Conventional Approaches Research Articles

Screening and Analysis of Skin Cancer Treatment Using Biocomponents of Plants Using Backpropagation Neural Networks: A Comprehensive Review

: In recent years, the use of natural compounds derived from plants for the treatment of skin cancer has gained significant attention due to their potential therapeutic effects and minimal side effects. This review focuses on the innovative approach of utilizing biocomponents sourced from plants in combination with backpropagation neural networks (BPNN) for the screening and analysis of skin cancer treatments. The integration of plant-derived compounds and AI-driven algorithms holds promise for enhancing the precision and effectiveness of skin cancer therapies. The review begins by highlighting the escalating global burden of skin cancer and the limitations of conventional treatment approaches. With the rise in concerns about the adverse effects of synthetic drugs, researchers have turned their attention towards exploring the therapeutic potential of plant-derived biocomponents. These natural compounds are known for their rich bioactive constituents that exhibit anti-cancer properties, making them suitable candidates for skin cancer treatment. One of the key challenges in harnessing the potential of plant-derived compounds is the need for accurate screening and analysis of their effects. This is where backpropagation neural networks, a type of artificial neural network, comes into play. These networks can process complex data and recognize intricate patterns, enabling them to predict the efficacy of various biocomponents in combating skin cancer. The review delves into the functioning of BPNN and its applications in drug discovery and treatment evaluation. Furthermore, the review explores several case studies that demonstrate the successful integration of plant-derived compounds with BPNN in the context of skin cancer treatment. These studies provide evidence of how this synergistic approach can lead to improved treatment outcomes by minimizing adverse effects and maximizing therapeutic benefits. The methodology section discusses the steps involved in training the neural network using relevant datasets and optimizing its performance for accurate predictions. While the integration of plant-derived compounds and BPNN shows great promise, the review also addresses the existing challenges and limitations. These include the need for comprehensive and standardized datasets, potential biases in training data, and the complexity of neural network architectures. The regulatory considerations surrounding plant-based therapies are also discussed, highlighting the importance of rigorous testing and validation.

Evaluating the representational power of pre-trained DNA language models for regulatory genomics.

The emergence of genomic language models (gLMs) offers an unsupervised approach to learning a wide diversity of cis-regulatory patterns in the non-coding genome without requiring labels of functional activity generated by wet-lab experiments. Previous evaluations have shown that pre-trained gLMs can be leveraged to improve predictive performance across a broad range of regulatory genomics tasks, albeit using relatively simple benchmark datasets and baseline models. Since the gLMs in these studies were tested upon fine-tuning their weights for each downstream task, determining whether gLM representations embody a foundational understanding of cis-regulatory biology remains an open question. Here we evaluate the representational power of pre-trained gLMs to predict and interpret cell-type-specific functional genomics data that span DNA and RNA regulation. Our findings suggest that probing the representations of pre-trained gLMs do not offer substantial advantages over conventional machine learning approaches that use one-hot encoded sequences. This work highlights a major gap with current gLMs, raising potential issues in conventional pre-training strategies for the non-coding genome.

Enhancing Drug-Target Binding Affinity Prediction through Deep Learning and Protein Secondary Structure Integration

Background: Conventional approaches to drug discovery are often characterized by lengthy and costly processes. To expedite the discovery of new drugs, the integration of artificial intelligence (AI) in predicting drug-target binding affinity (DTA) has emerged as a crucial approach. Despite the proliferation of deep learning methods for DTA prediction, many of these methods primarily concentrate on the amino acid sequence of proteins. Yet, the interactions between drug compounds and targets occur within distinct segments within the protein structures, whereas the primary sequence primarily captures global protein features. Consequently, it falls short of fully elucidating the intricate relationship between drugs and their respective targets. Objective: This study aims to employ advanced deep-learning techniques to forecast DTA while incorporating information about the secondary structure of proteins. Methods: In our research, both the primary sequence of protein and the secondary structure of protein were leveraged for protein representation. While the primary sequence played the role of the overarching feature, the secondary structure was employed as the localized feature. Convolutional neural networks and graph neural networks were utilized to independently model the intricate features of target proteins and drug compounds. This approach enhanced our ability to capture drugtarget interactions more effectively Results: We have introduced a novel method for predicting DTA. In comparison to DeepDTA, our approach demonstrates significant enhancements, achieving a 3.9% increase in the Concordance Index (CI) and a remarkable 34% reduction in Mean Squared Error (MSE) when evaluated on the KIBA dataset. Conclusion: In conclusion, our results unequivocally demonstrate that augmenting DTA prediction with the inclusion of the protein's secondary structure as a localized feature yields significantly improved accuracy compared to relying solely on the primary structure.

BAI-Net: Individualized Anatomical Cerebral Cartography Using Graph Neural Network.

Brain atlas is an important tool in the diagnosis and treatment of neurological disorders. However, due to large variations in the organizational principles of individual brains, many challenges remain in clinical applications. Brain atlas individualization network (BAI-Net) is an algorithm that subdivides individual cerebral cortex into segregated areas using brain morphology and connectomes. The presented method integrates group priors derived from a population atlas, adjusts areal probabilities using the context of connectivity fingerprints derived from the fiber-tract embedding of tractography, and provides reliable and explainable individualized brain areas across multiple sessions and scanners. We demonstrate that BAI-Net outperforms the conventional iterative clustering approach by capturing significantly heritable topographic variations in individualized cartographies. The topographic variability of BAI-Net cartographies has shown strong associations with individual variability in brain morphology, connectivity as well as higher relationship on individual cognitive behaviors and genetics. This study provides an explainable framework for individualized brain cartography that may be useful in the precise localization of neuromodulation and treatments on individual brains.

Constructing prediction intervals to explore uncertainty based on deep neural networks

The conventional approaches to constructing Prediction Intervals (PIs) always follow the principle of ‘high coverage and narrow width’. However, the deviation information has been largely neglected, making the PIs unsatisfactory. For high-risk forecasting tasks, the cost of forecast failure may be prohibitive. To address this, this work introduces a multi-objective loss function that includes Prediction Interval Accumulation Deviation (PIAD) within the Lower Upper Bound Estimation (LUBE) framework. The proposed model can achieve the goal of ‘high coverage, narrow width, and small bias’ in PIs, thus minimizing costs even in cases of prediction failure. A salient feature of the LUBE framework is its ability to discern uncertainty without explicit uncertainty labels, where the data uncertainty and model uncertainty are learned by Deep Neural Networks (DNN) and a model ensemble, respectively. The validity of the proposed method is demonstrated through its application to the prediction of carbon prices in China. Compared with conventional uncertainty quantification methods, the improved interval optimization method can achieve narrower PI widths.

Endoscopic Evacuation of Putaminal Hemorrhage Using the Trans-Middle Temporal Gyrus Approach: Technical Notes and Case Presentations.

The development of minimally invasive endoscopic neurosurgery has enabled widespread application of endoscopic surgery via the ipsilateral transfrontal approach for putaminal hematoma evacuation. However, this approach is unsuitable for putaminal hematomas that extend into the temporal lobe. We adopted the endoscopic trans-middle temporal gyrus approach, instead of the conventional surgical approach, for the management of these complicated cases and determined its safety and feasibility. Twenty patients with putaminal hemorrhage underwent surgical treatment at the Shinshu University Hospital between January 2016 and May 2021. Of these, two patients with left putaminal hemorrhage that extended into the temporal lobe underwent surgical treatment using the endoscopic trans-middle temporal gyrus approach. The procedure entailed the use of a thinner transparent sheath to reduce the technique's invasiveness, a navigation system to determine the location of the middle temporal gyrus and the sheath's trajectory, and an endoscope with a 4K camera for higher image quality and utility. The sylvian fissure was compressed superiorly using our novel "port retraction technique" (i.e., by tilting the transparent sheath superiorly) to avoid damage to the middle cerebral artery and Wernicke's area. The endoscopic trans-middle temporal gyrus approach allowed sufficient hematoma evacuation and hemostasis under endoscopic observation without any surgical complexities or complications. The postoperative course was uneventful in both patients. The endoscopic trans-middle temporal gyrus approach for putaminal hematoma evacuation helps avoid damage to normal brain tissue, which could result from the wide range of motion of the conventional technique, particularly when the hemorrhage extends to the temporal lobe.

Enhancing secondary school students’ engagement in chemistry through 7E context-based instructional strategy supported with simulation

Now days, the level of students’ engagement in secondary school chemistry is low. The aim of this study was then to enhance student chemistry engagement through simulation-integrated 7E context-based instructional strategy and compared its efficacy with 7E context-based instructional strategy, simulation-integrated conventional teaching approach, and conventional teaching approach. For the quantitative part, 15-item chemistry engagement scale was utilized to collect data from 229 grade 10 students as part of a quasi-experimental pre-/post-test non-equivalent control group design. Both descriptive and inferential statistics were utilized. Semi-structured interviews were used to collect qualitative data. The study’s findings revealed that, when compared to the other instructional strategies, the simulation-integrated 7E context-based instructional strategy was the most successful at raising students’ overall engagement and its dimensions. This study implies that implementing a simulation-integrated 7E context-based instructional strategy can boost students’ overall and individual levels of engagement in chemistry. Thus, to enhance chemistry learning, teachers may progressively move from the conventional approach to the use of simulation-integrated 7E context-based approach over the other strategies.

Measurement-device-independent quantum random number generation over 23 Mbps with imperfect single-photon sources

Quantum randomness relies heavily on the accurate characterization of the generator implementation, where the device imperfection or inaccurate characterization can lead to incorrect entropy estimation and practical bias, significantly affecting the reliability of the generated randomness. Measurement-device-independent (MDI) quantum random number generation (QRNG) endeavors to produce certified randomness, utilizing uncharacterized and untrusted measurement devices that are vulnerable to numerous attack schemes targeting measurement loopholes. However, existing implementations have shown insufficient performance thus far. Here, we propose a high-speed MDI-QRNG scheme based on a robust measurement tomography approach against the imperfection of single-photon sources. Compared with the conventional approach, the decoy-state method is introduced to obtain more accurate tomography results and a tighter lower bound of randomness. Finally, by using a high-speed time-bin encoding system, we experimentally demonstrated the scheme and obtained a reliable min-entropy lower bound of 7.37×10−2 bits per pulse, corresponding to a generation rate over 23 Mbps, which substantially outperforms the existing realizations and makes a record in discrete-variable semi-device-independent QRNGs.

Enhancing reading and writing instruction in inclusive environments: A meaningful and collaborative approach

n inclusive educational settings, educators often face challenges in effectively allocating time and providing appropriate support for students with disabilities. This research aims to address these challenges by proposing a complementary method that integrates seamlessly with conventional teaching approaches, benefiting both teachers and students in the realm of reading and writing education. The primary objective is to develop a comprehensive design that supports reading and writing instruction within an inclusive environment. The proposed approach adopts a holistic perspective by incorporating classroom walls, cubes, and diverse notebooks into the learning environment. At its core, this approach revolves around two fundamental elements: the utilization of meaningful reading and writing methods and the emphasis on collaborative learning. The study is substantiated by three tiny-research initiatives, providing practical insights into the implementation of inclusive classrooms aligned with the proposed recommendations. This research introduces a holistic design, and through various investigations conducted during its development, addresses key aspects such as the design specifications for the cubes, the functionality of notebooks facilitating interaction between walls and cube surfaces, and strategies for facilitating unhindered reading and writing instruction. The findings contribute to answering crucial questions on considerations for creating an inclusive and effective learning environment for primary reading and writing instruction.

Equivalent Input Disturbance-Based Control: Analysis, Development, and Applications.

This article reviews the concept, analysis, development, and applications of the equivalent-input-disturbance (EID) approach. First, the definition and existence of the EID are given, and the configuration of the EID estimator is provided. Next, estimation errors in the conventional EID approach are explained, and error-suppression methods are exhibited, which improve the disturbance-rejection performance. Then, this article describes how to apply the EID approach and associate challenges in dealing with nonlinearities, time delays, and uncertainties. Moreover, this article reviews some additional meaningful studies that cannot be categorized into the above-mentioned classes. Finally, some conclusions and future directions are given. The EID approach has been successfully used to suppress the influences of exogenous disturbances, nonlinearities, time delays, and uncertainties in many control systems to improve control performance and robustness. Studies can further rich the theory of the EID approach in the future, such as designing evaluation index, improving disturbance-rejection performance, developing new applications, and combining with other control theory.

Improved Adaptive CCS-MPCC for Distorted Model Parameters Mitigation of IPMSM Drives

In this study, a robust adaptive model continuous-control-set model predictive current control (CCS-MPCC) method is proposed for interior permanent magnet synchronous motors (IPMSMs) considering the existing disturbances, unmodeled dynamics, and parameter variations. The novel aspect of this research is that it merges the improved dynamic, useful properties of model predictive control (MPC), which includes easy implementation and fast dynamic response, together with the most effective criterion of an adaptive controller (i.e., robustness to model uncertainties), that result in enhanced dynamic and steady-state control performance despite unknown and changing disturbances. Unlike the conventional CCS-MPCC approach that heavily depends on the accurate knowledge of the system model to attain improved control performance, the proposed method achieves satisfactory control performance (e.g., fast dynamic response, smaller steady-state error, and low stator current THD) by stabilizing the state errors to approach zero and compensating for variations in the model parameters using the designed feedback control terms and adaptive control terms, respectively. The stability of the proposed control method is ensured by the state errors asymptotically decaying to zero. The proposed approach was simulated and then implemented on a PSIM simulation tool and a prototype IPMSM test bench using TI TMS320F28335 DSP, respectively, to confirm its feasibility.

Meaningful engagement of preschoolers through storytelling pedagogy

Engaging students in their learning depends on the teachers’ pedagogical practices. The first author is a STEAM scholar and preschool educator who realized engagement is necessary for meaningful learning. For this, teachers and students must have exposure to innovative and arts-integrated pedagogy (e.g., storytelling). However, the teachers in the first author’s school practiced a conventional teaching approach, such as lecture and monotonous activity-based instruction, that compelled a disengaged learning culture. Similarly, storytelling was limited to reading aloud from storybooks. Thus, this paper investigated integrating storytelling pedagogy to engage preschoolers in learning by centralizing on the research question: How do teachers integrate storytelling pedagogy to enhance meaningful learning? This study used an action research method to intervene in the current pedagogical practice with storytelling as an innovative pedagogy. The teachers and students of Upper Kindergarten were involved in practicing storytelling approaches to conceptualize content knowledge and learn meaningfully. The findings of this study revealed that storytelling as an innovative pedagogy enhances the students’ engagement in their learning process. Similarly, it also helps to enrich students’ imaginative and creative skills, which are crucial soft skills in the 21<sup>st </sup>century. Moreover, storytelling enhances a deeper understanding of the content knowledge if the stories are developed based on the content knowledge of the curriculum. Therefore, storytelling is an innovative and arts-integrated pedagogy to foster preschoolers’ knowledge and skills through engagement and motivation. This research is applicable for educators and schoolteachers to improve and innovate their teaching-learning practices for students’ meaningful learning experiences.

Delving Into the Devils of Bird's-Eye-View Perception: A Review, Evaluation and Recipe.

Learning powerful representations in bird's-eye-view (BEV) for perception tasks is trending and drawing extensive attention both from industry and academia. Conventional approaches for most autonomous driving algorithms perform detection, segmentation, tracking, etc., in a front or perspective view. As sensor configurations get more complex, integrating multi-source information from different sensors and representing features in a unified view come of vital importance. BEV perception inherits several advantages, as representing surrounding scenes in BEV is intuitive and fusion-friendly; and representing objects in BEV is most desirable for subsequent modules as in planning and/or control. The core problems for BEV perception lie in (a) how to reconstruct the lost 3D information via view transformation from perspective view to BEV; (b) how to acquire ground truth annotations in BEV grid; (c) how to formulate the pipeline to incorporate features from different sources and views; and (d) how to adapt and generalize algorithms as sensor configurations vary across different scenarios. In this survey, we review the most recent works on BEV perception and provide an in-depth analysis of different solutions. Moreover, several systematic designs of BEV approach from the industry are depicted as well. Furthermore, we introduce a full suite of practical guidebook to improve the performance of BEV perception tasks, including camera, LiDAR and fusion inputs. At last, we point out the future research directions in this area. We hope this report will shed some light on the community and encourage more research effort on BEV perception.

Cluster-Based Cross Layer-Cross Domain Routing Model with DNN-Based Energy Prediction

In WSN, extending the network life is still a major problem that needs to be tackled. Cross-layer protocols are used to get around these problems. In this paper, a new cross-layer design routing model is presented using a clustering-based technique. The proposed model is proceeding with the optimal cluster-based routing model via a new algorithm. Initially during the network generation, the node’s energy is predicted by the deep learning model termed as DNN model on the basis of the distance between node and sink as the input. Subsequently, during the clustering process, the cluster head is optimally selected via a new optimisation algorithm named Self-Improved Shuffle Shepherd Optimisation (SISSO) Algorithm. The cluster head selection is done by considering the constraints including Link quality, Distance, Overhead, Energy and Delay. Finally, a Modified Kernel Least Mean Square (MKLMS)-based data aggregation process is to eliminate the redundant data transmission. The performance of the SISSO method is proven superior over other conventional approaches with regard to the alive node and network lifetime. In the alive node analysis of supernode, the proposed SISSO model achieves the maximal number of alive supernodes at 2,000 rounds (i.e. 0.67) than other conventional methods.

Advanced Exergy Assessment of an Air Source Heat Pump Unit

Conventional exergy-based analysis methods are used for evaluating the performance of the energy conversation systems. Conventional exergy-based analyses identify the sources, amounts, and reasons of irreversibilities (exergy destructions), costs and environmental effects, and provide a general direction for improvement. However, interactions between system components (endogenous/exogenous) and technical limitations (avoidable/unavoidable) cannot be identified with any conventional analysis. Hence, the real potential for improvement and optimization strategies can be misguided. Advanced exergy based analysis seeks to overcome this limitation. An air source heat pump unit was assessed applying conventional and advanced exergy analysis approaches respectively. Avoidable/unavoidable and endogenous/exogenous exergy destructions, modified exergy efficiencies and modified exergy losses ratios were calculated for every single component of the system. The results showed that while the evaporator and condenser efficiencies could be upgraded via constructional enhancements to the overall system and other system components, internal operating conditions were mainly responsible of the inefficiencies regarding with the compressor. The analysis demonstrated that while it was possible to improve evaporator and condenser efficiency by making constructive enhancements to whole system design, the efficiency of the compressor was mainly determined by the internal conditions in which the compressor operated.

Lamination of >21% Efficient Perovskite Solar Cells with Independent Process Control of Transport Layers and Interfaces.

Transport layer and interface optimization is critical for improving the performance and stability of perovskite solar cells (PSCs) but is restricted by the conventional fabrication approach of sequential layer deposition. While the bottom transport layer is processed with minimum constraints, the narrow thermal and chemical stability window of the halide perovskite (HP) layer severely restricts the choice of top transport layer and its processing conditions. To overcome these limitations, we demonstrate lamination of HPs─where two transport layer-perovskite half-stacks are independently processed and diffusion-bonded at the HP-HP interface─as an alternative fabrication strategy that enables self-encapsulated solar cells. Power conversion efficiencies (PCE) of >21% are realized using cells that incorporate a novel transport layer combination along with dual-interface passivation via self-assembled monolayers, both of which are uniquely enabled by the lamination approach. This is the highest reported PCE for any laminated PSC encapsulated between glass substrates. We further show that this approach expands the processing window beyond traditional fabrication processes and is adaptable for different transport layer compositions. The laminated PSCs retained >75% of their initial PCE after 1000 h of 1-sun illumination at 40 °C in air using an all-inorganic transport layer configuration without additional encapsulation. Furthermore, a laminated 1 cm2 device maintained a Voc of 1.16 V. The scalable lamination strategy in this study enables the implementation of new transport layers and interfacial engineering approaches for improving performance and stability.

Deep-unrolling architecture for image-domain least-squares migration

Deep-image prior (DIP) is a novel approach to solving ill-posed inverse problems whose solution is parameterized with an untrained deep neural network and cascaded with the forward modeling operator. A key component to the success of such a method is represented by the choice of the network architecture, which must act as a natural prior to the inverse problem at hand and provide a strong inductive bias toward the desired solution. Inspired by the close link between neural networks and iterative algorithms in classical optimization, we apply an unrolled version of the gradient descent (GD) algorithm as our DIP network architecture, denoted as the deep-unrolling (DU) architecture. Each layer of the unrolled network is comprised of two parts: the first part corresponds to the GD step of the data-fidelity term, whereas the second part, formed by a six-layer convolutional neural network (CNN), plays the role of a regularizer in the associated objective function. The developed DU architecture is applied to the problem of image-domain least-squares migration (IDLSM) to invert migrated seismic images for their underlying reflectivity and is denoted as DU-IDLSM. As such, the DU architecture parameterizes the reflectivity, and the input of each layer of the unrolled network is the reflectivity at the previous layer. Similar to the classical DIP approach, the parameters of the DU architecture are optimized in an unsupervised fashion by minimizing the data misfit function itself. Through experiments with a part of the Sigsbee2A model and a marine field data set, we test the effectiveness of the DU-IDLSM approach and highlight two key benefits. First, the DU architecture can effectively regularize the inversion process, resulting in reflectivity estimates with fewer artifacts and higher image resolution than those produced by conventional IDLSM approaches. Second, we indicate that by including dropout layers in the CNN architecture, DU-IDLSM can produce a qualitative measure of the uncertainty associated with the least-squares migration process.

Optimizing nanoporous metallic actuators through multiscale calculations and machine learning

Nanoporous materials (NMs) immersed in electrolytes can achieve approximately 1 % deformation at a low operating voltage of about 1 V. The actuation renders them promising artificial muscles. The actuation performance significantly hinges on the structure and size of nanopores and ligaments in NMs. Consequently, designing an optimal configuration is imperative for excellent performance. The actuation mechanism of NMs involves the coupling of multiple fields at various length scales, posing a formidable challenge to conventional simulation and design approaches. To surmount this challenge, we have developed a computational framework capable of conducting concurrent and sequential multiscale calculations. By utilizing artificial neural network (ANN) surrogate models trained on data obtained through the finite element method (FEM), the framework achieves optimized values for both actuation strain and effective Young's modulus within a designated design space. The constitutive model, which establishes the relationship between surface stress and charges in FEM, is derived from the surface eigenstress model and symbolic regression. This involves utilizing data calculated through joint density functional theory. This framework not only ensures the desired properties but also demonstrates its potential for effectively addressing other multiscale optimization problems.

Use of Total Least Squares Adjustment in Geodetic Applications

This article discusses the method of computing the values of the unknowns under the condition of the minimum sum of the squares of the residuals of the observations, also known as the least squares method, with the additional condition of taking into account the errors in the unknowns. The problem has already been treated by many authors, especially in the field of regression analysis and the computation of transformation parameters. We give an overview of the theoretical foundations of the least squares method and extensions of this method by considering the errors in the unknowns in the model matrix. So, the total least squares method is presented in this paper, fitting the regression line to a set of points and computing transformation parameters for the transition between the old and the new Slovenian national coordinate systems. Furthermore, for the first time, the method is also presented and tested in the S-transformation between different geodetic datum-dependent solutions. Also, for the first time, we systematically compare the results of the approach with conventional approaches in all three considered tasks. With the results based on relevant statistics, we confirm the suitability of the described method for dealing with the considered computational tasks.

A detailed study of the current‐reuse VCO's operation and a simple circuit technique to generate intrinsic‐balanced outputs

SummaryIn the first part of this paper, we closely examine well‐known methods for balancing the output power level of the pseudo‐differential current‐reuse voltage‐controlled oscillator. We scrutinize their effectiveness in terms of canceling output mismatches, insensitivity to process, voltage, and temperature variations, and their capability of not degrading phase noise performance. Through analyses and simulations, it is shown that contrary to common belief, some techniques are not as effective as previously thought and should be employed only under specific circumstances. The best conventional approach is proven to be the use of a common‐mode shunting capacitor at the inductor's center tap node to create a virtual ground. In the second part, it is demonstrated that the current‐reuse voltage‐controlled oscillator can intrinsically produce balanced outputs without using any additional techniques or extra passive or active components. Using single‐ended tank capacitors instead of differential ones, the common‐mode voltage of the outputs is shunted to the real ground. This technique reintroduces a reference voltage to the tank circuit, forcing the oscillator to achieve equilibrium between positive and negative swings. The proposed current‐reuse oscillator is designed and post‐layout simulated in a 65‐nm CMOS process, covering a frequency range of 4.84–6.38 GHz with an average power consumption of 0.65 mW. It produces balanced outputs with an amplitude error of less than ±0.2% and achieves a phase noise of −126.7 dBc/Hz and FoMT of 201.8 dB at a 3‐MHz offset frequency.