Applied Sciences

This work is focused on deep learning methods, such as feedforward neural network (FNN) and convolutional neural network (CNN), for pathological voice detection using mel-frequency cepstral coefficients (MFCCs), linear prediction cepstrum coefficients (LPCCs), and higher-order statistics (HOSs) parameters. In total, 518 voice data samples were obtained from the publicly available Saarbruecken voice database (SVD), comprising recordings of 259 healthy and 259 pathological women and men, respectively, and using /a/, /i/, and /u/ vowels at normal pitch. Significant differences were observed between the normal and the pathological voice signals for normalized skewness (p = 0.000) and kurtosis (p = 0.000), except for normalized kurtosis (p = 0.051) that was estimated in the /u/ samples in women. These parameters are useful and meaningful for classifying pathological voice signals. The highest accuracy, 82.69%, was achieved by the CNN classifier with the LPCCs parameter in the /u/ vowel in men. The second-best performance, 80.77%, was obtained with a combination of the FNN classifier, MFCCs, and HOSs for the /i/ vowel samples in women. There was merit in combining the acoustic measures with HOS parameters for better characterization in terms of accuracy. The combination of various parameters and deep learning methods was also useful for distinguishing normal from pathological voices. Full article

Unmanned aerial vehicles (UAVs) are being widely utilized for various missions: in both civilian and military sectors. Many of these missions demand UAVs to acquire artificial intelligence about the environments they are navigating in. This perception can be realized by training a computing machine to classify objects in the environment. One of the well known machine training approaches is supervised deep learning, which enables a machine to classify objects. However, supervised deep learning comes with huge sacrifice in terms of time and computational resources. Collecting big input data, pre-training processes, such as labeling training data, and the need for a high performance computer for training are some of the challenges that supervised deep learning poses. To address these setbacks, this study proposes mission specific input data augmentation techniques and the design of light-weight deep neural network architecture that is capable of real-time object classification. Semi-direct visual odometry (SVO) data of augmented images are used to train the network for object classification. Ten classes of 10,000 different images in each class were used as input data where 80% were for training the network and the remaining 20% were used for network validation. For the optimization of the designed deep neural network, a sequential gradient descent algorithm was implemented. This algorithm has the advantage of handling redundancy in the data more efficiently than other algorithms. Full article

Outbound telemarketing is an efficient direct marketing method wherein telemarketers solicit potential customers by phone to purchase or subscribe to products or services. However, those who are not interested in the information or offers provided by outbound telemarketing generally experience such interactions negatively because they perceive telemarketing as spam. In this study, therefore, we investigate the use of deep learning models to predict the success of outbound telemarketing for insurance policy loans. We propose an explainable multiple-filter convolutional neural network model called XmCNN that can alleviate overfitting and extract various high-level features using hundreds of input variables. To enable the practical application of the proposed method, we also examine ensemble models to further improve its performance. We experimentally demonstrate that the proposed XmCNN significantly outperformed conventional deep neural network models and machine learning models. Furthermore, a deep learning ensemble model constructed using the XmCNN architecture achieved the lowest false positive rate (4.92%) and the highest F1-score (87.47%). We identified important variables influencing insurance policy loan prediction through the proposed model, suggesting that these factors should be considered in practice. The proposed method may increase the efficiency of outbound telemarketing and reduce the spam problems caused by calling non-potential customers. Full article

Robotic exoskeleton technologies are applied in the medical field to help patients with impaired mobility to recover their motor functions. Relevant literature shows that usability and cognitive workload may influence the patients’ likelihood to benefit from the use of rehabilitative exoskeletons. Following the PRISMA method, the present study aimed to systematically review the assessment methods of usability and cognitive workload in the use of exoskeletal devices for motor rehabilitation. The literature search was conducted in the Scopus and Web of Science bibliographical databases, using 16 keywords that were combined into one search query. A final sample of 23 articles was included in the review, from which 18 distinct assessment methods were identified. Of them, 15 aimed to assess usability, whereas 3 aimed to assess cognitive workload in the use of rehabilitative exoskeletons. Some of the identified methods (e.g., SUS, QUEST, SWAT, and NASA-TLX) showed good psychometric properties and were therefore proven to be appropriate to assess usability and cognitive workload while performing exoskeleton-based rehabilitation. The current study may contribute to the development of guidelines and analytical tools for exoskeletons’ usability and exoskeleton-related patients’ cognitive workload in the domain of medical rehabilitation. Full article

The built environment sector is one of the main sources of greenhouse gas emissions and resource depletion that contributes to the climate change crisis. The European Commission, in the “Green New Deal,” highlights that the sustainable regeneration/requalification of existing buildings plays a fundamental role to maximize the objective of decarbonization and resource conservation for 2050. The aim of this study was to understand how historic buildings’ energy retrofit projects can contribute to achieve this goal. In this study, we made a life cycle assessment to evaluate an energy retrofit project of Villa Vannucchi, an historic building located in San Giorgio a Cremano (Naples). The results of this application showed that the use of hemp material, for walls’ thermal insulation, significantly reduces the percentage of environmental impacts in the entire material life cycle (compared with traditional materials). This was because the plant removes a significant percentage of CO₂ already from the atmosphere when it is growing. In conclusion, the assessment of different design scenarios that promote the use of innovative technologies and materials can be of high utility to designers to compare and choose efficient solutions for the sustainable/circular renovation of historic buildings. Full article

Increasing evidence implicates intervertebral disc (IVD) degeneration as a major contributor to low back pain. In addition to a series of pathogenic processes, degenerated IVDs become vascularized in contrast to healthy IVDs. In this context, angiopoietin (Ang) plays a crucial role and is involved in cytokine recruitment, and anabolic and catabolic reactions within the extracellular matrix (ECM). Over the last decade, a progenitor cell population has been described in the nucleus pulposus (NP) of the IVD to be positive for the Tie2 marker (also known as Ang-1 receptor). In this study, we investigated the influence of Ang-1 and Ang-2 on human NP cell (Tie2⁺, Tie2^- or mixed) populations isolated from trauma patients during 7 days in normoxia (21% O₂) or hypoxia (≤ 5% O₂). At the end of the process, the proliferation and metabolic activity of the NP cells were analyzed. Additionally, the relative gene expression of NP-related markers was evaluated. NP cells showed a higher proliferation depending on the Ang treatment. Moreover, the study revealed higher NP cell metabolism when cultured in hypoxia. Additionally, the relative gene expression followed, with an increase linked to the oxygen level and Ang concentration. Our study comparing different NP cell populations may be the start of new approaches for the treatment of IVD degeneration. Full article

The imbalance of the currents leaked by CMOS standard cells when different logic values are applied to their inputs can be exploited as a side channel to recover the secrets of cryptographic implementations. Traditional side-channel countermeasures, primarily designed to thwart the dynamic leakage behavior, were shown to be much less powerful against this static threat. Thus, a special protection mechanism called Balanced Static Power Logic (BSPL) has been proposed very recently. Essentially, fundamental standard cells are re-designed to balance their drain-source leakage current independent of the given input. In this work, we analyze the BSPL concept in more detail and reveal several design issues that limit its effectiveness as a universal logic library. Although balancing drain-source currents remains a valid approach even in more advanced technology generations, we show that it is conceptually insufficient to achieve a fully data-independent leakage behavior in smaller geometries. Instead, we suggest an alternative approach, so-called improved BSPL (iBSPL). To evaluate the proposed method, we use information theoretic analysis. As an attack strategy, we have chosen Moments-Correlating DPA (MCDPA), since this analysis technique does not depend on a particular leakage model and allows a fair comparison. Through these evaluation methods, we show iBSPL demands fewer resources and delivers better balance in the ideal case as well as in the presence of process variations. Full article

Due to the lack of information about the concept of Tons of Steering Pull (TSP) of many escort tugs, and the lack of research works relating the TSP demanded by a tethered vessel with respect to the TSP provided by tugs, the present paper shows an original study with mathematical models on how to solve these problems. What is more, an important percentage of the towing sector always employs Bollard Pull (BP), which is considered the only parameter capable of defining performance, so this paper aims to relate BP with TSP. The present research was carried out based on more than 25 escort tugs of different towing companies. Furthermore, a real case study of different tanker vessels was used for modelling purposes of tethered vessels’ TSP. Finally, once the proposed models were obtained, they were compared with International Maritime Organization (IMO) guidelines. The results showed charts with the main independent variables of tugs and vessels in order to be as useful and practical as possible to the shipping industry, mainly to ship owners and tug operators, from a safety point of view. Full article

In vitro and in vivo models simulating the dental caries process enable the evaluation of anti-caries modalities for prevention and treatment. Animal experimentation remains important for improving human and animal health. Nonetheless, reducing animal sacrifice for research is desirable. The aim of the study was to establish a new reproducible in vitro caries model system and compare it to an in vivo model using similar conditions. Hemi-mandibles were extracted from previously euthanized healthy 10-week-old BALB/C female mice. Jaws were subjected to saliva, high-sucrose diet, and dental caries bacteria Streptococcus mutans UA159 for 5 days. Similar caries induction protocol was used in vivo in fifteen BALB/c female mice (6–7 weeks old) and compared to the in vitro model. Caries lesions were assessed clinically by photographic analysis and µCT analysis, and bacterial growth was evaluated. Under in vitro experimental conditions, carious lesions evolved within 5 days, prominently in the depth of the occlusal fissures in the control group as depicted by photographic analysis, µCT analysis, and bacterial growth. The developed in vitro caries model presented in this study may be a novel animal sparing model for caries disease studies and can be used widely to evaluate the efficacy of different antibacterial dental materials. Full article

In this work, we use a copula-based approach to select the most important features for a random forest classification. Based on associated copulas between these features, we carry out this feature selection. We then embed the selected features to a random forest algorithm to classify a label-valued outcome. Our algorithm enables us to select the most relevant features when the features are not necessarily connected by a linear function; also, we can stop the classification when we reach the desired level of accuracy. We apply this method on a simulation study as well as a real dataset of COVID-19 and for a diabetes dataset. Full article

The study tried to contribute to solving two serious environmental issues: CO₂ reducing and sewage sludge disposal. Thus, sewage-sludge-derived materials were obtained in order to be evaluated for CO₂ adsorption capacity. Therefore, the char resulted after the sewage sludge pyrolysis was subjected to oxidation and chemical activation processes by using different quantities of alkaline hydroxide. One of the obtained materials, activated with a lower quantity of alkaline hydroxide, was also treated with acid chloride. Further, the materials were structural and texturally characterized, and material treated with acid chloride was used for CO₂ adsorption tests, due to high surface area and pore volume. The handmade system coupled to a gas chromatograph allowed the adsorption efficiency evaluation using different feed gases (rich and poor in CO₂) by completed purge of pipe line and on-line check. Additionally, the adsorption capacity, separation efficiency, and CO₂ recovery were calculated. Taking into account the values for adsorption capacity (separation efficiency and CO₂ recovery), it can be concluded that the sewage sludge derived material could be a promising solution for CO₂ reduction and waste disposal. Full article

This article addresses timetable synchronization in public transportation, an important problem in modern smart cities, in order to guarantee a proper quality of service to citizens. Two variants of the bus timetabling synchronization problem considering extended transfer zones are studied: optimizing offsets and optimizing offsets and headways for each line. An exact mixed integer programming and an evolutionary algorithm are developed to solve both problem variants. The algorithms are evaluated on 45 instances of a real case study, the intelligent transportation system of Montevideo, Uruguay. Experimental results reported significant improvements over the current timetable implemented by the city administration. The number of successful synchronizations improved up to 66.6% and 179.9% for the first and second problem variant, respectively. The average waiting times for transfers improved, especially in tight problem instances (up to 57.8% and 158.3% for the first and second problem variant, respectively). The proposed planning methods are useful to help decision makers to configure public transportation systems. Full article

This paper presents an improved slope stability sensitivity analysis (ISSSA) model that takes anchoring factors into consideration in umbrella-anchored sand and clay slopes under reservoir water level fluctuation. The results of the ISSSA model show that the slope inclination and the layout density of anchors are the main controlling factors for sand slope stability under fluctuation of the water level, while the slope inclination and water head height are the main controlling factors for slope stability in the Cangjiang bridge—Yingpan slope of Yunnan province in China. Moreover, there is an optimum anchorage angle, in the range of 25–45 degrees, which has the greatest influence on slope stability. The fluctuation of the reservoir water level is an important factor that triggers slope instability; in particular, a sudden drop in the surface water level can easily lead to landslides; therefore, corresponding measures should be implemented in a timely manner in order to mitigate landslide disasters. Full article

With the advancement of intelligent compaction technology, real-time quality control has been widely investigated on the subgrade, while it is insufficient on asphalt pavement. This paper aims to estimate the real-time compaction quality of hot mix asphalt (HMA) using an artificial neural network (ANN) classifier. A field experiment of HMA compaction was designed. The vibration patterns of the drum were identified by using the ANN classifier and classified based on the compaction levels. The vibration signals were collected and the degree of compaction was measured in the field experiment. The collected signals were processed and the features of vibration patterns were extracted. The processed signals were tagged with their corresponding compaction level to form the sample dataset to train the ANN models. Four ANN models with different hidden layer setups were considered to investigate the effect of hidden layer structure on performance. To test the performance of the ANN classifier, the predictions made by ANN were compared with the measuring results from a non-nuclear density gauge (NNDG). The testing results show that the ANN classifier has good performance and huge potential for estimating the compaction quality of HMA in real-time. Full article

The burial of organic carbon in lake sediments plays an important role in the terrestrial carbon cycle. Clarifying the current status of carbon burial in the lakes of Central Asia is of great significance for the application of carbon balance assessments. With the analysis of the total organic carbon and nitrogen and the carbon isotope and organic carbon burial rate in the core sediment of the North Aral Sea, the status and influencing factors of organic carbon burial over the past 70 years can be revealed. The results showed that the main source of organic carbon was predominantly from lacustrine aquatic plants. However, the contribution of terrigenous organic carbon increased from the 1950s to the 1960s. The burial rate of organic carbon in North Aral Sea sediments was consistent with the overall change in the regional temperature. The burial rate of organic carbon showed an upward trend as a whole with an average of 28.78 g·m⁻²·a⁻¹. Since 2010, the burial rate of organic carbon has stood at the highest level in nearly 70 years, with an average of 55.66 g·m⁻²·a⁻¹. The protection of a lake by human beings can not only significantly improve the lake’s aquatic ecosystem but also help to increase the burial rate of the lake’s organic carbon. Full article

In the recent past, sustainable development has been considered a major issue for urban and regional studies. Adaptive reuse appears to be a practical solution for sustainable urban development. Beyond and in addition to a conceptual base consistent with circular economy and sustainability principles, how do we know if adaptive reuse is actually sustainable, provided that it constitutes a multidisciplinary and multilevel process? The present study aims at evaluating, in as much as feasible quantitative terms, adaptive reuse practices sustainability. This was attained using a set of indicators, developed combining PESTLE (the Political, Economic, Technical, Social, Legal, and Environmental aspects) and SWOT (the Strengths, Weaknesses, Opportunities, and Threats) approaches, of which the results were subjected to evaluation by experts (pairwise comparisons), following the Analytic Hierarchy Process (AHP). The indicators representing strengths and opportunities of the process were calculated to be of higher value (overall level of final cumulative indicators values; 70.4%) compared with indicators representing weaknesses and threats. Enhancing strengths and opportunities and counteracting weaknesses and threats contribute making the potential of adaptive reuse practices in urban sustainability more evident. Among analysis dimensions, political and economic aspects rank first, followed by environmental, socio-cultural, technological-technical, and legal aspect. The empirical results of this paper serve as a useful reference point for decision-making and policy formulation addressing adaptive reuse practices in sustainable development strategies. Full article

In Korea, the Ministry of Environment and regional environment management agencies conduct environmental impact assessments (EIA) to mitigate and assess the impact of major development projects on the environment. EIA Big Data are used in conjunction with a geographical information system (GIS), and consist of indicators related to air, soil, and water that are measured before and after the development project. The impact of the development project on the environment can be evaluated through the variations of each indicator. This study analyzed trends in the environmental impacts of development projects during 2007–2016 using 21 types of EIA Big Data. A model was developed to estimate the Korean Environment Institute’s Environmental Impact Assessment Index for Development Projects (KEIDP) using a multi-layer perceptron-based artificial neural network (MLP-ANN) approach. A trend analysis of development projects in South Korea revealed that the mean value of KEIDP gradually increased over the study period. The rate of increase was 0.007 per year, with an R² value of 0.8. In the future, it will be necessary for all management agencies to apply the KEDIP calculation model to minimize the impact of development projects on the environment and reduce deviations among development projects through continuous monitoring. Full article

Whether in developing or developed countries, traffic accidents caused by freight vehicles are responsible for more than 10% of deaths of all traffic accidents. Fatigue driving is one of the main causes of freight vehicle accidents. Existing fatigue driving studies mostly use vehicle operating data from experiments or simulation data, exposing certain drawbacks in the validity and reliability of the models used. This study collected a large quantity of real driving data to extract sample data under different fatigue degrees. The parameters of vehicle operating data were selected based on significant driver fatigue degrees. The k-nearest neighbor algorithm was used to establish the detection model of fatigue driving behaviors, taking into account influence of the number of training samples and other parameters in the accuracy of fatigue driving behavior detection. With the collected operating data of 50 freight vehicles in the past month, the fatigue driving behavior detection models based on the k-nearest neighbor algorithm and the commonly used BP neural network proposed in this paper were tested, respectively. The analysis results showed that the accuracy of both models are 75.9%, but the fatigue driving detection model based on the k-nearest neighbor algorithm is more reliable. Full article

Integral bridges are a class of bridges with integral or semi-integral abutments, designed without expansion joints in the bridge deck of the superstructure. The significance of an integral bridge design is that it avoids durability and recurring maintenance issues with bridge joints, and maybe bearings, which are prevalent in traditional bridges. Integral bridges are less costly to construct. They require less maintenance and therefore cause less traffic disruptions that incur socio-economic costs. As a consequence, integral bridges are becoming the first choice of bridge design for short-to-medium length bridges in many countries, including the UK, USA, Europe, Australia, New Zealand and many other Asian countries. However, integral bridge designs are not without challenges: issues that concern concrete creep, shrinkage, temperature effects, bridge skew, structural constraints, as well as soil–structure interactions are amplified in integral bridges. The increased cyclic soil–structure interactions between the bridge structure and soil will lead to adverse soil ratcheting and settlement bump at the bridge approach. If movements from bridge superstructures were also transferred to pile-supported substructures, there is a risk that the pile–soil interactions may lead to pile fatigue failure. These issues complicate the geotechnical aspects of integral bridges. The aim of this paper is to present a comprehensive review of current geotechnical design practices and the amelioration of soil–structure interactions of integral bridges. Full article