Accuracy In Classification Task Research Articles

Advancing Robotic Automation with Custom Sequential Deep CNN-Based Indoor Scene Recognition

Indoor scene recognition poses considerable hurdles, especially in cluttered and visually analogous settings. Although several current recognition systems perform well in outside settings, there is a distinct necessity for enhanced precision in inside scene detection, particularly for robotics and automation applications. This research presents a revolutionary deep Convolutional Neural Network (CNN) model tailored with bespoke parameters to improve indoor picture comprehension. Our proprietary dataset consists of seven unique interior scene types, and our deep CNN model is trained to attain excellent accuracy in classification tasks. The model exhibited exceptional performance, achieving a training accuracy of 99%, a testing accuracy of 89.73%, a precision of 90.11%, a recall of 89.73%, and an F1-score of 89.79%. These findings underscore the efficacy of our methodology in tackling the intricacies of indoor scene recognition. This research substantially advances the domain of robotics and automation by establishing a more resilient and dependable framework for autonomous navigation and scene comprehension in GPS-denied settings, facilitating the development of more efficient and intelligent robotic systems.

Achieving liquid processors by colloidal suspensions for reservoir computing

The increasing use of machine learning, with its significant computational and environmental costs, has motivated the exploration of unconventional computing substrates. Liquid substrates, such as colloids, are of particular interest due to their ability to conform to various shapes while exhibiting complex dynamics resulting from the collective behaviour of the constituent colloidal particles. This study explores the potential of using a PEDOT:PSS colloidal suspension as a physical reservoir for reservoir computing in spoken digit recognition. Reservoir computing uses high-dimensional dynamical systems to perform tasks with different substrates, including physical ones. Here, a physical reservoir is implemented that encodes temporal data by exploiting the rich dynamics inherent in colloidal suspensions, thus avoiding reliance on conventional computing hardware. The reservoir processes audio input encoded as spike sequences, which are then classified using a trained readout layer to identify spoken digits. Evaluation across different speaker scenarios shows that the colloidal reservoir achieves high accuracy in classification tasks, demonstrating its viability as a physical reservoir substrate.

A benchmark for evaluation of structure-based online tools for antibody-antigen binding affinity

The prediction of binding affinity changes caused by missense mutations can elucidate antigen-antibody interactions. A few accessible structure-based online computational tools have been proposed. However, selecting suitable software for particular research is challenging, especially research on the SARS-CoV-2 spike protein with antibodies. Therefore, benchmarking of the mutation-diverse SARS-CoV-2 datasets is critical. Here, we collected the datasets including 1216 variants about the changes in binding affinity of antigens from 22 complexes for SARS-CoV-2 S proteins and 22 monoclonal antibodies as well as applied them to evaluate the performance of seven binding affinity prediction tools. The tested tools' Pearson correlations between predicted and measured changes in binding affinity were between −0.158 and 0.657, while accuracy in classification tasks on predicting increasing or decreasing affinity ranged from 0.444 to 0.834. These tools performed relatively better on predicting single mutations, especially at epitope sites, whereas poor performance on extremely decreasing affinity. The tested tools were relatively insensitive to the experimental techniques used to obtain structures of complexes. In summary, we constructed a list of datasets and evaluated a range of structure-based online prediction tools that will explicate relevant processes of antigen-antibody interactions and enhance the computational design of therapeutic monoclonal antibodies.

Developing System-based Voice Features for Detecting Parkinson’s Disease Using Machine Learning Algorithms

Parkinson’s disease (PD) is a neurodegenerative disorder characterized by a deficit of dopamine in the brain. This condition has the potential to impact individuals of advanced age. The procedure for diagnosing PD is currently not well established. Diagnostics includes a range of methods, including the identification and evaluation of symptoms, the implementation of clinical trials, and the use of laboratory tests. This research work employs a range of machine learning (ML) algorithms, including k-nearest neighbors (k-NN), support vector machines (SVMs), random forest (RF), logistic regression (LR), and AdaBoost boosting approaches, to predict the occurrence of PD and assist healthcare practitioners in recommending tailored treatment plans. To evaluate the suggested ML methods, it is customary to use a standard dataset consisting of various biological voice measures obtained from individuals afflicted with PD as well as healthy individuals. The experimental results demonstrate that the LR model achieves an accuracy of 86%, the k-NN model achieves an accuracy of 92%, the SVM model achieves an accuracy of 95%, the RF model achieves an accuracy of 95%, and the AdaBoost boosting model achieves an accuracy of 93%. SVM and RF are well acknowledged for their high accuracy in classification tasks. Upon conducting a comparative analysis with other studies, it was shown that the proposed intervention yielded outcomes that were either comparable to or superior to those reported in previous research.

Useful blunders: Can automated speech recognition errors improve downstream dementia classification?

Objectives:We aimed to investigate how errors from automatic speech recognition (ASR) systems affect dementia classification accuracy, specifically in the “Cookie Theft” picture description task. We aimed to assess whether imperfect ASR-generated transcripts could provide valuable information for distinguishing between language samples from cognitively healthy individuals and those with Alzheimer’s disease (AD). Methods:We conducted experiments using various ASR models, refining their transcripts with post-editing techniques. Both these imperfect ASR transcripts and manually transcribed ones were used as inputs for the downstream dementia classification. We conducted comprehensive error analysis to compare model performance and assess ASR-generated transcript effectiveness in dementia classification. Results:Imperfect ASR-generated transcripts surprisingly outperformed manual transcription for distinguishing between individuals with AD and those without in the “Cookie Theft” task. These ASR-based models surpassed the previous state-of-the-art approach, indicating that ASR errors may contain valuable cues related to dementia. The synergy between ASR and classification models improved overall accuracy in dementia classification. Conclusion:Imperfect ASR transcripts effectively capture linguistic anomalies linked to dementia, improving accuracy in classification tasks. This synergy between ASR and classification models underscores ASR’s potential as a valuable tool in assessing cognitive impairment and related clinical applications.

Improving time efficiency in big data through progressive sampling-based classification model

<span>The proposed system aims to overcome challenges posed by large databases, data imbalance, heterogeneity, and multidimensionality through progressive sampling as a novel classification model. It leverages sampling techniques to enhance processing performance and overcome memory restrictions. The random forest regressor feature importance technique with the gini significance method is employed to identify important characteristics, reducing the data’s features for classification. The system utilizes diverse classifiers such as random forest, ensemble learning, support vector machine (SVM), k-nearest neighbors’ algorithm (KNN), and logistic regression, allowing flexibility in handling different data types and achieving high accuracy in classification tasks. By iteratively applying progressive sampling to the dataset with the best features, the proposed technique aims to significantly improve performance compared to using the entire dataset. This approach focuses computational resources on the most informative subsets of data, reducing time complexity. Results show that the system can achieve over 85% accuracy even with only 5-10% of the original data size, providing accurate predictions while reducing data processing requirements. In conclusion, the proposed system combines progressive sampling, feature selection using random forest regressor feature importance (RFRFI-PS), and a range of classifiers to address challenges in large databases and improve classification accuracy. It demonstrates promising results in accuracy and time complexity reduction.</span>

Diffraction deep neural network-based classification for vector vortex beams

The vector vortex beam (VVB) has attracted significant attention due to its intrinsic diversity of information and has found great applications in both classical and quantum communications. However, a VVB is unavoidably affected by atmospheric turbulence (AT) when it propagates through the free-space optical communication environment, which results in detection errors at the receiver. In this paper, we propose a VVB classification scheme to detect VVBs with continuously changing polarization states under AT, where a diffractive deep neural network (DDNN) is designed and trained to classify the intensity distribution of the input distorted VVBs, and the horizontal direction of polarization of the input distorted beam is adopted as the feature for the classification through the DDNN. The numerical simulations and experimental results demonstrate that the proposed scheme has high accuracy in classification tasks. The energy distribution percentage remains above 95% from weak to medium AT, and the classification accuracy can remain above 95% for various strengths of turbulence. It has a faster convergence and better accuracy than that based on a convolutional neural network.

A High Accuracy Recommendation System for the Rubber Industries: Integrating Collaborative Filtering with Multi-layer Perceptron Classifier

Abstract: Collaborative filtering is a widely used method in Machine Language to discover relationships between data. It facilitates recommendation systems that find similarities between user data and items, recommendation system playing a crucial role in various industries. Multilayer perceptron classifier used in our model, a connection with neural networks that performs well in regression and achieves high accuracy in classification tasks. When compared to other neural network architectures like convolution neural network (CNN), recurrent neural network (RNN), auto encoder (AE), and generative adversarial network (GAN), MLP remains a fundamental approach. Collaborative filtering involves multiple users, viewpoints, and data sources collaborating to classify information or patterns and recommend items that similar users might like. Instead of recommending items based on their features, we group users into neural networks with similar preferences and suggest items based on their classifier's preferences.

Approximate blocked Gibbs sampling for Bayesian neural networks

In this work, minibatch MCMC sampling for feedforward neural networks is made more feasible. To this end, it is proposed to sample subgroups of parameters via a blocked Gibbs sampling scheme. By partitioning the parameter space, sampling is possible irrespective of layer width. It is also possible to alleviate vanishing acceptance rates for increasing depth by reducing the proposal variance in deeper layers. Increasing the length of a non-convergent chain increases the predictive accuracy in classification tasks, so avoiding vanishing acceptance rates and consequently enabling longer chain runs have practical benefits. Moreover, non-convergent chain realizations aid in the quantification of predictive uncertainty. An open problem is how to perform minibatch MCMC sampling for feedforward neural networks in the presence of augmented data.

A comparative assessment of artificial intelligence models used for early prediction and evaluation of chronic kidney disease

Chronic Kidney Disease (CKD) is one of the most prevalent and fatal diseases influencing people on a larger that remains dormant until irreversible damage has been done to an individual’s kidney. Progression of CKD is related to a variety of great complications, including increased incidence of various disorders, anemia, hyperlipidemia, nerve damage, pregnancy complication, and even complete kidney failure. Millions of people die from this disease every year. Diagnosing CKD is a cumbersome task as no major symptoms can be used as a benchmark to detect the disease. In cases when diagnosis persists, some results may be interpreted incorrectly. This study proposes using a deep neural network-based Multi-Layer Perceptron Classifier to diagnose CKD in patients. The model was trained using data from 400 people and considered various symptoms and signs, including age, blood sugar, red blood cell count, etc. Experiments reveal that the proposed model achieves perfect testing accuracy in classification tasks. Our goal is to facilitate introducing Deep Learning approaches to learning from the dataset attribute reports and accurately detecting CKD. The paper’s primary contribution is a Deep Neural Network model for chronic kidney disease diagnosis that achieves 100% accuracy, outperforming standard machine learning models such as support vector machines and naive Bayes classifiers. This paper provides a detailed explanation of the multi-layer perceptron classifier, which uses the deep neural network provided by the PyTorch library as its basis. Neural models can be a better alternative for adaption techniques for classifying chronic kidney disease Because they can handle non-linearity in the data, compute complex data heaps fetched from datasets, and adapt and learn on their own about the key information using the layers of neurons present in the structure.

A Hybrid Grey Wolf-Whale Optimization Algorithm for Classification of Corona Virus Genome Sequences using Deep Learning

Genome sequence data is widely accepted as complex data and is still growing in an exponential rate. Classification of genome sequences plays a crucial role as it finds its applications in the area of biology, medical and forensics etc. For classification, Genome sequences can be represented in terms of features. More number of less significant features leads to lower accuracy in classification task. Feature selection addresses this issue by selecting the most important features which aids to improve the accuracy and lessens the computational complexity. In this research, Hybrid Grey Wolf-Whale Optimization Algorithm (HGWWOA) is proposed for Genome sequence classification. The proposed algorithm is evaluated using 23 benchmark objective functions along with Convolutional Neural Network classifier and its efficiency is verified using a novel metric namely “Feature Reduction Rate”. The proposed optimization algorithm can be applied for any optimization problems. In this research work, the proposed algorithm is used for classification of Corona Virus genome sequences. Performance comparison of the proposed and existing algorithms was carried out and it is evident that the performance of proposed algorithm exceeds the previous algorithms with an accuracy of 98.2%.

Classification of Distribution Network Planning Documents Based on LSTM Neural Network

Classification of distribution network planning documents based on LSTM neural network is a new project, which aims to solve the problem of classification of distribution network planning documents based on LSTM neural network. We will use this project in future projects, and we will share it with you in the near future. The main part of this project is about the working principle of distribution network planning document classification based on LSTM neural network. The project consists of data preparation and training process. In order to better understand this project and classify the distribution network planning documents, the main technical feature of this model is that it can effectively process a large amount of data and provide high accuracy in classification tasks.

Map-Reduce based Distance Weighted k-Nearest Neighbor Machine Learning Algorithm for Big Data Applications

With the evolution of Internet standards and advancements in various Internet and mobile technologies, especially since web 4.0, more and more web and mobile applications emerge such as e-commerce, social networks, online gaming applications and Internet of Things based applications. Due to the deployment and concurrent access of these applications on the Internet and mobile devices, the amount of data and the kind of data generated increases exponentially and the new era of Big Data has come into existence. Presently available data structures and data analyzing algorithms are not capable to handle such Big Data. Hence, there is a need for scalable, flexible, parallel and intelligent data analyzing algorithms to handle and analyze the complex massive data. In this article, we have proposed a novel distributed supervised machine learning algorithm based on the MapReduce programming model and Distance Weighted k-Nearest Neighbor algorithm called MR-DWkNN to process and analyze the Big Data in the Hadoop cluster environment. The proposed distributed algorithm is based on supervised learning performs both regression tasks as well as classification tasks on large-volume of Big Data applications. Three performance metrics, such as Root Mean Squared Error (RMSE), Determination coefficient (R2) for regression task, and Accuracy for classification tasks are utilized for the performance measure of the proposed MR-DWkNN algorithm. The extensive experimental results shows that there is an average increase of 3% to 4.5% prediction and classification performances as compared to standard distributed k-NN algorithm and a considerable decrease of Root Mean Squared Error (RMSE) with good parallelism characteristics of scalability and speedup thus, proves its effectiveness in Big Data predictive and classification applications.

An optimized fuzzy deep learning model for data classification based on NSGA-II

As a powerful paradigm, deep learning (DL) models have been used in many applications for classification tasks in images, text, and audio. Through DL models, we can learn task-driven features from big data. However, DL models are fully deterministic and cannot handle uncertain and imprecise data. DL models are often sensitive to noise in data and do not operate well in areas where data are vague. Moreover, when there is a large feature set or high-dimensional data with irrelevant and redundant features, the DL models’ performance decreases in classification due to training with irrelevant features. To gain reliable results in such high-dimensional problems, DL models require a large amount of data which usually grows exponentially concerning the number of features. Data uncertainty problems and irrelevant features in DL models cause low performance in classification tasks. This paper proposes an optimized fuzzy deep learning (OFDL) model for data classification based on Non-Dominated Sorting Genetic Algorithm II (NSGA-II). OFDL utilizes optimization in the composition of DL and fuzzy learning via the NSGA-II in multi-modal learning. To achieve effective classification, OFDL first considers intelligent feature selection by finding the best trade-offs between two conflicting objective functions, minimizing the number of features, and maximizing the accuracy (maximizing weights of selected features). Next, to reach optimized backpropagation and fuzzy membership functions, OFDL utilizes Pareto optimal solutions for multi-objective optimization using NSGA-II based on their objective functions. Furthermore, the fusion layer in OFDL fused optimized views of DL and fuzzy learning that provides a high-level representation of inputs and optimum features for classification tasks where the data contain high uncertainties and noises. This functionality gives valuable attributes during classification since identifying and selecting appropriate features ensures prompt and correct class. Also, it provides deep insight into tackling the effect of ambiguous data and each feature’s uncertainty in the classification tasks. The examination of OFDL reveals good performance in terms of F-measure, accuracy, recall, precision, and True Positive Rate (TPR) compared to fuzzy classifiers. Furthermore, OFDL has higher accuracy in classification tasks than earlier fuzzy DNN models.

A Compact Fully Ferroelectric-FETs Reservoir Computing Network With Sub-100 ns Operating Speed

Reservoir computing (RC) is a low-cost and temporary-signal friendly computational framework, whose hardware implementation is hindered by integrating huge amounts and various kinds of devices. Benefitted from the logic in memory (LIM) capability, the process compatible Hf <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">0.5</sub> Zr <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">0.5</sub> O <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> (HZO)-based ferroelectric field-effect-transistor (FeFET) is a promising candidate for implementing artificial networks. In this letter, a fully FeFETs RC network is proposed. Multiple functions can be achieved in a single device owing to its intrinsic characteristics, and the richness of virtual nodes is largely enhanced through full-connection structures. Impressively, only 44 FeFETs are required to construct a compact RC network with 100 ns operating speed and high accuracy in classification tasks. This paves the way to develop the high energy-efficiency FeFET RC networks.

Application of Chaos Mutation Adaptive Sparrow Search Algorithm in Edge Data Compression.

In view of the large amount of data collected by an edge server, when compression technology is used for data compression, data classification accuracy is reduced and data loss is large. This paper proposes a data compression algorithm based on the chaotic mutation adaptive sparrow search algorithm (CMASSA). Constructing a new fitness function, CMASSA optimizes the hyperparameters of the Convolutional Auto-Encoder Network (CAEN) on the cloud service center, aiming to obtain the optimal CAEN model. The model is sent to the edge server to compress the data at the lower level of edge computing. The effectiveness of CMASSA performance is tested on ten high-dimensional benchmark functions, and the results show that CMASSA outperforms other comparison algorithms. Subsequently, experiments are compared with other literature on the Multi-class Weather Dataset (MWD). Experiments show that under the premise of ensuring a certain compression ratio, the proposed algorithm not only has better accuracy in classification tasks than other algorithms but also maintains a high degree of data reconstruction.

KNOWM memristors in a bridge synapse delay-based reservoir computing system for detection of epileptic seizures

ABSTRACT Nanodevices that show the potential for non-linear transformation of electrical signals and various forms of memory can be successfully used in new computational paradigms, such as neuromorphic or reservoir computing. In this work, we present single-node Echo State Machine (SNESM) RC system based on bridge synapse as a computational substrate (consisting of 4 memristors and a differential amplifier) used for epileptic seizure detection. The results show that the evolution of the signal in a feedback loop helps improve the classification accuracy of the system for that task. The transformation in SNESM changes the correlation and distribution of the complexity parameters of the input signal. In general, there are more differences in the correlation of complexity parameters between the transformed signal and the input signal, which may explain the improvement in the classification scores. SNESM could prove to be a useful time series signal processing system designed to improve accuracy in classification tasks.

Conscious Empathic AI in Service

Recent advances in artificial intelligence (AI) have achieved human-scale speed and accuracy for classification tasks. Current systems do not need to be conscious to recognize patterns and classify them. However, for AI to advance to the next level, it needs to develop capabilities such as metathinking, creativity, and empathy. We contend that such a paradigm shift is possible through a fundamental change in the state of artificial intelligence toward consciousness, similar to what took place for humans through the process of natural selection and evolution. To that end, we propose that consciousness in AI is an emergent phenomenon that primordially appears when two machines cocreate their own language through which they can recall and communicate their internal state of time-varying symbol manipulation. Because, in our view, consciousness arises from the communication of inner states, it leads to empathy. We then provide a link between the empathic quality of machines and better service outcomes associated with empathic human agents that can also lead to accountability in AI services.

Tolerating Noise Effects in Processing‐in‐Memory Systems for Neural Networks: A Hardware–Software Codesign Perspective

Neural networks have been widely used for advanced tasks from image recognition to natural language processing. Many recent works focus on improving the efficiency of executing neural networks in diverse applications. Researchers have advocated processing‐in‐memory (PIM) architecture as a promising candidate for training and testing neural networks because PIM design can reduce the communication cost between storage and computing units. However, there exist noises in the PIM system generated from the intrinsic physical properties of both memory devices and the peripheral circuits. The noises introduce challenges in stably training the systems and achieving high test performance, e.g., accuracy in classification tasks. This review discusses the current approaches to tolerating noise effects for both training and inference in PIM systems and provides an analysis from a hardware–software codesign perspective. Noise‐tolerant strategies for PIM systems based on resistive random‐access memory (ReRAM), including circuit‐level, algorithm‐level, and system‐level solutions are explained. In addition, we also present some selected noise‐tolerate cases in PIM systems for generative adversarial networks and physical neural networks.

Supervised Learning Using Homology Stable Rank Kernels

Exciting recent developments in Topological Data Analysis have aimed at combining homology-based invariants with Machine Learning. In this article, we use hierarchical stabilization to bridge between persistence and kernel-based methods by introducing the so-called stable rank kernels. A fundamental property of the stable rank kernels is that they depend on metrics to compare persistence modules. We illustrate their use on artificial and real-world datasets and show that by varying the metric we can improve accuracy in classification tasks.