Optimal Level Of Accuracy Research Articles

DEEP LEARNING FOR AUTOMATIC CLASSIFICATION OF AVOCADO FRUIT MATURITY

Avocado (Persea Americana), a fleshy fruit with a single seed, has increased in popularity globally, especially in tropical and Mediterranean climates, thanks to its commercial and nutritional value. Rich in bioactive compounds, avocados contribute to the prevention and treatment of various diseases, including cardiovascular problems and cancer. Avocado production in Indonesia, for example, is showing a significant increase, reflecting the growing demand. Avocado ripeness affects shelf life and quality, making the determination of ripeness level a critical aspect of postharvest management. Skin color and pulp firmness change during storage, affecting quality and nutritional value. Proper classification of ripeness is important to reduce post-harvest losses, improve quality and optimize export costs. Recent research shows the use of technologies such as machine learning and YOLO (You Only Look Once) version 9 in real-time detection of avocado ripeness, offering innovative solutions to reduce post-harvest losses and improve distribution efficiency. This approach not only benefits farmers and consumers but also ensures consumer satisfaction and reduces economic losses. This study highlights the importance of real-time detection in monitoring avocado ripeness, where the training process was conducted for 89,280 iterations resulting in a new model for avocado ripeness detection. The final model has a mean Average Precision (mAP) validation value of 84.3%, mAP 84.3% signifies the optimal level of accuracy in object recognition in avocado fruit maturity images using the YOLO model that has undergone an intensive training process.

COMPARATIVE ANALYSIS OF STROKE CLASSIFICATION USING THE K-NEAREST NEIGHBOR DECISION TREE, AND MULTILAYER PERCEPTRON METHODS

Stroke has become a serious health problem; the main cause of stroke is usually a blood clot in the arteries that supply blood to the brain. Strokes can also be caused by bleeding when blood vessels burst and blood leaks into the brain. In one year, about 12.2 million people will have their first stroke, and 6.5 million people will die from a stroke. More than 110 million people worldwide have had a stroke. Handling that is done quickly can minimize the level of brain damage and the potential adverse effects. Therefore, it is very important to predict whether a patient has the potential to experience a stroke. The K-Nearest Neighbor, Decision Tree, and Multilayer Perceptron algorithms are applied as a classification method to identify symptoms in patients and achieve an optimal accuracy level. The results of making the three algorithms are quite good, where K-Nearest Neighbor (K-NN) has an accuracy value of 93.84%, Decision Tree is 93.97%, and Multilayer Perceptron (MLP) is 93.91%. The best accuracy value is the Decision Tree algorithm with an accuracy difference of no more than 0.10% with the two algorithms used.

Optimal Accuracy of Unbiased Tullock Contests with Two Heterogeneous Players

I characterize the optimal accuracy level r of an unbiased Tullock contest between two players with heterogeneous prize valuations. The designer maximizes the winning probability of the strong player or the winner’s expected valuation by choosing a contest with an all-pay auction equilibrium (r≥2). By contrast, if she aims at maximizing the expected aggregate effort or the winner’s expected effort, she will choose a contest with a pure-strategy equilibrium, and the optimal accuracy level r<2 decreases in the players’ heterogeneity. Finally, a contest designer who faces a tradeoff between selection quality and minimum (maximum) effort will never choose a contest with a semi-mixed equilibrium.

Big Cats Classification Based on Body Covering

The reduced habitat owned by an animal has a very bad impact on the survival of the animal, resulting in a continuous decrease in the number of animal populations especially in animals belonging to the big cat family such as tigers, cheetahs, jaguars, and others. To overcome the decline in the animal population, a classification model was built to classify images that focuses on the pattern of body covering possessed by animals. However, in designing an accurate classification model with an optimal level of accuracy, it is necessary to consider many aspects such as the dataset used, the number of parameters, and computation time. In this study, we propose an animal image classification model that focuses on animal body covering by combining the Pyramid Histogram of Oriented Gradient (PHOG) as the feature extraction method and the Support Vector Machine (SVM) as the classifier. Initially, the input image is processed to take the body covering pattern of the animal and converted it into a grayscale image. Then, the image is segmented by employing the median filter and the Otsu method. Therefore, the noise contained in the image can be removed and the image can be segmented. The results of the segmentation image are then extracted by using the PHOG and then proceed with the classification process by implementing the SVM. The experimental results showed that the classification model has an accuracy of 91.07%.

Improving the Accuracy of Static Source Code Based Software Change Impact Analysis Through Hybrid Techniques: A Review

Change is an inevitable phenomenon of life. This inevitability of change in the real world has made a software change an indispensable characteristic of software systems and a fundamental task of software maintenance and evolution. The continuous evolution process of software systems can greatly affect the systems’ quality and reliability if proper mechanisms to manage them are not adequately provided. Therefore, there is a need for automated techniques to effectively make an assessment of proposed software changes that may arise due to bug fixes, technological advancements, changing user requirements etc., before their implementation. Software Change Impact Analysis (CIA) is an essential activity for comprehending and identifying potential change impacts of software changes that can help prevent the system from entering into an erroneous state. Despite the emergence of different CIA techniques, they are yet to reach an optimal level of accuracy desired by software engineers. Consequently, researchers in recent years have come up with hybrid CIA techniques which are a blend of multiple CIA approaches, as a way of improving the accuracy of change impacts analysis techniques. This study presents these hybrid CIA techniques and how they improve accuracy. They are also compared and areas for further research are identified.

PENGEMBANGAN SISTEM INFORMASI MANAJEMEN PENGELOLAAN KEARSIPAN DI LEMBAGA JAMINAN SOSIAL

This study aims to see to what extent the effectiveness of an information system that has just been implemented in a social security institution where this system is a replacement for the previous system which is considered less effective in managing archives. Based on the results of research and testing, it was found that this new system has a better effectiveness value and a far more optimal level of accuracy in archiving management.

Study of the Constraint Selection Through ASVDADD Method for Rate-Controlled Constrained-Equilibrium Modeling on Ethanol Oxidation Without PLOG Reactions

Abstract Reduction of the detail chemical kinetic mechanism is important in solving complex combustion simulation. In this work, a model reduction scheme rate-controlled constrained-equilibrium (RCCE) is considered in predicting the oxidation of ethanol. A detail kinetic mechanism by Merinov from Lawrence Livermore National Laboratory (LLNL) is used in modeling this reduction technique. The RCCE method considers constrained equilibrium states which subjected to a lower number of constraints compared to the number of species. It then has to solve a smaller number of differential equations compared to the number of equations required in solving the detailed kinetic model (DKM). The accuracy of this solution depends on the selection of the constraint. A systematic procedure which will help in identifying the constraint at an optimal level of accuracy is an essential for RCCE modeling. A fully automated Approximate Singular Value Decomposition of the Actual Degrees of Disequilibrium (ASVDADD) method is used in this study to derive the constraint for RCCE simulation. ASVDADD uses an algorithm which follows the simple algebraic analysis on results of underlying DKM to find the degree of disequilibrium (DoD) of the individual chemical reactions. The number of constraints which will be used in RCCE simulation can be selected to reduce the number of equations required to solve. In the current work, this ASVDADD method is applied on ethanol oxidation to select the constraint for RCCE simulation. Both DKM and RCCE calculations on ethanol fuel are demonstrated to compare the result of temperature distribution and an ignition delay time for validating the method.

Deep learning with convolutional neural networks for identification of liver masses and hepatocellular carcinoma: A systematic review.

BACKGROUNDArtificial intelligence, such as convolutional neural networks (CNNs), has been used in the interpretation of images and the diagnosis of hepatocellular cancer (HCC) and liver masses. CNN, a machine-learning algorithm similar to deep learning, has demonstrated its capability to recognise specific features that can detect pathological lesions.AIMTo assess the use of CNNs in examining HCC and liver masses images in the diagnosis of cancer and evaluating the accuracy level of CNNs and their performance.METHODSThe databases PubMed, EMBASE, and the Web of Science and research books were systematically searched using related keywords. Studies analysing pathological anatomy, cellular, and radiological images on HCC or liver masses using CNNs were identified according to the study protocol to detect cancer, differentiating cancer from other lesions, or staging the lesion. The data were extracted as per a predefined extraction. The accuracy level and performance of the CNNs in detecting cancer or early stages of cancer were analysed. The primary outcomes of the study were analysing the type of cancer or liver mass and identifying the type of images that showed optimum accuracy in cancer detection.RESULTSA total of 11 studies that met the selection criteria and were consistent with the aims of the study were identified. The studies demonstrated the ability to differentiate liver masses or differentiate HCC from other lesions (n = 6), HCC from cirrhosis or development of new tumours (n = 3), and HCC nuclei grading or segmentation (n = 2). The CNNs showed satisfactory levels of accuracy. The studies aimed at detecting lesions (n = 4), classification (n = 5), and segmentation (n = 2). Several methods were used to assess the accuracy of CNN models used.CONCLUSIONThe role of CNNs in analysing images and as tools in early detection of HCC or liver masses has been demonstrated in these studies. While a few limitations have been identified in these studies, overall there was an optimal level of accuracy of the CNNs used in segmentation and classification of liver cancers images.

Mood Analysis using Neural Networks

Identifying mood of a person using the facial expression has been an area of research interest. The research work described in this paper aims to propose a methodology to do the same. In this work, the input from a webcam is fed to the system which is captured frame by frame. The images are preprocessed and a model based on Convolutional Neural Network (CNN) has been used to predict the emotion of a person. The CNN model is trained using the FER2013 dataset to extract features for identification of emotions. The work flow consists of procuring model for training, cleaning the data, building the model and fine-tuning hyperparameters for an optimal level of accuracy. Parallel to this, the functions have been created to take input from webcam and to process the input to feed the model. The final step has been to integrate all the units. The testing of the application has been done for each function separately, then for the entire work as a whole.

Optimasi Naïve Bayes Dan Algoritma Genetika Untuk Prediksi Penerimaan Beasiswa Pendidikan Pada SMP Utama

Educational scholarships are one of the efforts to sustain students in getting a better education. Not a few students drop out in the middle of the road or cannot continue their education at the same level or higher level. Selection according to the criteria for scholarship recipients is important so that scholarships are on target. Similar to Depok Primary Middle School, educational scholarships are provided by schools based on 9 criteria for scholarship recipients, namely parent status, parent work, rented house, home appliances, vehicles, parents 'savings, parents' jewelry, cellphones and pocket money. With the number of prospective scholarship recipients there is an algorithm needed to accurately predict students who are entitled to scholarships. With the naïve bayes algorithm, accuracy is 77.50% in predicting scholarship recipients based on the criteria found in students. The use of genetic algorithms is done to get a more optimal level of accuracy. This is evidenced by the accuracy of 83.33%.

Implementasi Transformasi Haar Wavelet untuk Deteksi Citra Jeruk Nipis yang Busuk

Lime is a fruit that has been widely cultivated and used in Indonesia. Many products use this fruit in the production process. The process of sorting fruit is undeniably a very substantial early process. It is necessary for large-scale be aware of this in term of result and time required for the sorting process. Pattern Recognition is a discipline that focuses on classifying or picturing an object based on characteristics or main attribute of the object. In this research, the author implements Haar Wavelet Transformation method by characteristic extraction based on colour and texture , performs classification using K-Nearest Neighbor (k-NN) to detect indication of rotten lime and the grade of k on k-NN so the accuracy of the result could be acquired. Based on analysis result, Haar Wavelet Transformation method is able to be implemented to detect the indication of rotten lime and most optimal accuracy level of this system reaches the number of 85 percent.

AcT: Accuracy-aware crawling techniques for cloud-crawler

News aggregation websites collect news from various online sources using crawling techniques and provide a unified view to millions of users. Since, news sources update information frequently; aggregators have to recrawl them from time to time in order to have durable archiving of the news content. The majority of recrawling techniques assume the availability of unlimited resources and zero operating cost. However, in reality, the resources and budget are limited and it is impossible to crawl every news source at every point of time. To the best of our knowledge, none of the existing techniques discuss the crawling strategy that can retrieve the maximum amount of information in a resource/budget constrained environment. In this paper, we present a framework AcT that supports two different accuracy-aware personalized crawling techniques to attain the optimal accuracy level of retrieving the information. Given the crawling frequency as a resource constraint, the first scheme aims to find the optimal schedule that maximizes the accuracy. In the second scheme, we optimize the crawling frequency and the corresponding crawling schedule for a given accuracy level. We propose a supervised technique that monitors each news source for a particular time period and collect the news update patterns. The news update patterns are later analyzed using mixed integer programming to discover the optimal crawling schedule for the first scheme, whereas a greedy strategy is proposed to discover the optimal crawling frequency and crawling schedule for the second scheme. We develop a crawler for 87 news sources and performed a series of experiments to demonstrate the quality and efficiency of our proposed techniques against benchmark strategies.

Efficient Implementation of Inner-Outer Flexible GMRES for the Method of Moments Based on a Volume-Surface Integral Equation

This paper presents flexible inner-outer Krylov subspace methods, which are implemented using the fast multipole method (FMM) for solving scattering problems with mixed dielectric and conducting object. The flexible Krylov subspace methods refer to a class of methods that accept variable preconditioning. To obtain the maximum efficiency of the inner-outer methods, it is desirable to compute the inner iterations with the least possible effort. Hence, generally, inaccurate matrix-vector multiplication (MVM) is performed in the inner solver within a short computation time. This is realized by using a particular feature of the multipole techniques. The accuracy and computational cost of the FMM can be controlled by appropriately selecting the truncation number, which indicates the number of multipoles used to express far-field interactions. On the basis of the abovementioned fact, we construct a less-accurate but much cheaper version of the FMM by intentionally setting the truncation number to a sufficiently low value, and then use it for the computation of inaccurate MVM in the inner solver. However, there exists no definite rule for determining the suitable level of accuracy for the FMM within the inner solver. The main focus of this study is to clarify the relationship between the overall efficiency of the flexible inner-outer Krylov solver and the accuracy of the FMM within the inner solver. Numerical experiments reveal that there exits an optimal accuracy level for the FMM within the inner solver, and that a moderately accurate FMM operator serves as the optimal preconditioner.

The Optimal Accuracy Level in Asymmetric Contests

We interpret the discriminatory power, r, in the Power Contest Success Function (Tullock, 1980) as the contest designer's accuracy level. We look at the cases where two contestants are heterogeneous in ability and construct an equilibrium set for r > 0. We find that if the contestants are sufficiently different in ability, there always exists an optimal accuracy level for the contest designer. Additionally, as the difference in their abilities increases, the optimal accuracy level decreases.

Diagnosis of Dry Eye

An accurate measurement of tear production is clinically important in the diagnosis and monitoring of dry eye conditions. Re-examination of the results of Schirmer test indicated that the rate of tear secretion decreased with advancing age. Fluorophotometry revealed that the tear turnover rate also decreased with age. Then reappraisal was made on the clinical tests for dry eye syndrome. The non-invasive tear film breakup time (NIBUT) showed a resonable level of accuracy with a cut-off value of 5 seconds (sensitivity 95.9% and specificity 90.8%). The concentration of lactoferrin showed an optimal level of accuracy with a cut-off value of 1.1 mg/ml (sensitivity 79.4% and specificity 78.3%). A study of the ocular surface area revealed that the decrease of ocular surface area was related to the values of NIBUT in normal subjects younger than 50 years of age. The present findings suggested that a combination of these clinical tests was needed for the diagnosis of dry eye syndrome.

Enhanced attention in rhesus monkeys as a common factor for the cognitive effects of drugs with abuse potential.

One of the common neurochemical features of many drugs of abuse is their ability to directly or indirectly enhance dopaminergic activity in the brain, particularly within the ventral tegmental-nucleus accumbens pathway. Dopaminergic pathways in the frontal and limbic cortex also may be targets for these agents, where pharmacological effects could result in heightened attention and/or support self-administration behavior. The purpose of this study was to determine whether drugs from differing pharmacological classes that exhibit abuse potential would share the ability to counter distractability in the delayed matching task. Well trained mature macaques performed a computer-assisted delayed matching-to-sample task which included trials associated with three delay intervals and randomly interspersed task-relevant distractors. Drug regimens included four to five doses and subjects were tested no more than twice per week. All but one of the six compounds (tomoxetine), on average, increased task accuracy for either non-distractor or distractor trials. It was evident that for several compounds, doses required to improve accuracy for non-distractor trials were routinely greater than the doses required to improve accuracy for distractor trials. Data for the individualized Best dose (based upon the subject's optimal level of accuracy during distractor trials) revealed statistically significant distractor-related improvements in task accuracy for the same five compounds. The relative efficacy for reversing distractor-induced decrements in task accuracy was estimated by the level of improvement with respect to baseline: nomifensine (31%)>nicotine (22%) approximately morphine (19%) approximately caffeine (19%) approximately methylphenidate (22%) >tomoxetine (9%). Tomoxetine (noradrenergic preferring) was the only compound that did not produce a significant improvement in accuracy. These results provide pharmacological support for the concept that attentional mechanisms may play an important role in the "environmental" associative aspects of drug seeking behavior, and as such they may provide the basis for treatment strategies aimed at preventing relapse in detoxified addicts.

What makes a categorization task difficult?

To understand why some categorization tasks are more difficult than others, we consider five factors that may affect human performance--namely, covariance complexity, optimal accuracy level with and without internal noise, orientation of the optimal categorization rule, and class separability. We argue that covariance complexity, an information-theoretic measure of complexity, is an excellent predictor of task difficulty. We present an experiment that consists of five conditions using a simulated medical decision-making task In the task human observers view hundreds of hypothetical patient profiles and classify each profile into Disease Category A or B. Each profile is a continuous-valued, three-dimensional stimulus consisting of three vertical bars, where each bar height represents the result of a medical test. Across the five conditions, covariance complexity was systematically manipulated. Results indicate that variation in performance is largely a function of covariance complexity and partly a function of internal noise. The remaining three factors do not explain performance results. We present a challenge to categorization theorists to design models that account for human performance as predicted by covariance complexity.

A recursive full search algorithm based on temporal correlation

Although many fast searching-algorithms for motion estimations aim at reducing the computational complexity, the optimal accuracy is hardly achieved. Hence these methods are not suitable for bit-rate constrained environments. Due to a lack of regularity, VLSI implementation of these algorithms is not easy. In this study, we propose a new adaptive full search algorithm using the temporal correlation method and iterative layer process. Our algorithm is useful to decrease the computational complexity and achieves an optimal level of accuracy. Simulations demonstrate that our method can at least halve the computational complexity for full search estimation.