Creativity of Secondary School Pupils of Bengarpet Taluk
Indian Streams Research Journal Vol. 2, Issue 9, PP. 138-142, ISSN No. 2230-7850 -
Integrated Effect of Flow Field Misalignment and Gas Diffusion Layer Compression/Intrusion on High Temperature - Polymer Electrolyte Membrane Fuel Cell Performance
Misalignment in the flow field plates of High-Temperature Polymer Electrolyte Membrane Fuel Cell (HT-PEMFC) due to manufacturing tolerances, assembly process, or unavoidable vibration during the cell operation is contemplated its performance and durability. This study investigates the effect of flow field plate misalignment and its concomitant impact with varying the clamping pressures on HT-PEMFC operation. The study considers six degrees of cathode flow field misalignment, varying from 0% to 100% with respect to the anode flow field. Clamping pressures ranging from 1 to 2 MPa are applied to the various cases of misalignment to study their effect on GDL deformation and intrusion into the channels. The structural analysis shows that as the misalignment increases from 0 to 100%, the GDL compression increases from 26.72% to 37.75% for 1 MPa, 40.07% to 56.63% for 1.5 MPa, and 53.43% to 75.51% for 2 MPa, owing to the increase in compression approximately by 41% from their base cases and it is also crucial to note that GDL compression exaggerates at higher clamping pressures. The misalignment results in the sagging of Membrane Electrode Assembly (MEA), and the amplitude of wave nature is proportional to the degree of misalignment and clamping pressure, indicating the misalignment is the sole factor for structural changes. As a result, considerable variance in current distribution and average value is observed, i.e., at operating voltage 0.5 V, the current density drops from 4472.7 to 4264.4, 4420.7 to 4211.8, and 4374.1 to 4161.3 A m?2 from cases 1 to 6 for clamping pressures 1, 1.5, and 2 MPa, respectively, resulting in a 4.7% loss in performance. According to the observations, a misalignment of 60% is tolerable, with minimal performance loss and negligible non-uniformity in cell distributions. 2022 The Electrochemical Society (ECS). Published on behalf of ECS by IOP Publishing Limited. -
Biogenic synthesis of g-C3N4/Bi2O3 heterojunction with enhanced photocatalytic activity and statistical optimization of reaction parameters /
Applied Surface Science, Vol.494, pp.465-476, ISSN No: 0169-4332. -
Zone based relative density feature extraction algorithm for unconstrained handwritten numeral recognition /
Journal of Theoretical and Applied Information Technology, Vol.64, Issue 1, pp.304-314, ISSN No: 1992-8645 (Print), 1817-3195 (Online)