Artificial intelligence-driven radiomics study in cancer:the role of feature engineering and modeling

Modern medicine is reliant on various medical imaging technologies for non-invasively observing patients’anatomy.However,the interpretation of medical images can be highly subjective and dependent on the expertise of clinicians.Moreover,some potentially useful quantitative information in medical images,especially that which is not visible to the naked eye,is often ignored during clinical practice.In contrast,radiomics performs high-throughput feature extraction from medical images,which enables quantitative analysis of medical images and prediction of various clinical endpoints.Studies have reported that radiomics exhibits promising performance in diagnosis and predicting treatment responses and prognosis,demonstrating its potential to be a non-invasive auxiliary tool for personalized medicine.However,radiomics remains in a developmental phase as numerous technical challenges have yet to be solved,especially in feature engineering and statistical modeling.In this review,we introduce the current utility of radiomics by summarizing research on its application in the diagnosis,prognosis,and prediction of treatment responses in patients with cancer.We focus on machine learning approaches,for feature extraction and selection during feature engineering and for imbalanced datasets and multi-modality fusion during statistical modeling.Furthermore,we introduce the stability,reproducibility,and interpretability of features,and the generalizability and interpretability of models.Finally,we offer possible solutions to current challenges in radiomics research.

Single-base editing in IGF2 improves meat production and intramuscular fat deposition in Liang Guang Small Spotted pigs

Background Chinese indigenous pigs are popular with consumers for their juiciness,flavour and meat quality,but they have lower meat production.Insulin-like growth factor 2(IGF2) is a maternally imprinted growth factor that promotes skeletal muscle growth by regulating cell proliferation and differentiation.A single nucleotide polymorphism(SNP) within intron 3 of porcine IGF2 disrupts a binding site for the repressor,zinc finger BED-type containing 6(ZBED6),leading to up-regulation of IGF2 and causing major effects on muscle growth,heart size,and backfat thickness.This favorable mutation is common in Western commercial pig populations,but absent in most Chinese indigenous pig breeds.To improve meat production of Chinese indigenous pigs,we used cytosine base editor 3(CBE3)to introduce IGF2 intron3-C3071T mutation into porcine embryonic fibroblasts(PEFs) isolated from a male Liang Guang Small Spotted pig(LGSS),and single-cell clones harboring the desired mutation were selected for somatic cell nuclear transfer(SCNT) to generate the founder line of IGF2^(T/T) pigs.Results We found the heterozygous progeny IGF2^(C/T) pigs exhibited enhanced expression of IGF2,increased lean meat by 18%-36%,enlarged loin muscle area by 3%-17%,improved intramuscular fat(IMF) content by 18%-39%,marbling score by 0.75-1,meat color score by 0.53-1.25,and reduced backfat thickness by 5%-16%.The enhanced accumulation of intramuscular fat in IGF2^(C/T) pigs was identified to be regulated by the PI3K-AKT/AMPK pathway,which activated SREBP1 to promote adipogenesis.Conclusions We demonstrated the introduction of IGF2-intron3-C3071T in Chinese LGSS can improve both meat production and quality,and first identified the regulation of IMF deposition by IGF2 through SREBP1 via the PI3KAKT/AMPK signaling pathways.Our study provides a further understanding of the biological functions of IGF2and an example for improving porcine economic traits through precise base editing.

Endoscopic features and treatments of gastric cystica profunda

BACKGROUND Gastric cystica profunda(GCP)represents a rare condition characterized by cystic dilation of gastric glands within the mucosal and/or submucosal layers.GCP is often linked to,or may progress into,early gastric cancer(EGC).AIM To provide a comprehensive evaluation of the endoscopic features of GCP while assessing the efficacy of endoscopic treatment,thereby offering guidance for diagnosis and treatment.METHODS This retrospective study involved 104 patients with GCP who underwent endoscopic resection.Alongside demographic and clinical data,regular patient followups were conducted to assess local recurrence.RESULTS Among the 104 patients diagnosed with GCP who underwent endoscopic resection,12.5%had a history of previous gastric procedures.The primary site predominantly affected was the cardia(38.5%,n=40).GCP commonly exhibited intraluminal growth(99%),regular presentation(74.0%),and ulcerative mucosa(61.5%).The leading endoscopic feature was the mucosal lesion type(59.6%,n=62).The average maximum diameter was 20.9±15.3 mm,with mucosal involvement in 60.6%(n=63).Procedures lasted 73.9±57.5 min,achieving complete resection in 91.3%(n=95).Recurrence(4.8%)was managed via either surgical intervention(n=1)or through endoscopic resection(n=4).Final pathology confirmed that 59.6%of GCP cases were associated with EGC.Univariate analysis indicated that elderly males were more susceptible to GCP associated with EGC.Conversely,multivariate analysis identified lesion morphology and endoscopic features as significant risk factors.Survival analysis demonstrated no statistically significant difference in recurrence between GCP with and without EGC(P=0.72).CONCLUSION The findings suggested that endoscopic resection might serve as an effective and minimally invasive treatment for GCP with or without EGC.

Epidemiological and clinical features,treatment status,and economic burden of traumatic spinal cord injury in China:a hospital-based retrospective study

Traumatic spinal cord injury is potentially catastrophic and can lead to permanent disability or even death.China has the largest population of patients with traumatic spinal cord injury.Previous studies of traumatic spinal cord injury in China have mostly been regional in scope;national-level studies have been rare.To the best of our knowledge,no national-level study of treatment status and economic burden has been performed.This retrospective study aimed to examine the epidemiological and clinical features,treatment status,and economic burden of traumatic spinal cord injury in China at the national level.We included 13,465 traumatic spinal cord injury patients who were injured between January 2013 and December 2018 and treated in 30 hospitals in 11 provinces/municipalities representing all geographical divisions of China.Patient epidemiological and clinical features,treatment status,and total and daily costs were recorded.Trends in the percentage of traumatic spinal cord injuries among all hospitalized patients and among patients hospitalized in the orthopedic department and cost of care were assessed by annual percentage change using the Joinpoint Regression Program.The percentage of traumatic spinal cord injuries among all hospitalized patients and among patients hospitalized in the orthopedic department did not significantly change overall(annual percentage change,-0.5%and 2.1%,respectively).A total of 10,053(74.7%)patients underwent surgery.Only 2.8%of patients who underwent surgery did so within 24 hours of injury.A total of 2005(14.9%)patients were treated with high-dose(≥500 mg)methylprednisolone sodium succinate/methylprednisolone(MPSS/MP);615(4.6%)received it within 8 hours.The total cost for acute traumatic spinal cord injury decreased over the study period(-4.7%),while daily cost did not significantly change(1.0%increase).Our findings indicate that public health initiatives should aim at improving hospitals’ability to complete early surgery within 24 hours,which is associated with improved sensorimotor recovery,increasing the awareness rate of clinical guidelines related to high-dose MPSS/MP to reduce the use of the treatment with insufficient evidence.

The Use of Secondary Grape Biomass in Beef Cattle Nutrition on Carcass Characteristics, Quality and Shelf Life of Meat

We determined whether the inclusion of 100 g/kg dry matter of grape pomace silage (GPS) and grape pomace bran (GPB) as substitutes for other traditional fiber sources in the diet of steers (Charolais x Nellore) would improve carcass characteristics, meat quality and composition, and shelf life. Twenty-four animals (248 ± 19.32 kg of initial body weight) were fed a high concentrate diet for 121 days. Carcass characteristics were measured, and the longissimus dorsi muscle was analyzed for fatty acid (FA) profile and composition. The meat was sliced and stored in air-permeable packages for 10 days. On each sampling day (d 1, 3, 7, and 10), oxidative stability, bacterial load, lipid and protein oxidation, and staining were analyzed. The experimental diets influenced the pH of cold carcasses only. The GPS group had a higher pH than the control. The GPS and GPB groups showed improved oxidant status (i.e., lower lipid peroxidation and concentrations of reactive oxygen species were in the meat of both groups than in control). On the first day of storage, the antioxidant enzyme glutathione S-transferase activity was more significant in the meat of the GPS and GPB groups than in the control. The bacterial loads in the meat were attenuated by GPS inclusion;there were lower total coliform counts and a trend toward lower counts for enterobacteria in the control group. The diets altered the FA profile of the meat;i.e., the GPB diet allowed for a more significant amount of the n-6 omegas in the meat, while the GPS diet showed a tendency for a more significant amount of n-6 and 9 omegas. Both diets (GPS and GPB) increased the amounts of long-chain FAs. The GPS diet decreased saturated FA levels. We conclude that the dietary treatments GPS and GPB are a promising alternative to maintain meat quality standards throughout in real-world retail conditions. These treatments gave rise to an improvement in the nutritional value of the meat due to the more significant amounts of FAs that improve human health.

Investigation of the Acceptability of Cultured Meat in University Students

Background: Over the past 20 years, cultured meat has drawn a lot of public attention as a potential solution to issues with animal husbandry, including inadequate use of natural sources, improper animal welfare practices, and possible risks to public health and safety. The novel method of producing meat through culture reduces the need for animals to produce muscle fiber, thereby obviating the necessity for animal slaughter. Apart from its ethical advantages, cultured meat presents a possible way to fulfill the expanding need for food among growing populations. The purpose of this research was to find out whether Turkish students would be willing to pay for and accept cultured meat. Technique: Method: 371 university students who willingly consented to fill out a questionnaire and provide demographic data make up the research sample. Questions from previous studies on the acceptability of cultured meat were compiled to create the survey. The research’s data collection took place in March and April of 2022. The research was completed in June 2022 after the data had been processed and analyzed. Results: The results showed that the majority of participants were female and had omnivorous eating habits. Based on the results of the Bonferroni correction test, students with a higher intention to purchase and consume cultured meat were those who received economics and business education. Students with two years of university education had a higher overall survey score than those with four years of education (p < 0.05). Furthermore, it is discovered that there is a negative correlation between the participants’ ages and their Factor 2 (using cultured meat as an alternative to industrial meat) and Factor 3 (consuming and purchasing it) section points (r = -109, p = 0.036) (r = -0.121, p = 0.019). In conclusion, university students generally have a negative outlook on health-related issues, such as eating cultured meat as an alternative.

Effects of dietary Clostridium butyricum and rumen protected fat on meat quality,oxidative stability,and chemical composition of finishing goats

Background Clostridium butyricum(CB)is a probiotic that can regulate intestinal microbial composition and improve meat quality.Rumen protected fat(RPF)has been shown to increase the dietary energy density and provide essential fatty acids.However,it is still unknown whether dietary supplementation with CB and RPF exerts beneficial effects on growth performance and nutritional value of goat meat.This study aimed to investigate the effects of dietary CB and RPF supplementation on growth performance,meat quality,oxidative stability,and meat nutritional value of finishing goats.Thirty-two goats(initial body weight,20.5±0.82 kg)were used in a completely randomized block design with a 2 RPF supplementation(0 vs.30 g/d)×2 CB supplementation(0 vs.1.0 g/d)factorial treatment arrangement.The experiment included a 14-d adaptation and 70-d data and sample collection period.The goats were fed a diet consisted of 400 g/kg peanut seedling and 600 g/kg corn-based concentrate(dry matter basis).Result Interaction between CB and RPF was rarely observed on the variables measured,except that shear force was reduced(P<0.05)by adding CB or RPF alone or their combination;the increased intramuscular fat(IMF)content with adding RPF was more pronounced(P<0.05)with CB than without CB addition.The pH24h(P=0.009),a*values(P=0.007),total antioxidant capacity(P=0.050),glutathione peroxidase activities(P=0.006),concentrations of 18:3(P<0.001),20:5(P=0.003)and total polyunsaturated fatty acids(P=0.048)were increased,whereas the L*values(P<0.001),shear force(P=0.050)and malondialdehyde content(P=0.044)were decreased by adding CB.Furthermore,CB supplementation increased essential amino acid(P=0.027),flavor amino acid(P=0.010)and total amino acid contents(P=0.024)as well as upregulated the expression of lipoprotein lipase(P=0.034)and peroxisome proliferator-activated receptorγ(PPARγ)(P=0.012),and downregulated the expression of stearoyl-CoA desaturase(SCD)(P=0.034).The RPF supplementation increased dry matter intake(P=0.005),averaged daily gain(trend,P=0.058),hot carcass weight(P=0.046),backfat thickness(P=0.006),concentrations of 16:0(P<0.001)and c9-18:1(P=0.002),and decreased the shear force(P<0.001),isoleucine(P=0.049)and lysine content(P=0.003)of meat.In addition,the expressions of acetyl-CoA carboxylase(P=0.003),fatty acid synthase(P=0.038),SCD(P<0.001)and PPARγ(P=0.022)were upregulated due to RPF supplementation,resulting in higher(P<0.001)content of IMF.Conclusions CB and RPF could be fed to goats for improving the growth performance,carcass traits and meat quality,and promote fat deposition by upregulating the expression of lipogenic genes of Longissimus thoracis muscle.

MSD-Net: Pneumonia Classification Model Based on Multi-Scale Directional Feature Enhancement

Computer-aided diagnosis of pneumonia based on deep learning is a research hotspot.However,there are some problems that the features of different sizes and different directions are not sufficient when extracting the features in lung X-ray images.A pneumonia classification model based on multi-scale directional feature enhancement MSD-Net is proposed in this paper.The main innovations are as follows:Firstly,the Multi-scale Residual Feature Extraction Module(MRFEM)is designed to effectively extract multi-scale features.The MRFEM uses dilated convolutions with different expansion rates to increase the receptive field and extract multi-scale features effectively.Secondly,the Multi-scale Directional Feature Perception Module(MDFPM)is designed,which uses a three-branch structure of different sizes convolution to transmit direction feature layer by layer,and focuses on the target region to enhance the feature information.Thirdly,the Axial Compression Former Module(ACFM)is designed to perform global calculations to enhance the perception ability of global features in different directions.To verify the effectiveness of the MSD-Net,comparative experiments and ablation experiments are carried out.In the COVID-19 RADIOGRAPHY DATABASE,the Accuracy,Recall,Precision,F1 Score,and Specificity of MSD-Net are 97.76%,95.57%,95.52%,95.52%,and 98.51%,respectively.In the chest X-ray dataset,the Accuracy,Recall,Precision,F1 Score and Specificity of MSD-Net are 97.78%,95.22%,96.49%,95.58%,and 98.11%,respectively.This model improves the accuracy of lung image recognition effectively and provides an important clinical reference to pneumonia Computer-Aided Diagnosis.

Japanese Sign Language Recognition by Combining Joint Skeleton-Based Handcrafted and Pixel-Based Deep Learning Features with Machine Learning Classification

Sign language recognition is vital for enhancing communication accessibility among the Deaf and hard-of-hearing communities.In Japan,approximately 360,000 individualswith hearing and speech disabilities rely on Japanese Sign Language(JSL)for communication.However,existing JSL recognition systems have faced significant performance limitations due to inherent complexities.In response to these challenges,we present a novel JSL recognition system that employs a strategic fusion approach,combining joint skeleton-based handcrafted features and pixel-based deep learning features.Our system incorporates two distinct streams:the first stream extracts crucial handcrafted features,emphasizing the capture of hand and body movements within JSL gestures.Simultaneously,a deep learning-based transfer learning stream captures hierarchical representations of JSL gestures in the second stream.Then,we concatenated the critical information of the first stream and the hierarchy of the second stream features to produce the multiple levels of the fusion features,aiming to create a comprehensive representation of the JSL gestures.After reducing the dimensionality of the feature,a feature selection approach and a kernel-based support vector machine(SVM)were used for the classification.To assess the effectiveness of our approach,we conducted extensive experiments on our Lab JSL dataset and a publicly available Arabic sign language(ArSL)dataset.Our results unequivocally demonstrate that our fusion approach significantly enhances JSL recognition accuracy and robustness compared to individual feature sets or traditional recognition methods.

Dynamic changes of rumen microbiota and serum metabolome revealed increases in meat quality and growth performances of sheep fed bio‑fermented rice straw

Background Providing high-quality roughage is crucial for improvement of ruminant production because it is an essential component of their feed.Our previous study showed that feeding bio-fermented rice straw(BF)improved the feed intake and weight gain of sheep.However,it remains unclear why feeding BF to sheep increased their feed intake and weight gain.Therefore,the purposes of this research were to investigate how the rumen micro-biota and serum metabolome are dynamically changing after feeding BF,as well as how their changes influence the feed intake,digestibility,nutrient transport,meat quality and growth performances of sheep.Twelve growing Hu sheep were allocated into 3 groups:alfalfa hay fed group(AH:positive control),rice straw fed group(RS:negative control)and BF fed group(BF:treatment).Samples of rumen content,blood,rumen epithelium,muscle,feed offered and refusals were collected for the subsequent analysis.Results Feeding BF changed the microbial community and rumen fermentation,particularly increasing(P<0.05)relative abundance of Prevotella and propionate production,and decreasing(P<0.05)enteric methane yield.The histomorphology(height,width,area and thickness)of rumen papillae and gene expression for carbohydrate trans-port(MCT1),tight junction(claudin-1,claudin-4),and cell proliferation(CDK4,Cyclin A2,Cyclin E1)were improved(P<0.05)in sheep fed BF.Additionally,serum metabolome was also dynamically changed,which led to up-regulating(P<0.05)the primary bile acid biosynthesis and biosynthesis of unsaturated fatty acid in sheep fed BF.As a result,the higher(P<0.05)feed intake,digestibility,growth rate,feed efficiency,meat quality and mono-unsaturated fatty acid concentration in muscle,and the lower(P<0.05)feed cost per kg of live weight were achieved by feeding BF.Conclusions Feeding BF improved the growth performances and meat quality of sheep and reduced their feed cost.Therefore,bio-fermentation of rice straw could be an innovative way for improving ruminant production with mini-mizing production costs.

Insights into the mechanism of L-malic acid on drip loss of chicken meat under commercial conditions

Background A deterioration in the meat quality of broilers has attracted much more attention in recent years.L-malic acid(MA)is evidenced to decrease meat drip loss in broilers,but the underlying molecular mechanisms are still unclear.It’s also not sure whether the outputs obtained under experimental conditions can be obtained in a com-mercial condition.Here,we investigated the effects and mechanisms of dietary MA supplementation on chicken meat drip loss at large-scale rearing.Results Results showed that the growth performance and drip loss were improved by MA supplementation.Meat metabolome revealed that L-2-aminoadipic acid,β-aminoisobutyric acid,eicosapentaenoic acid,and nicotinamide,as well as amino acid metabolism pathways connected to the improvements of meat quality by MA addition.The transcriptome analysis further indicated that the effect of MA on drip loss was also related to the proper immune response,evidenced by the enhanced B cell receptor signaling pathway,NF-κB signaling pathway,TNF signaling pathway,and IL-17 signaling pathway.Conclusions We provided evidence that MA decreased chicken meat drip loss under commercial conditions.Metabolome and transcriptome revealed a comprehensive understanding of the underlying mechanisms.Together,MA could be used as a promising dietary supplement for enhancing the water-holding capacity of chicken meat.

Plant-based meat analogues aggravated lipid accumulation by regulating lipid metabolism homeostasis in mice

To determine the effects of plant-based meat analogues on the metabolic health and the possible mechanisms,mice were fed with a real pork diet(AP),a real beef diet(AB),a plant-based pork analogue diet(PP)and plant-based beef analogue diet(PB)for 68 days.Compared with real meat,the plant-based meat analogues increased food and energy intake,body weight,white fat and liver weight and caused adipocyte hypertrophy,hepatic lipid droplet accumulation,and inflammatory responses in mice.Metabolomics revealed that plantbased meat analogues altered the composition of serum metabolites,which regulated lipid metabolism homeostasis.The PB diet upregulated gene expression related to lipid synthesis,lipolysis and adipocyte differentiation while the PP diet upregulated expression of lipolysis-related genes but downregulated expression of adipocyte differentiation-related genes in white adipose tissue.Meanwhile,both PP and PB diets upregulated lipid influx-and synthesis-related genes but downregulated lipid oxidation-related genes in liver.The specific metabolite biomarkers may affect fat accumulation mainly by direct lipid metabolism pathways or indirect amino acid metabolism,protein digestion and absorption,bile secretion,aminoacyl-tRNA biosynthesis,neuroactive ligand-receptor interaction and ABC transporters pathways.These findings provide a new insight into understanding the differences in nutritional functions of meat and plant-based meat analogues.

Cross-Dimension Attentive Feature Fusion Network for Unsupervised Time-Series Anomaly Detection

Time series anomaly detection is crucial in various industrial applications to identify unusual behaviors within the time series data.Due to the challenges associated with annotating anomaly events,time series reconstruction has become a prevalent approach for unsupervised anomaly detection.However,effectively learning representations and achieving accurate detection results remain challenging due to the intricate temporal patterns and dependencies in real-world time series.In this paper,we propose a cross-dimension attentive feature fusion network for time series anomaly detection,referred to as CAFFN.Specifically,a series and feature mixing block is introduced to learn representations in 1D space.Additionally,a fast Fourier transform is employed to convert the time series into 2D space,providing the capability for 2D feature extraction.Finally,a cross-dimension attentive feature fusion mechanism is designed that adaptively integrates features across different dimensions for anomaly detection.Experimental results on real-world time series datasets demonstrate that CAFFN performs better than other competing methods in time series anomaly detection.

FusionNN:A Semantic Feature Fusion Model Based on Multimodal for Web Anomaly Detection

With the rapid development of the mobile communication and the Internet,the previous web anomaly detectionand identificationmodels were built relying on security experts’empirical knowledge and attack features.Althoughthis approach can achieve higher detection performance,it requires huge human labor and resources to maintainthe feature library.In contrast,semantic feature engineering can dynamically discover new semantic featuresand optimize feature selection by automatically analyzing the semantic information contained in the data itself,thus reducing dependence on prior knowledge.However,current semantic features still have the problem ofsemantic expression singularity,as they are extracted from a single semantic mode such as word segmentation,character segmentation,or arbitrary semantic feature extraction.This paper extracts features of web requestsfrom dual semantic granularity,and proposes a semantic feature fusion method to solve the above problems.Themethod first preprocesses web requests,and extracts word-level and character-level semantic features of URLs viaconvolutional neural network(CNN),respectively.By constructing three loss functions to reduce losses betweenfeatures,labels and categories.Experiments on the HTTP CSIC 2010,Malicious URLs and HttpParams datasetsverify the proposedmethod.Results show that compared withmachine learning,deep learningmethods and BERTmodel,the proposed method has better detection performance.And it achieved the best detection rate of 99.16%in the dataset HttpParams.

Video-Based Deception Detection with Non-Contact Heart Rate Monitoring and Multi-Modal Feature Selection

Deception detection plays a crucial role in criminal investigation.Videos contain a wealth of information regarding apparent and physiological changes in individuals,and thus can serve as an effective means of deception detection.In this paper,we investigate video-based deception detection considering both apparent visual features such as eye gaze,head pose and facial action unit(AU),and non-contact heart rate detected by remote photoplethysmography(rPPG)technique.Multiple wrapper-based feature selection methods combined with the K-nearest neighbor(KNN)and support vector machine(SVM)classifiers are employed to screen the most effective features for deception detection.We evaluate the performance of the proposed method on both a self-collected physiological-assisted visual deception detection(PV3D)dataset and a public bag-oflies(BOL)dataset.Experimental results demonstrate that the SVM classifier with symbiotic organisms search(SOS)feature selection yields the best overall performance,with an area under the curve(AUC)of 83.27%and accuracy(ACC)of 83.33%for PV3D,and an AUC of 71.18%and ACC of 70.33%for BOL.This demonstrates the stability and effectiveness of the proposed method in video-based deception detection tasks.

A Heuristic Radiomics Feature Selection Method Based on Frequency Iteration and Multi-Supervised Training Mode

Radiomics is a non-invasive method for extracting quantitative and higher-dimensional features from medical images for diagnosis.It has received great attention due to its huge application prospects in recent years.We can know that the number of features selected by the existing radiomics feature selectionmethods is basically about ten.In this paper,a heuristic feature selection method based on frequency iteration and multiple supervised training mode is proposed.Based on the combination between features,it decomposes all features layer by layer to select the optimal features for each layer,then fuses the optimal features to form a local optimal group layer by layer and iterates to the global optimal combination finally.Compared with the currentmethod with the best prediction performance in the three data sets,thismethod proposed in this paper can reduce the number of features fromabout ten to about three without losing classification accuracy and even significantly improving classification accuracy.The proposed method has better interpretability and generalization ability,which gives it great potential in the feature selection of radiomics.

Effect of the Dietary Substitution of Fish Meal with Achatina fulica Meat Meal on the Growth Performance and Production Cost of African Catfish (Clarias gariepinus) Fingerlings

Fishmeal is the most preferred source of protein in aquafeeds, but it is expensive and scarce. Hence, Achatina fulica meat meal (AFM), which is much less preferred for human consumption out of three species of African giant land snails, was tested as a fishmeal substitute for Clarias gariepinus growth. Five iso-nitrogenous and iso-calorific diets were formulated, in which AFM substituted fish meal at 0% (control or Diet A), 25% (Diet B), 50% (Diet C), 75% (Diet D) and 100% (Diet E). These dietary treatments were each replicated thrice in a completely randomized design experiment, using 36-L plastic tanks in which the fish were fed daily rations corresponding to 5% of their body weight, for 8 weeks. Water quality parameters in the tanks were monitored. Proximate analyses were conducted on the fish meal, snail meal and experimental diets before the feeding trials. Cost-benefit analysis of the different diets was performed. The crude protein content of AFM (69.18%) was significantly higher than that of fish meal (55.81%). There was no significant difference (P > 0.05) in the mean weight gain, specific growth rate, feed conversion ratio, protein efficiency ratio and survival rate in fish fed Diet A and Diet B. The best protein efficiency ratio (0.77) was recorded in fish fed Diet B. Furthermore, the survival rate of fish increased with increased levels of AFM substitution. Water quality parameters were within a suitable range for tropical fish culture, indicating that the AFM did not pollute the water. The fish fed 25% AFM diet significantly (P Clarias gariepinus diets at a 25% substitution level. The aquaculture industry can thus exploit the availability of this feed resource.

Feature extraction and learning approaches for cancellable biometrics:A survey

Biometric recognition is a widely used technology for user authentication.In the application of this technology,biometric security and recognition accuracy are two important issues that should be considered.In terms of biometric security,cancellable biometrics is an effective technique for protecting biometric data.Regarding recognition accuracy,feature representation plays a significant role in the performance and reliability of cancellable biometric systems.How to design good feature representations for cancellable biometrics is a challenging topic that has attracted a great deal of attention from the computer vision community,especially from researchers of cancellable biometrics.Feature extraction and learning in cancellable biometrics is to find suitable feature representations with a view to achieving satisfactory recognition performance,while the privacy of biometric data is protected.This survey informs the progress,trend and challenges of feature extraction and learning for cancellable biometrics,thus shedding light on the latest developments and future research of this area.

Curve Classification Based onMean-Variance Feature Weighting and Its Application

The classification of functional data has drawn much attention in recent years.The main challenge is representing infinite-dimensional functional data by finite-dimensional features while utilizing those features to achieve better classification accuracy.In this paper,we propose a mean-variance-based(MV)feature weighting method for classifying functional data or functional curves.In the feature extraction stage,each sample curve is approximated by B-splines to transfer features to the coefficients of the spline basis.After that,a feature weighting approach based on statistical principles is introduced by comprehensively considering the between-class differences and within-class variations of the coefficients.We also introduce a scaling parameter to adjust the gap between the weights of features.The new feature weighting approach can adaptively enhance noteworthy local features while mitigating the impact of confusing features.The algorithms for feature weighted K-nearest neighbor and support vector machine classifiers are both provided.Moreover,the new approach can be well integrated into existing functional data classifiers,such as the generalized functional linear model and functional linear discriminant analysis,resulting in a more accurate classification.The performance of the mean-variance-based classifiers is evaluated by simulation studies and real data.The results show that the newfeatureweighting approach significantly improves the classification accuracy for complex functional data.

Feature extraction for machine learning-based intrusion detection in IoT networks

A large number of network security breaches in IoT networks have demonstrated the unreliability of current Network Intrusion Detection Systems(NIDSs).Consequently,network interruptions and loss of sensitive data have occurred,which led to an active research area for improving NIDS technologies.In an analysis of related works,it was observed that most researchers aim to obtain better classification results by using a set of untried combinations of Feature Reduction(FR)and Machine Learning(ML)techniques on NIDS datasets.However,these datasets are different in feature sets,attack types,and network design.Therefore,this paper aims to discover whether these techniques can be generalised across various datasets.Six ML models are utilised:a Deep Feed Forward(DFF),Convolutional Neural Network(CNN),Recurrent Neural Network(RNN),Decision Tree(DT),Logistic Regression(LR),and Naive Bayes(NB).The accuracy of three Feature Extraction(FE)algorithms is detected;Principal Component Analysis(PCA),Auto-encoder(AE),and Linear Discriminant Analysis(LDA),are evaluated using three benchmark datasets:UNSW-NB15,ToN-IoT and CSE-CIC-IDS2018.Although PCA and AE algorithms have been widely used,the determination of their optimal number of extracted dimensions has been overlooked.The results indicate that no clear FE method or ML model can achieve the best scores for all datasets.The optimal number of extracted dimensions has been identified for each dataset,and LDA degrades the performance of the ML models on two datasets.The variance is used to analyse the extracted dimensions of LDA and PCA.Finally,this paper concludes that the choice of datasets significantly alters the performance of the applied techniques.We believe that a universal(benchmark)feature set is needed to facilitate further advancement and progress of research in this field.