Explore the vast range of titles available.

Accurate building energy prediction is useful in various applications starting from building energy automation and management to optimal storage control. However, vulnerabilities should be considered when designing building energy prediction models, as intelligent attackers can deliberately influence the model performance using sophisticated attack models. These may consequently degrade the prediction accuracy, which may affect the efficiency and performance of the building energy management systems. In this paper, we investigate the impact of bi-level poisoning attacks on regression models of energy usage obtained from household appliances. Furthermore, an effective countermeasure against the poisoning attacks on the prediction model is proposed in this paper. Attacks and defenses are evaluated on a benchmark dataset. Experimental results show that an intelligent cyber-attacker can poison the prediction model to manipulate the decision. However, our proposed solution successfully ensures defense against such poisoning attacks effectively compared to other benchmark techniques.

Early diagnosis of rice disease is important because it poses a considerable threat to agricultural productivity as well as the global food security of the world. It is challenging to obtain more reliable outcomes based on the percentage of RGB value using image processing outcomes for rice disease detections and classifications in the agricultural field. Machine learning, especially with a Convolutional Neural Network (CNN), is a great tool to overcome this problem. But the utilization of deep learning techniques often necessitates high-performance computing devices, costly GPUs and extensive machine infrastructure. As a result, this significantly raises the overall expenses for users. Therefore, the demand for smaller CNN models becomes particularly pronounced, especially in embedded systems, robotics and mobile applications. These domains require real-time performance and minimal computational overhead, making smaller CNN models highly desirable due to their lower computational cost. This paper introduces a novel CNN architecture which is comparatively small in size and promising in performance to predict rice leaf disease with moderate accuracy and lower time complexity. The CNN network is trained with processed images. The image processing is performed using segmentation and k-means clustering to remove background and green parts of affected images. This technique proposes to detect rice disease of rice brown spot, rice bacterial blight and leaf smut with reliable outcomes in disease classifications. The model is trained using an augmented dataset of 2700 images (60% data) and validated with 1200 images of disease-affected samples to identify rice disease in agricultural fields. The model is tested with 630 images (14% data); testing accuracy is 97.9%. The model is exported into a mobile application to introduce the real-life application of the outcome of this work. The model accuracy is compared to others work associated with this type of problem. It is found that the performance of the model and the application are satisfactory compared to other works related to this work. The over-all accuracy is notable, showing the reliability and dependability of this model to classify rice leaf diseases.

The Bay of Bengal, the world's largest bay, is bordered by populous countries and rich in resources like fisheries, oil, gas, and minerals, while also hosting diverse marine ecosystems such as coral reefs, mangroves, and seagrass beds; regrettably, its microbial diversity and ecological significance have received limited research attention. Here, we present amplicon (16S and 18S) profiling and shotgun metagenomics data regarding microbial communities from BoB’s eastern coast, viz., Saint Martin and Cox’s Bazar, Bangladesh. From the 16S barcoding data, Proteobacteria appeared to be the dominant phylum in both locations, with Alteromonas , Methylophaga , Anaerospora , Marivita , and Vibrio dominating in Cox’s Bazar and Pseudoalteromonas , Nautella , Marinomonas , Vibrio , and Alteromonas dominating the Saint Martin site. From the 18S barcoding data, Ochrophyta, Chlorophyta, and Protalveolata appeared among the most abundant eukaryotic divisions in both locations, with significantly higher abundance of Choanoflagellida, Florideophycidae, and Dinoflagellata in Cox’s Bazar. The shotgun sequencing data reveals that in both locations, Alteromonas is the most prevalent bacterial genus, closely paralleling the dominance observed in the metabarcoding data, with Methylophaga in Cox’s Bazar and Vibrio in Saint Martin. Functional annotations revealed that the microbial communities in these samples harbor genes for biofilm formation, quorum sensing, xenobiotics degradation, antimicrobial resistance, and a variety of other processes. Together, these results provide the first molecular insight into the functional and phylogenetic diversity of microbes along the BoB coast of Bangladesh. This baseline understanding of microbial community structure and functional potential will be critical for assessing impacts of climate change, pollution, and other anthropogenic disturbances on this ecologically and economically vital bay.

Protein secondary structure is an immense achievement of bioinformatics. It's an amino acid residue in a polypeptide backbone. In this paper, an innovative method has been proposed for predicting protein secondary structures based on 3-state protein secondary structure by neural network architecture with simple positioning algorithm (SIMPA) technique. Q3 (3-state prediction of protein secondary structure) is a fundamental methodology for our approach. Initially, the prediction of the secondary structure of the protein using the Q3 prediction method has been done. For this, a model has been built from its primary structure. Then it will retrieve the percentage of amino acid sequences from the original sequence to the accuracy of the predicted sequence. Utilizing the SIMPA technique from the 3-state secondary structure predicted sequence, the percentage of dissimilar residues of the three types (α-helix, β-sheet and coil) of Q3 has been extracted. Then the verification of the Q3 predicted accuracy through the SIMPA technique was done. Finally using a new method of neural network, it is verified that the Q3 prediction method gives good results from the neural network approach.

Background and Aims Since the beginning of the SARS‐CoV‐2 pandemic, multiple new variants have emerged posing an increased risk to global public health. This study aimed to investigate SARS‐CoV‐2 variants, their temporal dynamics, infection rate (IFR) and case fatality rate (CFR) in Bangladesh by analyzing the published genomes. Methods We retrieved 6610 complete whole genome sequences of the SARS‐CoV‐2 from the GISAID (Global Initiative on Sharing all Influenza Data) platform from March 2020 to October 2022, and performed different in‐silico bioinformatics analyses. The clade and Pango lineages were assigned by using Nextclade v2.8.1. SARS‐CoV‐2 infections and fatality data were collected from the Institute of Epidemiology Disease Control and Research (IEDCR), Bangladesh. The average IFR was calculated from the monthly COVID‐19 cases and population size while average CFR was calculated from the number of monthly deaths and number of confirmed COVID‐19 cases. Results SARS‐CoV‐2 first emerged in Bangladesh on March 3, 2020 and created three pandemic waves so far. The phylogenetic analysis revealed multiple introductions of SARS‐CoV‐2 variant(s) into Bangladesh with at least 22 Nextstrain clades and 107 Pangolin lineages with respect to the SARS‐CoV‐2 reference genome of Wuhan/Hu‐1/2019. The Delta variant was detected as the most predominant (48.06%) variant followed by Omicron (27.88%), Beta (7.65%), Alpha (1.56%), Eta (0.33%) and Gamma (0.03%) variant. The overall IFR and CFR from circulating variants were 13.59% and 1.45%, respectively. A time‐dependent monthly analysis showed significant variations in the IFR (p = 0.012, Kruskal–Wallis test) and CFR (p = 0.032, Kruskal–Wallis test) throughout the study period. We found the highest IFR (14.35%) in 2020 while Delta (20A) and Beta (20H) variants were circulating in Bangladesh. Remarkably, the highest CFR (1.91%) from SARS‐CoV‐2 variants was recorded in 2021. Conclusion Our findings highlight the importance of genomic surveillance for careful monitoring of variants of concern emergence to interpret correctly their relative IFR and CFR, and thus, for implementation of strengthened public health and social measures to control the spread of the virus. Furthermore, the results of the present study may provide important context for sequence‐based inference in SARS‐CoV‐2 variant(s) evolution and clinical epidemiology beyond Bangladesh.

This is the age of information. Now-a-days everyone communicates with each other by means of digital systems. Humans are always communicating with each other on the go. On-demand broadcasting is an efficient way to broadcast information according to user requests. In an on-demand broadcasting network, anyone can satisfy multiple clients in one broadcast which helps to fulfill the enormous demand of information by clients. The optimized flow of digital data in a network through the transmission of digital evidence about messages is called network coding. The “digital evidence” is composed of two or more messages. Network coding incorporated with data scheduling algorithms can further improve the performance of on-demand broadcasting networks. Using network coding, anyone can broadcast multiple data items using single broadcast strategy which can satisfy the needs of more clients. In this work, it is described that network coding cannot always maintain its superiority over non-network coding when the system handles different sized data items. However, the causes of performance reduction on network coding have been analyzed and THETA based dynamic threshold value integration strategy has been proposed through which the network coding can overcome its limitation for handling heterogeneous data items. In the proposed strategy, THETA based dynamic threshold will control which data item will be selected from the Client Relationship graph (CR-graph) so that large sized data items cannot be encoded with small sized data items. Simulation result shows some interesting performance comparison.

One of the most important topics in computational biology is protein secondary structure prediction. Primary, secondary, tertiary, and quaternary structure are the four levels of complexity that can be used to characterize the entire structure of a protein that are totally ordered by the amino acid sequences. The polypeptide backbone of a protein's local configuration is referred to as a secondary structure. In this paper, three prediction algorithms have been proposed which will predict the protein secondary structure based on machine learning. These prediction methods have been improved by the model structure of convolutional neural networks (CNN). The Rectified Linear Units (ReLU) has been used as the activation function. The 2D CNN has been trained with machine learning algorithms, including Support Vector Machine, Naive Bays and Random Forest. The SVM is used to correctly classify the unseen data. Naïve Bays (NB) and Random Forest (RF) are also applied to solve the prediction problems for not only classification problems but also regression problems. The 2D CNN, hybrid of 2D CNN -SVM, CNN-RF and CNN-NB have been proposed in this experiment. These different methods are implemented with the RS126, 25PDB and CB513 dataset. Further, all prediction Q3 accuracy is compared and improved with their datasets.

This work proposes a weighting‐factor‐free finite control set predictive torque control (FCS‐PTC) for induction motor drives by incorporating a hysteresis controller to eliminate stator flux error from the cost function. The tuning of the weighting factor coefficient in FCS‐PTC is critical for improved drive performance. Conventionally, the tuning is based on an intuitive understanding of the dynamical system and empirical methods, which may not yield optimal results. The proposed method regulates the flux by incorporating a separate two‐level hysteresis controller and torque by the conventional cost function‐based PTC. The cost function uses torque error only and employs a reduced number of voltage vectors. The reduction of voltage vectors is obtained through the flux hysteresis output and sector determination. The proposed work is implemented experimentally on the dSpace DS1104 controller board for a two‐level three, three‐phase voltage source inverter‐fed induction motor drive. The experimental results validate the effectiveness of the proposed work under different drive tests compared to conventional PTC and direct torque control (DTC). The obtained results show comparable dynamic performance of the drive with 43% $43\\%$lower computational burden than conventional PTC. Along with computational benefit, the proposed work demonstrates improved total harmonic distortion (THD) at low‐speed regions due to the absence of a weighting factor in the cost function. A weighting‐factor‐free finite control set predictive torque control (FCS‐PTC) has been developed for induction motor drives by incorporating a hysteresis controller to eliminate stator flux error from the cost function. The tuning of the weighting factor coefficient in FCS‐PTC is critical for improved drive performance. The proposed method regulates the flux by incorporating a separate two level hysteresis controller and torque by the conventional cost function based PTC. The cost function uses torque error only and employs a reduced number of voltage vectors. The reduction of voltage vectors is obtained through the flux hysteresis output and sector determination. The obtained results show comparable dynamic performance of the drive with 43% lower computational burden as compared to conventional PTC. Along with computational benefits, proposed work also demonstrates improved total harmonic distortion (THD) at low speed regions due to the absence of weighting factor in cost function.

Network slicing is a fundamental technological advancement that facilitates the provision of novel services and solutions within the realm of 5G and the forthcoming 6G communications. Numerous challenges emerge when implementing network slicing on a large-scale commercial level since it necessitates comprehensive control and automation of the entire network. Cyberattacks, such as distributed denial of service (DDoS) and address resolution protocol (ARP) spoofing, can significantly disrupt the performance and accessibility of slices inside a multi-tenant virtualized networking infrastructure due to the shared utilization of physical resources. This article employs intent-based networking (IBN) to identify and address diverse threats through automated methods. A conceptual framework is presented in which the IBN manager is integrated into the network-slicing architecture to facilitate the implementation of automated security controls. The proposed work is assessed using an experimental test bed. The study's findings indicate that the network slice's performance exhibits improvement when successful detection and mitigation measures are implemented. This improvement is observed in various metrics: availability, packet loss, response time, central processing unit (CPU) and memory utilization.