Balancing Technique Research Articles

Target firm's integrity culture and M&A performance

AbstractThis study investigates whether the attribute of integrity culture (derived from target firms’ annual reports) influences merger and acquisition (M&A) performance. We find that a target firm's integrity culture, measured from its 10‐K reports, has a positive and significant effect on market reaction to the bidder firm's M&A announcement. Our study's analysis is found to be robust to sample selection bias by utilising the entropy balancing technique and to endogeneity concerns by employing an instrumental variable approach. Our results are also robust to alternative measures of integrity culture and when controlling for a target firm's religiosity and corporate social responsibility, an acquirer firm's fixed effects, chief executive officer's fixed effects, governance for corporate control and advisor quality. We identify the retention of a target firm's directors and of its customers as channels that underlie our main findings. Furthermore, we find that acquisition synergies improve, with decreased time taken to complete the deal, for acquisitions of target firms with a higher integrity culture.

Improving clinical abbreviation sense disambiguation using attention-based Bi-LSTM and hybrid balancing techniques in imbalanced datasets.

Clinical abbreviations pose a challenge for clinical decision support systems due to their ambiguity. Additionally, clinical datasets often suffer from class imbalance, hindering the classification of such data. This imbalance leads to classifiers with low accuracy and high error rates. Traditional feature-engineered models struggle with this task, and class imbalance is a known factor that reduces the performance of neural network techniques. This study proposes an attention-based bidirectional long short-term memory (Bi-LSTM) model to improve clinical abbreviation disambiguation in clinical documents. We aim to address the challenges of limited training data and class imbalance by employing data generation techniques like reverse substitution and data augmentation with synonym substitution. We utilise a Bi-LSTM classification model with an attention mechanism to disambiguate each abbreviation. The model's performance is evaluated based on accuracy for each abbreviation. To address the limitations of imbalanced data, we employ data generation techniques to create a more balanced dataset. The evaluation results demonstrate that our data balancing technique significantly improves the model's accuracy by 2.08%. Furthermore, the proposed attention-based Bi-LSTM model achieves an accuracy of 96.09% on the UMN dataset, outperforming state-of-the-art results. Deep neural network methods, particularly Bi-LSTM, offer promising alternatives to traditional feature-engineered models for clinical abbreviation disambiguation. By employing data generation techniques, we can address the challenges posed by limited-resource and imbalanced clinical datasets. This approach leads to a significant improvement in model accuracy for clinical abbreviation disambiguation tasks.

Sentiment analysis of the Hamas-Israel war on YouTube comments using deep learning

Sentiment analysis aims to classify text based on the opinion or mentality expressed in a situation, which can be positive, negative, or neutral. Therefore, in the world, a lot of opinions are available on various social media sites, which must be gathered and analyzed to assess the general public’s opinion. Finding and monitoring comments, as well as manually extracting the information contained in them, is a difficult task due to the vast diversity of ideas on YouTube. Identifying public opinion on war topics is crucial for offering insights to opposing sides based on popular opinion and emotions about the ongoing war. To address the gap, we build a model on YouTube comment sentiment analysis of the Hamas-Israel war to determine public opinion. In this study, we address the gaps by developing a deep learning-based approach for sentiment analysis. We have collected 24,360 comments from popular YouTube News Channels including BBC, WION, Aljazeera, and others about the Hamas-Israel War using YouTube API and Google spreadsheet and labeled them by linguistic experts into three classes: positive, negative, and neutral. Then, textual comments were preprocessed using natural language processing (NLP) techniques, and features were extracted using Word2vec, FastText, and GloVe. Moreover, we have used the SMOTE data balancing technique and used different data splits, but the 80/20 train-test split ratio has the highest accuracy. For classification model building, commonly used classification algorithms LSTM, Bi-LSTM, GRU, and Hybrid of CNN and Bi-LSTM were applied, and their performance is compared. As a result, the Hybrid of CNN and Bi-LSTM with Word2vec achieved the highest performance with 95.73% accuracy for comments classifications.

Automated Sensor Node Malicious Activity Detection with Explainability Analysis.

Cybersecurity has become a major concern in the modern world due to our heavy reliance on cyber systems. Advanced automated systems utilize many sensors for intelligent decision-making, and any malicious activity of these sensors could potentially lead to a system-wide collapse. To ensure safety and security, it is essential to have a reliable system that can automatically detect and prevent any malicious activity, and modern detection systems are created based on machine learning (ML) models. Most often, the dataset generated from the sensor node for detecting malicious activity is highly imbalanced because the Malicious class is significantly fewer than the Non-Malicious class. To address these issues, we proposed a hybrid data balancing technique in combination with a Cluster-based Under Sampling and Synthetic Minority Oversampling Technique (SMOTE). We have also proposed an ensemble machine learning model that outperforms other standard ML models, achieving 99.7% accuracy. Additionally, we have identified the critical features that pose security risks to the sensor nodes with extensive explainability analysis of our proposed machine learning model. In brief, we have explored a hybrid data balancing method, developed a robust ensemble machine learning model for detecting malicious sensor nodes, and conducted a thorough analysis of the model's explainability.

Comprehensive review of load balancing in cloud computing system

Load balancing plays a critical role in optimizing resource utilization and enhancing performance in cloud computing systems. As cloud environments grow in scale and complexity, efficient load balancing mechanisms become increasingly vital. This paper presents a comprehensive review of load balancing techniques in cloud computing systems, with a focus on their applicability, advantages, and limitations. The review encompasses both static and dynamic load balancing approaches, evaluating their effectiveness in addressing the challenges posed by cloud infrastructure, such as heterogeneity, scalability, and variability in workload demands. Furthermore, the review examines load balancing algorithms considering factors such as resource utilization, response time, fault tolerance, and energy efficiency. Additionally, the impact of load balancing on cloud performance metrics, including throughput, latency, and scalability, is analyzed. This review aims to provide insights into the state-of-the-art load balancing strategies and serve as a valuable resource for researchers, practitioners, and system designers involved in the development and optimization of cloud computing systems.

Uso de las técnicas DownSampling y UpSampling para abordar el desequilibrio de datos en la predicción de personas propensas a sufrir accidentes cerebrovasculares

The DownSampling and UpSampling data balancing techniques are used applied to a set related to individuals prone to having a stroke. The purpose of this work is to demonstrate the importance of the application of DownSampling and UpSampling techniques when we find data that present imbalance; making a comparison between the two mentioned techniques and analyzing the behavior of the measures that are calculated in the confusion matrix when the prediction model is created. The data set is composed of 4981 records, of which 4773 belong to the class of those who have not suffered a stroke and 248 to the class that has had one. It was found that for this data set the best technique to treat the imbalance is UpSampling with the largest of its replicas and when the model is going to be evaluated it is important not only to base it on its Accuracy, but also on other measures that result from the confusion matrix, this to achieve a better analysis of the results obtained.

Optimizing Cloud Application Performance: A Survey on Load Balancing Techniques

In the contemporary realm of operation in the World Wide Web, the cloud applications have to meet the high availability, operations on dynamic loads and must function at a very high quality. Load balancing is a proper technique to achieve above goals to distribute the loads across the server or to the various resources. This distribution optimizes performance, scalability, reliability and resources to be used, hence making the network to be appealing to bigger organizations to adopt it. The advantages because of load balancing are reduced response time, increased throughput and fault tolerance because the network traffic load is spread evenly among different servers thereby avoiding the occurrence of a bottleneck server. Some of these ways include Round Robin, Least Connection, and Weighted Distribution, help in the process by making it possible for systems to horizontally scale up for more traffic. As cloud services becomes popular, it becomes very important to manage the load since some applications or services may be more resource intensive than others. It distributes the incoming requests following the current loads on various servers and consequently, no server is too busy or idle. Also, load balancers provide for fault tolerance in the sense that traffic will be handled by other healthy servers in the occurrence of failures hence the solutions are highly available and reliable. Load balancing algorithms such from the basic rule-dependent to complex reinforcement learning algorithms are very crucial with respect to allocation of resources, energy management, and stability of the system. These algorithms will be increasingly important as cloud environments develop further in the efficiency of delivering services and the managing of resources needed, benefiting both the economy and the environment. INDEX TERMS: Performance, Scalability, Response Times, Latency, Horizontal Scaling, Load Balancing

Integrating SMOTE-Tomek and Fusion Learning with XGBoost Meta-Learner for Robust Diabetes Recognition

This research aims to develop a robust diabetes classification method by integrating the Synthetic Minority Over-sampling Technique (SMOTE)-Tomek technique for data balancing and using a machine learning ensemble led by eXtreme Gradient Boosting (XGB) as a meta-learner. We propose an ensemble model that combines deep learning techniques such as Bidirectional Long Short-Term Memory (BiLSTM) and Bidirectional Gated Recurrent Units (BiGRU) with XGB classifier as the base learner. The data used included the Pima Indians Diabetes and Iraqi Society Diabetes datasets, which were processed by missing value handling, duplication, normalization, and the application of SMOTE-Tomek to resolve data imbalances. XGB, as a meta-learner, successfully improves the model's predictive ability by reducing bias and variance, resulting in more accurate and robust classification. The proposed ensemble model achieves perfect accuracy, precision, recall, specificity, and F1 score of 100% on all tested datasets. This method shows that combining ensemble learning techniques with a rigorous preprocessing approach can significantly improve diabetes classification performance.

An ensemble of deep learning architectures for accurate plant disease classification

A substantial fraction of agricultural produce loss can be attributed to plant diseases. Agricultural yield loss can have far-reaching consequences for a country's economy and contribute to global food insecurity. Early detection of plant diseases can be instrumental in maintaining global health and welfare. A pathologist's visual evaluation is typically used to make an early diagnosis of plant diseases. This technique involves experts or farmers examining plants with the naked eye and classifying the disease depending on their previous experience. This conventional approach includes drawbacks like low accuracy and the need for human expertise. This motivates researchers to investigate automated systems for the early diagnosis of plant diseases.To achieve this goal an ensemble of different deep learning architectures (DenseNet201, efficientNetB0, inceptionresnetV2, efficientNetB3) is introduced to increase the classification accuracy of plant leaf diseases. In this work, a novel image-processing technique is proposed to increase the efficiency of deep-learning models. Also, a data balancing technique is used to solve the problem of the imbalanced dataset. Five different deep-learning models are trained and tested using the largest plant disease dataset; PlantVillage. Ten different ensembles (chosen randomly) of the deep learning models are tested and compared to find the ensemble with the highest accuracy.The proposed ensemble model was able to achieve 99.89% accuracy on the New PlantVillage dataset. PlantVillage is a challenging dataset with 38 classes. Achieving high accuracies on such a dataset proves the ability of the system to generalize on unseen data or real-world scenarios. A comparison with the state-of-the-art is made with other available models from the literature. A section about this is added to show the superior performance of the proposed ensemble model in terms of accuracy and F1-score.

Advanced Deep Learning for ECG Anomaly Detection in Imbalanced Data

Segmentation of ECG to obtain significant and relevant features has been an inevitable step to reduce the dimensionality of dataset in automated heart disease diagno- sis systems.Accurate and speedy classification of heart beats is required to reduce high mortality rate which is prevalent due to cardiovascular diseases(CVD). Nonstationarity and high variability exhibited by ECG signal leads to increase in com- plexity of analysis in time and frequency domain.Challenges in processing are further enhanced due to imbalanced and vague datasets.Deep learning based methods have been used in litera- ture to combat the problem of imbalanced datasets.This paper employs an effective recurrent neural network with long short term memory layers(LSTM) to classify the heart beats into two classes.It has been observed that LSTM network can effectively extract the sequential timing information in the input ECG samples.To remove the imbalance in the datasets,oversampling and focal loss based weight balancing techniques have been used which eventually enhance the accuracy of classification. MIT- BIH database has been used for experimental evaluation.The proposed approach ,LSTM network with oversampling tech- nique,provides an accuracy of 99.54% which is far better as compared to the traditional approaches which yield accuracy around 95%.Moreover this method is insensitive to quality of ECG signals due to the involvement of fuzzification procedure in the initial steps.Deployment of the proposed method for biosignal telemetry or pharmaceutical research to assist the physicians in their work is a possible future advancement in this domain. Index Terms—ECG, RNN, LSTM,Classification, imbalance.

Arrhythmia Classification from ECG Signals Using Transformers and Data Balancing Techniques

While many arrhythmias pose minimal threat, certain heart rhythm irregularities elevate the potential for stroke or heart failure. The complexity arises particularly with the supraventricular premature heartbeat which has a resemblance to a normal beat and occurs infrequently. Consequently, this research proposes a data balancing and classification technique that enhances the accuracy of identifying mentioned hard-to-classify heartbeats while maintaining robust metrics for other classes. The study introduces a deep learning framework combined with a multi-head attention transformer, for balancing – under-sampling and synthetic minority oversampling are used. To evaluate the proposed model, various experiments based on real data were conducted. The results were compared with an existing model used in chest belt heartbeat monitoring, and the results show that the transformer model achieved better performance for supraventricular premature heartbeats, at the same time reaching high overall and per-class metrics.

A Novel Data Augmentation Method for Radiomics Analysis Using Image Perturbations

Radiomics extracts hundreds of features from medical images to quantitively characterize a region of interest (ROI). When applying radiomics, imbalanced or small dataset issues are commonly addressed using under or over-sampling, the latter being applied directly to the extracted features. Aim of this study is to propose a novel balancing and data augmentation technique by applying perturbations (erosion, dilation, contour randomization) to the ROI in cardiac computed tomography images. From the perturbed ROIs, radiomic features are extracted, thus creating additional samples. This approach was tested addressing the clinical problem of distinguishing cardiac amyloidosis (CA) from aortic stenosis (AS) and hypertrophic cardiomyopathy (HCM). Twenty-one CA, thirty-two AS and twenty-one HCM patients were included in the study. From each original and perturbed ROI, 107 radiomic features were extracted. The CA-AS dataset was balanced using the perturbation-based method along with random over-sampling, adaptive synthetic (ADASYN) and the synthetic minority oversampling technique (SMOTE). The same methods were tested to perform data augmentation dealing with CA and HCM. Features were submitted to robustness, redundancy, and relevance analysis testing five feature selection methods (p-value, least absolute shrinkage and selection operator (LASSO), semi-supervised LASSO, principal component analysis (PCA), semi-supervised PCA). Support vector machine performed the classification tasks, and its performance were evaluated by means of a 10-fold cross-validation. The perturbation-based approach provided the best performances in terms of f1 score and balanced accuracy in both CA-AS (f1 score: 80%, AUC: 0.91) and CA-HCM (f1 score: 86%, AUC: 0.92) classifications. These results suggest that ROI perturbations represent a powerful approach to address both data balancing and augmentation issues.

A hybrid framework for routing and channel assignment in WMN’s

Wireless mesh network (WMNs) can replace the physical existence of wired network; nevertheless, to solve the problem of traffic and congestion, they must carefully arrange radio resource assignment. In this paper, we focus on the major issues while transferring the data over the network and optimization of resources. WMN mainly suffers from congestion problem when numbers of channel transfer data at a same time which indirectly leads to overlapping channels and sometime data cannot be mitigated to destination. To overcome this problem and provide optimal solution we proposed hybrid channel assignment technique which offers four phase solution technique, in this technique firstly by mitigating the traffic than assigning the optimal path based on greedy and BFS. The purpose of this congestion control hybrid ant based greedy-BFS-load balancing (CCHAGBL) technique is to diminish the number of used slots, which is directly related to the overall resource assignment. We also provide optimal solution using Ant colony optimization technique with hybrid algorithm to achieve the network efficiency and resource utilization with randomly generated traffic. With the help of hybrid ant based greedy-BFS-load balancing (GBL) channel assignment algorithm throughput and packet delivery ratio is upgraded and delay is reduced to minimum.

Efficient diagnosis of psoriasis and lichen planus cutaneous diseases using deep learning approach

The tendency of skin diseases to manifest in a unique and yet similar appearance, absence of enough competent dermatologists, and urgency of diagnosis and classification on time and accurately, makes the need of machine aided diagnosis blatant. This study is conducted with the purpose of broadening the research in skin disease diagnosis with computer by traversing the capabilities of deep Learning algorithms to classify two skin diseases noticeably close in appearance, Psoriasis and Lichen Planus. The resemblance between these two skin diseases is striking, often resulting in their classification within the same category. Despite this, there is a dearth of research focusing specifically on these diseases. A customized 50 layers ResNet-50 architecture of convolutional neural network is used and the results are validated through fivefold cross-validation, threefold cross-validation, and random split. By utilizing advanced data augmentation and class balancing techniques, the diversity of the dataset has increased, and the dataset imbalance has been minimized. ResNet-50 has achieved an accuracy of 89.07%, sensitivity of 86.46%, and specificity of 86.02%. With their promising results, these algorithms make the potential of machine aided diagnosis clear. Deep Learning algorithms could provide assistance to physicians and dermatologists by classification of skin diseases, with similar appearance, in real-time.

Quality Evaluation of Fermented Pre Gelatinized Unripe Plantain and Soybean Based Complementary Foods 1: Physicochemical, Sensory and Rheological Properties

Aims: This study aimed at evaluating the effect of the degree (%) of starch gelatinization (G) and fermentation (F) on the physicochemical characteristics of the flours and also the sensory and flow properties of the gruels of unripe plantain fruits and soybean seeds based complementary foods. Study Design: Completely randomized design Place and duration of the Study: This study was carried out in Makurdi, Benue State, Nigeria, between January and November 2023. Methodology: Plantain slices heated to obtain 10% to 100% starch gelatinization were subjected to accelerated natural fermentation followed by drying and milling to yield fermented (F) flours. Non-gelatinized (NG) and nonfermented (NF) lots served as controls. The flours were each combined with soybean flour to obtain 16 g protein/100 g of each mixture based on the proximate compositions of the inputs using material balancing technique. The flours’ oil absorption capacities (OAC), water absorption capacities (WAC), packed bulk densities (PBD), sensory attributes (taste, mouth feel, appearance, overall acceptability) and flow properties of their gruels were evaluated using standard methods. Significant differences and separation of the data means were achieved by Duncan multiple range and Turkey’s tests using an SPSS package, respectively. Results: Gelatinization and fermentation increased WAC and OAC, but decreased packed bulk density (PBD) of the flours with concomitant reduction in pH, viscosities and improved sensory attributes of the gruels. Generally, viscosities increased with increase in slurry concentration and decreased with increase in temperature and shear rates. The flow behavior indices ranged from 0.27 to 0.64, with lower values in gelatinized and fermented samples, showing more pseudoplastic behavior in pretreated samples. Conclusion: Gelatinization and natural fermentation are therefore adaptable technologies, especially at rural levels, to improve acceptability and bulk reduction of resistant starch-based complementary foods.

Secure authentication scheme with Archimedes optimization algorithm for load balancing technique in fog computing

Secure authentication scheme with Archimedes optimization algorithm for load balancing technique in fog computing

Earnings Management via Not-Wholly-Owned Subsidiaries

We investigate an unexplored mechanism of earnings management: income shifting from not-wholly-owned subsidiaries to help the parent company avoid losses at the expense of subsidiaries. Consolidated net income attributable to the parent company (i.e., net income) increases through this mechanism, as the parent company enjoys the full amount of the shifted earnings rather than sharing them with minority investors. We design an empirical model to directly estimate the amount of income shifted from subsidiaries to parent firms. Employing this measure, we find that firms opportunistically decrease earnings of their not-wholly-owned subsidiaries to manage net income upward to avoid losses. The results are stronger for firms with high noncontrolling ownership, firms with large subsidiaries, firms with strong influence over not-wholly-owned subsidiaries, and firms with a high level of related-party transactions. Our results are robust to alternative research designs, including controls for within-firm variations, alternative earnings thresholds, propensity score matching, and entropy balancing techniques. Our mechanism of earnings management is generalizable to other earnings management scenarios, such as share pledging. This paper was accepted by Brian Bushee, accounting. Funding: X. Zhang thanks the National Natural Science Foundation of China [Grant 72102243] for financial support. M. Luo thank the financial support from National Natural Science Foundation of China [Grant 71840011], and the Research Center for Digital Financial Assets at School of Economics and Management of Tsinghua University. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2022.03090 .

Balancing Techniques for Advanced Financial Distress Detection Using Artificial Intelligence

Imbalanced datasets are one of the main issues encountered by artificial intelligence researchers, as machine learning (ML) algorithms can become biased toward the majority class and perform insufficiently on the minority classes. Financial distress (FD) is one of the numerous real-world applications of ML, struggling with this issue. Furthermore, the topic of financial distress holds considerable interest for both academics and practitioners due to the non-determined indicators of condition states. This research focuses on the involvement of balancing techniques according to different FD condition states. Moreover, this research was expanded by implementing ML models and dimensionality reduction techniques. During the course of this study, a Combined FD was constructed using five distinct conditions, ten distinct class balancing techniques, five distinct dimensionality reduction techniques, two features selection strategies, eleven machine learning models, and twelve weighted majority algorithms (WMAs). Results revealed that the highest area under the receiver operating characteristic (ROC) curve (AUC) score was achieved when using the extreme gradient boosting machine (XGBoost) feature selection technique, the experimental max number strategy, the undersampling methods, and the WMA 3.1 weighted majority algorithm (i.e., with categorical boosting (CatBoost), XGBoost, and random forest (RF) having equal voting weights). Moreover, this research has introduced a novel approach for setting the condition states of financial distress, including perspectives from debt and change in employment. These outcomes have been achieved utilizing authentic enterprise data from small and medium Lithuanian enterprises.

Explainable prediction of node labels in multilayer networks: a case study of turnover prediction in organizations.

In real-world classification problems, it is important to build accurate prediction models and provide information that can improve decision-making. Decision-support tools are often based on network models, and this article uses information encoded by social networks to solve the problem of employer turnover. However, understanding the factors behind black-box prediction models can be challenging. Our question was about the predictability of employee turnover, given information from the multilayer network that describes collaborations and perceptions that assess the performance of organizations that indicate the success of cooperation. Our goal was to develop an accurate prediction procedure, preserve the interpretability of the classification, and capture the wide variety of specific reasons that explain positive cases. After a feature engineering, we identified variables with the best predictive power using decision trees and ranked them based on their added value considering their frequent co-occurrence. We applied the Random Forest using the SMOTE balancing technique for prediction. We calculated the SHAP values to identify the variables that contribute the most to individual predictions. As a last step, we clustered the sample based on SHAP values to fine-tune the explanations for quitting due to different background factors.

A CMOS BD-BCI: Neural Recorder with Two-Step Time-Domain Quantizer and Multi-Polar Stimulator with Dual-Mode Charge Balancing.

This work presents a bi-directional brain-computer interface (BD-BCI) including a high-dynamic-range (HDR) two-step time-domain neural acquisition (TTNA) system and a high-voltage (HV) multipolar neural stimulation system incorporating dual-mode time-based charge balancing (DTCB) technique. The proposed TTNA includes four independent recording modules that can sense microvolt neural signals while tolerating large stimulation artifacts. In addition, it exhibits an integrated input-referred noise of 2.3 μVrms from 0.1- to 250-Hz and can handle a linear input-signal swing of up to 340 mVPP. The multipolar stimulator is composed of four standalone stimulators each with a maximum current of up to 14 mA (±20-V of voltage compliance) and 8-bit resolution. An inter-channel interference cancellation circuitry is introduced to preserve the accuracy and effectiveness of the DTCB method in the multipolar-stimulation configuration. Fabricated in an HV 180-nm CMOS technology, the BD-BCI chipset undergoes extensive in-vitro and in-vivo evaluations. The recording system achieves a measured SNDR, SFDR, and CMRR of 84.8 dB, 89.6 dB, and >105 dB, respectively. The measurement results verify that the stimulation system is capable of performing high-precision charge balancing with ±2 mV and ±7.5 mV accuracy in the interpulse-bounded time-based charge balancing (TCB) and artifactless TCB modes, respectively.